michael/stable-diffusion-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge branch 'AUTOMATIC1111:master' into kr-localization

Browse source
This commit is contained in:
Dynamic 2022-10-23 22:36:56 +09:00 committed by GitHub
commit 660ae690bd
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
61 changed files with 3924 additions and 1046 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
.github/ISSUE_TEMPLATE/bug_report.md vendored
View file

@ -1,32 +0,0 @@
---
name: Bug report
about: Create a report to help us improve
title: ''
labels: bug-report
assignees: ''
---
**Describe the bug**
A clear and concise description of what the bug is.
**To Reproduce**
Steps to reproduce the behavior:
1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error
**Expected behavior**
A clear and concise description of what you expected to happen.
**Screenshots**
If applicable, add screenshots to help explain your problem.
**Desktop (please complete the following information):**
- OS: [e.g. Windows, Linux]
- Browser [e.g. chrome, safari]
- Commit revision [looks like this: e68484500f76a33ba477d5a99340ab30451e557b; can be seen when launching webui.bat, or obtained manually by running `git rev-parse HEAD`]
**Additional context**
Add any other context about the problem here.

83
.github/ISSUE_TEMPLATE/bug_report.yml vendored Normal file
View file

@ -0,0 +1,83 @@
name: Bug Report
description: You think somethings is broken in the UI
title: "[Bug]: "
labels: ["bug-report"]
body:
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the bug you encountered, and that it hasn't been fixed in a recent build/commit.
options:
- label: I have searched the existing issues and checked the recent builds/commits
required: true
- type: markdown
attributes:
value: |
*Please fill this form with as much information as possible, don't forget to fill "What OS..." and "What browsers" and *provide screenshots if possible**
- type: textarea
id: what-did
attributes:
label: What happened?
description: Tell us what happened in a very clear and simple way
validations:
required: true
- type: textarea
id: steps
attributes:
label: Steps to reproduce the problem
description: Please provide us with precise step by step information on how to reproduce the bug
value: |
1. Go to ....
2. Press ....
3. ...
validations:
required: true
- type: textarea
id: what-should
attributes:
label: What should have happened?
description: tell what you think the normal behavior should be
validations:
required: true
- type: input
id: commit
attributes:
label: Commit where the problem happens
description: Which commit are you running ? (copy the **Commit hash** shown in the cmd/terminal when you launch the UI)
validations:
required: true
- type: dropdown
id: platforms
attributes:
label: What platforms do you use to access UI ?
multiple: true
options:
- Windows
- Linux
- MacOS
- iOS
- Android
- Other/Cloud
- type: dropdown
id: browsers
attributes:
label: What browsers do you use to access the UI ?
multiple: true
options:
- Mozilla Firefox
- Google Chrome
- Brave
- Apple Safari
- Microsoft Edge
- type: textarea
id: cmdargs
attributes:
label: Command Line Arguments
description: Are you using any launching parameters/command line arguments (modified webui-user.py) ? If yes, please write them below
render: Shell
- type: textarea
id: misc
attributes:
label: Additional information, context and logs
description: Please provide us with any relevant additional info, context or log output.

5
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View file

@ -0,0 +1,5 @@
blank_issues_enabled: false
contact_links:
- name: WebUI Community Support
url: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions
about: Please ask and answer questions here.

20
.github/ISSUE_TEMPLATE/feature_request.md vendored
View file

@ -1,20 +0,0 @@
---
name: Feature request
about: Suggest an idea for this project
title: ''
labels: 'suggestion'
assignees: ''
---
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
**Describe the solution you'd like**
A clear and concise description of what you want to happen.
**Describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.
**Additional context**
Add any other context or screenshots about the feature request here.

40
.github/ISSUE_TEMPLATE/feature_request.yml vendored Normal file
View file

@ -0,0 +1,40 @@
name: Feature request
description: Suggest an idea for this project
title: "[Feature Request]: "
labels: ["suggestion"]
body:
- type: checkboxes
attributes:
label: Is there an existing issue for this?
description: Please search to see if an issue already exists for the feature you want, and that it's not implemented in a recent build/commit.
options:
- label: I have searched the existing issues and checked the recent builds/commits
required: true
- type: markdown
attributes:
value: |
*Please fill this form with as much information as possible, provide screenshots and/or illustrations of the feature if possible*
- type: textarea
id: feature
attributes:
label: What would your feature do ?
description: Tell us about your feature in a very clear and simple way, and what problem it would solve
validations:
required: true
- type: textarea
id: workflow
attributes:
label: Proposed workflow
description: Please provide us with step by step information on how you'd like the feature to be accessed and used
value: |
1. Go to ....
2. Press ....
3. ...
validations:
required: true
- type: textarea
id: misc
attributes:
label: Additional information
description: Add any other context or screenshots about the feature request here.

2
.gitignore vendored
View file

@ -27,3 +27,5 @@ __pycache__
notification.mp3
/SwinIR
/textual_inversion
.vscode
/extensions

39
README.md
View file

@ -11,6 +11,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
- One click install and run script (but you still must install python and git)
- Outpainting
- Inpainting
- Color Sketch
- Prompt Matrix
- Stable Diffusion Upscale
- Attention, specify parts of text that the model should pay more attention to
@ -23,6 +24,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
- have as many embeddings as you want and use any names you like for them
- use multiple embeddings with different numbers of vectors per token
- works with half precision floating point numbers
- train embeddings on 8GB (also reports of 6GB working)
- Extras tab with:
- GFPGAN, neural network that fixes faces
- CodeFormer, face restoration tool as an alternative to GFPGAN
@ -37,14 +39,14 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
- Interrupt processing at any time
- 4GB video card support (also reports of 2GB working)
- Correct seeds for batches
- Prompt length validation
- get length of prompt in tokens as you type
- get a warning after generation if some text was truncated
- Live prompt token length validation
- Generation parameters
- parameters you used to generate images are saved with that image
- in PNG chunks for PNG, in EXIF for JPEG
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
- can be disabled in settings
- drag and drop an image/text-parameters to promptbox
- Read Generation Parameters Button, loads parameters in promptbox to UI
- Settings page
- Running arbitrary python code from UI (must run with --allow-code to enable)
- Mouseover hints for most UI elements
@ -59,10 +61,10 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
- CLIP interrogator, a button that tries to guess prompt from an image
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
- Batch Processing, process a group of files using img2img
- Img2img Alternative
- Img2img Alternative, reverse Euler method of cross attention control
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
- Reloading checkpoints on the fly
- Checkpoint Merger, a tab that allows you to merge two checkpoints into one
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
- separate prompts using uppercase `AND`
@ -70,14 +72,35 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
- DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args)
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
- History tab: view, direct and delete images conveniently within the UI
- Generate forever option
- Training tab
- hypernetworks and embeddings options
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
- Clip skip
- Use Hypernetworks
- Use VAEs
- Estimated completion time in progress bar
- API
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
## Where are Aesthetic Gradients?!?!
Aesthetic Gradients are now an extension. You can install it using git:
```commandline
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients extensions/aesthetic-gradients
```
After running this command, make sure that you have `aesthetic-gradients` dir in webui's `extensions` directory and restart
the UI. The interface for Aesthetic Gradients should appear exactly the same as it was.
## Installation and Running
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
Alternatively, use Google Colab:
Alternatively, use online services (like Google Colab):
- [Colab, maintained by Akaibu](https://colab.research.google.com/drive/1kw3egmSn-KgWsikYvOMjJkVDsPLjEMzl)
- [Colab, original by me, outdated](https://colab.research.google.com/drive/1Iy-xW9t1-OQWhb0hNxueGij8phCyluOh).
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
### Automatic Installation on Windows
1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"

7
artists.csv
View file

@ -523,7 +523,6 @@ Affandi,0.7170285,nudity
Diane Arbus,0.655138,digipa-high-impact
Joseph Ducreux,0.65247905,digipa-high-impact
Berthe Morisot,0.7165984,fineart
Hilma AF Klint,0.71643853,scribbles
Hilma af Klint,0.71643853,scribbles
Filippino Lippi,0.7163017,fineart
Leonid Afremov,0.7163005,fineart
@ -738,14 +737,12 @@ Abraham Mignon,0.60605425,fineart
Albert Bloch,0.69573116,nudity
Charles Dana Gibson,0.67155975,fineart
Alexandre-Évariste Fragonard,0.6507174,fineart
Alexandre-Évariste Fragonard,0.6507174,fineart
Ernst Fuchs,0.6953538,nudity
Alfredo Jaar,0.6952965,digipa-high-impact
Judy Chicago,0.6952246,weird
Frans van Mieris the Younger,0.6951849,fineart
Aertgen van Leyden,0.6951305,fineart
Emily Carr,0.69512105,fineart
Frances Macdonald,0.6950408,scribbles
Frances MacDonald,0.6950408,scribbles
Hannah Höch,0.69495845,scribbles
Gillis Rombouts,0.58770025,fineart
@ -895,7 +892,6 @@ Richard McGuire,0.6820089,scribbles
Anni Albers,0.65708244,digipa-high-impact
Aleksey Savrasov,0.65207493,fineart
Wayne Barlowe,0.6537874,fineart
Giorgio De Chirico,0.6815907,fineart
Giorgio de Chirico,0.6815907,fineart
Ernest Procter,0.6815795,fineart
Adriaen Brouwer,0.6815058,fineart
@ -1241,7 +1237,6 @@ Betty Churcher,0.65387225,fineart
Claes Corneliszoon Moeyaert,0.65386075,fineart
David Bomberg,0.6537477,fineart
Abraham Bosschaert,0.6535562,fineart
Giuseppe De Nittis,0.65354455,fineart
Giuseppe de Nittis,0.65354455,fineart
John La Farge,0.65342575,fineart
Frits Thaulow,0.65341854,fineart
@ -1522,7 +1517,6 @@ Gertrude Harvey,0.5903887,fineart
Grant Wood,0.6266253,fineart
Fyodor Vasilyev,0.5234919,digipa-med-impact
Cagnaccio di San Pietro,0.6261671,fineart
Cagnaccio Di San Pietro,0.6261671,fineart
Doris Boulton-Maude,0.62593174,fineart
Adolf Hirémy-Hirschl,0.5946784,fineart
Harold von Schmidt,0.6256755,fineart
@ -2411,7 +2405,6 @@ Hermann Feierabend,0.5346168,digipa-high-impact
Antonio Donghi,0.4610982,digipa-low-impact
Adonna Khare,0.4858036,digipa-med-impact
James Stokoe,0.5015107,digipa-med-impact
Art & Language,0.5341332,digipa-high-impact
Agustín Fernández,0.53403986,fineart
Germán Londoño,0.5338712,fineart
Emmanuelle Moureaux,0.5335641,digipa-high-impact

1 artist score category
523 Diane Arbus 0.655138 digipa-high-impact
524 Joseph Ducreux 0.65247905 digipa-high-impact
525 Berthe Morisot 0.7165984 fineart
Hilma AF Klint 0.71643853 scribbles
526 Hilma af Klint 0.71643853 scribbles
527 Filippino Lippi 0.7163017 fineart
528 Leonid Afremov 0.7163005 fineart
737 Albert Bloch 0.69573116 nudity
738 Charles Dana Gibson 0.67155975 fineart
739 Alexandre-Évariste Fragonard 0.6507174 fineart
Alexandre-Évariste Fragonard 0.6507174 fineart
740 Ernst Fuchs 0.6953538 nudity
741 Alfredo Jaar 0.6952965 digipa-high-impact
742 Judy Chicago 0.6952246 weird
743 Frans van Mieris the Younger 0.6951849 fineart
744 Aertgen van Leyden 0.6951305 fineart
745 Emily Carr 0.69512105 fineart
Frances Macdonald 0.6950408 scribbles
746 Frances MacDonald 0.6950408 scribbles
747 Hannah Höch 0.69495845 scribbles
748 Gillis Rombouts 0.58770025 fineart
892 Anni Albers 0.65708244 digipa-high-impact
893 Aleksey Savrasov 0.65207493 fineart
894 Wayne Barlowe 0.6537874 fineart
Giorgio De Chirico 0.6815907 fineart
895 Giorgio de Chirico 0.6815907 fineart
896 Ernest Procter 0.6815795 fineart
897 Adriaen Brouwer 0.6815058 fineart
1237 Claes Corneliszoon Moeyaert 0.65386075 fineart
1238 David Bomberg 0.6537477 fineart
1239 Abraham Bosschaert 0.6535562 fineart
Giuseppe De Nittis 0.65354455 fineart
1240 Giuseppe de Nittis 0.65354455 fineart
1241 John La Farge 0.65342575 fineart
1242 Frits Thaulow 0.65341854 fineart
1517 Grant Wood 0.6266253 fineart
1518 Fyodor Vasilyev 0.5234919 digipa-med-impact
1519 Cagnaccio di San Pietro 0.6261671 fineart
Cagnaccio Di San Pietro 0.6261671 fineart
1520 Doris Boulton-Maude 0.62593174 fineart
1521 Adolf Hirémy-Hirschl 0.5946784 fineart
1522 Harold von Schmidt 0.6256755 fineart
2405 Antonio Donghi 0.4610982 digipa-low-impact
2406 Adonna Khare 0.4858036 digipa-med-impact
2407 James Stokoe 0.5015107 digipa-med-impact
Art & Language 0.5341332 digipa-high-impact
2408 Agustín Fernández 0.53403986 fineart
2409 Germán Londoño 0.5338712 fineart
2410 Emmanuelle Moureaux 0.5335641 digipa-high-impact

0
extensions/put extension here.txt Normal file
View file

55
javascript/aspectRatioOverlay.js
View file

@ -3,12 +3,12 @@ let currentWidth = null;
let currentHeight = null;
let arFrameTimeout = setTimeout(function(){},0);
function dimensionChange(e,dimname){
function dimensionChange(e, is_width, is_height){
if(dimname == 'Width'){
if(is_width){
currentWidth = e.target.value*1.0
}
if(dimname == 'Height'){
if(is_height){
currentHeight = e.target.value*1.0
}
@ -18,22 +18,13 @@ function dimensionChange(e,dimname){
return;
}
var img2imgMode = gradioApp().querySelector('#mode_img2img.tabs > div > button.rounded-t-lg.border-gray-200')
if(img2imgMode){
img2imgMode=img2imgMode.innerText
}else{
return;
}
var redrawImage = gradioApp().querySelector('div[data-testid=image] img');
var inpaintImage = gradioApp().querySelector('#img2maskimg div[data-testid=image] img')
var targetElement = null;
if(img2imgMode=='img2img' && redrawImage){
targetElement = redrawImage;
}else if(img2imgMode=='Inpaint' && inpaintImage){
targetElement = inpaintImage;
var tabIndex = get_tab_index('mode_img2img')
if(tabIndex == 0){
targetElement = gradioApp().querySelector('div[data-testid=image] img');
} else if(tabIndex == 1){
targetElement = gradioApp().querySelector('#img2maskimg div[data-testid=image] img');
}
if(targetElement){
@ -98,22 +89,20 @@ onUiUpdate(function(){
var inImg2img = Boolean(gradioApp().querySelector("button.rounded-t-lg.border-gray-200"))
if(inImg2img){
let inputs = gradioApp().querySelectorAll('input');
inputs.forEach(function(e){
let parentLabel = e.parentElement.querySelector('label')
if(parentLabel && parentLabel.innerText){
if(!e.classList.contains('scrollwatch')){
if(parentLabel.innerText == 'Width' || parentLabel.innerText == 'Height'){
e.addEventListener('input', function(e){dimensionChange(e,parentLabel.innerText)} )
e.classList.add('scrollwatch')
}
if(parentLabel.innerText == 'Width'){
currentWidth = e.value*1.0
}
if(parentLabel.innerText == 'Height'){
currentHeight = e.value*1.0
}
}
}
inputs.forEach(function(e){
var is_width = e.parentElement.id == "img2img_width"
var is_height = e.parentElement.id == "img2img_height"
if((is_width || is_height) && !e.classList.contains('scrollwatch')){
e.addEventListener('input', function(e){dimensionChange(e, is_width, is_height)} )
e.classList.add('scrollwatch')
}
if(is_width){
currentWidth = e.value*1.0
}
if(is_height){
currentHeight = e.value*1.0
}
})
}
});

2
javascript/dragdrop.js vendored
View file

@ -43,7 +43,7 @@ function dropReplaceImage( imgWrap, files ) {
window.document.addEventListener('dragover', e => {
const target = e.composedPath()[0];
const imgWrap = target.closest('[data-testid="image"]');
if ( !imgWrap && target.placeholder.indexOf("Prompt") == -1) {
if ( !imgWrap && target.placeholder && target.placeholder.indexOf("Prompt") == -1) {
return;
}
e.stopPropagation();

35
javascript/edit-attention.js
View file

@ -9,9 +9,38 @@ addEventListener('keydown', (event) => {
let minus = "ArrowDown"
if (event.key != plus && event.key != minus) return;
selectionStart = target.selectionStart;
selectionEnd = target.selectionEnd;
if(selectionStart == selectionEnd) return;
let selectionStart = target.selectionStart;
let selectionEnd = target.selectionEnd;
// If the user hasn't selected anything, let's select their current parenthesis block
if (selectionStart === selectionEnd) {
// Find opening parenthesis around current cursor
const before = target.value.substring(0, selectionStart);
let beforeParen = before.lastIndexOf("(");
if (beforeParen == -1) return;
let beforeParenClose = before.lastIndexOf(")");
while (beforeParenClose !== -1 && beforeParenClose > beforeParen) {
beforeParen = before.lastIndexOf("(", beforeParen - 1);
beforeParenClose = before.lastIndexOf(")", beforeParenClose - 1);
}
// Find closing parenthesis around current cursor
const after = target.value.substring(selectionStart);
let afterParen = after.indexOf(")");
if (afterParen == -1) return;
let afterParenOpen = after.indexOf("(");
while (afterParenOpen !== -1 && afterParen > afterParenOpen) {
afterParen = after.indexOf(")", afterParen + 1);
afterParenOpen = after.indexOf("(", afterParenOpen + 1);
}
if (beforeParen === -1 || afterParen === -1) return;
// Set the selection to the text between the parenthesis
const parenContent = target.value.substring(beforeParen + 1, selectionStart + afterParen);
const lastColon = parenContent.lastIndexOf(":");
selectionStart = beforeParen + 1;
selectionEnd = selectionStart + lastColon;
target.setSelectionRange(selectionStart, selectionEnd);
}
event.preventDefault();

2
javascript/hints.js
View file

@ -91,6 +91,8 @@ titles = {
"Weighted sum": "Result = A * (1 - M) + B * M",
"Add difference": "Result = A + (B - C) * M",
"Learning rate": "how fast should the training go. Low values will take longer to train, high values may fail to converge (not generate accurate results) and/or may break the embedding (This has happened if you see Loss: nan in the training info textbox. If this happens, you need to manually restore your embedding from an older not-broken backup).\n\nYou can set a single numeric value, or multiple learning rates using the syntax:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nWill train with rate of 0.005 for first 100 steps, then 1e-3 until 1000 steps, then 1e-5 for all remaining steps.",
}

114
javascript/images_history.js
View file

@ -17,14 +17,6 @@ var images_history_click_image = function(){
images_history_set_image_info(this);
}
var images_history_click_tab = function(){
var tabs_box = gradioApp().getElementById("images_history_tab");
if (!tabs_box.classList.contains(this.getAttribute("tabname"))) {
gradioApp().getElementById(this.getAttribute("tabname") + "_images_history_renew_page").click();
tabs_box.classList.add(this.getAttribute("tabname"))
}
}
function images_history_disabled_del(){
gradioApp().querySelectorAll(".images_history_del_button").forEach(function(btn){
btn.setAttribute('disabled','disabled');
@ -43,7 +35,6 @@ function images_history_get_parent_by_tagname(item, tagname){
var parent = item.parentElement;
tagname = tagname.toUpperCase()
while(parent.tagName != tagname){
console.log(parent.tagName, tagname)
parent = parent.parentElement;
}
return parent;
@ -88,15 +79,15 @@ function images_history_set_image_info(button){
}
function images_history_get_current_img(tabname, image_path, files){
function images_history_get_current_img(tabname, img_index, files){
return [
gradioApp().getElementById(tabname + '_images_history_set_index').getAttribute("img_index"),
image_path,
tabname,
gradioApp().getElementById(tabname + '_images_history_set_index').getAttribute("img_index"),
files
];
}
function images_history_delete(del_num, tabname, img_path, img_file_name, page_index, filenames, image_index){
function images_history_delete(del_num, tabname, image_index){
image_index = parseInt(image_index);
var tab = gradioApp().getElementById(tabname + '_images_history');
var set_btn = tab.querySelector(".images_history_set_index");
@ -107,6 +98,7 @@ function images_history_delete(del_num, tabname, img_path, img_file_name, page_i
}
});
var img_num = buttons.length / 2;
del_num = Math.min(img_num - image_index, del_num)
if (img_num <= del_num){
setTimeout(function(tabname){
gradioApp().getElementById(tabname + '_images_history_renew_page').click();
@ -114,30 +106,28 @@ function images_history_delete(del_num, tabname, img_path, img_file_name, page_i
} else {
var next_img
for (var i = 0; i < del_num; i++){
if (image_index + i < image_index + img_num){
buttons[image_index + i].style.display = 'none';
buttons[image_index + img_num + 1].style.display = 'none';
next_img = image_index + i + 1
}
buttons[image_index + i].style.display = 'none';
buttons[image_index + i + img_num].style.display = 'none';
next_img = image_index + i + 1
}
var bnt;
if (next_img >= img_num){
btn = buttons[image_index - del_num];
btn = buttons[image_index - 1];
} else {
btn = buttons[next_img];
}
setTimeout(function(btn){btn.click()}, 30, btn);
}
images_history_disabled_del();
return [del_num, tabname, img_path, img_file_name, page_index, filenames, image_index];
}
function images_history_turnpage(img_path, page_index, image_index, tabname){
function images_history_turnpage(tabname){
gradioApp().getElementById(tabname + '_images_history_del_button').setAttribute('disabled','disabled');
var buttons = gradioApp().getElementById(tabname + '_images_history').querySelectorAll(".gallery-item");
buttons.forEach(function(elem) {
elem.style.display = 'block';
})
return [img_path, page_index, image_index, tabname];
})
}
function images_history_enable_del_buttons(){
@ -147,60 +137,64 @@ function images_history_enable_del_buttons(){
}
function images_history_init(){
var load_txt2img_button = gradioApp().getElementById('txt2img_images_history_renew_page')
if (load_txt2img_button){
var tabnames = gradioApp().getElementById("images_history_tabnames_list")
if (tabnames){
images_history_tab_list = tabnames.querySelector("textarea").value.split(",")
for (var i in images_history_tab_list ){
tab = images_history_tab_list[i];
var tab = images_history_tab_list[i];
gradioApp().getElementById(tab + '_images_history').classList.add("images_history_cantainor");
gradioApp().getElementById(tab + '_images_history_set_index').classList.add("images_history_set_index");
gradioApp().getElementById(tab + '_images_history_del_button').classList.add("images_history_del_button");
gradioApp().getElementById(tab + '_images_history_gallery').classList.add("images_history_gallery");
gradioApp().getElementById(tab + '_images_history_gallery').classList.add("images_history_gallery");
gradioApp().getElementById(tab + "_images_history_start").setAttribute("style","padding:20px;font-size:25px");
}
var tabs_box = gradioApp().getElementById("tab_images_history").querySelector("div").querySelector("div").querySelector("div");
tabs_box.setAttribute("id", "images_history_tab");
var tab_btns = tabs_box.querySelectorAll("button");
for (var i in images_history_tab_list){
var tabname = images_history_tab_list[i]
tab_btns[i].setAttribute("tabname", tabname);
// this refreshes history upon tab switch
// until the history is known to work well, which is not the case now, we do not do this at startup
//tab_btns[i].addEventListener('click', images_history_click_tab);
}
tabs_box.classList.add(images_history_tab_list[0]);
// same as above, at page load
//load_txt2img_button.click();
//preload
if (gradioApp().getElementById("images_history_preload").querySelector("input").checked ){
var tabs_box = gradioApp().getElementById("tab_images_history").querySelector("div").querySelector("div").querySelector("div");
tabs_box.setAttribute("id", "images_history_tab");
var tab_btns = tabs_box.querySelectorAll("button");
for (var i in images_history_tab_list){
var tabname = images_history_tab_list[i]
tab_btns[i].setAttribute("tabname", tabname);
tab_btns[i].addEventListener('click', function(){
var tabs_box = gradioApp().getElementById("images_history_tab");
if (!tabs_box.classList.contains(this.getAttribute("tabname"))) {
gradioApp().getElementById(this.getAttribute("tabname") + "_images_history_start").click();
tabs_box.classList.add(this.getAttribute("tabname"))
}
});
}
tab_btns[0].click()
}
} else {
setTimeout(images_history_init, 500);
}
}
var images_history_tab_list = ["txt2img", "img2img", "extras"];
var images_history_tab_list = "";
setTimeout(images_history_init, 500);
document.addEventListener("DOMContentLoaded", function() {
var mutationObserver = new MutationObserver(function(m){
for (var i in images_history_tab_list ){
let tabname = images_history_tab_list[i]
var buttons = gradioApp().querySelectorAll('#' + tabname + '_images_history .gallery-item');
buttons.forEach(function(bnt){
bnt.addEventListener('click', images_history_click_image, true);
});
if (images_history_tab_list != ""){
for (var i in images_history_tab_list ){
let tabname = images_history_tab_list[i]
var buttons = gradioApp().querySelectorAll('#' + tabname + '_images_history .gallery-item');
buttons.forEach(function(bnt){
bnt.addEventListener('click', images_history_click_image, true);
});
// same as load_txt2img_button.click() above
/*
var cls_btn = gradioApp().getElementById(tabname + '_images_history_gallery').querySelector("svg");
if (cls_btn){
cls_btn.addEventListener('click', function(){
gradioApp().getElementById(tabname + '_images_history_renew_page').click();
}, false);
}*/
var cls_btn = gradioApp().getElementById(tabname + '_images_history_gallery').querySelector("svg");
if (cls_btn){
cls_btn.addEventListener('click', function(){
gradioApp().getElementById(tabname + '_images_history_renew_page').click();
}, false);
}
}
}
}
});
mutationObserver.observe( gradioApp(), { childList:true, subtree:true });
mutationObserver.observe(gradioApp(), { childList:true, subtree:true });
});

7
javascript/ui.js
View file

@ -1,5 +1,12 @@
// various functions for interation with ui.py not large enough to warrant putting them in separate files
function set_theme(theme){
gradioURL = window.location.href
if (!gradioURL.includes('?__theme=')) {
window.location.replace(gradioURL + '?__theme=' + theme);
}
}
function selected_gallery_index(){
var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem .gallery-item')
var button = gradioApp().querySelector('[style="display: block;"].tabitem .gallery-item.\\!ring-2')

49
launch.py
View file

@ -86,7 +86,24 @@ def git_clone(url, dir, name, commithash=None):
if commithash is not None:
run(f'"{git}" -C {dir} checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
def version_check(commit):
try:
import requests
commits = requests.get('https://api.github.com/repos/AUTOMATIC1111/stable-diffusion-webui/branches/master').json()
if commit != "<none>" and commits['commit']['sha'] != commit:
print("--------------------------------------------------------")
print("| You are not up to date with the most recent release. |")
print("| Consider running `git pull` to update. |")
print("--------------------------------------------------------")
elif commits['commit']['sha'] == commit:
print("You are up to date with the most recent release.")
else:
print("Not a git clone, can't perform version check.")
except Exception as e:
print("versipm check failed",e)
def prepare_enviroment():
torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113")
requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
@ -110,13 +127,14 @@ def prepare_enviroment():
codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
args = shlex.split(commandline_args)
sys.argv += shlex.split(commandline_args)
args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
args, reinstall_xformers = extract_arg(args, '--reinstall-xformers')
xformers = '--xformers' in args
deepdanbooru = '--deepdanbooru' in args
ngrok = '--ngrok' in args
sys.argv, skip_torch_cuda_test = extract_arg(sys.argv, '--skip-torch-cuda-test')
sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
sys.argv, update_check = extract_arg(sys.argv, '--update-check')
xformers = '--xformers' in sys.argv
deepdanbooru = '--deepdanbooru' in sys.argv
ngrok = '--ngrok' in sys.argv
try:
commit = run(f"{git} rev-parse HEAD").strip()
@ -125,7 +143,7 @@ def prepare_enviroment():
print(f"Python {sys.version}")
print(f"Commit hash: {commit}")
if not is_installed("torch") or not is_installed("torchvision"):
run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch")
@ -138,9 +156,15 @@ def prepare_enviroment():
if not is_installed("clip"):
run_pip(f"install {clip_package}", "clip")
if (not is_installed("xformers") or reinstall_xformers) and xformers and platform.python_version().startswith("3.10"):
if (not is_installed("xformers") or reinstall_xformers) and xformers:
if platform.system() == "Windows":
run_pip(f"install -U -I --no-deps {xformers_windows_package}", "xformers")
if platform.python_version().startswith("3.10"):
run_pip(f"install -U -I --no-deps {xformers_windows_package}", "xformers")
else:
print("Installation of xformers is not supported in this version of Python.")
print("You can also check this and build manually: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers#building-xformers-on-windows-by-duckness")
if not is_installed("xformers"):
exit(0)
elif platform.system() == "Linux":
run_pip("install xformers", "xformers")
@ -163,9 +187,10 @@ def prepare_enviroment():
run_pip(f"install -r {requirements_file}", "requirements for Web UI")
sys.argv += args
if "--exit" in args:
if update_check:
version_check(commit)
if "--exit" in sys.argv:
print("Exiting because of --exit argument")
exit(0)

413
localizations/ja_JP.json Normal file
View file

@ -0,0 +1,413 @@
{
"⤡": "⤡",
"⊞": "⊞",
"×": "×",
"❮": "❮",
"❯": "❯",
"Loading...": "読み込み中...",
"view": "view",
"api": "api",
"•": "•",
"gradioで作ろう": "gradioで作ろう",
"Stable Diffusion checkpoint": "Stable Diffusion checkpoint",
"txt2img": "txt2img",
"img2img": "img2img",
"Extras": "その他",
"PNG Info": "PNG内の情報を表示",
"History": "履歴",
"Checkpoint Merger": "Checkpointの統合",
"Train": "学習",
"Settings": "設定",
"Prompt": "プロンプト",
"Negative prompt": "ネガティブ プロンプト",
"Run": "実行",
"Skip": "スキップ",
"Interrupt": "中断",
"Generate": "生成！",
"Style 1": "スタイル 1",
"Style 2": "スタイル 2",
"Label": "ラベル",
"File": "ファイル",
"ここにファイルをドロップ": "ここにファイルをドロップ",
"-": "-",
"または": "または",
"クリックしてアップロード": "クリックしてアップロード",
"Image": "画像",
"Check progress": "Check progress",
"Check progress (first)": "Check progress (first)",
"Sampling Steps": "サンプリング回数",
"Sampling method": "サンプリングアルゴリズム",
"Euler a": "Euler a",
"Euler": "Euler",
"LMS": "LMS",
"Heun": "Heun",
"DPM2": "DPM2",
"DPM2 a": "DPM2 a",
"DPM fast": "DPM fast",
"DPM adaptive": "DPM adaptive",
"LMS Karras": "LMS Karras",
"DPM2 Karras": "DPM2 Karras",
"DPM2 a Karras": "DPM2 a Karras",
"DDIM": "DDIM",
"PLMS": "PLMS",
"Width": "幅",
"Height": "高さ",
"Restore faces": "顔修復",
"Tiling": "テクスチャ生成モード",
"Highres. fix": "高解像度 fix(マウスオーバーで詳細)",
"Firstpass width": "Firstpass width",
"Firstpass height": "Firstpass height",
"Denoising strength": "ノイズ除去 強度",
"Batch count": "バッチ生成回数",
"Batch size": "バッチあたり生成枚数",
"CFG Scale": "CFG Scale",
"Seed": "シード値",
"Extra": "その他",
"Variation seed": "Variation シード値",
"Variation strength": "Variation 強度",
"Resize seed from width": "Resize seed from width",
"Resize seed from height": "Resize seed from height",
"Script": "スクリプト",
"None": "なし",
"Prompt matrix": "Prompt matrix",
"Prompts from file or textbox": "Prompts from file or textbox",
"X/Y plot": "X/Y plot",
"Put variable parts at start of prompt": "Put variable parts at start of prompt",
"Show Textbox": "Show Textbox",
"File with inputs": "File with inputs",
"Prompts": "プロンプト",
"X type": "X軸の種類",
"Nothing": "なし",
"Var. seed": "Var. seed",
"Var. strength": "Var. 強度",
"Steps": "ステップ数",
"Prompt S/R": "Prompt S/R",
"Prompt order": "Prompt order",
"Sampler": "サンプラー",
"Checkpoint name": "Checkpoint名",
"Hypernetwork": "Hypernetwork",
"Hypernet str.": "Hypernet強度",
"Sigma Churn": "Sigma Churn",
"Sigma min": "Sigma min",
"Sigma max": "Sigma max",
"Sigma noise": "Sigma noise",
"Eta": "Eta",
"Clip skip": "Clip skip",
"Denoising": "Denoising",
"X values": "Xの値",
"Y type": "Y軸の種類",
"Y values": "Yの値",
"Draw legend": "凡例を描画",
"Include Separate Images": "Include Separate Images",
"Keep -1 for seeds": "シード値を-1で固定",
"ここに画像をドロップ": "ここに画像をドロップ",
"Save": "保存",
"Send to img2img": "img2imgに送る",
"Send to inpaint": "描き直しに送る",
"Send to extras": "その他タブに送る",
"Make Zip when Save?": "保存するときZipも同時に作る",
"Textbox": "Textbox",
"Interrogate\nCLIP": "Interrogate\nCLIP",
"Interrogate\nDeepBooru": "Interrogate\nDeepBooru",
"Inpaint": "描き直し(Inpaint)",
"Batch img2img": "Batch img2img",
"Image for img2img": "Image for img2img",
"Image for inpainting with mask": "Image for inpainting with mask",
"Mask": "Mask",
"Mask blur": "Mask blur",
"Mask mode": "Mask mode",
"Draw mask": "Draw mask",
"Upload mask": "Upload mask",
"Masking mode": "Masking mode",
"Inpaint masked": "Inpaint masked",
"Inpaint not masked": "Inpaint not masked",
"Masked content": "Masked content",
"fill": "fill",
"original": "オリジナル",
"latent noise": "latent noise",
"latent nothing": "latent nothing",
"Inpaint at full resolution": "Inpaint at full resolution",
"Inpaint at full resolution padding, pixels": "Inpaint at full resolution padding, pixels",
"Process images in a directory on the same machine where the server is running.": "Process images in a directory on the same machine where the server is running.",
"Use an empty output directory to save pictures normally instead of writing to the output directory.": "Use an empty output directory to save pictures normally instead of writing to the output directory.",
"Input directory": "入力フォルダ",
"Output directory": "出力フォルダ",
"Resize mode": "リサイズモード",
"Just resize": "リサイズのみ",
"Crop and resize": "切り取ってからリサイズ",
"Resize and fill": "リサイズして埋める",
"img2img alternative test": "img2img alternative test",
"Loopback": "ループバック",
"Outpainting mk2": "Outpainting mk2",
"Poor man's outpainting": "Poor man's outpainting",
"SD upscale": "SD アップスケール",
"should be 2 or lower.": "2以下にすること",
"Override `Sampling method` to Euler?(this method is built for it)": "サンプリングアルゴリズムをEulerに上書きする(そうすることを前提に設計されています)",
"Override `prompt` to the same value as `original prompt`?(and `negative prompt`)": "Override `prompt` to the same value as `original prompt`?(and `negative prompt`)",
"Original prompt": "Original prompt",
"Original negative prompt": "Original negative prompt",
"Override `Sampling Steps` to the same value as `Decode steps`?": "Override `Sampling Steps` to the same value as `Decode steps`?",
"Decode steps": "Decode steps",
"Override `Denoising strength` to 1?": "Override `Denoising strength` to 1?",
"Decode CFG scale": "Decode CFG scale",
"Randomness": "Randomness",
"Sigma adjustment for finding noise for image": "Sigma adjustment for finding noise for image",
"Loops": "Loops",
"Denoising strength change factor": "Denoising strength change factor",
"Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8": "Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8",
"Pixels to expand": "Pixels to expand",
"Outpainting direction": "Outpainting direction",
"left": "左",
"right": "右",
"up": "上",
"down": "下",
"Fall-off exponent (lower=higher detail)": "Fall-off exponent (lower=higher detail)",
"Color variation": "Color variation",
"Will upscale the image to twice the dimensions; use width and height sliders to set tile size": "画像を2倍の大きさにアップスケールします。幅と高さのスライダーでタイルの大きさを設定します。",
"Tile overlap": "Tile overlap",
"Upscaler": "アップスケーラー",
"Lanczos": "Lanczos",
"LDSR": "LDSR",
"BSRGAN 4x": "BSRGAN 4x",
"ESRGAN_4x": "ESRGAN_4x",
"ScuNET GAN": "ScuNET GAN",
"ScuNET PSNR": "ScuNET PSNR",
"SwinIR 4x": "SwinIR 4x",
"Single Image": "単一画像",
"Batch Process": "バッチ処理",
"Batch from Directory": "フォルダからバッチ処理",
"Source": "入力",
"Show result images": "出力画像を表示",
"Scale by": "倍率指定",
"Scale to": "解像度指定",
"Resize": "倍率",
"Crop to fit": "合うように切り抜き",
"Upscaler 2": "アップスケーラー 2",
"Upscaler 2 visibility": "Upscaler 2 visibility",
"GFPGAN visibility": "GFPGAN visibility",
"CodeFormer visibility": "CodeFormer visibility",
"CodeFormer weight (0 = maximum effect, 1 = minimum effect)": "CodeFormer weight (0 = maximum effect, 1 = minimum effect)",
"Open output directory": "出力フォルダを開く",
"Send to txt2img": "txt2imgに送る",
"txt2img history": "txt2imgの履歴",
"img2img history": "img2imgの履歴",
"extras history": "その他タブの履歴",
"Renew Page": "更新",
"First Page": "最初のぺージへ",
"Prev Page": "前ページへ",
"Page Index": "ページ番号",
"Next Page": "次ページへ",
"End Page": "最後のページへ",
"number of images to delete consecutively next": "number of images to delete consecutively next",
"Delete": "削除",
"Generate Info": "生成情報",
"File Name": "ファイル名",
"set_index": "set_index",
"A merger of the two checkpoints will be generated in your": "統合されたチェックポイントはあなたの",
"checkpoint": "checkpoint",
"directory.": "フォルダに保存されます.",
"Primary model (A)": "1つめのmodel (A)",
"Secondary model (B)": "2つめのmodel (B)",
"Tertiary model (C)": "3つめのmodel (C)",
"Custom Name (Optional)": "Custom Name (任意)",
"Multiplier (M) - set to 0 to get model A": "Multiplier (M) 0にすると完全にmodel Aとなります (ツールチップ参照)",
"Interpolation Method": "混合(Interpolation)方式",
"Weighted sum": "加重平均",
"Add difference": "差を加える",
"Save as float16": "float16で保存",
"See": "詳細な説明については",
"wiki": "wiki",
"for detailed explanation.": "を見てください。",
"Create embedding": "Embeddingを作る",
"Create hypernetwork": "Hypernetworkを作る",
"Preprocess images": "画像の前処理",
"Name": "ファイル名",
"Initialization text": "Initialization text",
"Number of vectors per token": "Number of vectors per token",
"Modules": "Modules",
"Source directory": "入力フォルダ",
"Destination directory": "出力フォルダ",
"Create flipped copies": "反転画像を生成する",
"Split oversized images into two": "大きすぎる画像を2分割する",
"Use BLIP for caption": "BLIPで説明をつける",
"Use deepbooru for caption": "deepbooruで説明をつける",
"Preprocess": "前処理開始",
"Train an embedding; must specify a directory with a set of 1:1 ratio images": "embeddingの学習をします;データセット内の画像は正方形でなければなりません。",
"Embedding": "Embedding",
"Learning rate": "学習率",
"Dataset directory": "データセットフォルダ",
"Log directory": "ログフォルダ",
"Prompt template file": "Prompt template file",
"Max steps": "最大ステップ数",
"Save an image to log directory every N steps, 0 to disable": "指定したステップ数ごとに画像を生成し、ログに保存する。0で無効化。",
"Save a copy of embedding to log directory every N steps, 0 to disable": "指定したステップ数ごとにEmbeddingのコピーをログに保存する。0で無効化。",
"Save images with embedding in PNG chunks": "保存する画像にembeddingを埋め込む",
"Read parameters (prompt, etc...) from txt2img tab when making previews": "Read parameters (prompt, etc...) from txt2img tab when making previews",
"Train Hypernetwork": "Hypernetworkの学習を開始",
"Train Embedding": "Embeddingの学習を開始",
"Apply settings": "Apply settings",
"Saving images/grids": "画像/グリッドの保存",
"Always save all generated images": "生成された画像をすべて保存する",
"File format for images": "画像ファイルの保存形式",
"Images filename pattern": "ファイル名のパターン",
"Always save all generated image grids": "グリッド画像を常に保存する",
"File format for grids": "グリッド画像の保存形式",
"Add extended info (seed, prompt) to filename when saving grid": "保存するグリッド画像のファイル名に追加情報(シード値、プロンプト)を加える",
"Do not save grids consisting of one picture": "1画像からなるグリッド画像は保存しない",
"Prevent empty spots in grid (when set to autodetect)": "(自動設定のとき)グリッドに空隙が生じるのを防ぐ",
"Grid row count; use -1 for autodetect and 0 for it to be same as batch size": "グリッドの列数; -1で自動設定、0でバッチ生成回数と同じにする",
"Save text information about generation parameters as chunks to png files": "生成に関するパラメーターをpng画像に含める",
"Create a text file next to every image with generation parameters.": "保存する画像とともに生成パラメータをテキストファイルで保存する",
"Save a copy of image before doing face restoration.": "顔修復を行う前にコピーを保存しておく。",
"Quality for saved jpeg images": "JPG保存時の画質",
"If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG": "PNG画像が4MBを超えるか、どちらか1辺の長さが4000を超えたなら、ダウンスケールしてコピーを別にJPGで保存する",
"Use original name for output filename during batch process in extras tab": "Use original name for output filename during batch process in extras tab",
"When using 'Save' button, only save a single selected image": "When using 'Save' button, only save a single selected image",
"Do not add watermark to images": "電子透かしを画像に追加しない",
"Paths for saving": "Paths for saving",
"Output directory for images; if empty, defaults to three directories below": "画像の保存先フォルダ(下項目のデフォルト値になります)",
"Output directory for txt2img images": "txt2imgで作った画像の保存先フォルダ",
"Output directory for img2img images": "img2imgで作った画像の保存先フォルダ",
"Output directory for images from extras tab": "その他タブで作った画像の保存先フォルダ",
"Output directory for grids; if empty, defaults to two directories below": "画像の保存先フォルダ(下項目のデフォルト値になります)",
"Output directory for txt2img grids": "txt2imgで作ったグリッドの保存先フォルダ",
"Output directory for img2img grids": "img2imgで作ったグリッドの保存先フォルダ",
"Directory for saving images using the Save button": "保存ボタンを押したときの画像の保存先フォルダ",
"Saving to a directory": "フォルダについて",
"Save images to a subdirectory": "画像をサブフォルダに保存する",
"Save grids to a subdirectory": "グリッドをサブフォルダに保存する",
"When using \"Save\" button, save images to a subdirectory": "保存ボタンを押した時、画像をサブフォルダに保存する",
"Directory name pattern": "フォルダ名のパターン",
"Max prompt words for [prompt_words] pattern": "Max prompt words for [prompt_words] pattern",
"Upscaling": "アップスケール",
"Tile size for ESRGAN upscalers. 0 = no tiling.": "ESRGANのタイルサイズ。0とするとタイルしない。",
"Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.": "ESRGANのタイルの重複部分のピクセル数。少なくするとつなぎ目が見えやすくなる。",
"Tile size for all SwinIR.": "SwinIRのタイルサイズ",
"Tile overlap, in pixels for SwinIR. Low values = visible seam.": "SwinIRのタイルの重複部分のピクセル数。少なくするとつなぎ目が見えやすくなる。",
"LDSR processing steps. Lower = faster": "LDSR processing steps. Lower = faster",
"Upscaler for img2img": "img2imgで使うアップスケーラー",
"Upscale latent space image when doing hires. fix": "高解像度 fix時に潜在空間(latent space)の画像をアップスケールする",
"Face restoration": "顔修復",
"CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect": "CodeFormerの重みパラメーター;0が最大で1が最小",
"Move face restoration model from VRAM into RAM after processing": "処理終了後、顔修復モデルをVRAMからRAMへと移動する",
"System": "システム設定",
"VRAM usage polls per second during generation. Set to 0 to disable.": "VRAM usage polls per second during generation. Set to 0 to disable.",
"Always print all generation info to standard output": "常にすべての生成に関する情報を標準出力(stdout)に出力する",
"Add a second progress bar to the console that shows progress for an entire job.": "Add a second progress bar to the console that shows progress for an entire job.",
"Training": "学習",
"Unload VAE and CLIP from VRAM when training": "学習を行う際、VAEとCLIPをVRAMから削除する",
"Filename word regex": "Filename word regex",
"Filename join string": "Filename join string",
"Number of repeats for a single input image per epoch; used only for displaying epoch number": "Number of repeats for a single input image per epoch; used only for displaying epoch number",
"Save an csv containing the loss to log directory every N steps, 0 to disable": "Save an csv containing the loss to log directory every N steps, 0 to disable",
"Stable Diffusion": "Stable Diffusion",
"Checkpoints to cache in RAM": "RAMにキャッシュするCheckpoint数",
"Hypernetwork strength": "Hypernetwork strength",
"Apply color correction to img2img results to match original colors.": "元画像に合わせてimg2imgの結果を色補正する",
"Save a copy of image before applying color correction to img2img results": "色補正をする前の画像も保存する",
"With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising).": "img2imgでスライダーで指定されたステップ数を正確に実行する（通常は、ノイズ除去を少なくするためにより少ないステップ数で実行します）。",
"Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply.": "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply.",
"Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention": "強調: (text)とするとモデルはtextをより強く扱い、[text]とするとモデルはtextをより弱く扱います。",
"Use old emphasis implementation. Can be useful to reproduce old seeds.": "古い強調の実装を使う。古い生成物を再現するのに使えます。",
"Make K-diffusion samplers produce same images in a batch as when making a single image": "Make K-diffusion samplers produce same images in a batch as when making a single image",
"Increase coherency by padding from the last comma within n tokens when using more than 75 tokens": "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens",
"Filter NSFW content": "NSFW(≒R-18)なコンテンツを検閲する",
"Stop At last layers of CLIP model": "最後から何層目でCLIPを止めるか(stop…layers of CLIP model)",
"Interrogate Options": "Interrogate 設定",
"Interrogate: keep models in VRAM": "Interrogate: モデルをVRAMに保持する",
"Interrogate: use artists from artists.csv": "Interrogate: artists.csvにある芸術家などの名称を利用する",
"Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators).": "Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators).",
"Interrogate: num_beams for BLIP": "Interrogate: num_beams for BLIP",
"Interrogate: minimum description length (excluding artists, etc..)": "Interrogate: minimum description length (excluding artists, etc..)",
"Interrogate: maximum description length": "Interrogate: maximum description length",
"CLIP: maximum number of lines in text file (0 = No limit)": "CLIP: maximum number of lines in text file (0 = No limit)",
"Interrogate: deepbooru score threshold": "Interrogate: deepbooruで拾う単語のスコア閾値",
"Interrogate: deepbooru sort alphabetically": "Interrogate: deepbooruで単語をアルファベット順に並べる",
"use spaces for tags in deepbooru": "deepbooruのタグでスペースを使う",
"escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)": "deepbooruで括弧をエスケープする(\\) (強調を示す()ではなく、文字通りの()であることをモデルに示すため)",
"User interface": "UI設定",
"Show progressbar": "プログレスバーを表示",
"Show image creation progress every N sampling steps. Set 0 to disable.": "指定したステップ数ごとに画像の生成過程を表示する。0で無効化。",
"Show grid in results for web": "WebUI上でグリッド表示",
"Do not show any images in results for web": "WebUI上で一切画像を表示しない",
"Add model hash to generation information": "モデルのハッシュ値を生成情報に追加",
"Add model name to generation information": "モデルの名称を生成情報に追加",
"Font for image grids that have text": "画像グリッド内のテキストフォント",
"Enable full page image viewer": "フルページの画像ビューワーを有効化",
"Show images zoomed in by default in full page image viewer": "フルページ画像ビューアでデフォルトで画像を拡大して表示する",
"Show generation progress in window title.": "ウィンドウのタイトルで生成の進捗を表示",
"Quicksettings list": "Quicksettings list",
"Localization (requires restart)": "言語 (プログラムの再起動が必要)",
"ja_JP": "ja_JP",
"Sampler parameters": "サンプラー parameters",
"Hide samplers in user interface (requires restart)": "使わないサンプリングアルゴリズムを隠す (再起動が必要)",
"eta (noise multiplier) for DDIM": "DDIMで用いるeta (noise multiplier)",
"eta (noise multiplier) for ancestral samplers": "ancestral サンプラーで用いるeta (noise multiplier)",
"img2img DDIM discretize": "img2img DDIM discretize",
"uniform": "uniform",
"quad": "quad",
"sigma churn": "sigma churn",
"sigma tmin": "sigma tmin",
"sigma noise": "sigma noise",
"Eta noise seed delta": "Eta noise seed delta",
"Request browser notifications": "ブラウザ通知の許可を要求する",
"Download localization template": "ローカライゼーション用のテンプレートをダウンロードする",
"Reload custom script bodies (No ui updates, No restart)": "カスタムスクリプトを再読み込み (UIは変更されず、再起動もしません。)",
"Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)": "Gradioを再起動してコンポーネントをリフレッシュする (Custom Scripts, ui.py, js, cssのみ影響を受ける)",
"Prompt (press Ctrl+Enter or Alt+Enter to generate)": "プロンプト (Ctrl+Enter か Alt+Enter を押して生成)",
"Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "ネガティブ プロンプト (Ctrl+Enter か Alt+Enter を押して生成)",
"Add a random artist to the prompt.": "芸術家などの名称をプロンプトに追加",
"Read generation parameters from prompt or last generation if prompt is empty into user interface.": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
"Save style": "スタイルを保存する",
"Apply selected styles to current prompt": "現在のプロンプトに選択したスタイルを適用する",
"Stop processing current image and continue processing.": "現在の処理を中断し、その後の処理は続ける",
"Stop processing images and return any results accumulated so far.": "処理を中断し、それまでに出来た結果を表示する",
"Style to apply; styles have components for both positive and negative prompts and apply to both": "Style to apply; styles have components for both positive and negative prompts and apply to both",
"Do not do anything special": "特別なことをなにもしない",
"Which algorithm to use to produce the image": "どのアルゴリズムを使って生成するか",
"Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps to higher than 30-40 does not help": "Euler Ancestral - 非常に独創的で、ステップ数によって全く異なる画像が得られる、ステップ数を30～40より高く設定しても効果がない。",
"Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit Models - 描き直しには最適",
"Produce an image that can be tiled.": "Produce an image that can be tiled.",
"Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition": "2ステップで、まず部分的に小さい解像度で画像を作成し、その後アップスケールすることで、構図を変えずにディテールが改善されます。",
"Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.": "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.",
"How many batches of images to create": "バッチ処理を何回行うか",
"How many image to create in a single batch": "1回のバッチ処理で何枚の画像を生成するか",
"Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results": "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results",
"A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result",
"Set seed to -1, which will cause a new random number to be used every time": "シード値を -1 に設定するとランダムに生成します。",
"Reuse seed from last generation, mostly useful if it was randomed": "前回生成時のシード値を読み出す。(ランダム生成時に便利)",
"Seed of a different picture to be mixed into the generation.": "Seed of a different picture to be mixed into the generation.",
"How strong of a variation to produce. At 0, there will be no effect. At 1, you will get the complete picture with variation seed (except for ancestral samplers, where you will just get something).": "How strong of a variation to produce. At 0, there will be no effect. At 1, you will get the complete picture with variation seed (except for ancestral samplers, where you will just get something).",
"Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution": "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution",
"Separate values for X axis using commas.": "X軸に用いる値をカンマ(,)で区切って入力してください。",
"Separate values for Y axis using commas.": "Y軸に用いる値をカンマ(,)で区切って入力してください。",
"Write image to a directory (default - log/images) and generation parameters into csv file.": "Write image to a directory (default - log/images) and generation parameters into csv file.",
"Open images output directory": "画像の出力フォルダを開く",
"How much to blur the mask before processing, in pixels.": "How much to blur the mask before processing, in pixels.",
"What to put inside the masked area before processing it with Stable Diffusion.": "What to put inside the masked area before processing it with Stable Diffusion.",
"fill it with colors of the image": "fill it with colors of the image",
"keep whatever was there originally": "keep whatever was there originally",
"fill it with latent space noise": "fill it with latent space noise",
"fill it with latent space zeroes": "fill it with latent space zeroes",
"Upscale masked region to target resolution, do inpainting, downscale back and paste into original image": "Upscale masked region to target resolution, do inpainting, downscale back and paste into original image",
"Resize image to target resolution. Unless height and width match, you will get incorrect aspect ratio.": "Resize image to target resolution. Unless height and width match, you will get incorrect aspect ratio.",
"Resize the image so that entirety of target resolution is filled with the image. Crop parts that stick out.": "Resize the image so that entirety of target resolution is filled with the image. Crop parts that stick out.",
"Resize the image so that entirety of image is inside target resolution. Fill empty space with image's colors.": "Resize the image so that entirety of image is inside target resolution. Fill empty space with image's colors.",
"How many times to repeat processing an image and using it as input for the next iteration": "How many times to repeat processing an image and using it as input for the next iteration",
"In loopback mode, on each loop the denoising strength is multiplied by this value. <1 means decreasing variety so your sequence will converge on a fixed picture. >1 means increasing variety so your sequence will become more and more chaotic.": "In loopback mode, on each loop the denoising strength is multiplied by this value. <1 means decreasing variety so your sequence will converge on a fixed picture. >1 means increasing variety so your sequence will become more and more chaotic.",
"For SD upscale, how much overlap in pixels should there be between tiles. Tiles overlap so that when they are merged back into one picture, there is no clearly visible seam.": "For SD upscale, how much overlap in pixels should there be between tiles. Tiles overlap so that when they are merged back into one picture, there is no clearly visible seam.",
"A directory on the same machine where the server is running.": "A directory on the same machine where the server is running.",
"Leave blank to save images to the default path.": "空欄でデフォルトの場所へ画像を保存",
"Result = A * (1 - M) + B * M": "結果モデル = A * (1 - M) + B * M",
"Result = A + (B - C) * M": "結果モデル = A + (B - C) * M",
"Path to directory with input images": "Path to directory with input images",
"Path to directory where to write outputs": "Path to directory where to write outputs",
"Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.",
"If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.": "このオプションを有効にすると、作成された画像にウォーターマークが追加されなくなります。警告:ウォーターマークを追加しない場合、非倫理的な行動とみなされる場合があります。",
"Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.",
"Restore low quality faces using GFPGAN neural network": "GFPGANを用いて低クオリティーの画像を修復",
"This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.": "This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.",
"This string will be used to join split words into a single line if the option above is enabled.": "This string will be used to join split words into a single line if the option above is enabled.",
"List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.": "List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.",
"If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing."
}

475
localizations/ru_RU.json Normal file
View file

@ -0,0 +1,475 @@
{
"⤡": "⤡",
"⊞": "⊞",
"×": "×",
"❮": "❮",
"❯": "❯",
"Loading...": "Загрузка...",
"view": "просмотр",
"api": "api",
"•": "•",
"built with gradio": "На основе Gradio",
"Stable Diffusion checkpoint": "Веса Stable Diffusion",
"txt2img": "текст-в-рисунок",
"img2img": "рисунок-в-рисунок",
"Extras": "Дополнения",
"PNG Info": "Информация о PNG",
"Image Browser": "Просмотр изображений",
"History": "Журнал",
"Checkpoint Merger": "Слияние весов",
"Train": "Обучение",
"Create aesthetic embedding": "Создать эмбеддинг эстетики",
"Settings": "Настройки",
"Prompt": "Запрос",
"Negative prompt": "Исключающий запрос",
"Run": "Запустить",
"Skip": "Пропустить",
"Interrupt": "Прервать",
"Generate": "Создать",
"Style 1": "Стиль 1",
"Style 2": "Стиль 2",
"Label": "Метка",
"File": "Файл",
"Drop File Here": "Перетащите файл сюда",
"-": "-",
"or": "или",
"Click to Upload": "Нажмите, чтобы загрузить",
"Image": "Рисунок",
"Check progress": "Узнать состояние",
"Check progress (first)": "Узнать состояние первого",
"Sampling Steps": "Шагов семплера",
"Sampling method": "Метод семплирования",
"Euler a": "Euler a",
"Euler": "Euler",
"LMS": "LMS",
"Heun": "Heun",
"DPM2": "DPM2",
"DPM2 a": "DPM2 a",
"DPM fast": "DPM fast",
"DPM adaptive": "DPM adaptive",
"LMS Karras": "LMS Karras",
"DPM2 Karras": "DPM2 Karras",
"DPM2 a Karras": "DPM2 a Karras",
"DDIM": "DDIM",
"PLMS": "PLMS",
"Width": "Ширина",
"Height": "Высота",
"Restore faces": "Восстановить лица",
"Tiling": "Замощение",
"Highres. fix": "HD-режим",
"Firstpass width": "Ширина первого прохода",
"Firstpass height": "Высота первого прохода",
"Denoising strength": "Сила шумоподавления",
"Batch count": "Рисунков подряд",
"Batch size": "Рисунков параллельно",
"CFG Scale": "Близость к запросу",
"Seed": "Семя",
"Extra": "Дополнения",
"Variation seed": "Вариация семени",
"Variation strength": "Вариация шумоподавления",
"Resize seed from width": "Поправка в семя от ширины",
"Resize seed from height": "Поправка в семя от высоты",
"Open for Clip Aesthetic!": "Clip-эстетика!",
"▼": "▼",
"Aesthetic weight": "Вес эстетики",
"Aesthetic steps": "Шагов эстетики",
"Aesthetic learning rate": "Скорость обучения эстетики",
"Slerp interpolation": "Slerp-интерполяция",
"Aesthetic imgs embedding": "Рисунки - эмбеддинги эстетики",
"None": "Ничего",
"Aesthetic text for imgs": "Имя эстетики рисунков",
"Slerp angle": "Угол slerp",
"Is negative text": "Это текст для исключения",
"Script": "Скрипт",
"Prompt matrix": "Матрица запросов",
"Prompts from file or textbox": "Запросы из файла или текста",
"X/Y plot": "X/Y-график",
"Put variable parts at start of prompt": "Переменное начало запроса",
"Show Textbox": "Показать текстовый ввод",
"File with inputs": "Файл входа",
"Prompts": "Запросы",
"X type": "Ось X",
"Nothing": "Ничего",
"Var. seed": "Вариация семени",
"Var. strength": "Вариация силы",
"Steps": "Число шагов",
"Prompt S/R": "Вариация запроса",
"Prompt order": "Порядок запросов",
"Sampler": "Семплер",
"Checkpoint name": "Имя файла весов",
"Hypernetwork": "Гиперсеть",
"Hypernet str.": "Строка гиперсети",
"Sigma Churn": "Возмущение сигмы",
"Sigma min": "Мин. сигма",
"Sigma max": "Макс. сигма",
"Sigma noise": "Сигма-шум",
"Eta": "Расчётное время",
"Clip skip": "Пропустить Clip",
"Denoising": "Шумоподавление",
"X values": "Значения X",
"Y type": "Тип Y",
"Y values": "Значения Y",
"Draw legend": "Легенда графика",
"Include Separate Images": "Включить отдельные рисунки",
"Keep -1 for seeds": "-1 для семени",
"Drop Image Here": "Перетащите рисунок сюда",
"Save": "Сохранить",
"Send to img2img": "В рисунок-в-рисунок",
"Send to inpaint": "В режим врисовывания",
"Send to extras": "В дополнения",
"Make Zip when Save?": "Создать zip при сохранении?",
"Textbox": "Текст",
"Interrogate\nCLIP": "Распознавание\nCLIP",
"Interrogate\nDeepBooru": "Распознавание\nDeepBooru",
"Inpaint": "врисовать",
"Batch img2img": "рисунок-в-рисунок (набор)",
"Image for img2img": "рисунок-в-рисунок (вход)",
"Image for inpainting with mask": "врисовать (вход с трафаретом)",
"Mask": "Трафарет",
"Mask blur": "Размытие трафарета",
"Mask mode": "Режим трафарета",
"Draw mask": "Нарисовать трафарет",
"Upload mask": "Загрузить трафарет",
"Masking mode": "Режим трафарета",
"Inpaint masked": "Внутри трафарета",
"Inpaint not masked": "Вне трафарета",
"Masked content": "Под трафаретом",
"fill": "залить",
"original": "сохранить",
"latent noise": "латентный шум",
"latent nothing": "латентная пустота",
"Inpaint at full resolution": "Врисовать при полном разрешении",
"Inpaint at full resolution padding, pixels": "Врисовать с достройкой до полного разрешения, в пикселях",
"Process images in a directory on the same machine where the server is running.": "Обрабатывать рисунки на том же компьютере, где сервер",
"Use an empty output directory to save pictures normally instead of writing to the output directory.": "Использовать пустую папку вместо того, чтобы выводить в output",
"Disabled when launched with --hide-ui-dir-config.": "Выключено при запуске с --hide-ui-dir-config",
"Input directory": "Папка входа",
"Output directory": "Папка выхода",
"Resize mode": "Масштабирование",
"Just resize": "Только сжать",
"Crop and resize": "Сжать и обрезать",
"Resize and fill": "Сжать и залить",
"img2img alternative test": "рисунок-в-рисунок (альтернатива)",
"Loopback": "Прокручивание",
"Outpainting mk2": "Обрисовыватель mk2",
"Poor man's outpainting": "Хоть какой-то обрисовыватель",
"SD upscale": "SD-апскейл",
"should be 2 or lower.": "должно быть меньше равно 2",
"Override `Sampling method` to Euler?(this method is built for it)": "Сменить метод семплирования на метод Эйлера?(скрипт строился с его учётом)",
"Override `prompt` to the same value as `original prompt`?(and `negative prompt`)": "Сменить `запрос` на `изначальный запрос`?(и `запрос-исключение`)",
"Original prompt": "Изначальный запрос",
"Original negative prompt": "Изначальный запрос-исключение",
"Override `Sampling Steps` to the same value as `Decode steps`?": "Сменить число шагов на число шагов декодирования?",
"Decode steps": "Шагов декодирования",
"Override `Denoising strength` to 1?": "Сменить силу шумоподавления на 1?",
"Decode CFG scale": "Близость к запросу декодирования",
"Randomness": "Случайность",
"Sigma adjustment for finding noise for image": "Поправка к сигме подбора шума для рисунка",
"Loops": "Циклов",
"Denoising strength change factor": "Множитель силы шумоподавления",
"Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8": "Рекоммендуемые настройки： Число шагов：80-100，Метод：Euler a，Шумоподавление：0.8",
"Pixels to expand": "Пикселов расширить",
"Outpainting direction": "Направление обрисовывания",
"left": "влево",
"right": "вправо",
"up": "вверх",
"down": "вниз",
"Fall-off exponent (lower=higher detail)": "Степень затухания （меньше=больше деталей）",
"Color variation": "Вариация цвета",
"Will upscale the image to twice the dimensions; use width and height sliders to set tile size": "Расширит рисунок дважды； ползунки ширины и высоты устанавливают размеры плиток",
"Tile overlap": "Перекрытие плиток",
"Upscaler": "Апскейлер",
"Lanczos": "Lanczos",
"LDSR": "LDSR",
"BSRGAN 4x": "BSRGAN 4x",
"ESRGAN_4x": "ESRGAN_4x",
"R-ESRGAN 4x+ Anime6B": "R-ESRGAN 4x+ Anime6B",
"ScuNET GAN": "ScuNET GAN",
"ScuNET PSNR": "ScuNET PSNR",
"SwinIR_4x": "SwinIR 4x",
"Single Image": "Один рисунок",
"Batch Process": "Набор рисунков",
"Batch from Directory": "Рисунки из папки",
"Source": "Вход",
"Show result images": "Показать результаты",
"Scale by": "Увеличить в",
"Scale to": "Увеличить до",
"Resize": "Масштабировать",
"Crop to fit": "Обрезать до рамки",
"Upscaler 2": "Апскейлер 2",
"Upscaler 2 visibility": "Видимость Апскейлера 2",
"GFPGAN visibility": "Видимость GFPGAN",
"CodeFormer visibility": "Видимость CodeFormer",
"CodeFormer weight (0 = maximum effect, 1 = minimum effect)": "Вес CodeFormer (0 = максимальное действие, 1 = минимальное)",
"Open output directory": "Открыть папку выхода",
"Send to txt2img": "В текст-в-рисунок",
"txt2img history": "журнал текста-в-рисунок",
"img2img history": "журнал рисунка-в-рисунок",
"extras history": "журнал дополнений",
"Renew Page": "Обновить страницу",
"extras": "дополнения",
"favorites": "избранное",
"Load": "Загрузить",
"Images directory": "Папка с рисунками",
"Prev batch": "Пред. набор",
"Next batch": "След. набор",
"First Page": "Первая страница",
"Prev Page": "Пред. страница",
"Page Index": "Список страниц",
"Next Page": "След. страница",
"End Page": "Конец страницы",
"number of images to delete consecutively next": "сколько рисунков удалить подряд",
"Delete": "Удалить",
"Generate Info": "Сведения о генерации",
"File Name": "Имя файла",
"Collect": "Накопить",
"Refresh page": "Обновить страницу",
"Date to": "Дата",
"Number": "Число",
"set_index": "индекс",
"Checkbox": "Галочка",
"A merger of the two checkpoints will be generated in your": "Слияние весов будет создано, где хранятся",
"checkpoint": "ckpt",
"directory.": "веса",
"Primary model (A)": "Первичная модель (A)",
"Secondary model (B)": "Вторичная модель (B)",
"Tertiary model (C)": "Третичная модель (C)",
"Custom Name (Optional)": "Произвольное имя (необязательно)",
"Multiplier (M) - set to 0 to get model A": "Множитель (M) - 0 даст модель A",
"Interpolation Method": "Метод интерполяции",
"Weighted sum": "Взвешенная сумма",
"Add difference": "Сумма разностей",
"Save as float16": "Сохранить как float16",
"See": "См.",
"wiki": "вики",
"for detailed explanation.": "для подробных объяснений.",
"Create embedding": "Создать эмбеддинг",
"Create aesthetic images embedding": "Создать эмбеддинг эстетики по рисункам",
"Create hypernetwork": "Создать гиперсеть",
"Preprocess images": "Предобработать рисунки",
"Name": "Имя",
"Initialization text": "Соответствующий текст",
"Number of vectors per token": "Векторов на токен",
"Overwrite Old Embedding": "Перезаписать эмбеддинг",
"Source directory": "Исходная папка",
"Modules": "Модули",
"Enter hypernetwork layer structure": "Структура слоёв гиперсети",
"Add layer normalization": "Добавить нормализацию слоёв",
"Overwrite Old Hypernetwork": "Перезаписать гиперсеть",
"Select activation function of hypernetwork": "Функция активации гиперсети",
"linear": "линейная",
"relu": "relu",
"leakyrelu": "leakyrelu",
"Destination directory": "Папка назначения",
"Existing Caption txt Action": "Что делать с предыдущим текстом",
"ignore": "игнорировать",
"copy": "копировать",
"prepend": "в начало",
"append": "в конец",
"Create flipped copies": "Создать отражённые копии",
"Split oversized images into two": "Поделить слишком большие рисунки пополам",
"Split oversized images": "Поделить слишком большие рисунки",
"Use BLIP for caption": "Использовать BLIP для названий",
"Use deepbooru for caption": "Использовать deepbooru для тегов",
"Split image threshold": "Порог разделения рисунков",
"Split image overlap ratio": "Пропорции разделения рисунков",
"Preprocess": "Предобработка",
"Train an embedding; must specify a directory with a set of 1:1 ratio images": "Обучить эмбеддинг； укажите папку рисунков с пропорциями 1:1",
"Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images": "Обучить эмбеддинг или гиперсеть； укажите папку рисунков с пропорциями 1:1",
"[wiki]": "[вики]",
"Embedding": "Эмбеддинг",
"Embedding Learning rate": "Скорость обучения эмбеддинга",
"Hypernetwork Learning rate": "Скорость обучения гиперсети",
"Learning rate": "Скорость обучения",
"Dataset directory": "Папка датасета",
"Log directory": "Папка журнала",
"Prompt template file": "Файл шаблона запроса",
"Max steps": "Макс. шагов",
"Save an image to log directory every N steps, 0 to disable": "Сохранять рисунок каждые N шагов, 0 чтобы отключить",
"Save a copy of embedding to log directory every N steps, 0 to disable": "Сохранять эмбеддинг каждые N шагов, 0 чтобы отключить",
"Save images with embedding in PNG chunks": "Сохранить рисунок с эмбеддингом в виде PNG-фрагментов",
"Read parameters (prompt, etc...) from txt2img tab when making previews": "Считать параметры (запрос и т.д.) из вкладки текст-в-рисунок для предпросмотра",
"Train Hypernetwork": "Обучить гиперсеть",
"Train Embedding": "Обучить эмбеддинг",
"Create an aesthetic embedding out of any number of images": "Создать эмбеддинг эстетики по любому числу рисунков",
"Create images embedding": "Создать эмбеддинг рисунков",
"Apply settings": "Применить настройки",
"Saving images/grids": "Сохранение рисунков/таблиц",
"Always save all generated images": "Всегда сохранять созданные рисунки",
"File format for images": "Формат файла рисунков",
"Images filename pattern": "Формат имени файлов рисунков",
"Always save all generated image grids": "Всегда сохранять созданные таблицы",
"File format for grids": "Формат файла таблиц",
"Add extended info (seed, prompt) to filename when saving grid": "Вставлять доп. сведения (семя, запрос) в имя файла таблиц",
"Do not save grids consisting of one picture": "Не сохранять таблицы из одного рисунка",
"Prevent empty spots in grid (when set to autodetect)": "Не допускать пустоты в таблицах （автообнаружение）",
"Grid row count; use -1 for autodetect and 0 for it to be same as batch size": "Число строк таблицы； -1, чтобы автоматически, 0 — размер набора",
"Save text information about generation parameters as chunks to png files": "Встроить сведения о генерации в файлы png",
"Create a text file next to every image with generation parameters.": "Создать текстовый файл для каждого рисунка с параметрами генерации",
"Save a copy of image before doing face restoration.": "Сохранить копию перед восстановлением лиц",
"Quality for saved jpeg images": "Качество jpeg-рисунков",
"If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG": "Если размер PNG больше 4МБ или рисунок шире 4000 пикселей, пересжать в JPEG",
"Use original name for output filename during batch process in extras tab": "Использовать исходное имя выходного файла для обработки набора во вкладке дополнений",
"When using 'Save' button, only save a single selected image": "Сохранять только один рисунок при нажатии кнопки Сохранить",
"Do not add watermark to images": "Не добавлять водяной знак",
"Paths for saving": "Папки сохранений",
"Output directory for images; if empty, defaults to three directories below": "Папка выхода рисунков; если пусто, использует те, что ниже",
"Output directory for txt2img images": "Папка выхода текста-в-рисунок",
"Output directory for img2img images": "Папка выхода рисунка-в-рисунок",
"Output directory for images from extras tab": "Папка выхода для дополнений",
"Output directory for grids; if empty, defaults to two directories below": "Папка выхода таблиц; если пусто, использует папки выше",
"Output directory for txt2img grids": "Папка выхода текста-в-рисунок",
"Output directory for img2img grids": "Папка выхода рисунка-в-рисунок",
"Directory for saving images using the Save button": "Папка выхода для кнопки Сохранить",
"Saving to a directory": "Сохранить в папку",
"Save images to a subdirectory": "Сохранить рисунки в подпапку",
"Save grids to a subdirectory": "Сохранить таблицы в подпапку",
"When using \"Save\" button, save images to a subdirectory": "При нажатии кнопки Сохранить, сложить рисунки в подпапку",
"Directory name pattern": "Шаблон имени папки",
"Max prompt words for [prompt_words] pattern": "Макс. число слов для шаблона [prompt_words]",
"Upscaling": "Апскейл",
"Tile size for ESRGAN upscalers. 0 = no tiling.": "Размер плитки для ESRGAN. 0 = нет замощения",
"Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.": "Наложение плиток ESRGAN, в пикселях. Меньше = выделеннее шов",
"Tile size for all SwinIR.": "Размер плиток SwinIR",
"Tile overlap, in pixels for SwinIR. Low values = visible seam.": "Наложение плиток SwinIR, в пикселях. Меньше = выделеннее шов",
"LDSR processing steps. Lower = faster": "Число шагов LDSR. Меньше = быстрее",
"Upscaler for img2img": "Апскейлер рисунка-в-рисунок",
"Upscale latent space image when doing hires. fix": "Апскейлить образ латентного пространства для HD-режима",
"Face restoration": "Восстановление лиц",
"CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect": "Вес CodeFormer； 0 = максимальное действие； 1 = минимальное",
"Move face restoration model from VRAM into RAM after processing": "Переместить модель восстановления лиц из ВОЗУ в ОЗУ после обработки",
"System": "Система",
"VRAM usage polls per second during generation. Set to 0 to disable.": "Сколько раз в секунду следить за потреблением ВОЗУ. 0, чтобы отключить",
"Always print all generation info to standard output": "Выводить все сведения о генерации в стандартный вывод",
"Add a second progress bar to the console that shows progress for an entire job.": "Вторая шкала прогресса для всей задачи",
"Training": "Обучение",
"Unload VAE and CLIP from VRAM when training": "Убрать VAE и CLIP из ВОЗУ на время обучения",
"Move VAE and CLIP to RAM when training hypernetwork. Saves VRAM.": "Переместить VAE и CLIP в ОЗУ на время обучения гиперсети. Сохраняет ВОЗУ",
"Filename word regex": "Regex имени файла",
"Filename join string": "Дополнить к имени файла",
"Number of repeats for a single input image per epoch; used only for displaying epoch number": "Число повторов для каждого рисунка за эпоху; используется только, чтобы отобразить число эпохи",
"Save an csv containing the loss to log directory every N steps, 0 to disable": "Сохранять csv с параметром loss в папку журнала каждые N шагов, 0 - отключить",
"Stable Diffusion": "Stable Diffusion",
"Checkpoints to cache in RAM": "Удерживать веса в ОЗУ",
"Hypernetwork strength": "Сила гиперсети",
"Apply color correction to img2img results to match original colors.": "Цветокоррекция вывода рисунка-в-рисунок, сохраняющая исходные цвета",
"Save a copy of image before applying color correction to img2img results": "Сохранить копию рисунка перед цветокоррекцией",
"With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising).": "В режиме рисунок-в-рисунок сделать ровно указанное ползунком число шагов (обычно шумоподавление их уменьшает)",
"Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply.": "Включить квантование К-семплерах для более резких и чистых результатов. Может потребовать поменять семя. Требует перезапуска.",
"Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention": "Скобки: (понятие) - больше внимания к тексту, [понятие] - меньше внимания к тексту",
"Use old emphasis implementation. Can be useful to reproduce old seeds.": "Включить старую обработку скобок. Может потребоваться, чтобы воспроизвести старые семена.",
"Make K-diffusion samplers produce same images in a batch as when making a single image": "Заставить семплеры K-diffusion производить тот же самый рисунок в наборе, как и в единичной генерации",
"Increase coherency by padding from the last comma within n tokens when using more than 75 tokens": "Увеличить связность, достраивая запрос от последней запятой до n токенов, когда используется свыше 75 токенов",
"Filter NSFW content": "Фильтровать небезопасный контент",
"Stop At last layers of CLIP model": "Остановиться на последних слоях модели CLIP",
"Interrogate Options": "Опции распознавания",
"Interrogate: keep models in VRAM": "Распознавание: хранить модели в ВОЗУ",
"Interrogate: use artists from artists.csv": "Распознавание: использовать художников из artists.csv",
"Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators).": "Распознавание: включить ранжирование совпавших тегов в результате (не работает для распознавателей-создателей заголовков)",
"Interrogate: num_beams for BLIP": "Распознавание: num_beams для BLIP",
"Interrogate: minimum description length (excluding artists, etc..)": "Распознавание: минимальная длина описания (исключая художников и т.п.)",
"Interrogate: maximum description length": "Распознавание: максимальная длина описания",
"CLIP: maximum number of lines in text file (0 = No limit)": "CLIP: максимальное число строк в текстовом файле (0 = без ограничений)",
"Interrogate: deepbooru score threshold": "Распознавание: ограничение счёта deepbooru",
"Interrogate: deepbooru sort alphabetically": "Распознавание: сортировать deepbooru по алфавиту",
"use spaces for tags in deepbooru": "Пробелы для тегов deepbooru",
"escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)": "Использовать скобки в deepbooru как обычные скобки, а не для усиления",
"User interface": "Пользовательский интерфейс",
"Show progressbar": "Шкала прогресса",
"Show image creation progress every N sampling steps. Set 0 to disable.": "Показывать процесс созданния рисунка каждые N шагов. 0 - отключить",
"Show grid in results for web": "Показать таблицу в выводе браузера",
"Do not show any images in results for web": "Не показывать выходные рисунки в браузере",
"Add model hash to generation information": "Добавить хеш весов к параметрам генерации",
"Add model name to generation information": "Добавить имя весов к параметрам генерации",
"When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint.": "При считывании параметров генерации из текста в интерфейс, не менять выбранную модель/веса.",
"Font for image grids that have text": "Шрифт для таблиц, содержащих текст",
"Enable full page image viewer": "Включить полноэкранный просмотр картинок",
"Show images zoomed in by default in full page image viewer": "По умолчанию увеличивать картинки в полноэкранном просмотре",
"Show generation progress in window title.": "Отображать прогресс в имени вкладки",
"Quicksettings list": "Список быстрых настроек",
"Localization (requires restart)": "Перевод （требует перезапуск）",
"Sampler parameters": "Параметры семплера",
"Hide samplers in user interface (requires restart)": "Убрать семплеры из интерфейса (требует перезапуск)",
"eta (noise multiplier) for DDIM": "eta (множитель шума) DDIM",
"eta (noise multiplier) for ancestral samplers": "eta (множитель шума) для ancestral-семплеров",
"img2img DDIM discretize": "дискретизация DDIM для рисунка-в-рисунок",
"uniform": "однородная",
"quad": "квадратичная",
"sigma churn": "сигма-вариация",
"sigma tmin": "сигма-tmin",
"sigma noise": "сигма-шум",
"Eta noise seed delta": "Eta (дельта шума семени)",
"Images Browser": "Просмотр изображений",
"Preload images at startup": "Предзагружать рисунки во время запуска",
"Number of pictures displayed on each page": "Число рисунков на каждой странице",
"Minimum number of pages per load": "Мин. число загружаемых страниц",
"Number of grids in each row": "Число таблиц в каждой строке",
"Request browser notifications": "Запросить уведомления браузера",
"Download localization template": "Загрузить щаблон перевода",
"Reload custom script bodies (No ui updates, No restart)": "Перезагрузить пользовательские скрипты (не требует обновления интерфейса и перезапуска)",
"Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)": "Перезагрузить Gradio и обновить компоненты (только пользовательские скрипты, ui.py, js и css)",
"Prompt (press Ctrl+Enter or Alt+Enter to generate)": "Запрос （нажмите Ctrl+Enter или Alt+Enter для генерации）",
"Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "Запрос-исключение （нажмите Ctrl+Enter или Alt+Enter для генерации）",
"Add a random artist to the prompt.": "Добавить случайного художника к запросу",
"Read generation parameters from prompt or last generation if prompt is empty into user interface.": "Считать параметры генерации из запроса или из предыдущей генерации в пользовательский интерфейс, если пусто",
"Save style": "Сохранить стиль",
"Apply selected styles to current prompt": "Применить выбранные стили к текущему промпту",
"Stop processing current image and continue processing.": "Прекратить обрабатывать текущий рисунок, но продолжить работу",
"Stop processing images and return any results accumulated so far.": "Прекратить обрабатку рисунков и вернуть всё, что успели сделать.",
"Style to apply; styles have components for both positive and negative prompts and apply to both": "Стиль к применению; стили содержат как запрос, так и исключение, и применяют их оба",
"Do not do anything special": "Не делать ничего особенного",
"Which algorithm to use to produce the image": "Какой алгоритм использовать для того, чтобы произвести рисунок",
"Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps to higher than 30-40 does not help": "Euler Ancestral - очень творческий, в зависимости от числа шагов может привести совершенно к различным результатам, выше 30-40 лучше не ставить",
"Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit модели - лучше всего для обрисовки",
"Produce an image that can be tiled.": "Сделать из рисунка непрерывную обёртку",
"Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition": "Применить двушаговый процесс, чтобы создать рисунок на меньшем разрешении, апскейлнуть, а затем улучшить детали без смены композиции",
"Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.": "Определяет, насколько сильно алгоритм будет опираться на содержание изображения. 0 - не меняет ничего, 1 - совсем не связанный выход. Меньше 1.0 процесс использует меньше шагов, чем указано их ползунком.",
"How many batches of images to create": "Сколько создать наборов из картинок",
"How many image to create in a single batch": "Сколько картинок создать в каждом наборе",
"Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results": "Classifier Free Guidance Scale: насколько сильно изображение должно соответсвтовать запросу — меньшие значения приведут к более свободным итогам",
"A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result": "Значение, которое определяет выход генератора случайных чисел — если вы создадите рисунок с теми же параметрами и семенем, как у другого изображения, вы получите тот же результат",
"Set seed to -1, which will cause a new random number to be used every time": "Установить семя в -1, что вызовет каждый раз случайное число",
"Reuse seed from last generation, mostly useful if it was randomed": "Использовать семя предыдущей генерации, обычно полезно, если оно было случайным",
"Seed of a different picture to be mixed into the generation.": "Семя с другого рисунка, подмешенного в генерацию.",
"How strong of a variation to produce. At 0, there will be no effect. At 1, you will get the complete picture with variation seed (except for ancestral samplers, where you will just get something).": "Насколько сильную вариацию произвести. При 0м значении действия не будет. Для 1 вы получите полноценный рисунок с семенем вариации (кроме ancestral-семплеров, где вы просто что-то получите).",
"Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution": "Попытаться воспроизвести изображение, похожее на то, чтобы получилось с тем же семенем на выбранном разрешении",
"This text is used to rotate the feature space of the imgs embs": "Этот текст используется, чтобы произвести вращение пространства признаков из эмбеддинга рисунков",
"Separate values for X axis using commas.": "Отдельные значения оси X через запятую.",
"Separate values for Y axis using commas.": "Отдельные значения оси Y через запятую.",
"Write image to a directory (default - log/images) and generation parameters into csv file.": "Записать изображение в папку (по-умолчанию - log/images), а параметры генерации - в csv файл",
"Open images output directory": "Открыть папку сохранения изображений",
"How much to blur the mask before processing, in pixels.": "Насколько пикселей размыть трафарет перед обработкой",
"What to put inside the masked area before processing it with Stable Diffusion.": "Что поместить в область под трафаретом перед обработкой Stable Diffusion",
"fill it with colors of the image": "залить цветами изображения",
"keep whatever was there originally": "сохранить то, что было до этого",
"fill it with latent space noise": "залить латентным шумом",
"fill it with latent space zeroes": "залить латентными нулями",
"Upscale masked region to target resolution, do inpainting, downscale back and paste into original image": "апскейл до нужного разрешения, врисовка, сжатие до начального размера и вставка в исходный рисунок",
"Resize image to target resolution. Unless height and width match, you will get incorrect aspect ratio.": "Масшабировать изображение до нужного разрешения. Если только высота и ширина не совпадают, вы получите неверное соотношение сторон.",
"Resize the image so that entirety of target resolution is filled with the image. Crop parts that stick out.": "Масштабировать изображение так, чтобы им заполнялось всё выбранное выходное разрешение. Обрезать выступающие части",
"Resize the image so that entirety of image is inside target resolution. Fill empty space with image's colors.": "Масштабировать изображение так, всё изображение помещалось в выбранное выходное разрешение. Заполнить пустое место цветами изображения.",
"How many times to repeat processing an image and using it as input for the next iteration": "Сколько раз повторить обработку изображения и использовать её как вход для следующией итерации",
"In loopback mode, on each loop the denoising strength is multiplied by this value. <1 means decreasing variety so your sequence will converge on a fixed picture. >1 means increasing variety so your sequence will become more and more chaotic.": "В режиме прокрутки, для каждого цикла сила шумоподавления умножается на это значение. <1 уменьшает вариации так, чтобы последовательность сошлась на какой-то одной картинке. >1 увеличивает вариации, так что ваша последовательность станет всё более и более сумбурной.",
"For SD upscale, how much overlap in pixels should there be between tiles. Tiles overlap so that when they are merged back into one picture, there is no clearly visible seam.": "Для SD-апскейла, как много перекрытия в пикселях должно быть между плитками. Плитки перекрываются таким образом, чтобы они могли сойтись обратно в единое изображение, без видимого шва.",
"A directory on the same machine where the server is running.": "Папка на той же машине, где запущен сервер",
"Leave blank to save images to the default path.": "Оставьте пустым, чтобы сохранить рисунки в папку по-умолчанию",
"Result = A * (1 - M) + B * M": "Выход = A * (1 - M) + B * M",
"Result = A + (B - C) * M": "Выход = A + (B - C) * M",
"1st and last digit must be 1. ex:'1, 2, 1'": "1я и последняя цифры должны быть 1. напр.'1, 2, 1'",
"how fast should the training go. Low values will take longer to train, high values may fail to converge (not generate accurate results) and/or may break the embedding (This has happened if you see Loss: nan in the training info textbox. If this happens, you need to manually restore your embedding from an older not-broken backup).\n\nYou can set a single numeric value, or multiple learning rates using the syntax:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nWill train with rate of 0.005 for first 100 steps, then 1e-3 until 1000 steps, then 1e-5 for all remaining steps.": "как быстро будет происходить обучение. Меньшие значения увеличат время обучения, но высокие могут нарушить сходимость модели (не будет создавать должные результаты) и/или сломать эмбеддинг. (Это случилось, если вы видете Loss: nan в текстовом окне вывода обучения. В этом случае вам придётся восстанавливать эмбеддинг вручную из старой, не повреждённой резервной копии).\n\nВы также можете указать единичное значение или последовательность из нескольких, используя следующий синтаксис:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nБудет обучаться со скоростью 0.005 первые 100 шагов, затем 1e-3 до 1000 шагов, после 1e-5 для всех оставшихся шагов.",
"Path to directory with input images": "Путь к папке со входными изображениями",
"Path to directory where to write outputs": "Путь к папке, в которую записывать результаты",
"Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.": "Используйте следующие теги, чтобы определить, как подбираются названия файлов для изображений: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; если пусто, используется значение по-умолчанию",
"If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.": "Когда эта опция включена, на созданные изображения не будет добавляться водяной знак. Предупреждение: не добавляя водяной знак, вы, вероятно, ведёте себя аморально.",
"Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.": "Используйте следующие теги, чтобы определить, как подбираются названия подпапок для рисунков и табоиц: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; если пусто, используется значение по-умолчанию",
"Restore low quality faces using GFPGAN neural network": "Восстановить низкокачественные лица, используя нейросеть GFPGAN",
"This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.": "Это регулярное выражение будет использовано, чтобы извлечь слова из имени файла, и они будут соединены с текстом в метке ниже как вход во время обучения. Оставьте пустым, чтобы сохранить имя файла как есть",
"This string will be used to join split words into a single line if the option above is enabled.": "Эта строка будет использована, чтобы объединить разделённые слова в одну строку, если включена опция выше.",
"List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.": "Список имён настроек, разделённый запятыми, предназначенных для быстрого доступа через панель наверху, а не через привычную вкладку настроек. Для применения требует перезапуска.",
"If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.": "Если это значение не нулевое, оно будет добавлено к семени и использовано для инициалицации ГСЧ шума семплеров с параметром Eta. Вы можете использовать это, чтобы произвести ещё больше вариаций рисунков, либо же для того, чтобы подойти близко к результатам других программ, если знаете, что делаете.",
"Enable Autocomplete": "Включить автодополнение",
"Allowed categories for random artists selection when using the Roll button": "Разрешённые категории художников для случайного выбора при использовании кнопки + три",
"Roll three": "+ три",
"Generate forever": "Непрерывная генерация",
"Cancel generate forever": "Отключить непрерывную генерацию"
}

124
modules/api/api.py Normal file
View file

@ -0,0 +1,124 @@
from modules.api.processing import StableDiffusionTxt2ImgProcessingAPI, StableDiffusionImg2ImgProcessingAPI
from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
from modules.sd_samplers import all_samplers
from modules.extras import run_pnginfo
import modules.shared as shared
import uvicorn
from fastapi import Body, APIRouter, HTTPException
from fastapi.responses import JSONResponse
from pydantic import BaseModel, Field, Json
import json
import io
import base64
from PIL import Image
sampler_to_index = lambda name: next(filter(lambda row: name.lower() == row[1].name.lower(), enumerate(all_samplers)), None)
class TextToImageResponse(BaseModel):
images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
parameters: Json
info: Json
class ImageToImageResponse(BaseModel):
images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
parameters: Json
info: Json
class Api:
def __init__(self, app, queue_lock):
self.router = APIRouter()
self.app = app
self.queue_lock = queue_lock
self.app.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"])
self.app.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"])
def __base64_to_image(self, base64_string):
# if has a comma, deal with prefix
if "," in base64_string:
base64_string = base64_string.split(",")[1]
imgdata = base64.b64decode(base64_string)
# convert base64 to PIL image
return Image.open(io.BytesIO(imgdata))
def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
sampler_index = sampler_to_index(txt2imgreq.sampler_index)
if sampler_index is None:
raise HTTPException(status_code=404, detail="Sampler not found")
populate = txt2imgreq.copy(update={ # Override __init__ params
"sd_model": shared.sd_model,
"sampler_index": sampler_index[0],
"do_not_save_samples": True,
"do_not_save_grid": True
}
)
p = StableDiffusionProcessingTxt2Img(**vars(populate))
# Override object param
with self.queue_lock:
processed = process_images(p)
b64images = []
for i in processed.images:
buffer = io.BytesIO()
i.save(buffer, format="png")
b64images.append(base64.b64encode(buffer.getvalue()))
return TextToImageResponse(images=b64images, parameters=json.dumps(vars(txt2imgreq)), info=json.dumps(processed.info))
def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
sampler_index = sampler_to_index(img2imgreq.sampler_index)
if sampler_index is None:
raise HTTPException(status_code=404, detail="Sampler not found")
init_images = img2imgreq.init_images
if init_images is None:
raise HTTPException(status_code=404, detail="Init image not found")
mask = img2imgreq.mask
if mask:
mask = self.__base64_to_image(mask)
populate = img2imgreq.copy(update={ # Override __init__ params
"sd_model": shared.sd_model,
"sampler_index": sampler_index[0],
"do_not_save_samples": True,
"do_not_save_grid": True,
"mask": mask
}
)
p = StableDiffusionProcessingImg2Img(**vars(populate))
imgs = []
for img in init_images:
img = self.__base64_to_image(img)
imgs = [img] * p.batch_size
p.init_images = imgs
# Override object param
with self.queue_lock:
processed = process_images(p)
b64images = []
for i in processed.images:
buffer = io.BytesIO()
i.save(buffer, format="png")
b64images.append(base64.b64encode(buffer.getvalue()))
return ImageToImageResponse(images=b64images, parameters=json.dumps(vars(img2imgreq)), info=json.dumps(processed.info))
def extrasapi(self):
raise NotImplementedError
def pnginfoapi(self):
raise NotImplementedError
def launch(self, server_name, port):
self.app.include_router(self.router)
uvicorn.run(self.app, host=server_name, port=port)

106
modules/api/processing.py Normal file
View file

@ -0,0 +1,106 @@
from array import array
from inflection import underscore
from typing import Any, Dict, Optional
from pydantic import BaseModel, Field, create_model
from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
import inspect
API_NOT_ALLOWED = [
"self",
"kwargs",
"sd_model",
"outpath_samples",
"outpath_grids",
"sampler_index",
"do_not_save_samples",
"do_not_save_grid",
"extra_generation_params",
"overlay_images",
"do_not_reload_embeddings",
"seed_enable_extras",
"prompt_for_display",
"sampler_noise_scheduler_override",
"ddim_discretize"
]
class ModelDef(BaseModel):
"""Assistance Class for Pydantic Dynamic Model Generation"""
field: str
field_alias: str
field_type: Any
field_value: Any
class PydanticModelGenerator:
"""
Takes in created classes and stubs them out in a way FastAPI/Pydantic is happy about:
source_data is a snapshot of the default values produced by the class
params are the names of the actual keys required by __init__
"""
def __init__(
self,
model_name: str = None,
class_instance = None,
additional_fields = None,
):
def field_type_generator(k, v):
# field_type = str if not overrides.get(k) else overrides[k]["type"]
# print(k, v.annotation, v.default)
field_type = v.annotation
return Optional[field_type]
def merge_class_params(class_):
all_classes = list(filter(lambda x: x is not object, inspect.getmro(class_)))
parameters = {}
for classes in all_classes:
parameters = {**parameters, **inspect.signature(classes.__init__).parameters}
return parameters
self._model_name = model_name
self._class_data = merge_class_params(class_instance)
self._model_def = [
ModelDef(
field=underscore(k),
field_alias=k,
field_type=field_type_generator(k, v),
field_value=v.default
)
for (k,v) in self._class_data.items() if k not in API_NOT_ALLOWED
]
for fields in additional_fields:
self._model_def.append(ModelDef(
field=underscore(fields["key"]),
field_alias=fields["key"],
field_type=fields["type"],
field_value=fields["default"]))
def generate_model(self):
"""
Creates a pydantic BaseModel
from the json and overrides provided at initialization
"""
fields = {
d.field: (d.field_type, Field(default=d.field_value, alias=d.field_alias)) for d in self._model_def
}
DynamicModel = create_model(self._model_name, **fields)
DynamicModel.__config__.allow_population_by_field_name = True
DynamicModel.__config__.allow_mutation = True
return DynamicModel
StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
"StableDiffusionProcessingTxt2Img",
StableDiffusionProcessingTxt2Img,
[{"key": "sampler_index", "type": str, "default": "Euler"}]
).generate_model()
StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
"StableDiffusionProcessingImg2Img",
StableDiffusionProcessingImg2Img,
[{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}]
).generate_model()

76
modules/bsrgan_model.py
View file

@ -1,76 +0,0 @@
import os.path
import sys
import traceback
import PIL.Image
import numpy as np
import torch
from basicsr.utils.download_util import load_file_from_url
import modules.upscaler
from modules import devices, modelloader
from modules.bsrgan_model_arch import RRDBNet
class UpscalerBSRGAN(modules.upscaler.Upscaler):
def __init__(self, dirname):
self.name = "BSRGAN"
self.model_name = "BSRGAN 4x"
self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/BSRGAN.pth"
self.user_path = dirname
super().__init__()
model_paths = self.find_models(ext_filter=[".pt", ".pth"])
scalers = []
if len(model_paths) == 0:
scaler_data = modules.upscaler.UpscalerData(self.model_name, self.model_url, self, 4)
scalers.append(scaler_data)
for file in model_paths:
if "http" in file:
name = self.model_name
else:
name = modelloader.friendly_name(file)
try:
scaler_data = modules.upscaler.UpscalerData(name, file, self, 4)
scalers.append(scaler_data)
except Exception:
print(f"Error loading BSRGAN model: {file}", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
self.scalers = scalers
def do_upscale(self, img: PIL.Image, selected_file):
torch.cuda.empty_cache()
model = self.load_model(selected_file)
if model is None:
return img
model.to(devices.device_bsrgan)
torch.cuda.empty_cache()
img = np.array(img)
img = img[:, :, ::-1]
img = np.moveaxis(img, 2, 0) / 255
img = torch.from_numpy(img).float()
img = img.unsqueeze(0).to(devices.device_bsrgan)
with torch.no_grad():
output = model(img)
output = output.squeeze().float().cpu().clamp_(0, 1).numpy()
output = 255. * np.moveaxis(output, 0, 2)
output = output.astype(np.uint8)
output = output[:, :, ::-1]
torch.cuda.empty_cache()
return PIL.Image.fromarray(output, 'RGB')
def load_model(self, path: str):
if "http" in path:
filename = load_file_from_url(url=self.model_url, model_dir=self.model_path, file_name="%s.pth" % self.name,
progress=True)
else:
filename = path
if not os.path.exists(filename) or filename is None:
print(f"BSRGAN: Unable to load model from {filename}", file=sys.stderr)
return None
model = RRDBNet(in_nc=3, out_nc=3, nf=64, nb=23, gc=32, sf=4) # define network
model.load_state_dict(torch.load(filename), strict=True)
model.eval()
for k, v in model.named_parameters():
v.requires_grad = False
return model

102
modules/bsrgan_model_arch.py
View file

@ -1,102 +0,0 @@
import functools
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.nn.init as init
def initialize_weights(net_l, scale=1):
if not isinstance(net_l, list):
net_l = [net_l]
for net in net_l:
for m in net.modules():
if isinstance(m, nn.Conv2d):
init.kaiming_normal_(m.weight, a=0, mode='fan_in')
m.weight.data *= scale # for residual block
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, nn.Linear):
init.kaiming_normal_(m.weight, a=0, mode='fan_in')
m.weight.data *= scale
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, nn.BatchNorm2d):
init.constant_(m.weight, 1)
init.constant_(m.bias.data, 0.0)
def make_layer(block, n_layers):
layers = []
for _ in range(n_layers):
layers.append(block())
return nn.Sequential(*layers)
class ResidualDenseBlock_5C(nn.Module):
def __init__(self, nf=64, gc=32, bias=True):
super(ResidualDenseBlock_5C, self).__init__()
# gc: growth channel, i.e. intermediate channels
self.conv1 = nn.Conv2d(nf, gc, 3, 1, 1, bias=bias)
self.conv2 = nn.Conv2d(nf + gc, gc, 3, 1, 1, bias=bias)
self.conv3 = nn.Conv2d(nf + 2 * gc, gc, 3, 1, 1, bias=bias)
self.conv4 = nn.Conv2d(nf + 3 * gc, gc, 3, 1, 1, bias=bias)
self.conv5 = nn.Conv2d(nf + 4 * gc, nf, 3, 1, 1, bias=bias)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
# initialization
initialize_weights([self.conv1, self.conv2, self.conv3, self.conv4, self.conv5], 0.1)
def forward(self, x):
x1 = self.lrelu(self.conv1(x))
x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1)))
x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1)))
x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
return x5 * 0.2 + x
class RRDB(nn.Module):
'''Residual in Residual Dense Block'''
def __init__(self, nf, gc=32):
super(RRDB, self).__init__()
self.RDB1 = ResidualDenseBlock_5C(nf, gc)
self.RDB2 = ResidualDenseBlock_5C(nf, gc)
self.RDB3 = ResidualDenseBlock_5C(nf, gc)
def forward(self, x):
out = self.RDB1(x)
out = self.RDB2(out)
out = self.RDB3(out)
return out * 0.2 + x
class RRDBNet(nn.Module):
def __init__(self, in_nc=3, out_nc=3, nf=64, nb=23, gc=32, sf=4):
super(RRDBNet, self).__init__()
RRDB_block_f = functools.partial(RRDB, nf=nf, gc=gc)
self.sf = sf
self.conv_first = nn.Conv2d(in_nc, nf, 3, 1, 1, bias=True)
self.RRDB_trunk = make_layer(RRDB_block_f, nb)
self.trunk_conv = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
#### upsampling
self.upconv1 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
if self.sf==4:
self.upconv2 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
self.HRconv = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
self.conv_last = nn.Conv2d(nf, out_nc, 3, 1, 1, bias=True)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
def forward(self, x):
fea = self.conv_first(x)
trunk = self.trunk_conv(self.RRDB_trunk(fea))
fea = fea + trunk
fea = self.lrelu(self.upconv1(F.interpolate(fea, scale_factor=2, mode='nearest')))
if self.sf==4:
fea = self.lrelu(self.upconv2(F.interpolate(fea, scale_factor=2, mode='nearest')))
out = self.conv_last(self.lrelu(self.HRconv(fea)))
return out

8
modules/deepbooru.py
View file

@ -50,11 +50,12 @@ def create_deepbooru_process(threshold, deepbooru_opts):
the tags.
"""
from modules import shared # prevents circular reference
shared.deepbooru_process_manager = multiprocessing.Manager()
context = multiprocessing.get_context("spawn")
shared.deepbooru_process_manager = context.Manager()
shared.deepbooru_process_queue = shared.deepbooru_process_manager.Queue()
shared.deepbooru_process_return = shared.deepbooru_process_manager.dict()
shared.deepbooru_process_return["value"] = -1
shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, deepbooru_opts))
shared.deepbooru_process = context.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, deepbooru_opts))
shared.deepbooru_process.start()
@ -157,8 +158,7 @@ def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, deepbooru_o
# sort by reverse by likelihood and normal for alpha, and format tag text as requested
unsorted_tags_in_theshold.sort(key=lambda y: y[sort_ndx], reverse=(not alpha_sort))
for weight, tag in unsorted_tags_in_theshold:
# note: tag_outformat will still have a colon if include_ranks is True
tag_outformat = tag.replace(':', ' ')
tag_outformat = tag
if use_spaces:
tag_outformat = tag_outformat.replace('_', ' ')
if use_escape:

19
modules/devices.py
View file

@ -1,7 +1,6 @@
import sys, os, shlex
import contextlib
import torch
from modules import errors
# has_mps is only available in nightly pytorch (for now), `getattr` for compatibility
@ -9,10 +8,22 @@ has_mps = getattr(torch, 'has_mps', False)
cpu = torch.device("cpu")
def extract_device_id(args, name):
for x in range(len(args)):
if name in args[x]: return args[x+1]
return None
def get_optimal_device():
if torch.cuda.is_available():
return torch.device("cuda")
from modules import shared
device_id = shared.cmd_opts.device_id
if device_id is not None:
cuda_device = f"cuda:{device_id}"
return torch.device(cuda_device)
else:
return torch.device("cuda")
if has_mps:
return torch.device("mps")
@ -34,7 +45,7 @@ def enable_tf32():
errors.run(enable_tf32, "Enabling TF32")
device = device_interrogate = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = get_optimal_device()
device = device_interrogate = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = None
dtype = torch.float16
dtype_vae = torch.float16

176
modules/esrgan_model.py
View file

@ -11,62 +11,109 @@ from modules.upscaler import Upscaler, UpscalerData
from modules.shared import opts
def fix_model_layers(crt_model, pretrained_net):
# this code is adapted from https://github.com/xinntao/ESRGAN
if 'conv_first.weight' in pretrained_net:
return pretrained_net
if 'model.0.weight' not in pretrained_net:
is_realesrgan = "params_ema" in pretrained_net and 'body.0.rdb1.conv1.weight' in pretrained_net["params_ema"]
if is_realesrgan:
raise Exception("The file is a RealESRGAN model, it can't be used as a ESRGAN model.")
else:
raise Exception("The file is not a ESRGAN model.")
def mod2normal(state_dict):
# this code is copied from https://github.com/victorca25/iNNfer
if 'conv_first.weight' in state_dict:
crt_net = {}
items = []
for k, v in state_dict.items():
items.append(k)
crt_net = crt_model.state_dict()
load_net_clean = {}
for k, v in pretrained_net.items():
if k.startswith('module.'):
load_net_clean[k[7:]] = v
else:
load_net_clean[k] = v
pretrained_net = load_net_clean
crt_net['model.0.weight'] = state_dict['conv_first.weight']
crt_net['model.0.bias'] = state_dict['conv_first.bias']
tbd = []
for k, v in crt_net.items():
tbd.append(k)
for k in items.copy():
if 'RDB' in k:
ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
if '.weight' in k:
ori_k = ori_k.replace('.weight', '.0.weight')
elif '.bias' in k:
ori_k = ori_k.replace('.bias', '.0.bias')
crt_net[ori_k] = state_dict[k]
items.remove(k)
# directly copy
for k, v in crt_net.items():
if k in pretrained_net and pretrained_net[k].size() == v.size():
crt_net[k] = pretrained_net[k]
tbd.remove(k)
crt_net['model.1.sub.23.weight'] = state_dict['trunk_conv.weight']
crt_net['model.1.sub.23.bias'] = state_dict['trunk_conv.bias']
crt_net['model.3.weight'] = state_dict['upconv1.weight']
crt_net['model.3.bias'] = state_dict['upconv1.bias']
crt_net['model.6.weight'] = state_dict['upconv2.weight']
crt_net['model.6.bias'] = state_dict['upconv2.bias']
crt_net['model.8.weight'] = state_dict['HRconv.weight']
crt_net['model.8.bias'] = state_dict['HRconv.bias']
crt_net['model.10.weight'] = state_dict['conv_last.weight']
crt_net['model.10.bias'] = state_dict['conv_last.bias']
state_dict = crt_net
return state_dict
crt_net['conv_first.weight'] = pretrained_net['model.0.weight']
crt_net['conv_first.bias'] = pretrained_net['model.0.bias']
for k in tbd.copy():
if 'RDB' in k:
ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
if '.weight' in k:
ori_k = ori_k.replace('.weight', '.0.weight')
elif '.bias' in k:
ori_k = ori_k.replace('.bias', '.0.bias')
crt_net[k] = pretrained_net[ori_k]
tbd.remove(k)
def resrgan2normal(state_dict, nb=23):
# this code is copied from https://github.com/victorca25/iNNfer
if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict:
crt_net = {}
items = []
for k, v in state_dict.items():
items.append(k)
crt_net['trunk_conv.weight'] = pretrained_net['model.1.sub.23.weight']
crt_net['trunk_conv.bias'] = pretrained_net['model.1.sub.23.bias']
crt_net['upconv1.weight'] = pretrained_net['model.3.weight']
crt_net['upconv1.bias'] = pretrained_net['model.3.bias']
crt_net['upconv2.weight'] = pretrained_net['model.6.weight']
crt_net['upconv2.bias'] = pretrained_net['model.6.bias']
crt_net['HRconv.weight'] = pretrained_net['model.8.weight']
crt_net['HRconv.bias'] = pretrained_net['model.8.bias']
crt_net['conv_last.weight'] = pretrained_net['model.10.weight']
crt_net['conv_last.bias'] = pretrained_net['model.10.bias']
crt_net['model.0.weight'] = state_dict['conv_first.weight']
crt_net['model.0.bias'] = state_dict['conv_first.bias']
for k in items.copy():
if "rdb" in k:
ori_k = k.replace('body.', 'model.1.sub.')
ori_k = ori_k.replace('.rdb', '.RDB')
if '.weight' in k:
ori_k = ori_k.replace('.weight', '.0.weight')
elif '.bias' in k:
ori_k = ori_k.replace('.bias', '.0.bias')
crt_net[ori_k] = state_dict[k]
items.remove(k)
crt_net[f'model.1.sub.{nb}.weight'] = state_dict['conv_body.weight']
crt_net[f'model.1.sub.{nb}.bias'] = state_dict['conv_body.bias']
crt_net['model.3.weight'] = state_dict['conv_up1.weight']
crt_net['model.3.bias'] = state_dict['conv_up1.bias']
crt_net['model.6.weight'] = state_dict['conv_up2.weight']
crt_net['model.6.bias'] = state_dict['conv_up2.bias']
crt_net['model.8.weight'] = state_dict['conv_hr.weight']
crt_net['model.8.bias'] = state_dict['conv_hr.bias']
crt_net['model.10.weight'] = state_dict['conv_last.weight']
crt_net['model.10.bias'] = state_dict['conv_last.bias']
state_dict = crt_net
return state_dict
def infer_params(state_dict):
# this code is copied from https://github.com/victorca25/iNNfer
scale2x = 0
scalemin = 6
n_uplayer = 0
plus = False
for block in list(state_dict):
parts = block.split(".")
n_parts = len(parts)
if n_parts == 5 and parts[2] == "sub":
nb = int(parts[3])
elif n_parts == 3:
part_num = int(parts[1])
if (part_num > scalemin
and parts[0] == "model"
and parts[2] == "weight"):
scale2x += 1
if part_num > n_uplayer:
n_uplayer = part_num
out_nc = state_dict[block].shape[0]
if not plus and "conv1x1" in block:
plus = True
nf = state_dict["model.0.weight"].shape[0]
in_nc = state_dict["model.0.weight"].shape[1]
out_nc = out_nc
scale = 2 ** scale2x
return in_nc, out_nc, nf, nb, plus, scale
return crt_net
class UpscalerESRGAN(Upscaler):
def __init__(self, dirname):
@ -109,20 +156,39 @@ class UpscalerESRGAN(Upscaler):
print("Unable to load %s from %s" % (self.model_path, filename))
return None
pretrained_net = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
pretrained_net = fix_model_layers(crt_model, pretrained_net)
crt_model.load_state_dict(pretrained_net)
crt_model.eval()
if "params_ema" in state_dict:
state_dict = state_dict["params_ema"]
elif "params" in state_dict:
state_dict = state_dict["params"]
num_conv = 16 if "realesr-animevideov3" in filename else 32
model = arch.SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=num_conv, upscale=4, act_type='prelu')
model.load_state_dict(state_dict)
model.eval()
return model
return crt_model
if "body.0.rdb1.conv1.weight" in state_dict and "conv_first.weight" in state_dict:
nb = 6 if "RealESRGAN_x4plus_anime_6B" in filename else 23
state_dict = resrgan2normal(state_dict, nb)
elif "conv_first.weight" in state_dict:
state_dict = mod2normal(state_dict)
elif "model.0.weight" not in state_dict:
raise Exception("The file is not a recognized ESRGAN model.")
in_nc, out_nc, nf, nb, plus, mscale = infer_params(state_dict)
model = arch.RRDBNet(in_nc=in_nc, out_nc=out_nc, nf=nf, nb=nb, upscale=mscale, plus=plus)
model.load_state_dict(state_dict)
model.eval()
return model
def upscale_without_tiling(model, img):
img = np.array(img)
img = img[:, :, ::-1]
img = np.moveaxis(img, 2, 0) / 255
img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
img = torch.from_numpy(img).float()
img = img.unsqueeze(0).to(devices.device_esrgan)
with torch.no_grad():

487
modules/esrgan_model_arch.py
View file

@ -1,80 +1,463 @@
# this file is taken from https://github.com/xinntao/ESRGAN
# this file is adapted from https://github.com/victorca25/iNNfer
import math
import functools
import torch
import torch.nn as nn
import torch.nn.functional as F
def make_layer(block, n_layers):
layers = []
for _ in range(n_layers):
layers.append(block())
return nn.Sequential(*layers)
####################
# RRDBNet Generator
####################
class RRDBNet(nn.Module):
def __init__(self, in_nc, out_nc, nf, nb, nr=3, gc=32, upscale=4, norm_type=None,
act_type='leakyrelu', mode='CNA', upsample_mode='upconv', convtype='Conv2D',
finalact=None, gaussian_noise=False, plus=False):
super(RRDBNet, self).__init__()
n_upscale = int(math.log(upscale, 2))
if upscale == 3:
n_upscale = 1
class ResidualDenseBlock_5C(nn.Module):
def __init__(self, nf=64, gc=32, bias=True):
super(ResidualDenseBlock_5C, self).__init__()
# gc: growth channel, i.e. intermediate channels
self.conv1 = nn.Conv2d(nf, gc, 3, 1, 1, bias=bias)
self.conv2 = nn.Conv2d(nf + gc, gc, 3, 1, 1, bias=bias)
self.conv3 = nn.Conv2d(nf + 2 * gc, gc, 3, 1, 1, bias=bias)
self.conv4 = nn.Conv2d(nf + 3 * gc, gc, 3, 1, 1, bias=bias)
self.conv5 = nn.Conv2d(nf + 4 * gc, nf, 3, 1, 1, bias=bias)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
self.resrgan_scale = 0
if in_nc % 16 == 0:
self.resrgan_scale = 1
elif in_nc != 4 and in_nc % 4 == 0:
self.resrgan_scale = 2
# initialization
# mutil.initialize_weights([self.conv1, self.conv2, self.conv3, self.conv4, self.conv5], 0.1)
fea_conv = conv_block(in_nc, nf, kernel_size=3, norm_type=None, act_type=None, convtype=convtype)
rb_blocks = [RRDB(nf, nr, kernel_size=3, gc=32, stride=1, bias=1, pad_type='zero',
norm_type=norm_type, act_type=act_type, mode='CNA', convtype=convtype,
gaussian_noise=gaussian_noise, plus=plus) for _ in range(nb)]
LR_conv = conv_block(nf, nf, kernel_size=3, norm_type=norm_type, act_type=None, mode=mode, convtype=convtype)
def forward(self, x):
x1 = self.lrelu(self.conv1(x))
x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1)))
x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1)))
x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
return x5 * 0.2 + x
if upsample_mode == 'upconv':
upsample_block = upconv_block
elif upsample_mode == 'pixelshuffle':
upsample_block = pixelshuffle_block
else:
raise NotImplementedError('upsample mode [{:s}] is not found'.format(upsample_mode))
if upscale == 3:
upsampler = upsample_block(nf, nf, 3, act_type=act_type, convtype=convtype)
else:
upsampler = [upsample_block(nf, nf, act_type=act_type, convtype=convtype) for _ in range(n_upscale)]
HR_conv0 = conv_block(nf, nf, kernel_size=3, norm_type=None, act_type=act_type, convtype=convtype)
HR_conv1 = conv_block(nf, out_nc, kernel_size=3, norm_type=None, act_type=None, convtype=convtype)
outact = act(finalact) if finalact else None
self.model = sequential(fea_conv, ShortcutBlock(sequential(*rb_blocks, LR_conv)),
*upsampler, HR_conv0, HR_conv1, outact)
def forward(self, x, outm=None):
if self.resrgan_scale == 1:
feat = pixel_unshuffle(x, scale=4)
elif self.resrgan_scale == 2:
feat = pixel_unshuffle(x, scale=2)
else:
feat = x
return self.model(feat)
class RRDB(nn.Module):
'''Residual in Residual Dense Block'''
"""
Residual in Residual Dense Block
(ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks)
"""
def __init__(self, nf, gc=32):
def __init__(self, nf, nr=3, kernel_size=3, gc=32, stride=1, bias=1, pad_type='zero',
norm_type=None, act_type='leakyrelu', mode='CNA', convtype='Conv2D',
spectral_norm=False, gaussian_noise=False, plus=False):
super(RRDB, self).__init__()
self.RDB1 = ResidualDenseBlock_5C(nf, gc)
self.RDB2 = ResidualDenseBlock_5C(nf, gc)
self.RDB3 = ResidualDenseBlock_5C(nf, gc)
# This is for backwards compatibility with existing models
if nr == 3:
self.RDB1 = ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
gaussian_noise=gaussian_noise, plus=plus)
self.RDB2 = ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
gaussian_noise=gaussian_noise, plus=plus)
self.RDB3 = ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
gaussian_noise=gaussian_noise, plus=plus)
else:
RDB_list = [ResidualDenseBlock_5C(nf, kernel_size, gc, stride, bias, pad_type,
norm_type, act_type, mode, convtype, spectral_norm=spectral_norm,
gaussian_noise=gaussian_noise, plus=plus) for _ in range(nr)]
self.RDBs = nn.Sequential(*RDB_list)
def forward(self, x):
out = self.RDB1(x)
out = self.RDB2(out)
out = self.RDB3(out)
if hasattr(self, 'RDB1'):
out = self.RDB1(x)
out = self.RDB2(out)
out = self.RDB3(out)
else:
out = self.RDBs(x)
return out * 0.2 + x
class RRDBNet(nn.Module):
def __init__(self, in_nc, out_nc, nf, nb, gc=32):
super(RRDBNet, self).__init__()
RRDB_block_f = functools.partial(RRDB, nf=nf, gc=gc)
class ResidualDenseBlock_5C(nn.Module):
"""
Residual Dense Block
The core module of paper: (Residual Dense Network for Image Super-Resolution, CVPR 18)
Modified options that can be used:
- "Partial Convolution based Padding" arXiv:1811.11718
- "Spectral normalization" arXiv:1802.05957
- "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C.
{Rakotonirina} and A. {Rasoanaivo}
"""
self.conv_first = nn.Conv2d(in_nc, nf, 3, 1, 1, bias=True)
self.RRDB_trunk = make_layer(RRDB_block_f, nb)
self.trunk_conv = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
#### upsampling
self.upconv1 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
self.upconv2 = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
self.HRconv = nn.Conv2d(nf, nf, 3, 1, 1, bias=True)
self.conv_last = nn.Conv2d(nf, out_nc, 3, 1, 1, bias=True)
def __init__(self, nf=64, kernel_size=3, gc=32, stride=1, bias=1, pad_type='zero',
norm_type=None, act_type='leakyrelu', mode='CNA', convtype='Conv2D',
spectral_norm=False, gaussian_noise=False, plus=False):
super(ResidualDenseBlock_5C, self).__init__()
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
self.noise = GaussianNoise() if gaussian_noise else None
self.conv1x1 = conv1x1(nf, gc) if plus else None
self.conv1 = conv_block(nf, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
spectral_norm=spectral_norm)
self.conv2 = conv_block(nf+gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
spectral_norm=spectral_norm)
self.conv3 = conv_block(nf+2*gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
spectral_norm=spectral_norm)
self.conv4 = conv_block(nf+3*gc, gc, kernel_size, stride, bias=bias, pad_type=pad_type,
norm_type=norm_type, act_type=act_type, mode=mode, convtype=convtype,
spectral_norm=spectral_norm)
if mode == 'CNA':
last_act = None
else:
last_act = act_type
self.conv5 = conv_block(nf+4*gc, nf, 3, stride, bias=bias, pad_type=pad_type,
norm_type=norm_type, act_type=last_act, mode=mode, convtype=convtype,
spectral_norm=spectral_norm)
def forward(self, x):
fea = self.conv_first(x)
trunk = self.trunk_conv(self.RRDB_trunk(fea))
fea = fea + trunk
x1 = self.conv1(x)
x2 = self.conv2(torch.cat((x, x1), 1))
if self.conv1x1:
x2 = x2 + self.conv1x1(x)
x3 = self.conv3(torch.cat((x, x1, x2), 1))
x4 = self.conv4(torch.cat((x, x1, x2, x3), 1))
if self.conv1x1:
x4 = x4 + x2
x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
if self.noise:
return self.noise(x5.mul(0.2) + x)
else:
return x5 * 0.2 + x
fea = self.lrelu(self.upconv1(F.interpolate(fea, scale_factor=2, mode='nearest')))
fea = self.lrelu(self.upconv2(F.interpolate(fea, scale_factor=2, mode='nearest')))
out = self.conv_last(self.lrelu(self.HRconv(fea)))
####################
# ESRGANplus
####################
class GaussianNoise(nn.Module):
def __init__(self, sigma=0.1, is_relative_detach=False):
super().__init__()
self.sigma = sigma
self.is_relative_detach = is_relative_detach
self.noise = torch.tensor(0, dtype=torch.float)
def forward(self, x):
if self.training and self.sigma != 0:
self.noise = self.noise.to(x.device)
scale = self.sigma * x.detach() if self.is_relative_detach else self.sigma * x
sampled_noise = self.noise.repeat(*x.size()).normal_() * scale
x = x + sampled_noise
return x
def conv1x1(in_planes, out_planes, stride=1):
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
####################
# SRVGGNetCompact
####################
class SRVGGNetCompact(nn.Module):
"""A compact VGG-style network structure for super-resolution.
This class is copied from https://github.com/xinntao/Real-ESRGAN
"""
def __init__(self, num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu'):
super(SRVGGNetCompact, self).__init__()
self.num_in_ch = num_in_ch
self.num_out_ch = num_out_ch
self.num_feat = num_feat
self.num_conv = num_conv
self.upscale = upscale
self.act_type = act_type
self.body = nn.ModuleList()
# the first conv
self.body.append(nn.Conv2d(num_in_ch, num_feat, 3, 1, 1))
# the first activation
if act_type == 'relu':
activation = nn.ReLU(inplace=True)
elif act_type == 'prelu':
activation = nn.PReLU(num_parameters=num_feat)
elif act_type == 'leakyrelu':
activation = nn.LeakyReLU(negative_slope=0.1, inplace=True)
self.body.append(activation)
# the body structure
for _ in range(num_conv):
self.body.append(nn.Conv2d(num_feat, num_feat, 3, 1, 1))
# activation
if act_type == 'relu':
activation = nn.ReLU(inplace=True)
elif act_type == 'prelu':
activation = nn.PReLU(num_parameters=num_feat)
elif act_type == 'leakyrelu':
activation = nn.LeakyReLU(negative_slope=0.1, inplace=True)
self.body.append(activation)
# the last conv
self.body.append(nn.Conv2d(num_feat, num_out_ch * upscale * upscale, 3, 1, 1))
# upsample
self.upsampler = nn.PixelShuffle(upscale)
def forward(self, x):
out = x
for i in range(0, len(self.body)):
out = self.body[i](out)
out = self.upsampler(out)
# add the nearest upsampled image, so that the network learns the residual
base = F.interpolate(x, scale_factor=self.upscale, mode='nearest')
out += base
return out
####################
# Upsampler
####################
class Upsample(nn.Module):
r"""Upsamples a given multi-channel 1D (temporal), 2D (spatial) or 3D (volumetric) data.
The input data is assumed to be of the form
`minibatch x channels x [optional depth] x [optional height] x width`.
"""
def __init__(self, size=None, scale_factor=None, mode="nearest", align_corners=None):
super(Upsample, self).__init__()
if isinstance(scale_factor, tuple):
self.scale_factor = tuple(float(factor) for factor in scale_factor)
else:
self.scale_factor = float(scale_factor) if scale_factor else None
self.mode = mode
self.size = size
self.align_corners = align_corners
def forward(self, x):
return nn.functional.interpolate(x, size=self.size, scale_factor=self.scale_factor, mode=self.mode, align_corners=self.align_corners)
def extra_repr(self):
if self.scale_factor is not None:
info = 'scale_factor=' + str(self.scale_factor)
else:
info = 'size=' + str(self.size)
info += ', mode=' + self.mode
return info
def pixel_unshuffle(x, scale):
""" Pixel unshuffle.
Args:
x (Tensor): Input feature with shape (b, c, hh, hw).
scale (int): Downsample ratio.
Returns:
Tensor: the pixel unshuffled feature.
"""
b, c, hh, hw = x.size()
out_channel = c * (scale**2)
assert hh % scale == 0 and hw % scale == 0
h = hh // scale
w = hw // scale
x_view = x.view(b, c, h, scale, w, scale)
return x_view.permute(0, 1, 3, 5, 2, 4).reshape(b, out_channel, h, w)
def pixelshuffle_block(in_nc, out_nc, upscale_factor=2, kernel_size=3, stride=1, bias=True,
pad_type='zero', norm_type=None, act_type='relu', convtype='Conv2D'):
"""
Pixel shuffle layer
(Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional
Neural Network, CVPR17)
"""
conv = conv_block(in_nc, out_nc * (upscale_factor ** 2), kernel_size, stride, bias=bias,
pad_type=pad_type, norm_type=None, act_type=None, convtype=convtype)
pixel_shuffle = nn.PixelShuffle(upscale_factor)
n = norm(norm_type, out_nc) if norm_type else None
a = act(act_type) if act_type else None
return sequential(conv, pixel_shuffle, n, a)
def upconv_block(in_nc, out_nc, upscale_factor=2, kernel_size=3, stride=1, bias=True,
pad_type='zero', norm_type=None, act_type='relu', mode='nearest', convtype='Conv2D'):
""" Upconv layer """
upscale_factor = (1, upscale_factor, upscale_factor) if convtype == 'Conv3D' else upscale_factor
upsample = Upsample(scale_factor=upscale_factor, mode=mode)
conv = conv_block(in_nc, out_nc, kernel_size, stride, bias=bias,
pad_type=pad_type, norm_type=norm_type, act_type=act_type, convtype=convtype)
return sequential(upsample, conv)
####################
# Basic blocks
####################
def make_layer(basic_block, num_basic_block, **kwarg):
"""Make layers by stacking the same blocks.
Args:
basic_block (nn.module): nn.module class for basic block. (block)
num_basic_block (int): number of blocks. (n_layers)
Returns:
nn.Sequential: Stacked blocks in nn.Sequential.
"""
layers = []
for _ in range(num_basic_block):
layers.append(basic_block(**kwarg))
return nn.Sequential(*layers)
def act(act_type, inplace=True, neg_slope=0.2, n_prelu=1, beta=1.0):
""" activation helper """
act_type = act_type.lower()
if act_type == 'relu':
layer = nn.ReLU(inplace)
elif act_type in ('leakyrelu', 'lrelu'):
layer = nn.LeakyReLU(neg_slope, inplace)
elif act_type == 'prelu':
layer = nn.PReLU(num_parameters=n_prelu, init=neg_slope)
elif act_type == 'tanh': # [-1, 1] range output
layer = nn.Tanh()
elif act_type == 'sigmoid': # [0, 1] range output
layer = nn.Sigmoid()
else:
raise NotImplementedError('activation layer [{:s}] is not found'.format(act_type))
return layer
class Identity(nn.Module):
def __init__(self, *kwargs):
super(Identity, self).__init__()
def forward(self, x, *kwargs):
return x
def norm(norm_type, nc):
""" Return a normalization layer """
norm_type = norm_type.lower()
if norm_type == 'batch':
layer = nn.BatchNorm2d(nc, affine=True)
elif norm_type == 'instance':
layer = nn.InstanceNorm2d(nc, affine=False)
elif norm_type == 'none':
def norm_layer(x): return Identity()
else:
raise NotImplementedError('normalization layer [{:s}] is not found'.format(norm_type))
return layer
def pad(pad_type, padding):
""" padding layer helper """
pad_type = pad_type.lower()
if padding == 0:
return None
if pad_type == 'reflect':
layer = nn.ReflectionPad2d(padding)
elif pad_type == 'replicate':
layer = nn.ReplicationPad2d(padding)
elif pad_type == 'zero':
layer = nn.ZeroPad2d(padding)
else:
raise NotImplementedError('padding layer [{:s}] is not implemented'.format(pad_type))
return layer
def get_valid_padding(kernel_size, dilation):
kernel_size = kernel_size + (kernel_size - 1) * (dilation - 1)
padding = (kernel_size - 1) // 2
return padding
class ShortcutBlock(nn.Module):
""" Elementwise sum the output of a submodule to its input """
def __init__(self, submodule):
super(ShortcutBlock, self).__init__()
self.sub = submodule
def forward(self, x):
output = x + self.sub(x)
return output
def __repr__(self):
return 'Identity + \n|' + self.sub.__repr__().replace('\n', '\n|')
def sequential(*args):
""" Flatten Sequential. It unwraps nn.Sequential. """
if len(args) == 1:
if isinstance(args[0], OrderedDict):
raise NotImplementedError('sequential does not support OrderedDict input.')
return args[0] # No sequential is needed.
modules = []
for module in args:
if isinstance(module, nn.Sequential):
for submodule in module.children():
modules.append(submodule)
elif isinstance(module, nn.Module):
modules.append(module)
return nn.Sequential(*modules)
def conv_block(in_nc, out_nc, kernel_size, stride=1, dilation=1, groups=1, bias=True,
pad_type='zero', norm_type=None, act_type='relu', mode='CNA', convtype='Conv2D',
spectral_norm=False):
""" Conv layer with padding, normalization, activation """
assert mode in ['CNA', 'NAC', 'CNAC'], 'Wrong conv mode [{:s}]'.format(mode)
padding = get_valid_padding(kernel_size, dilation)
p = pad(pad_type, padding) if pad_type and pad_type != 'zero' else None
padding = padding if pad_type == 'zero' else 0
if convtype=='PartialConv2D':
c = PartialConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
dilation=dilation, bias=bias, groups=groups)
elif convtype=='DeformConv2D':
c = DeformConv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
dilation=dilation, bias=bias, groups=groups)
elif convtype=='Conv3D':
c = nn.Conv3d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
dilation=dilation, bias=bias, groups=groups)
else:
c = nn.Conv2d(in_nc, out_nc, kernel_size=kernel_size, stride=stride, padding=padding,
dilation=dilation, bias=bias, groups=groups)
if spectral_norm:
c = nn.utils.spectral_norm(c)
a = act(act_type) if act_type else None
if 'CNA' in mode:
n = norm(norm_type, out_nc) if norm_type else None
return sequential(p, c, n, a)
elif mode == 'NAC':
if norm_type is None and act_type is not None:
a = act(act_type, inplace=False)
n = norm(norm_type, in_nc) if norm_type else None
return sequential(n, a, p, c)

24
modules/extras.py
View file

@ -39,9 +39,12 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
if input_dir == '':
return outputs, "Please select an input directory.", ''
image_list = [file for file in [os.path.join(input_dir, x) for x in os.listdir(input_dir)] if os.path.isfile(file)]
image_list = [file for file in [os.path.join(input_dir, x) for x in sorted(os.listdir(input_dir))] if os.path.isfile(file)]
for img in image_list:
image = Image.open(img)
try:
image = Image.open(img)
except Exception:
continue
imageArr.append(image)
imageNameArr.append(img)
else:
@ -118,10 +121,14 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
while len(cached_images) > 2:
del cached_images[next(iter(cached_images.keys()))]
if opts.use_original_name_batch and image_name != None:
basename = os.path.splitext(os.path.basename(image_name))[0]
else:
basename = ''
images.save_image(image, path=outpath, basename="", seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo,
forced_filename=image_name if opts.use_original_name_batch else None)
images.save_image(image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None)
if opts.enable_pnginfo:
image.info = existing_pnginfo
@ -216,8 +223,11 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam
if theta_func1:
for key in tqdm.tqdm(theta_1.keys()):
if 'model' in key:
t2 = theta_2.get(key, torch.zeros_like(theta_1[key]))
theta_1[key] = theta_func1(theta_1[key], t2)
if key in theta_2:
t2 = theta_2.get(key, torch.zeros_like(theta_1[key]))
theta_1[key] = theta_func1(theta_1[key], t2)
else:
theta_1[key] = torch.zeros_like(theta_1[key])
del theta_2, teritary_model
for key in tqdm.tqdm(theta_0.keys()):

25
modules/generation_parameters_copypaste.py
View file

@ -4,13 +4,22 @@ import gradio as gr
from modules.shared import script_path
from modules import shared
re_param_code = r"\s*([\w ]+):\s*([^,]+)(?:,|$)"
re_param_code = r'\s*([\w ]+):\s*("(?:\\|\"|[^\"])+"|[^,]*)(?:,|$)'
re_param = re.compile(re_param_code)
re_params = re.compile(r"^(?:" + re_param_code + "){3,}$")
re_imagesize = re.compile(r"^(\d+)x(\d+)$")
type_of_gr_update = type(gr.update())
def quote(text):
if ',' not in str(text):
return text
text = str(text)
text = text.replace('\\', '\\\\')
text = text.replace('"', '\\"')
return f'"{text}"'
def parse_generation_parameters(x: str):
"""parses generation parameters string, the one you see in text field under the picture in UI:
```
@ -45,11 +54,8 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
else:
prompt += ("" if prompt == "" else "\n") + line
if len(prompt) > 0:
res["Prompt"] = prompt
if len(negative_prompt) > 0:
res["Negative prompt"] = negative_prompt
res["Prompt"] = prompt
res["Negative prompt"] = negative_prompt
for k, v in re_param.findall(lastline):
m = re_imagesize.match(v)
@ -86,7 +92,12 @@ def connect_paste(button, paste_fields, input_comp, js=None):
else:
try:
valtype = type(output.value)
val = valtype(v)
if valtype == bool and v == "False":
val = False
else:
val = valtype(v)
res.append(gr.update(value=val))
except Exception:
res.append(gr.update())

213
modules/hypernetworks/hypernetwork.py
View file

@ -1,46 +1,99 @@
import csv
import datetime
import glob
import html
import os
import sys
import traceback
import tqdm
import csv
import torch
from ldm.util import default
from modules import devices, shared, processing, sd_models
import torch
from torch import einsum
from einops import rearrange, repeat
import modules.textual_inversion.dataset
import torch
import tqdm
from einops import rearrange, repeat
from ldm.util import default
from modules import devices, processing, sd_models, shared
from modules.textual_inversion import textual_inversion
from modules.textual_inversion.learn_schedule import LearnRateScheduler
from torch import einsum
from statistics import stdev, mean
class HypernetworkModule(torch.nn.Module):
multiplier = 1.0
activation_dict = {
"relu": torch.nn.ReLU,
"leakyrelu": torch.nn.LeakyReLU,
"elu": torch.nn.ELU,
"swish": torch.nn.Hardswish,
}
def __init__(self, dim, state_dict=None):
def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, add_layer_norm=False, use_dropout=False):
super().__init__()
self.linear1 = torch.nn.Linear(dim, dim * 2)
self.linear2 = torch.nn.Linear(dim * 2, dim)
assert layer_structure is not None, "layer_structure must not be None"
assert layer_structure[0] == 1, "Multiplier Sequence should start with size 1!"
assert layer_structure[-1] == 1, "Multiplier Sequence should end with size 1!"
linears = []
for i in range(len(layer_structure) - 1):
# Add a fully-connected layer
linears.append(torch.nn.Linear(int(dim * layer_structure[i]), int(dim * layer_structure[i+1])))
# Add an activation func
if activation_func == "linear" or activation_func is None:
pass
elif activation_func in self.activation_dict:
linears.append(self.activation_dict[activation_func]())
else:
raise RuntimeError(f'hypernetwork uses an unsupported activation function: {activation_func}')
# Add layer normalization
if add_layer_norm:
linears.append(torch.nn.LayerNorm(int(dim * layer_structure[i+1])))
# Add dropout expect last layer
if use_dropout and i < len(layer_structure) - 3:
linears.append(torch.nn.Dropout(p=0.3))
self.linear = torch.nn.Sequential(*linears)
if state_dict is not None:
self.load_state_dict(state_dict, strict=True)
self.fix_old_state_dict(state_dict)
self.load_state_dict(state_dict)
else:
self.linear1.weight.data.normal_(mean=0.0, std=0.01)
self.linear1.bias.data.zero_()
self.linear2.weight.data.normal_(mean=0.0, std=0.01)
self.linear2.bias.data.zero_()
for layer in self.linear:
if type(layer) == torch.nn.Linear or type(layer) == torch.nn.LayerNorm:
layer.weight.data.normal_(mean=0.0, std=0.01)
layer.bias.data.zero_()
self.to(devices.device)
def fix_old_state_dict(self, state_dict):
changes = {
'linear1.bias': 'linear.0.bias',
'linear1.weight': 'linear.0.weight',
'linear2.bias': 'linear.1.bias',
'linear2.weight': 'linear.1.weight',
}
for fr, to in changes.items():
x = state_dict.get(fr, None)
if x is None:
continue
del state_dict[fr]
state_dict[to] = x
def forward(self, x):
return x + (self.linear2(self.linear1(x))) * self.multiplier
return x + self.linear(x) * self.multiplier
def trainables(self):
layer_structure = []
for layer in self.linear:
if type(layer) == torch.nn.Linear or type(layer) == torch.nn.LayerNorm:
layer_structure += [layer.weight, layer.bias]
return layer_structure
def apply_strength(value=None):
@ -51,16 +104,23 @@ class Hypernetwork:
filename = None
name = None
def __init__(self, name=None, enable_sizes=None):
def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, add_layer_norm=False, use_dropout=False):
self.filename = None
self.name = name
self.layers = {}
self.step = 0
self.sd_checkpoint = None
self.sd_checkpoint_name = None
self.layer_structure = layer_structure
self.activation_func = activation_func
self.add_layer_norm = add_layer_norm
self.use_dropout = use_dropout
for size in enable_sizes or []:
self.layers[size] = (HypernetworkModule(size), HypernetworkModule(size))
self.layers[size] = (
HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
)
def weights(self):
res = []
@ -68,7 +128,7 @@ class Hypernetwork:
for k, layers in self.layers.items():
for layer in layers:
layer.train()
res += [layer.linear1.weight, layer.linear1.bias, layer.linear2.weight, layer.linear2.bias]
res += layer.trainables()
return res
@ -80,6 +140,10 @@ class Hypernetwork:
state_dict['step'] = self.step
state_dict['name'] = self.name
state_dict['layer_structure'] = self.layer_structure
state_dict['activation_func'] = self.activation_func
state_dict['is_layer_norm'] = self.add_layer_norm
state_dict['use_dropout'] = self.use_dropout
state_dict['sd_checkpoint'] = self.sd_checkpoint
state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name
@ -92,9 +156,17 @@ class Hypernetwork:
state_dict = torch.load(filename, map_location='cpu')
self.layer_structure = state_dict.get('layer_structure', [1, 2, 1])
self.activation_func = state_dict.get('activation_func', None)
self.add_layer_norm = state_dict.get('is_layer_norm', False)
self.use_dropout = state_dict.get('use_dropout', False)
for size, sd in state_dict.items():
if type(size) == int:
self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
self.layers[size] = (
HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
)
self.name = state_dict.get('name', self.name)
self.step = state_dict.get('step', 0)
@ -196,7 +268,40 @@ def stack_conds(conds):
return torch.stack(conds)
def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
def log_statistics(loss_info:dict, key, value):
if key not in loss_info:
loss_info[key] = [value]
else:
loss_info[key].append(value)
if len(loss_info) > 1024:
loss_info.pop(0)
def statistics(data):
total_information = f"loss:{mean(data):.3f}"+u"\u00B1"+f"({stdev(data)/ (len(data)**0.5):.3f})"
recent_data = data[-32:]
recent_information = f"recent 32 loss:{mean(recent_data):.3f}"+u"\u00B1"+f"({stdev(recent_data)/ (len(recent_data)**0.5):.3f})"
return total_information, recent_information
def report_statistics(loss_info:dict):
keys = sorted(loss_info.keys(), key=lambda x: sum(loss_info[x]) / len(loss_info[x]))
for key in keys:
try:
print("Loss statistics for file " + key)
info, recent = statistics(loss_info[key])
print(info)
print(recent)
except Exception as e:
print(e)
def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log_directory, training_width, training_height, steps, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# images allows training previews to have infotext. Importing it at the top causes a circular import problem.
from modules import images
assert hypernetwork_name, 'hypernetwork not selected'
path = shared.hypernetworks.get(hypernetwork_name, None)
@ -225,8 +330,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
with torch.autocast("cuda"):
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size)
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size)
if unload:
shared.sd_model.cond_stage_model.to(devices.cpu)
shared.sd_model.first_stage_model.to(devices.cpu)
@ -236,22 +340,32 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
for weight in weights:
weight.requires_grad = True
losses = torch.zeros((32,))
size = len(ds.indexes)
loss_dict = {}
losses = torch.zeros((size,))
previous_mean_loss = 0
print("Mean loss of {} elements".format(size))
last_saved_file = "<none>"
last_saved_image = "<none>"
forced_filename = "<none>"
ititial_step = hypernetwork.step or 0
if ititial_step > steps:
return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
# if optimizer == "AdamW": or else Adam / AdamW / SGD, etc...
optimizer = torch.optim.AdamW(weights, lr=scheduler.learn_rate)
steps_without_grad = 0
pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
for i, entries in pbar:
hypernetwork.step = i + ititial_step
if len(loss_dict) > 0:
previous_mean_loss = sum(i[-1] for i in loss_dict.values()) / len(loss_dict)
scheduler.apply(optimizer, hypernetwork.step)
if scheduler.finished:
break
@ -261,33 +375,46 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
with torch.autocast("cuda"):
c = stack_conds([entry.cond for entry in entries]).to(devices.device)
# c = torch.vstack([entry.cond for entry in entries]).to(devices.device)
# c = torch.vstack([entry.cond for entry in entries]).to(devices.device)
x = torch.stack([entry.latent for entry in entries]).to(devices.device)
loss = shared.sd_model(x, c)[0]
del x
del c
losses[hypernetwork.step % losses.shape[0]] = loss.item()
for entry in entries:
log_statistics(loss_dict, entry.filename, loss.item())
optimizer.zero_grad()
weights[0].grad = None
loss.backward()
if weights[0].grad is None:
steps_without_grad += 1
else:
steps_without_grad = 0
assert steps_without_grad < 10, 'no gradient found for the trained weight after backward() for 10 steps in a row; this is a bug; training cannot continue'
optimizer.step()
mean_loss = losses.mean()
if torch.isnan(mean_loss):
if torch.isnan(losses[hypernetwork.step % losses.shape[0]]):
raise RuntimeError("Loss diverged.")
pbar.set_description(f"loss: {mean_loss:.7f}")
pbar.set_description(f"dataset loss: {previous_mean_loss:.7f}")
if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0:
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt')
# Before saving, change name to match current checkpoint.
hypernetwork.name = f'{hypernetwork_name}-{hypernetwork.step}'
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork.name}.pt')
hypernetwork.save(last_saved_file)
textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
"loss": f"{mean_loss:.7f}",
"loss": f"{previous_mean_loss:.7f}",
"learn_rate": scheduler.learn_rate
})
if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0:
last_saved_image = os.path.join(images_dir, f'{hypernetwork_name}-{hypernetwork.step}.png')
forced_filename = f'{hypernetwork_name}-{hypernetwork.step}'
last_saved_image = os.path.join(images_dir, forced_filename)
optimizer.zero_grad()
shared.sd_model.cond_stage_model.to(devices.device)
@ -323,27 +450,29 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
if image is not None:
shared.state.current_image = image
image.save(last_saved_image)
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename)
last_saved_image += f", prompt: {preview_text}"
shared.state.job_no = hypernetwork.step
shared.state.textinfo = f"""
<p>
Loss: {mean_loss:.7f}<br/>
Loss: {previous_mean_loss:.7f}<br/>
Step: {hypernetwork.step}<br/>
Last prompt: {html.escape(entries[0].cond_text)}<br/>
Last saved embedding: {html.escape(last_saved_file)}<br/>
Last saved hypernetwork: {html.escape(last_saved_file)}<br/>
Last saved image: {html.escape(last_saved_image)}<br/>
</p>
"""
report_statistics(loss_dict)
checkpoint = sd_models.select_checkpoint()
hypernetwork.sd_checkpoint = checkpoint.hash
hypernetwork.sd_checkpoint_name = checkpoint.model_name
# Before saving for the last time, change name back to the base name (as opposed to the save_hypernetwork_every step-suffixed naming convention).
hypernetwork.name = hypernetwork_name
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork.name}.pt')
hypernetwork.save(filename)
return hypernetwork, filename

28
modules/hypernetworks/ui.py
View file

@ -1,19 +1,33 @@
import html
import os
import re
import gradio as gr
import modules.textual_inversion.textual_inversion
import modules.textual_inversion.preprocess
from modules import sd_hijack, shared, devices
import modules.textual_inversion.textual_inversion
from modules import devices, sd_hijack, shared
from modules.hypernetworks import hypernetwork
def create_hypernetwork(name, enable_sizes):
fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt")
assert not os.path.exists(fn), f"file {fn} already exists"
def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, add_layer_norm=False, use_dropout=False):
# Remove illegal characters from name.
name = "".join( x for x in name if (x.isalnum() or x in "._- "))
hypernet = modules.hypernetworks.hypernetwork.Hypernetwork(name=name, enable_sizes=[int(x) for x in enable_sizes])
fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt")
if not overwrite_old:
assert not os.path.exists(fn), f"file {fn} already exists"
if type(layer_structure) == str:
layer_structure = [float(x.strip()) for x in layer_structure.split(",")]
hypernet = modules.hypernetworks.hypernetwork.Hypernetwork(
name=name,
enable_sizes=[int(x) for x in enable_sizes],
layer_structure=layer_structure,
activation_func=activation_func,
add_layer_norm=add_layer_norm,
use_dropout=use_dropout,
)
hypernet.save(fn)
shared.reload_hypernetworks()

499
modules/images_history.py
View file

@ -1,183 +1,424 @@
import os
import shutil
import sys
import time
import hashlib
import gradio
system_bak_path = "webui_log_and_bak"
custom_tab_name = "custom fold"
faverate_tab_name = "favorites"
tabs_list = ["txt2img", "img2img", "extras", faverate_tab_name]
def is_valid_date(date):
try:
time.strptime(date, "%Y%m%d")
return True
except:
return False
def traverse_all_files(output_dir, image_list, curr_dir=None):
curr_path = output_dir if curr_dir is None else os.path.join(output_dir, curr_dir)
def reduplicative_file_move(src, dst):
def same_name_file(basename, path):
name, ext = os.path.splitext(basename)
f_list = os.listdir(path)
max_num = 0
for f in f_list:
if len(f) <= len(basename):
continue
f_ext = f[-len(ext):] if len(ext) > 0 else ""
if f[:len(name)] == name and f_ext == ext:
if f[len(name)] == "(" and f[-len(ext)-1] == ")":
number = f[len(name)+1:-len(ext)-1]
if number.isdigit():
if int(number) > max_num:
max_num = int(number)
return f"{name}({max_num + 1}){ext}"
name = os.path.basename(src)
save_name = os.path.join(dst, name)
if not os.path.exists(save_name):
shutil.move(src, dst)
else:
name = same_name_file(name, dst)
shutil.move(src, os.path.join(dst, name))
def traverse_all_files(curr_path, image_list, all_type=False):
try:
f_list = os.listdir(curr_path)
except:
if curr_dir[-10:].rfind(".") > 0 and curr_dir[-4:] != ".txt":
image_list.append(curr_dir)
if all_type or (curr_path[-10:].rfind(".") > 0 and curr_path[-4:] != ".txt" and curr_path[-4:] != ".csv"):
image_list.append(curr_path)
return image_list
for file in f_list:
file = file if curr_dir is None else os.path.join(curr_dir, file)
file_path = os.path.join(curr_path, file)
if file[-4:] == ".txt":
file = os.path.join(curr_path, file)
if (not all_type) and (file[-4:] == ".txt" or file[-4:] == ".csv"):
pass
elif os.path.isfile(file_path) and file[-10:].rfind(".") > 0:
elif os.path.isfile(file) and file[-10:].rfind(".") > 0:
image_list.append(file)
else:
image_list = traverse_all_files(output_dir, image_list, file)
image_list = traverse_all_files(file, image_list)
return image_list
def auto_sorting(dir_name):
bak_path = os.path.join(dir_name, system_bak_path)
if not os.path.exists(bak_path):
os.mkdir(bak_path)
log_file = None
files_list = []
f_list = os.listdir(dir_name)
for file in f_list:
if file == system_bak_path:
continue
file_path = os.path.join(dir_name, file)
if not is_valid_date(file):
if file[-10:].rfind(".") > 0:
files_list.append(file_path)
else:
files_list = traverse_all_files(file_path, files_list, all_type=True)
def get_recent_images(dir_name, page_index, step, image_index, tabname):
page_index = int(page_index)
image_list = []
if not os.path.exists(dir_name):
pass
elif os.path.isdir(dir_name):
image_list = traverse_all_files(dir_name, image_list)
image_list = sorted(image_list, key=lambda file: -os.path.getctime(os.path.join(dir_name, file)))
for file in files_list:
date_str = time.strftime("%Y%m%d",time.localtime(os.path.getmtime(file)))
file_path = os.path.dirname(file)
hash_path = hashlib.md5(file_path.encode()).hexdigest()
path = os.path.join(dir_name, date_str, hash_path)
if not os.path.exists(path):
os.makedirs(path)
if log_file is None:
log_file = open(os.path.join(bak_path,"path_mapping.csv"),"a")
log_file.write(f"{hash_path},{file_path}\n")
reduplicative_file_move(file, path)
date_list = []
f_list = os.listdir(dir_name)
for f in f_list:
if is_valid_date(f):
date_list.append(f)
elif f == system_bak_path:
continue
else:
try:
reduplicative_file_move(os.path.join(dir_name, f), bak_path)
except:
pass
today = time.strftime("%Y%m%d",time.localtime(time.time()))
if today not in date_list:
date_list.append(today)
return sorted(date_list, reverse=True)
def archive_images(dir_name, date_to):
filenames = []
batch_size =int(opts.images_history_num_per_page * opts.images_history_pages_num)
if batch_size <= 0:
batch_size = opts.images_history_num_per_page * 6
today = time.strftime("%Y%m%d",time.localtime(time.time()))
date_to = today if date_to is None or date_to == "" else date_to
date_to_bak = date_to
if False: #opts.images_history_reconstruct_directory:
date_list = auto_sorting(dir_name)
for date in date_list:
if date <= date_to:
path = os.path.join(dir_name, date)
if date == today and not os.path.exists(path):
continue
filenames = traverse_all_files(path, filenames)
if len(filenames) > batch_size:
break
filenames = sorted(filenames, key=lambda file: -os.path.getmtime(file))
else:
print(f'ERROR: "{dir_name}" is not a directory. Check the path in the settings.', file=sys.stderr)
num = 48 if tabname != "extras" else 12
max_page_index = len(image_list) // num + 1
page_index = max_page_index if page_index == -1 else page_index + step
page_index = 1 if page_index < 1 else page_index
page_index = max_page_index if page_index > max_page_index else page_index
idx_frm = (page_index - 1) * num
image_list = image_list[idx_frm:idx_frm + num]
image_index = int(image_index)
if image_index < 0 or image_index > len(image_list) - 1:
current_file = None
hidden = None
else:
current_file = image_list[int(image_index)]
hidden = os.path.join(dir_name, current_file)
return [os.path.join(dir_name, file) for file in image_list], page_index, image_list, current_file, hidden, ""
filenames = traverse_all_files(dir_name, filenames)
total_num = len(filenames)
tmparray = [(os.path.getmtime(file), file) for file in filenames ]
date_stamp = time.mktime(time.strptime(date_to, "%Y%m%d")) + 86400
filenames = []
date_list = {date_to:None}
date = time.strftime("%Y%m%d",time.localtime(time.time()))
for t, f in tmparray:
date = time.strftime("%Y%m%d",time.localtime(t))
date_list[date] = None
if t <= date_stamp:
filenames.append((t, f ,date))
date_list = sorted(list(date_list.keys()), reverse=True)
sort_array = sorted(filenames, key=lambda x:-x[0])
if len(sort_array) > batch_size:
date = sort_array[batch_size][2]
filenames = [x[1] for x in sort_array]
else:
date = date_to if len(sort_array) == 0 else sort_array[-1][2]
filenames = [x[1] for x in sort_array]
filenames = [x[1] for x in sort_array if x[2]>= date]
num = len(filenames)
last_date_from = date_to_bak if num == 0 else time.strftime("%Y%m%d", time.localtime(time.mktime(time.strptime(date, "%Y%m%d")) - 1000))
date = date[:4] + "/" + date[4:6] + "/" + date[6:8]
date_to_bak = date_to_bak[:4] + "/" + date_to_bak[4:6] + "/" + date_to_bak[6:8]
load_info = "<div style='color:#999' align='center'>"
load_info += f"{total_num} images in this directory. Loaded {num} images during {date} - {date_to_bak}, divided into {int((num + 1) // opts.images_history_num_per_page + 1)} pages"
load_info += "</div>"
_, image_list, _, _, visible_num = get_recent_images(1, 0, filenames)
return (
date_to,
load_info,
filenames,
1,
image_list,
"",
"",
visible_num,
last_date_from,
gradio.update(visible=total_num > num)
)
def first_page_click(dir_name, page_index, image_index, tabname):
return get_recent_images(dir_name, 1, 0, image_index, tabname)
def end_page_click(dir_name, page_index, image_index, tabname):
return get_recent_images(dir_name, -1, 0, image_index, tabname)
def prev_page_click(dir_name, page_index, image_index, tabname):
return get_recent_images(dir_name, page_index, -1, image_index, tabname)
def next_page_click(dir_name, page_index, image_index, tabname):
return get_recent_images(dir_name, page_index, 1, image_index, tabname)
def page_index_change(dir_name, page_index, image_index, tabname):
return get_recent_images(dir_name, page_index, 0, image_index, tabname)
def show_image_info(num, image_path, filenames):
# print(f"select image {num}")
file = filenames[int(num)]
return file, num, os.path.join(image_path, file)
def delete_image(delete_num, tabname, dir_name, name, page_index, filenames, image_index):
def delete_image(delete_num, name, filenames, image_index, visible_num):
if name == "":
return filenames, delete_num
else:
delete_num = int(delete_num)
visible_num = int(visible_num)
image_index = int(image_index)
index = list(filenames).index(name)
i = 0
new_file_list = []
for name in filenames:
if i >= index and i < index + delete_num:
path = os.path.join(dir_name, name)
if os.path.exists(path):
print(f"Delete file {path}")
os.remove(path)
txt_file = os.path.splitext(path)[0] + ".txt"
if os.path.exists(name):
if visible_num == image_index:
new_file_list.append(name)
i += 1
continue
print(f"Delete file {name}")
os.remove(name)
visible_num -= 1
txt_file = os.path.splitext(name)[0] + ".txt"
if os.path.exists(txt_file):
os.remove(txt_file)
else:
print(f"Not exists file {path}")
print(f"Not exists file {name}")
else:
new_file_list.append(name)
i += 1
return new_file_list, 1
return new_file_list, 1, visible_num
def save_image(file_name):
if file_name is not None and os.path.exists(file_name):
shutil.copy(file_name, opts.outdir_save)
def get_recent_images(page_index, step, filenames):
page_index = int(page_index)
num_of_imgs_per_page = int(opts.images_history_num_per_page)
max_page_index = len(filenames) // num_of_imgs_per_page + 1
page_index = max_page_index if page_index == -1 else page_index + step
page_index = 1 if page_index < 1 else page_index
page_index = max_page_index if page_index > max_page_index else page_index
idx_frm = (page_index - 1) * num_of_imgs_per_page
image_list = filenames[idx_frm:idx_frm + num_of_imgs_per_page]
length = len(filenames)
visible_num = num_of_imgs_per_page if idx_frm + num_of_imgs_per_page <= length else length % num_of_imgs_per_page
visible_num = num_of_imgs_per_page if visible_num == 0 else visible_num
return page_index, image_list, "", "", visible_num
def loac_batch_click(date_to):
if date_to is None:
return time.strftime("%Y%m%d",time.localtime(time.time())), []
else:
return None, []
def forward_click(last_date_from, date_to_recorder):
if len(date_to_recorder) == 0:
return None, []
if last_date_from == date_to_recorder[-1]:
date_to_recorder = date_to_recorder[:-1]
if len(date_to_recorder) == 0:
return None, []
return date_to_recorder[-1], date_to_recorder[:-1]
def backward_click(last_date_from, date_to_recorder):
if last_date_from is None or last_date_from == "":
return time.strftime("%Y%m%d",time.localtime(time.time())), []
if len(date_to_recorder) == 0 or last_date_from != date_to_recorder[-1]:
date_to_recorder.append(last_date_from)
return last_date_from, date_to_recorder
def first_page_click(page_index, filenames):
return get_recent_images(1, 0, filenames)
def end_page_click(page_index, filenames):
return get_recent_images(-1, 0, filenames)
def prev_page_click(page_index, filenames):
return get_recent_images(page_index, -1, filenames)
def next_page_click(page_index, filenames):
return get_recent_images(page_index, 1, filenames)
def page_index_change(page_index, filenames):
return get_recent_images(page_index, 0, filenames)
def show_image_info(tabname_box, num, page_index, filenames):
file = filenames[int(num) + int((page_index - 1) * int(opts.images_history_num_per_page))]
tm = "<div style='color:#999' align='right'>" + time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(os.path.getmtime(file))) + "</div>"
return file, tm, num, file
def enable_page_buttons():
return gradio.update(visible=True)
def change_dir(img_dir, date_to):
warning = None
try:
if os.path.exists(img_dir):
try:
f = os.listdir(img_dir)
except:
warning = f"'{img_dir} is not a directory"
else:
warning = "The directory is not exist"
except:
warning = "The format of the directory is incorrect"
if warning is None:
today = time.strftime("%Y%m%d",time.localtime(time.time()))
return gradio.update(visible=False), gradio.update(visible=True), None, None if date_to != today else today, gradio.update(visible=True), gradio.update(visible=True)
else:
return gradio.update(visible=True), gradio.update(visible=False), warning, date_to, gradio.update(visible=False), gradio.update(visible=False)
def show_images_history(gr, opts, tabname, run_pnginfo, switch_dict):
if opts.outdir_samples != "":
dir_name = opts.outdir_samples
elif tabname == "txt2img":
custom_dir = False
if tabname == "txt2img":
dir_name = opts.outdir_txt2img_samples
elif tabname == "img2img":
dir_name = opts.outdir_img2img_samples
elif tabname == "extras":
dir_name = opts.outdir_extras_samples
elif tabname == faverate_tab_name:
dir_name = opts.outdir_save
else:
return
with gr.Row():
renew_page = gr.Button('Renew Page', elem_id=tabname + "_images_history_renew_page")
first_page = gr.Button('First Page')
prev_page = gr.Button('Prev Page')
page_index = gr.Number(value=1, label="Page Index")
next_page = gr.Button('Next Page')
end_page = gr.Button('End Page')
with gr.Row(elem_id=tabname + "_images_history"):
with gr.Row():
with gr.Column(scale=2):
history_gallery = gr.Gallery(show_label=False, elem_id=tabname + "_images_history_gallery").style(grid=6)
with gr.Row():
delete_num = gr.Number(value=1, interactive=True, label="number of images to delete consecutively next")
delete = gr.Button('Delete', elem_id=tabname + "_images_history_del_button")
with gr.Column():
with gr.Row():
pnginfo_send_to_txt2img = gr.Button('Send to txt2img')
pnginfo_send_to_img2img = gr.Button('Send to img2img')
with gr.Row():
with gr.Column():
img_file_info = gr.Textbox(label="Generate Info", interactive=False)
img_file_name = gr.Textbox(label="File Name", interactive=False)
with gr.Row():
custom_dir = True
dir_name = None
if not custom_dir:
d = dir_name.split("/")
dir_name = d[0]
for p in d[1:]:
dir_name = os.path.join(dir_name, p)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
with gr.Column() as page_panel:
with gr.Row():
with gr.Column(scale=1, visible=not custom_dir) as load_batch_box:
load_batch = gr.Button('Load', elem_id=tabname + "_images_history_start", full_width=True)
with gr.Column(scale=4):
with gr.Row():
img_path = gr.Textbox(dir_name, label="Images directory", placeholder="Input images directory", interactive=custom_dir)
with gr.Row():
with gr.Column(visible=False, scale=1) as batch_panel:
with gr.Row():
forward = gr.Button('Prev batch')
backward = gr.Button('Next batch')
with gr.Column(scale=3):
load_info = gr.HTML(visible=not custom_dir)
with gr.Row(visible=False) as warning:
warning_box = gr.Textbox("Message", interactive=False)
with gr.Row(visible=not custom_dir, elem_id=tabname + "_images_history") as main_panel:
with gr.Column(scale=2):
with gr.Row(visible=True) as turn_page_buttons:
#date_to = gr.Dropdown(label="Date to")
first_page = gr.Button('First Page')
prev_page = gr.Button('Prev Page')
page_index = gr.Number(value=1, label="Page Index")
next_page = gr.Button('Next Page')
end_page = gr.Button('End Page')
history_gallery = gr.Gallery(show_label=False, elem_id=tabname + "_images_history_gallery").style(grid=opts.images_history_grid_num)
with gr.Row():
delete_num = gr.Number(value=1, interactive=True, label="number of images to delete consecutively next")
delete = gr.Button('Delete', elem_id=tabname + "_images_history_del_button")
with gr.Column():
with gr.Row():
with gr.Column():
img_file_info = gr.Textbox(label="Generate Info", interactive=False, lines=6)
gr.HTML("<hr>")
img_file_name = gr.Textbox(value="", label="File Name", interactive=False)
img_file_time= gr.HTML()
with gr.Row():
if tabname != faverate_tab_name:
save_btn = gr.Button('Collect')
pnginfo_send_to_txt2img = gr.Button('Send to txt2img')
pnginfo_send_to_img2img = gr.Button('Send to img2img')
# hiden items
with gr.Row(visible=False):
renew_page = gr.Button('Refresh page', elem_id=tabname + "_images_history_renew_page")
batch_date_to = gr.Textbox(label="Date to")
visible_img_num = gr.Number()
date_to_recorder = gr.State([])
last_date_from = gr.Textbox()
tabname_box = gr.Textbox(tabname)
image_index = gr.Textbox(value=-1)
set_index = gr.Button('set_index', elem_id=tabname + "_images_history_set_index")
filenames = gr.State()
all_images_list = gr.State()
hidden = gr.Image(type="pil")
info1 = gr.Textbox()
info2 = gr.Textbox()
img_path = gr.Textbox(dir_name.rstrip("/"), visible=False)
tabname_box = gr.Textbox(tabname, visible=False)
image_index = gr.Textbox(value=-1, visible=False)
set_index = gr.Button('set_index', elem_id=tabname + "_images_history_set_index", visible=False)
filenames = gr.State()
hidden = gr.Image(type="pil", visible=False)
info1 = gr.Textbox(visible=False)
info2 = gr.Textbox(visible=False)
img_path.submit(change_dir, inputs=[img_path, batch_date_to], outputs=[warning, main_panel, warning_box, batch_date_to, load_batch_box, load_info])
# turn pages
gallery_inputs = [img_path, page_index, image_index, tabname_box]
gallery_outputs = [history_gallery, page_index, filenames, img_file_name, hidden, img_file_name]
#change batch
change_date_output = [batch_date_to, load_info, filenames, page_index, history_gallery, img_file_name, img_file_time, visible_img_num, last_date_from, batch_panel]
batch_date_to.change(archive_images, inputs=[img_path, batch_date_to], outputs=change_date_output)
batch_date_to.change(enable_page_buttons, inputs=None, outputs=[turn_page_buttons])
batch_date_to.change(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
first_page.click(first_page_click, _js="images_history_turnpage", inputs=gallery_inputs, outputs=gallery_outputs)
next_page.click(next_page_click, _js="images_history_turnpage", inputs=gallery_inputs, outputs=gallery_outputs)
prev_page.click(prev_page_click, _js="images_history_turnpage", inputs=gallery_inputs, outputs=gallery_outputs)
end_page.click(end_page_click, _js="images_history_turnpage", inputs=gallery_inputs, outputs=gallery_outputs)
page_index.submit(page_index_change, _js="images_history_turnpage", inputs=gallery_inputs, outputs=gallery_outputs)
renew_page.click(page_index_change, _js="images_history_turnpage", inputs=gallery_inputs, outputs=gallery_outputs)
# page_index.change(page_index_change, inputs=[tabname_box, img_path, page_index], outputs=[history_gallery, page_index])
load_batch.click(loac_batch_click, inputs=[batch_date_to], outputs=[batch_date_to, date_to_recorder])
forward.click(forward_click, inputs=[last_date_from, date_to_recorder], outputs=[batch_date_to, date_to_recorder])
backward.click(backward_click, inputs=[last_date_from, date_to_recorder], outputs=[batch_date_to, date_to_recorder])
#delete
delete.click(delete_image, inputs=[delete_num, img_file_name, filenames, image_index, visible_img_num], outputs=[filenames, delete_num, visible_img_num])
delete.click(fn=None, _js="images_history_delete", inputs=[delete_num, tabname_box, image_index], outputs=None)
if tabname != faverate_tab_name:
save_btn.click(save_image, inputs=[img_file_name], outputs=None)
#turn page
gallery_inputs = [page_index, filenames]
gallery_outputs = [page_index, history_gallery, img_file_name, img_file_time, visible_img_num]
first_page.click(first_page_click, inputs=gallery_inputs, outputs=gallery_outputs)
next_page.click(next_page_click, inputs=gallery_inputs, outputs=gallery_outputs)
prev_page.click(prev_page_click, inputs=gallery_inputs, outputs=gallery_outputs)
end_page.click(end_page_click, inputs=gallery_inputs, outputs=gallery_outputs)
page_index.submit(page_index_change, inputs=gallery_inputs, outputs=gallery_outputs)
renew_page.click(page_index_change, inputs=gallery_inputs, outputs=gallery_outputs)
first_page.click(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
next_page.click(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
prev_page.click(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
end_page.click(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
page_index.submit(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
renew_page.click(fn=None, inputs=[tabname_box], outputs=None, _js="images_history_turnpage")
# other funcitons
set_index.click(show_image_info, _js="images_history_get_current_img", inputs=[tabname_box, img_path, filenames], outputs=[img_file_name, image_index, hidden])
img_file_name.change(fn=None, _js="images_history_enable_del_buttons", inputs=None, outputs=None)
delete.click(delete_image, _js="images_history_delete", inputs=[delete_num, tabname_box, img_path, img_file_name, page_index, filenames, image_index], outputs=[filenames, delete_num])
set_index.click(show_image_info, _js="images_history_get_current_img", inputs=[tabname_box, image_index, page_index, filenames], outputs=[img_file_name, img_file_time, image_index, hidden])
img_file_name.change(fn=None, _js="images_history_enable_del_buttons", inputs=None, outputs=None)
hidden.change(fn=run_pnginfo, inputs=[hidden], outputs=[info1, img_file_info, info2])
# pnginfo.click(fn=run_pnginfo, inputs=[hidden], outputs=[info1, img_file_info, info2])
switch_dict["fn"](pnginfo_send_to_txt2img, switch_dict["t2i"], img_file_info, 'switch_to_txt2img')
switch_dict["fn"](pnginfo_send_to_img2img, switch_dict["i2i"], img_file_info, 'switch_to_img2img_img2img')
def create_history_tabs(gr, opts, run_pnginfo, switch_dict):
def create_history_tabs(gr, sys_opts, cmp_ops, run_pnginfo, switch_dict):
global opts;
opts = sys_opts
loads_files_num = int(opts.images_history_num_per_page)
num_of_imgs_per_page = int(opts.images_history_num_per_page * opts.images_history_pages_num)
if cmp_ops.browse_all_images:
tabs_list.append(custom_tab_name)
with gr.Blocks(analytics_enabled=False) as images_history:
with gr.Tabs() as tabs:
with gr.Tab("txt2img history"):
with gr.Blocks(analytics_enabled=False) as images_history_txt2img:
show_images_history(gr, opts, "txt2img", run_pnginfo, switch_dict)
with gr.Tab("img2img history"):
with gr.Blocks(analytics_enabled=False) as images_history_img2img:
show_images_history(gr, opts, "img2img", run_pnginfo, switch_dict)
with gr.Tab("extras history"):
with gr.Blocks(analytics_enabled=False) as images_history_img2img:
show_images_history(gr, opts, "extras", run_pnginfo, switch_dict)
for tab in tabs_list:
with gr.Tab(tab):
with gr.Blocks(analytics_enabled=False) :
show_images_history(gr, opts, tab, run_pnginfo, switch_dict)
gradio.Checkbox(opts.images_history_preload, elem_id="images_history_preload", visible=False)
gradio.Textbox(",".join(tabs_list), elem_id="images_history_tabnames_list", visible=False)
return images_history

3
modules/img2img.py
View file

@ -109,6 +109,9 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
inpainting_mask_invert=inpainting_mask_invert,
)
p.scripts = modules.scripts.scripts_txt2img
p.script_args = args
if shared.cmd_opts.enable_console_prompts:
print(f"\nimg2img: {prompt}", file=shared.progress_print_out)

12
modules/interrogate.py
View file

@ -28,9 +28,11 @@ class InterrogateModels:
clip_preprocess = None
categories = None
dtype = None
running_on_cpu = None
def __init__(self, content_dir):
self.categories = []
self.running_on_cpu = devices.device_interrogate == torch.device("cpu")
if os.path.exists(content_dir):
for filename in os.listdir(content_dir):
@ -53,7 +55,11 @@ class InterrogateModels:
def load_clip_model(self):
import clip
model, preprocess = clip.load(clip_model_name)
if self.running_on_cpu:
model, preprocess = clip.load(clip_model_name, device="cpu")
else:
model, preprocess = clip.load(clip_model_name)
model.eval()
model = model.to(devices.device_interrogate)
@ -62,14 +68,14 @@ class InterrogateModels:
def load(self):
if self.blip_model is None:
self.blip_model = self.load_blip_model()
if not shared.cmd_opts.no_half:
if not shared.cmd_opts.no_half and not self.running_on_cpu:
self.blip_model = self.blip_model.half()
self.blip_model = self.blip_model.to(devices.device_interrogate)
if self.clip_model is None:
self.clip_model, self.clip_preprocess = self.load_clip_model()
if not shared.cmd_opts.no_half:
if not shared.cmd_opts.no_half and not self.running_on_cpu:
self.clip_model = self.clip_model.half()
self.clip_model = self.clip_model.to(devices.device_interrogate)

9
modules/lowvram.py
View file

@ -1,9 +1,8 @@
import torch
from modules.devices import get_optimal_device
from modules import devices
module_in_gpu = None
cpu = torch.device("cpu")
device = gpu = get_optimal_device()
def send_everything_to_cpu():
@ -33,7 +32,7 @@ def setup_for_low_vram(sd_model, use_medvram):
if module_in_gpu is not None:
module_in_gpu.to(cpu)
module.to(gpu)
module.to(devices.device)
module_in_gpu = module
# see below for register_forward_pre_hook;
@ -51,7 +50,7 @@ def setup_for_low_vram(sd_model, use_medvram):
# send the model to GPU. Then put modules back. the modules will be in CPU.
stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model
sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model = None, None, None
sd_model.to(device)
sd_model.to(devices.device)
sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model = stored
# register hooks for those the first two models
@ -70,7 +69,7 @@ def setup_for_low_vram(sd_model, use_medvram):
# so that only one of them is in GPU at a time
stored = diff_model.input_blocks, diff_model.middle_block, diff_model.output_blocks, diff_model.time_embed
diff_model.input_blocks, diff_model.middle_block, diff_model.output_blocks, diff_model.time_embed = None, None, None, None
sd_model.model.to(device)
sd_model.model.to(devices.device)
diff_model.input_blocks, diff_model.middle_block, diff_model.output_blocks, diff_model.time_embed = stored
# install hooks for bits of third model

140
modules/processing.py
View file

@ -9,9 +9,10 @@ from PIL import Image, ImageFilter, ImageOps
import random
import cv2
from skimage import exposure
from typing import Any, Dict, List, Optional
import modules.sd_hijack
from modules import devices, prompt_parser, masking, sd_samplers, lowvram
from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste
from modules.sd_hijack import model_hijack
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@ -51,9 +52,15 @@ def get_correct_sampler(p):
return sd_samplers.samplers
elif isinstance(p, modules.processing.StableDiffusionProcessingImg2Img):
return sd_samplers.samplers_for_img2img
elif isinstance(p, modules.api.processing.StableDiffusionProcessingAPI):
return sd_samplers.samplers
class StableDiffusionProcessing:
def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt="", styles=None, seed=-1, subseed=-1, subseed_strength=0, seed_resize_from_h=-1, seed_resize_from_w=-1, seed_enable_extras=True, sampler_index=0, batch_size=1, n_iter=1, steps=50, cfg_scale=7.0, width=512, height=512, restore_faces=False, tiling=False, do_not_save_samples=False, do_not_save_grid=False, extra_generation_params=None, overlay_images=None, negative_prompt=None, eta=None, do_not_reload_embeddings=False):
class StableDiffusionProcessing():
"""
The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
"""
def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str="", styles: List[str]=None, seed: int=-1, subseed: int=-1, subseed_strength: float=0, seed_resize_from_h: int=-1, seed_resize_from_w: int=-1, seed_enable_extras: bool=True, sampler_index: int=0, batch_size: int=1, n_iter: int=1, steps:int =50, cfg_scale:float=7.0, width:int=512, height:int=512, restore_faces:bool=False, tiling:bool=False, do_not_save_samples:bool=False, do_not_save_grid:bool=False, extra_generation_params: Dict[Any,Any]=None, overlay_images: Any=None, negative_prompt: str=None, eta: float =None, do_not_reload_embeddings: bool=False, denoising_strength: float = 0, ddim_discretize: str = "uniform", s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0):
self.sd_model = sd_model
self.outpath_samples: str = outpath_samples
self.outpath_grids: str = outpath_grids
@ -86,10 +93,10 @@ class StableDiffusionProcessing:
self.denoising_strength: float = 0
self.sampler_noise_scheduler_override = None
self.ddim_discretize = opts.ddim_discretize
self.s_churn = opts.s_churn
self.s_tmin = opts.s_tmin
self.s_tmax = float('inf') # not representable as a standard ui option
self.s_noise = opts.s_noise
self.s_churn = s_churn or opts.s_churn
self.s_tmin = s_tmin or opts.s_tmin
self.s_tmax = s_tmax or float('inf') # not representable as a standard ui option
self.s_noise = s_noise or opts.s_noise
if not seed_enable_extras:
self.subseed = -1
@ -97,6 +104,13 @@ class StableDiffusionProcessing:
self.seed_resize_from_h = 0
self.seed_resize_from_w = 0
self.scripts = None
self.script_args = None
self.all_prompts = None
self.all_seeds = None
self.all_subseeds = None
def init(self, all_prompts, all_seeds, all_subseeds):
pass
@ -296,7 +310,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration
"Size": f"{p.width}x{p.height}",
"Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
"Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
"Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name.replace(',', '').replace(':', '')),
"Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name),
"Batch size": (None if p.batch_size < 2 else p.batch_size),
"Batch pos": (None if p.batch_size < 2 else position_in_batch),
"Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
@ -310,7 +324,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration
generation_params.update(p.extra_generation_params)
generation_params_text = ", ".join([k if k == v else f'{k}: {v}' for k, v in generation_params.items() if v is not None])
generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None])
negative_prompt_text = "\nNegative prompt: " + p.negative_prompt if p.negative_prompt else ""
@ -342,32 +356,35 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
shared.prompt_styles.apply_styles(p)
if type(p.prompt) == list:
all_prompts = p.prompt
p.all_prompts = p.prompt
else:
all_prompts = p.batch_size * p.n_iter * [p.prompt]
p.all_prompts = p.batch_size * p.n_iter * [p.prompt]
if type(seed) == list:
all_seeds = seed
p.all_seeds = seed
else:
all_seeds = [int(seed) + (x if p.subseed_strength == 0 else 0) for x in range(len(all_prompts))]
p.all_seeds = [int(seed) + (x if p.subseed_strength == 0 else 0) for x in range(len(p.all_prompts))]
if type(subseed) == list:
all_subseeds = subseed
p.all_subseeds = subseed
else:
all_subseeds = [int(subseed) + x for x in range(len(all_prompts))]
p.all_subseeds = [int(subseed) + x for x in range(len(p.all_prompts))]
def infotext(iteration=0, position_in_batch=0):
return create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration, position_in_batch)
return create_infotext(p, p.all_prompts, p.all_seeds, p.all_subseeds, comments, iteration, position_in_batch)
if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings:
model_hijack.embedding_db.load_textual_inversion_embeddings()
if p.scripts is not None:
p.scripts.run_alwayson_scripts(p)
infotexts = []
output_images = []
with torch.no_grad(), p.sd_model.ema_scope():
with devices.autocast():
p.init(all_prompts, all_seeds, all_subseeds)
p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
if state.job_count == -1:
state.job_count = p.n_iter
@ -379,15 +396,13 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
if state.interrupted:
break
prompts = all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
seeds = all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
subseeds = all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
if (len(prompts) == 0):
break
#uc = p.sd_model.get_learned_conditioning(len(prompts) * [p.negative_prompt])
#c = p.sd_model.get_learned_conditioning(prompts)
with devices.autocast():
uc = prompt_parser.get_learned_conditioning(shared.sd_model, len(prompts) * [p.negative_prompt], p.steps)
c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps)
@ -402,12 +417,6 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
with devices.autocast():
samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)
if state.interrupted or state.skipped:
# if we are interrupted, sample returns just noise
# use the image collected previously in sampler loop
samples_ddim = shared.state.current_latent
samples_ddim = samples_ddim.to(devices.dtype_vae)
x_samples_ddim = decode_first_stage(p.sd_model, samples_ddim)
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
@ -488,16 +497,16 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
index_of_first_image = 1
if opts.grid_save:
images.save_image(grid, p.outpath_grids, "grid", all_seeds[0], all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True)
images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(), short_filename=not opts.grid_extended_filename, p=p, grid=True)
devices.torch_gc()
return Processed(p, output_images, all_seeds[0], infotext() + "".join(["\n\n" + x for x in comments]), subseed=all_subseeds[0], all_prompts=all_prompts, all_seeds=all_seeds, all_subseeds=all_subseeds, index_of_first_image=index_of_first_image, infotexts=infotexts)
return Processed(p, output_images, p.all_seeds[0], infotext() + "".join(["\n\n" + x for x in comments]), subseed=p.all_subseeds[0], all_prompts=p.all_prompts, all_seeds=p.all_seeds, all_subseeds=p.all_subseeds, index_of_first_image=index_of_first_image, infotexts=infotexts)
class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
sampler = None
def __init__(self, enable_hr=False, denoising_strength=0.75, firstphase_width=0, firstphase_height=0, **kwargs):
def __init__(self, enable_hr: bool=False, denoising_strength: float=0.75, firstphase_width: int=0, firstphase_height: int=0, **kwargs):
super().__init__(**kwargs)
self.enable_hr = enable_hr
self.denoising_strength = denoising_strength
@ -513,6 +522,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
else:
state.job_count = state.job_count * 2
self.extra_generation_params["First pass size"] = f"{self.firstphase_width}x{self.firstphase_height}"
if self.firstphase_width == 0 or self.firstphase_height == 0:
desired_pixel_count = 512 * 512
actual_pixel_count = self.width * self.height
@ -534,21 +545,40 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
firstphase_width_truncated = self.firstphase_height * self.width / self.height
firstphase_height_truncated = self.firstphase_height
self.extra_generation_params["First pass size"] = f"{self.firstphase_width}x{self.firstphase_height}"
self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f
self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f
def create_dummy_mask(self, x, width=None, height=None):
if self.sampler.conditioning_key in {'hybrid', 'concat'}:
height = height or self.height
width = width or self.width
# The "masked-image" in this case will just be all zeros since the entire image is masked.
image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
# Add the fake full 1s mask to the first dimension.
image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
image_conditioning = image_conditioning.to(x.dtype)
else:
# Dummy zero conditioning if we're not using inpainting model.
# Still takes up a bit of memory, but no encoder call.
# Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
image_conditioning = torch.zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
return image_conditioning
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)
if not self.enable_hr:
x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.create_dummy_mask(x))
return samples
x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning)
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.create_dummy_mask(x, self.firstphase_width, self.firstphase_height))
samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
@ -585,7 +615,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
x = None
devices.torch_gc()
samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps)
samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=self.create_dummy_mask(samples))
return samples
@ -593,7 +623,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
sampler = None
def __init__(self, init_images=None, resize_mode=0, denoising_strength=0.75, mask=None, mask_blur=4, inpainting_fill=0, inpaint_full_res=True, inpaint_full_res_padding=0, inpainting_mask_invert=0, **kwargs):
def __init__(self, init_images: list=None, resize_mode: int=0, denoising_strength: float=0.75, mask: Any=None, mask_blur: int=4, inpainting_fill: int=0, inpaint_full_res: bool=True, inpaint_full_res_padding: int=0, inpainting_mask_invert: int=0, **kwargs):
super().__init__(**kwargs)
self.init_images = init_images
@ -611,6 +641,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
self.inpainting_mask_invert = inpainting_mask_invert
self.mask = None
self.nmask = None
self.image_conditioning = None
def init(self, all_prompts, all_seeds, all_subseeds):
self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers_for_img2img, self.sampler_index, self.sd_model)
@ -683,6 +714,10 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
batch_images = np.expand_dims(imgs[0], axis=0).repeat(self.batch_size, axis=0)
if self.overlay_images is not None:
self.overlay_images = self.overlay_images * self.batch_size
if self.color_corrections is not None and len(self.color_corrections) == 1:
self.color_corrections = self.color_corrections * self.batch_size
elif len(imgs) <= self.batch_size:
self.batch_size = len(imgs)
batch_images = np.array(imgs)
@ -712,10 +747,39 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
elif self.inpainting_fill == 3:
self.init_latent = self.init_latent * self.mask
if self.sampler.conditioning_key in {'hybrid', 'concat'}:
if self.image_mask is not None:
conditioning_mask = np.array(self.image_mask.convert("L"))
conditioning_mask = conditioning_mask.astype(np.float32) / 255.0
conditioning_mask = torch.from_numpy(conditioning_mask[None, None])
# Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0
conditioning_mask = torch.round(conditioning_mask)
else:
conditioning_mask = torch.ones(1, 1, *image.shape[-2:])
# Create another latent image, this time with a masked version of the original input.
conditioning_mask = conditioning_mask.to(image.device)
conditioning_image = image * (1.0 - conditioning_mask)
conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
# Create the concatenated conditioning tensor to be fed to `c_concat`
conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=self.init_latent.shape[-2:])
conditioning_mask = conditioning_mask.expand(conditioning_image.shape[0], -1, -1, -1)
self.image_conditioning = torch.cat([conditioning_mask, conditioning_image], dim=1)
self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype)
else:
self.image_conditioning = torch.zeros(
self.init_latent.shape[0], 5, 1, 1,
dtype=self.init_latent.dtype,
device=self.init_latent.device
)
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning)
samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
if self.mask is not None:
samples = samples * self.nmask + self.init_latent * self.mask
@ -723,4 +787,4 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
del x
devices.torch_gc()
return samples
return samples

2
modules/prompt_parser.py
View file

@ -275,7 +275,7 @@ re_attention = re.compile(r"""
def parse_prompt_attention(text):
"""
Parses a string with attention tokens and returns a list of pairs: text and its assoicated weight.
Parses a string with attention tokens and returns a list of pairs: text and its associated weight.
Accepted tokens are:
(abc) - increases attention to abc by a multiplier of 1.1
(abc:3.12) - increases attention to abc by a multiplier of 3.12

53
modules/script_callbacks.py Normal file
View file

@ -0,0 +1,53 @@
callbacks_model_loaded = []
callbacks_ui_tabs = []
callbacks_ui_settings = []
def clear_callbacks():
callbacks_model_loaded.clear()
callbacks_ui_tabs.clear()
def model_loaded_callback(sd_model):
for callback in callbacks_model_loaded:
callback(sd_model)
def ui_tabs_callback():
res = []
for callback in callbacks_ui_tabs:
res += callback() or []
return res
def ui_settings_callback():
for callback in callbacks_ui_settings:
callback()
def on_model_loaded(callback):
"""register a function to be called when the stable diffusion model is created; the model is
passed as an argument"""
callbacks_model_loaded.append(callback)
def on_ui_tabs(callback):
"""register a function to be called when the UI is creating new tabs.
The function must either return a None, which means no new tabs to be added, or a list, where
each element is a tuple:
(gradio_component, title, elem_id)
gradio_component is a gradio component to be used for contents of the tab (usually gr.Blocks)
title is tab text displayed to user in the UI
elem_id is HTML id for the tab
"""
callbacks_ui_tabs.append(callback)
def on_ui_settings(callback):
"""register a function to be called before UI settings are populated; add your settings
by using shared.opts.add_option(shared.OptionInfo(...)) """
callbacks_ui_settings.append(callback)

253
modules/scripts.py
View file

@ -1,86 +1,175 @@
import os
import sys
import traceback
from collections import namedtuple
import modules.ui as ui
import gradio as gr
from modules.processing import StableDiffusionProcessing
from modules import shared
from modules import shared, paths, script_callbacks
AlwaysVisible = object()
class Script:
filename = None
args_from = None
args_to = None
alwayson = False
infotext_fields = None
"""if set in ui(), this is a list of pairs of gradio component + text; the text will be used when
parsing infotext to set the value for the component; see ui.py's txt2img_paste_fields for an example
"""
# The title of the script. This is what will be displayed in the dropdown menu.
def title(self):
"""this function should return the title of the script. This is what will be displayed in the dropdown menu."""
raise NotImplementedError()
# How the script is displayed in the UI. See https://gradio.app/docs/#components
# for the different UI components you can use and how to create them.
# Most UI components can return a value, such as a boolean for a checkbox.
# The returned values are passed to the run method as parameters.
def ui(self, is_img2img):
"""this function should create gradio UI elements. See https://gradio.app/docs/#components
The return value should be an array of all components that are used in processing.
Values of those returned componenbts will be passed to run() and process() functions.
"""
pass
# Determines when the script should be shown in the dropdown menu via the
# returned value. As an example:
# is_img2img is True if the current tab is img2img, and False if it is txt2img.
# Thus, return is_img2img to only show the script on the img2img tab.
def show(self, is_img2img):
"""
is_img2img is True if this function is called for the img2img interface, and Fasle otherwise
This function should return:
- False if the script should not be shown in UI at all
- True if the script should be shown in UI if it's scelected in the scripts drowpdown
- script.AlwaysVisible if the script should be shown in UI at all times
"""
return True
# This is where the additional processing is implemented. The parameters include
# self, the model object "p" (a StableDiffusionProcessing class, see
# processing.py), and the parameters returned by the ui method.
# Custom functions can be defined here, and additional libraries can be imported
# to be used in processing. The return value should be a Processed object, which is
# what is returned by the process_images method.
def run(self, *args):
def run(self, p, *args):
"""
This function is called if the script has been selected in the script dropdown.
It must do all processing and return the Processed object with results, same as
one returned by processing.process_images.
Usually the processing is done by calling the processing.process_images function.
args contains all values returned by components from ui()
"""
raise NotImplementedError()
# The description method is currently unused.
# To add a description that appears when hovering over the title, amend the "titles"
# dict in script.js to include the script title (returned by title) as a key, and
# your description as the value.
def process(self, p, *args):
"""
This function is called before processing begins for AlwaysVisible scripts.
scripts. You can modify the processing object (p) here, inject hooks, etc.
"""
pass
def describe(self):
"""unused"""
return ""
current_basedir = paths.script_path
def basedir():
"""returns the base directory for the current script. For scripts in the main scripts directory,
this is the main directory (where webui.py resides), and for scripts in extensions directory
(ie extensions/aesthetic/script/aesthetic.py), this is extension's directory (extensions/aesthetic)
"""
return current_basedir
scripts_data = []
ScriptFile = namedtuple("ScriptFile", ["basedir", "filename", "path"])
ScriptClassData = namedtuple("ScriptClassData", ["script_class", "path", "basedir"])
def load_scripts(basedir):
if not os.path.exists(basedir):
return
def list_scripts(scriptdirname, extension):
scripts_list = []
for filename in sorted(os.listdir(basedir)):
path = os.path.join(basedir, filename)
basedir = os.path.join(paths.script_path, scriptdirname)
if os.path.exists(basedir):
for filename in sorted(os.listdir(basedir)):
scripts_list.append(ScriptFile(paths.script_path, filename, os.path.join(basedir, filename)))
if os.path.splitext(path)[1].lower() != '.py':
extdir = os.path.join(paths.script_path, "extensions")
if os.path.exists(extdir):
for dirname in sorted(os.listdir(extdir)):
dirpath = os.path.join(extdir, dirname)
scriptdirpath = os.path.join(dirpath, scriptdirname)
if not os.path.isdir(scriptdirpath):
continue
for filename in sorted(os.listdir(scriptdirpath)):
scripts_list.append(ScriptFile(dirpath, filename, os.path.join(scriptdirpath, filename)))
scripts_list = [x for x in scripts_list if os.path.splitext(x.path)[1].lower() == extension and os.path.isfile(x.path)]
return scripts_list
def list_files_with_name(filename):
res = []
dirs = [paths.script_path]
extdir = os.path.join(paths.script_path, "extensions")
if os.path.exists(extdir):
dirs += [os.path.join(extdir, d) for d in sorted(os.listdir(extdir))]
for dirpath in dirs:
if not os.path.isdir(dirpath):
continue
if not os.path.isfile(path):
continue
path = os.path.join(dirpath, filename)
if os.path.isfile(filename):
res.append(path)
return res
def load_scripts():
global current_basedir
scripts_data.clear()
script_callbacks.clear_callbacks()
scripts_list = list_scripts("scripts", ".py")
syspath = sys.path
for scriptfile in sorted(scripts_list):
try:
with open(path, "r", encoding="utf8") as file:
if scriptfile.basedir != paths.script_path:
sys.path = [scriptfile.basedir] + sys.path
current_basedir = scriptfile.basedir
with open(scriptfile.path, "r", encoding="utf8") as file:
text = file.read()
from types import ModuleType
compiled = compile(text, path, 'exec')
module = ModuleType(filename)
compiled = compile(text, scriptfile.path, 'exec')
module = ModuleType(scriptfile.filename)
exec(compiled, module.__dict__)
for key, script_class in module.__dict__.items():
if type(script_class) == type and issubclass(script_class, Script):
scripts_data.append((script_class, path))
scripts_data.append(ScriptClassData(script_class, scriptfile.path, scriptfile.basedir))
except Exception:
print(f"Error loading script: {filename}", file=sys.stderr)
print(f"Error loading script: {scriptfile.filename}", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
finally:
sys.path = syspath
current_basedir = paths.script_path
def wrap_call(func, filename, funcname, *args, default=None, **kwargs):
try:
@ -96,49 +185,84 @@ def wrap_call(func, filename, funcname, *args, default=None, **kwargs):
class ScriptRunner:
def __init__(self):
self.scripts = []
self.selectable_scripts = []
self.alwayson_scripts = []
self.titles = []
self.infotext_fields = []
def setup_ui(self, is_img2img):
for script_class, path in scripts_data:
for script_class, path, basedir in scripts_data:
script = script_class()
script.filename = path
if not script.show(is_img2img):
continue
visibility = script.show(is_img2img)
self.scripts.append(script)
if visibility == AlwaysVisible:
self.scripts.append(script)
self.alwayson_scripts.append(script)
script.alwayson = True
titles = [wrap_call(script.title, script.filename, "title") or f"{script.filename} [error]" for script in self.scripts]
elif visibility:
self.scripts.append(script)
self.selectable_scripts.append(script)
dropdown = gr.Dropdown(label="Script", choices=["None"] + titles, value="None", type="index")
inputs = [dropdown]
self.titles = [wrap_call(script.title, script.filename, "title") or f"{script.filename} [error]" for script in self.selectable_scripts]
for script in self.scripts:
inputs = [None]
inputs_alwayson = [True]
def create_script_ui(script, inputs, inputs_alwayson):
script.args_from = len(inputs)
script.args_to = len(inputs)
controls = wrap_call(script.ui, script.filename, "ui", is_img2img)
if controls is None:
continue
return
for control in controls:
control.custom_script_source = os.path.basename(script.filename)
control.visible = False
if not script.alwayson:
control.visible = False
if script.infotext_fields is not None:
self.infotext_fields += script.infotext_fields
inputs += controls
inputs_alwayson += [script.alwayson for _ in controls]
script.args_to = len(inputs)
for script in self.alwayson_scripts:
with gr.Group():
create_script_ui(script, inputs, inputs_alwayson)
dropdown = gr.Dropdown(label="Script", choices=["None"] + self.titles, value="None", type="index")
dropdown.save_to_config = True
inputs[0] = dropdown
for script in self.selectable_scripts:
create_script_ui(script, inputs, inputs_alwayson)
def select_script(script_index):
if 0 < script_index <= len(self.scripts):
script = self.scripts[script_index-1]
if 0 < script_index <= len(self.selectable_scripts):
script = self.selectable_scripts[script_index-1]
args_from = script.args_from
args_to = script.args_to
else:
args_from = 0
args_to = 0
return [ui.gr_show(True if i == 0 else args_from <= i < args_to) for i in range(len(inputs))]
return [ui.gr_show(True if i == 0 else args_from <= i < args_to or is_alwayson) for i, is_alwayson in enumerate(inputs_alwayson)]
def init_field(title):
if title == 'None':
return
script_index = self.titles.index(title)
script = self.selectable_scripts[script_index]
for i in range(script.args_from, script.args_to):
inputs[i].visible = True
dropdown.init_field = init_field
dropdown.change(
fn=select_script,
inputs=[dropdown],
@ -153,7 +277,7 @@ class ScriptRunner:
if script_index == 0:
return None
script = self.scripts[script_index-1]
script = self.selectable_scripts[script_index-1]
if script is None:
return None
@ -165,7 +289,16 @@ class ScriptRunner:
return processed
def reload_sources(self):
def run_alwayson_scripts(self, p):
for script in self.alwayson_scripts:
try:
script_args = p.script_args[script.args_from:script.args_to]
script.process(p, *script_args)
except Exception:
print(f"Error running alwayson script: {script.filename}", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
def reload_sources(self, cache):
for si, script in list(enumerate(self.scripts)):
with open(script.filename, "r", encoding="utf8") as file:
args_from = script.args_from
@ -175,9 +308,12 @@ class ScriptRunner:
from types import ModuleType
compiled = compile(text, filename, 'exec')
module = ModuleType(script.filename)
exec(compiled, module.__dict__)
module = cache.get(filename, None)
if module is None:
compiled = compile(text, filename, 'exec')
module = ModuleType(script.filename)
exec(compiled, module.__dict__)
cache[filename] = module
for key, script_class in module.__dict__.items():
if type(script_class) == type and issubclass(script_class, Script):
@ -186,19 +322,22 @@ class ScriptRunner:
self.scripts[si].args_from = args_from
self.scripts[si].args_to = args_to
scripts_txt2img = ScriptRunner()
scripts_img2img = ScriptRunner()
def reload_script_body_only():
scripts_txt2img.reload_sources()
scripts_img2img.reload_sources()
cache = {}
scripts_txt2img.reload_sources(cache)
scripts_img2img.reload_sources(cache)
def reload_scripts(basedir):
def reload_scripts():
global scripts_txt2img, scripts_img2img
scripts_data.clear()
load_scripts(basedir)
load_scripts()
scripts_txt2img = ScriptRunner()
scripts_img2img = ScriptRunner()

29
modules/sd_hijack.py
View file

@ -19,6 +19,7 @@ attention_CrossAttention_forward = ldm.modules.attention.CrossAttention.forward
diffusionmodules_model_nonlinearity = ldm.modules.diffusionmodules.model.nonlinearity
diffusionmodules_model_AttnBlock_forward = ldm.modules.diffusionmodules.model.AttnBlock.forward
def apply_optimizations():
undo_optimizations()
@ -167,11 +168,11 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
remade_tokens = remade_tokens[:last_comma]
length = len(remade_tokens)
rem = int(math.ceil(length / 75)) * 75 - length
remade_tokens += [id_end] * rem + reloc_tokens
multipliers = multipliers[:last_comma] + [1.0] * rem + reloc_mults
if embedding is None:
remade_tokens.append(token)
multipliers.append(weight)
@ -223,7 +224,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
return batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count
def process_text_old(self, text):
id_start = self.wrapped.tokenizer.bos_token_id
id_end = self.wrapped.tokenizer.eos_token_id
@ -280,7 +280,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
token_count = len(remade_tokens)
remade_tokens = remade_tokens + [id_end] * (maxlen - 2 - len(remade_tokens))
remade_tokens = [id_start] + remade_tokens[0:maxlen-2] + [id_end]
remade_tokens = [id_start] + remade_tokens[0:maxlen - 2] + [id_end]
cache[tuple_tokens] = (remade_tokens, fixes, multipliers)
multipliers = multipliers + [1.0] * (maxlen - 2 - len(multipliers))
@ -290,7 +290,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
hijack_fixes.append(fixes)
batch_multipliers.append(multipliers)
return batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count
def forward(self, text):
use_old = opts.use_old_emphasis_implementation
if use_old:
@ -302,11 +302,11 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
if len(used_custom_terms) > 0:
self.hijack.comments.append("Used embeddings: " + ", ".join([f'{word} [{checksum}]' for word, checksum in used_custom_terms]))
if use_old:
self.hijack.fixes = hijack_fixes
return self.process_tokens(remade_batch_tokens, batch_multipliers)
z = None
i = 0
while max(map(len, remade_batch_tokens)) != 0:
@ -320,7 +320,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
if fix[0] == i:
fixes.append(fix[1])
self.hijack.fixes.append(fixes)
tokens = []
multipliers = []
for j in range(len(remade_batch_tokens)):
@ -333,19 +333,18 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
z1 = self.process_tokens(tokens, multipliers)
z = z1 if z is None else torch.cat((z, z1), axis=-2)
remade_batch_tokens = rem_tokens
batch_multipliers = rem_multipliers
i += 1
return z
def process_tokens(self, remade_batch_tokens, batch_multipliers):
if not opts.use_old_emphasis_implementation:
remade_batch_tokens = [[self.wrapped.tokenizer.bos_token_id] + x[:75] + [self.wrapped.tokenizer.eos_token_id] for x in remade_batch_tokens]
batch_multipliers = [[1.0] + x[:75] + [1.0] for x in batch_multipliers]
tokens = torch.asarray(remade_batch_tokens).to(device)
outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
@ -385,8 +384,8 @@ class EmbeddingsWithFixes(torch.nn.Module):
for fixes, tensor in zip(batch_fixes, inputs_embeds):
for offset, embedding in fixes:
emb = embedding.vec
emb_len = min(tensor.shape[0]-offset-1, emb.shape[0])
tensor = torch.cat([tensor[0:offset+1], emb[0:emb_len], tensor[offset+1+emb_len:]])
emb_len = min(tensor.shape[0] - offset - 1, emb.shape[0])
tensor = torch.cat([tensor[0:offset + 1], emb[0:emb_len], tensor[offset + 1 + emb_len:]])
vecs.append(tensor)

331
modules/sd_hijack_inpainting.py Normal file
View file

@ -0,0 +1,331 @@
import torch
from einops import repeat
from omegaconf import ListConfig
import ldm.models.diffusion.ddpm
import ldm.models.diffusion.ddim
import ldm.models.diffusion.plms
from ldm.models.diffusion.ddpm import LatentDiffusion
from ldm.models.diffusion.plms import PLMSSampler
from ldm.models.diffusion.ddim import DDIMSampler, noise_like
# =================================================================================================
# Monkey patch DDIMSampler methods from RunwayML repo directly.
# Adapted from:
# https://github.com/runwayml/stable-diffusion/blob/main/ldm/models/diffusion/ddim.py
# =================================================================================================
@torch.no_grad()
def sample_ddim(self,
S,
batch_size,
shape,
conditioning=None,
callback=None,
normals_sequence=None,
img_callback=None,
quantize_x0=False,
eta=0.,
mask=None,
x0=None,
temperature=1.,
noise_dropout=0.,
score_corrector=None,
corrector_kwargs=None,
verbose=True,
x_T=None,
log_every_t=100,
unconditional_guidance_scale=1.,
unconditional_conditioning=None,
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
**kwargs
):
if conditioning is not None:
if isinstance(conditioning, dict):
ctmp = conditioning[list(conditioning.keys())[0]]
while isinstance(ctmp, list):
ctmp = ctmp[0]
cbs = ctmp.shape[0]
if cbs != batch_size:
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
else:
if conditioning.shape[0] != batch_size:
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
# sampling
C, H, W = shape
size = (batch_size, C, H, W)
print(f'Data shape for DDIM sampling is {size}, eta {eta}')
samples, intermediates = self.ddim_sampling(conditioning, size,
callback=callback,
img_callback=img_callback,
quantize_denoised=quantize_x0,
mask=mask, x0=x0,
ddim_use_original_steps=False,
noise_dropout=noise_dropout,
temperature=temperature,
score_corrector=score_corrector,
corrector_kwargs=corrector_kwargs,
x_T=x_T,
log_every_t=log_every_t,
unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning,
)
return samples, intermediates
@torch.no_grad()
def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
unconditional_guidance_scale=1., unconditional_conditioning=None):
b, *_, device = *x.shape, x.device
if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
e_t = self.model.apply_model(x, t, c)
else:
x_in = torch.cat([x] * 2)
t_in = torch.cat([t] * 2)
if isinstance(c, dict):
assert isinstance(unconditional_conditioning, dict)
c_in = dict()
for k in c:
if isinstance(c[k], list):
c_in[k] = [
torch.cat([unconditional_conditioning[k][i], c[k][i]])
for i in range(len(c[k]))
]
else:
c_in[k] = torch.cat([unconditional_conditioning[k], c[k]])
else:
c_in = torch.cat([unconditional_conditioning, c])
e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
if score_corrector is not None:
assert self.model.parameterization == "eps"
e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
# select parameters corresponding to the currently considered timestep
a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
# current prediction for x_0
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
if quantize_denoised:
pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
# direction pointing to x_t
dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
if noise_dropout > 0.:
noise = torch.nn.functional.dropout(noise, p=noise_dropout)
x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
return x_prev, pred_x0
# =================================================================================================
# Monkey patch PLMSSampler methods.
# This one was not actually patched correctly in the RunwayML repo, but we can replicate the changes.
# Adapted from:
# https://github.com/CompVis/stable-diffusion/blob/main/ldm/models/diffusion/plms.py
# =================================================================================================
@torch.no_grad()
def sample_plms(self,
S,
batch_size,
shape,
conditioning=None,
callback=None,
normals_sequence=None,
img_callback=None,
quantize_x0=False,
eta=0.,
mask=None,
x0=None,
temperature=1.,
noise_dropout=0.,
score_corrector=None,
corrector_kwargs=None,
verbose=True,
x_T=None,
log_every_t=100,
unconditional_guidance_scale=1.,
unconditional_conditioning=None,
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
**kwargs
):
if conditioning is not None:
if isinstance(conditioning, dict):
ctmp = conditioning[list(conditioning.keys())[0]]
while isinstance(ctmp, list):
ctmp = ctmp[0]
cbs = ctmp.shape[0]
if cbs != batch_size:
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
else:
if conditioning.shape[0] != batch_size:
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
# sampling
C, H, W = shape
size = (batch_size, C, H, W)
print(f'Data shape for PLMS sampling is {size}')
samples, intermediates = self.plms_sampling(conditioning, size,
callback=callback,
img_callback=img_callback,
quantize_denoised=quantize_x0,
mask=mask, x0=x0,
ddim_use_original_steps=False,
noise_dropout=noise_dropout,
temperature=temperature,
score_corrector=score_corrector,
corrector_kwargs=corrector_kwargs,
x_T=x_T,
log_every_t=log_every_t,
unconditional_guidance_scale=unconditional_guidance_scale,
unconditional_conditioning=unconditional_conditioning,
)
return samples, intermediates
@torch.no_grad()
def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None):
b, *_, device = *x.shape, x.device
def get_model_output(x, t):
if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
e_t = self.model.apply_model(x, t, c)
else:
x_in = torch.cat([x] * 2)
t_in = torch.cat([t] * 2)
if isinstance(c, dict):
assert isinstance(unconditional_conditioning, dict)
c_in = dict()
for k in c:
if isinstance(c[k], list):
c_in[k] = [
torch.cat([unconditional_conditioning[k][i], c[k][i]])
for i in range(len(c[k]))
]
else:
c_in[k] = torch.cat([unconditional_conditioning[k], c[k]])
else:
c_in = torch.cat([unconditional_conditioning, c])
e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
if score_corrector is not None:
assert self.model.parameterization == "eps"
e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
return e_t
alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
def get_x_prev_and_pred_x0(e_t, index):
# select parameters corresponding to the currently considered timestep
a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
# current prediction for x_0
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
if quantize_denoised:
pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
# direction pointing to x_t
dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
if noise_dropout > 0.:
noise = torch.nn.functional.dropout(noise, p=noise_dropout)
x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
return x_prev, pred_x0
e_t = get_model_output(x, t)
if len(old_eps) == 0:
# Pseudo Improved Euler (2nd order)
x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t, index)
e_t_next = get_model_output(x_prev, t_next)
e_t_prime = (e_t + e_t_next) / 2
elif len(old_eps) == 1:
# 2nd order Pseudo Linear Multistep (Adams-Bashforth)
e_t_prime = (3 * e_t - old_eps[-1]) / 2
elif len(old_eps) == 2:
# 3nd order Pseudo Linear Multistep (Adams-Bashforth)
e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
elif len(old_eps) >= 3:
# 4nd order Pseudo Linear Multistep (Adams-Bashforth)
e_t_prime = (55 * e_t - 59 * old_eps[-1] + 37 * old_eps[-2] - 9 * old_eps[-3]) / 24
x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index)
return x_prev, pred_x0, e_t
# =================================================================================================
# Monkey patch LatentInpaintDiffusion to load the checkpoint with a proper config.
# Adapted from:
# https://github.com/runwayml/stable-diffusion/blob/main/ldm/models/diffusion/ddpm.py
# =================================================================================================
@torch.no_grad()
def get_unconditional_conditioning(self, batch_size, null_label=None):
if null_label is not None:
xc = null_label
if isinstance(xc, ListConfig):
xc = list(xc)
if isinstance(xc, dict) or isinstance(xc, list):
c = self.get_learned_conditioning(xc)
else:
if hasattr(xc, "to"):
xc = xc.to(self.device)
c = self.get_learned_conditioning(xc)
else:
# todo: get null label from cond_stage_model
raise NotImplementedError()
c = repeat(c, "1 ... -> b ...", b=batch_size).to(self.device)
return c
class LatentInpaintDiffusion(LatentDiffusion):
def __init__(
self,
concat_keys=("mask", "masked_image"),
masked_image_key="masked_image",
*args,
**kwargs,
):
super().__init__(*args, **kwargs)
self.masked_image_key = masked_image_key
assert self.masked_image_key in concat_keys
self.concat_keys = concat_keys
def should_hijack_inpainting(checkpoint_info):
return str(checkpoint_info.filename).endswith("inpainting.ckpt") and not checkpoint_info.config.endswith("inpainting.yaml")
def do_inpainting_hijack():
ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning
ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion
ldm.models.diffusion.ddim.DDIMSampler.p_sample_ddim = p_sample_ddim
ldm.models.diffusion.ddim.DDIMSampler.sample = sample_ddim
ldm.models.diffusion.plms.PLMSSampler.p_sample_plms = p_sample_plms
ldm.models.diffusion.plms.PLMSSampler.sample = sample_plms

2
modules/sd_hijack_optimizations.py
View file

@ -181,7 +181,7 @@ def einsum_op_cuda(q, k, v):
mem_free_torch = mem_reserved - mem_active
mem_free_total = mem_free_cuda + mem_free_torch
# Divide factor of safety as there's copying and fragmentation
return self.einsum_op_tensor_mem(q, k, v, mem_free_total / 3.3 / (1 << 20))
return einsum_op_tensor_mem(q, k, v, mem_free_total / 3.3 / (1 << 20))
def einsum_op(q, k, v):
if q.device.type == 'cuda':

63
modules/sd_models.py
View file

@ -7,8 +7,9 @@ from omegaconf import OmegaConf
from ldm.util import instantiate_from_config
from modules import shared, modelloader, devices
from modules import shared, modelloader, devices, script_callbacks
from modules.paths import models_path
from modules.sd_hijack_inpainting import do_inpainting_hijack, should_hijack_inpainting
model_dir = "Stable-diffusion"
model_path = os.path.abspath(os.path.join(models_path, model_dir))
@ -20,7 +21,7 @@ checkpoints_loaded = collections.OrderedDict()
try:
# this silences the annoying "Some weights of the model checkpoint were not used when initializing..." message at start.
from transformers import logging
from transformers import logging, CLIPModel
logging.set_verbosity_error()
except Exception:
@ -122,13 +123,41 @@ def select_checkpoint():
return checkpoint_info
chckpoint_dict_replacements = {
'cond_stage_model.transformer.embeddings.': 'cond_stage_model.transformer.text_model.embeddings.',
'cond_stage_model.transformer.encoder.': 'cond_stage_model.transformer.text_model.encoder.',
'cond_stage_model.transformer.final_layer_norm.': 'cond_stage_model.transformer.text_model.final_layer_norm.',
}
def transform_checkpoint_dict_key(k):
for text, replacement in chckpoint_dict_replacements.items():
if k.startswith(text):
k = replacement + k[len(text):]
return k
def get_state_dict_from_checkpoint(pl_sd):
if "state_dict" in pl_sd:
return pl_sd["state_dict"]
pl_sd = pl_sd["state_dict"]
sd = {}
for k, v in pl_sd.items():
new_key = transform_checkpoint_dict_key(k)
if new_key is not None:
sd[new_key] = v
pl_sd.clear()
pl_sd.update(sd)
return pl_sd
vae_ignore_keys = {"model_ema.decay", "model_ema.num_updates"}
def load_model_weights(model, checkpoint_info):
checkpoint_file = checkpoint_info.filename
sd_model_hash = checkpoint_info.hash
@ -141,7 +170,7 @@ def load_model_weights(model, checkpoint_info):
print(f"Global Step: {pl_sd['global_step']}")
sd = get_state_dict_from_checkpoint(pl_sd)
model.load_state_dict(sd, strict=False)
missing, extra = model.load_state_dict(sd, strict=False)
if shared.cmd_opts.opt_channelslast:
model.to(memory_format=torch.channels_last)
@ -160,7 +189,7 @@ def load_model_weights(model, checkpoint_info):
if os.path.exists(vae_file):
print(f"Loading VAE weights from: {vae_file}")
vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss"}
vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
model.first_stage_model.load_state_dict(vae_dict)
model.first_stage_model.to(devices.dtype_vae)
@ -178,14 +207,26 @@ def load_model_weights(model, checkpoint_info):
model.sd_checkpoint_info = checkpoint_info
def load_model():
def load_model(checkpoint_info=None):
from modules import lowvram, sd_hijack
checkpoint_info = select_checkpoint()
checkpoint_info = checkpoint_info or select_checkpoint()
if checkpoint_info.config != shared.cmd_opts.config:
print(f"Loading config from: {checkpoint_info.config}")
sd_config = OmegaConf.load(checkpoint_info.config)
if should_hijack_inpainting(checkpoint_info):
# Hardcoded config for now...
sd_config.model.target = "ldm.models.diffusion.ddpm.LatentInpaintDiffusion"
sd_config.model.params.use_ema = False
sd_config.model.params.conditioning_key = "hybrid"
sd_config.model.params.unet_config.params.in_channels = 9
# Create a "fake" config with a different name so that we know to unload it when switching models.
checkpoint_info = checkpoint_info._replace(config=checkpoint_info.config.replace(".yaml", "-inpainting.yaml"))
do_inpainting_hijack()
sd_model = instantiate_from_config(sd_config.model)
load_model_weights(sd_model, checkpoint_info)
@ -197,6 +238,9 @@ def load_model():
sd_hijack.model_hijack.hijack(sd_model)
sd_model.eval()
shared.sd_model = sd_model
script_callbacks.model_loaded_callback(sd_model)
print(f"Model loaded.")
return sd_model
@ -209,9 +253,9 @@ def reload_model_weights(sd_model, info=None):
if sd_model.sd_model_checkpoint == checkpoint_info.filename:
return
if sd_model.sd_checkpoint_info.config != checkpoint_info.config:
if sd_model.sd_checkpoint_info.config != checkpoint_info.config or should_hijack_inpainting(checkpoint_info) != should_hijack_inpainting(sd_model.sd_checkpoint_info):
checkpoints_loaded.clear()
shared.sd_model = load_model()
load_model(checkpoint_info)
return shared.sd_model
if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
@ -224,6 +268,7 @@ def reload_model_weights(sd_model, info=None):
load_model_weights(sd_model, checkpoint_info)
sd_hijack.model_hijack.hijack(sd_model)
script_callbacks.model_loaded_callback(sd_model)
if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram:
sd_model.to(devices.device)

182
modules/sd_samplers.py
View file

@ -7,7 +7,7 @@ import inspect
import k_diffusion.sampling
import ldm.models.diffusion.ddim
import ldm.models.diffusion.plms
from modules import prompt_parser, devices, processing
from modules import prompt_parser, devices, processing, images
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@ -71,6 +71,7 @@ sampler_extra_params = {
'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
}
def setup_img2img_steps(p, steps=None):
if opts.img2img_fix_steps or steps is not None:
steps = int((steps or p.steps) / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
@ -82,14 +83,22 @@ def setup_img2img_steps(p, steps=None):
return steps, t_enc
def sample_to_image(samples):
x_sample = processing.decode_first_stage(shared.sd_model, samples[0:1])[0]
def single_sample_to_image(sample):
x_sample = processing.decode_first_stage(shared.sd_model, sample.unsqueeze(0))[0]
x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
x_sample = x_sample.astype(np.uint8)
return Image.fromarray(x_sample)
def sample_to_image(samples):
return single_sample_to_image(samples[0])
def samples_to_image_grid(samples):
return images.image_grid([single_sample_to_image(sample) for sample in samples])
def store_latent(decoded):
state.current_latent = decoded
@ -98,25 +107,8 @@ def store_latent(decoded):
shared.state.current_image = sample_to_image(decoded)
def extended_tdqm(sequence, *args, desc=None, **kwargs):
state.sampling_steps = len(sequence)
state.sampling_step = 0
seq = sequence if cmd_opts.disable_console_progressbars else tqdm.tqdm(sequence, *args, desc=state.job, file=shared.progress_print_out, **kwargs)
for x in seq:
if state.interrupted or state.skipped:
break
yield x
state.sampling_step += 1
shared.total_tqdm.update()
ldm.models.diffusion.ddim.tqdm = lambda *args, desc=None, **kwargs: extended_tdqm(*args, desc=desc, **kwargs)
ldm.models.diffusion.plms.tqdm = lambda *args, desc=None, **kwargs: extended_tdqm(*args, desc=desc, **kwargs)
class InterruptedException(BaseException):
pass
class VanillaStableDiffusionSampler:
@ -128,14 +120,40 @@ class VanillaStableDiffusionSampler:
self.init_latent = None
self.sampler_noises = None
self.step = 0
self.stop_at = None
self.eta = None
self.default_eta = 0.0
self.config = None
self.last_latent = None
self.conditioning_key = sd_model.model.conditioning_key
def number_of_needed_noises(self, p):
return 0
def launch_sampling(self, steps, func):
state.sampling_steps = steps
state.sampling_step = 0
try:
return func()
except InterruptedException:
return self.last_latent
def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs):
if state.interrupted or state.skipped:
raise InterruptedException
if self.stop_at is not None and self.step > self.stop_at:
raise InterruptedException
# Have to unwrap the inpainting conditioning here to perform pre-processing
image_conditioning = None
if isinstance(cond, dict):
image_conditioning = cond["c_concat"][0]
cond = cond["c_crossattn"][0]
unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)
@ -156,14 +174,25 @@ class VanillaStableDiffusionSampler:
img_orig = self.sampler.model.q_sample(self.init_latent, ts)
x_dec = img_orig * self.mask + self.nmask * x_dec
# Wrap the image conditioning back up since the DDIM code can accept the dict directly.
# Note that they need to be lists because it just concatenates them later.
if image_conditioning is not None:
cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
if self.mask is not None:
store_latent(self.init_latent * self.mask + self.nmask * res[1])
self.last_latent = self.init_latent * self.mask + self.nmask * res[1]
else:
store_latent(res[1])
self.last_latent = res[1]
store_latent(self.last_latent)
self.step += 1
state.sampling_step = self.step
shared.total_tqdm.update()
return res
def initialize(self, p):
@ -176,7 +205,7 @@ class VanillaStableDiffusionSampler:
self.mask = p.mask if hasattr(p, 'mask') else None
self.nmask = p.nmask if hasattr(p, 'nmask') else None
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None):
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = setup_img2img_steps(p, steps)
self.initialize(p)
@ -190,25 +219,38 @@ class VanillaStableDiffusionSampler:
x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise)
self.init_latent = x
self.last_latent = x
self.step = 0
samples = self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning)
# Wrap the conditioning models with additional image conditioning for inpainting model
if image_conditioning is not None:
conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
samples = self.launch_sampling(steps, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
return samples
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None):
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
self.initialize(p)
self.init_latent = None
self.last_latent = x
self.step = 0
steps = steps or p.steps
# Wrap the conditioning models with additional image conditioning for inpainting model
if image_conditioning is not None:
conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
# existing code fails with certain step counts, like 9
try:
samples_ddim, _ = self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)
samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
except Exception:
samples_ddim, _ = self.sampler.sample(S=steps+1, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)
samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps+1, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
return samples_ddim
@ -222,7 +264,10 @@ class CFGDenoiser(torch.nn.Module):
self.init_latent = None
self.step = 0
def forward(self, x, sigma, uncond, cond, cond_scale):
def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
if state.interrupted or state.skipped:
raise InterruptedException
conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step)
@ -230,28 +275,29 @@ class CFGDenoiser(torch.nn.Module):
repeats = [len(conds_list[i]) for i in range(batch_size)]
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
if tensor.shape[1] == uncond.shape[1]:
cond_in = torch.cat([tensor, uncond])
if shared.batch_cond_uncond:
x_out = self.inner_model(x_in, sigma_in, cond=cond_in)
x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
else:
x_out = torch.zeros_like(x_in)
for batch_offset in range(0, x_out.shape[0], batch_size):
a = batch_offset
b = a + batch_size
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b])
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
else:
x_out = torch.zeros_like(x_in)
batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
for batch_offset in range(0, tensor.shape[0], batch_size):
a = batch_offset
b = min(a + batch_size, tensor.shape[0])
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=tensor[a:b])
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [tensor[a:b]], "c_concat": [image_cond_in[a:b]]})
x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=uncond)
x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
denoised_uncond = x_out[-uncond.shape[0]:]
denoised = torch.clone(denoised_uncond)
@ -268,25 +314,6 @@ class CFGDenoiser(torch.nn.Module):
return denoised
def extended_trange(sampler, count, *args, **kwargs):
state.sampling_steps = count
state.sampling_step = 0
seq = range(count) if cmd_opts.disable_console_progressbars else tqdm.trange(count, *args, desc=state.job, file=shared.progress_print_out, **kwargs)
for x in seq:
if state.interrupted or state.skipped:
break
if sampler.stop_at is not None and x > sampler.stop_at:
break
yield x
state.sampling_step += 1
shared.total_tqdm.update()
class TorchHijack:
def __init__(self, kdiff_sampler):
self.kdiff_sampler = kdiff_sampler
@ -314,9 +341,30 @@ class KDiffusionSampler:
self.eta = None
self.default_eta = 1.0
self.config = None
self.last_latent = None
self.conditioning_key = sd_model.model.conditioning_key
def callback_state(self, d):
store_latent(d["denoised"])
step = d['i']
latent = d["denoised"]
store_latent(latent)
self.last_latent = latent
if self.stop_at is not None and step > self.stop_at:
raise InterruptedException
state.sampling_step = step
shared.total_tqdm.update()
def launch_sampling(self, steps, func):
state.sampling_steps = steps
state.sampling_step = 0
try:
return func()
except InterruptedException:
return self.last_latent
def number_of_needed_noises(self, p):
return p.steps
@ -339,9 +387,6 @@ class KDiffusionSampler:
self.sampler_noise_index = 0
self.eta = p.eta or opts.eta_ancestral
if hasattr(k_diffusion.sampling, 'trange'):
k_diffusion.sampling.trange = lambda *args, **kwargs: extended_trange(self, *args, **kwargs)
if self.sampler_noises is not None:
k_diffusion.sampling.torch = TorchHijack(self)
@ -355,7 +400,7 @@ class KDiffusionSampler:
return extra_params_kwargs
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None):
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = setup_img2img_steps(p, steps)
if p.sampler_noise_scheduler_override:
@ -382,11 +427,18 @@ class KDiffusionSampler:
extra_params_kwargs['sigmas'] = sigma_sched
self.model_wrap_cfg.init_latent = x
self.last_latent = x
return self.func(self.model_wrap_cfg, xi, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs)
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale
}, disable=False, callback=self.callback_state, **extra_params_kwargs))
return samples
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None):
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
steps = steps or p.steps
if p.sampler_noise_scheduler_override:
@ -406,6 +458,14 @@ class KDiffusionSampler:
extra_params_kwargs['n'] = steps
else:
extra_params_kwargs['sigmas'] = sigmas
samples = self.func(self.model_wrap_cfg, x, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs)
self.last_latent = x
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale
}, disable=False, callback=self.callback_state, **extra_params_kwargs))
return samples

43
modules/shared.py
View file

@ -3,6 +3,7 @@ import datetime
import json
import os
import sys
from collections import OrderedDict
import gradio as gr
import tqdm
@ -63,6 +64,7 @@ parser.add_argument("--port", type=int, help="launch gradio with given server po
parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
parser.add_argument("--ui-config-file", type=str, help="filename to use for ui configuration", default=os.path.join(script_path, 'ui-config.json'))
parser.add_argument("--hide-ui-dir-config", action='store_true', help="hide directory configuration from webui", default=False)
parser.add_argument("--freeze-settings", action='store_true', help="disable editing settings", default=False)
parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default=os.path.join(script_path, 'config.json'))
parser.add_argument("--gradio-debug", action='store_true', help="launch gradio with --debug option")
parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
@ -70,12 +72,16 @@ parser.add_argument("--gradio-img2img-tool", type=str, help='gradio image upload
parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(script_path, 'styles.csv'))
parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False)
parser.add_argument('--vae-path', type=str, help='Path to Variational Autoencoders model', default=None)
parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
parser.add_argument("--api", action='store_true', help="use api=True to launch the api with the webui")
parser.add_argument("--nowebui", action='store_true', help="use api=True to launch the api instead of the webui")
parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)
parser.add_argument("--browse-all-images", action='store_true', help="Allow browsing all images by Image Browser", default=False)
cmd_opts = parser.parse_args()
restricted_opts = [
@ -135,7 +141,7 @@ class State:
self.job_no += 1
self.sampling_step = 0
self.current_image_sampling_step = 0
def get_job_timestamp(self):
return datetime.datetime.now().strftime("%Y%m%d%H%M%S") # shouldn't this return job_timestamp?
@ -160,13 +166,13 @@ def realesrgan_models_names():
class OptionInfo:
def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, show_on_main_page=False, refresh=None):
def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None):
self.default = default
self.label = label
self.component = component
self.component_args = component_args
self.onchange = onchange
self.section = None
self.section = section
self.refresh = refresh
@ -247,7 +253,7 @@ options_templates.update(options_section(('system', "System"), {
}))
options_templates.update(options_section(('training', "Training"), {
"unload_models_when_training": OptionInfo(False, "Unload VAE and CLIP from VRAM when training"),
"unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training hypernetwork. Saves VRAM."),
"dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
"dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
"training_image_repeats_per_epoch": OptionInfo(1, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}),
@ -289,10 +295,12 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
options_templates.update(options_section(('ui', "User interface"), {
"show_progressbar": OptionInfo(True, "Show progressbar"),
"show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),
"show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"),
"return_grid": OptionInfo(True, "Show grid in results for web"),
"do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
"add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
"add_model_name_to_info": OptionInfo(False, "Add model name to generation information"),
"disable_weights_auto_swap": OptionInfo(False, "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint."),
"font": OptionInfo("", "Font for image grids that have text"),
"js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
"js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
@ -312,6 +320,15 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}),
}))
options_templates.update(options_section(('images-history', "Images Browser"), {
#"images_history_reconstruct_directory": OptionInfo(False, "Reconstruct output directory structure.This can greatly improve the speed of loading , but will change the original output directory structure"),
"images_history_preload": OptionInfo(False, "Preload images at startup"),
"images_history_num_per_page": OptionInfo(36, "Number of pictures displayed on each page"),
"images_history_pages_num": OptionInfo(6, "Minimum number of pages per load "),
"images_history_grid_num": OptionInfo(6, "Number of grids in each row"),
}))
class Options:
data = None
@ -375,6 +392,20 @@ class Options:
d = {k: self.data.get(k, self.data_labels.get(k).default) for k in self.data_labels.keys()}
return json.dumps(d)
def add_option(self, key, info):
self.data_labels[key] = info
def reorder(self):
"""reorder settings so that all items related to section always go together"""
section_ids = {}
settings_items = self.data_labels.items()
for k, item in settings_items:
if item.section not in section_ids:
section_ids[item.section] = len(section_ids)
self.data_labels = {k: v for k, v in sorted(settings_items, key=lambda x: section_ids[x[1].section])}
opts = Options()
if os.path.exists(config_filename):
@ -384,6 +415,8 @@ sd_upscalers = []
sd_model = None
clip_model = None
progress_print_out = sys.stdout

4
modules/styles.py
View file

@ -45,7 +45,7 @@ class StyleDatabase:
if not os.path.exists(path):
return
with open(path, "r", encoding="utf8", newline='') as file:
with open(path, "r", encoding="utf-8-sig", newline='') as file:
reader = csv.DictReader(file)
for row in reader:
# Support loading old CSV format with "name, text"-columns
@ -79,7 +79,7 @@ class StyleDatabase:
def save_styles(self, path: str) -> None:
# Write to temporary file first, so we don't nuke the file if something goes wrong
fd, temp_path = tempfile.mkstemp(".csv")
with os.fdopen(fd, "w", encoding="utf8", newline='') as file:
with os.fdopen(fd, "w", encoding="utf-8-sig", newline='') as file:
# _fields is actually part of the public API: typing.NamedTuple is a replacement for collections.NamedTuple,
# and collections.NamedTuple has explicit documentation for accessing _fields. Same goes for _asdict()
writer = csv.DictWriter(file, fieldnames=PromptStyle._fields)

4
modules/textual_inversion/dataset.py
View file

@ -83,7 +83,7 @@ class PersonalizedBase(Dataset):
self.dataset.append(entry)
assert len(self.dataset) > 1, "No images have been found in the dataset."
assert len(self.dataset) > 0, "No images have been found in the dataset."
self.length = len(self.dataset) * repeats // batch_size
self.initial_indexes = np.arange(len(self.dataset))
@ -91,7 +91,7 @@ class PersonalizedBase(Dataset):
self.shuffle()
def shuffle(self):
self.indexes = self.initial_indexes[torch.randperm(self.initial_indexes.shape[0])]
self.indexes = self.initial_indexes[torch.randperm(self.initial_indexes.shape[0]).numpy()]
def create_text(self, filename_text):
text = random.choice(self.lines)

5
modules/textual_inversion/image_embedding.py
View file

@ -5,6 +5,7 @@ import zlib
from PIL import Image, PngImagePlugin, ImageDraw, ImageFont
from fonts.ttf import Roboto
import torch
from modules.shared import opts
class EmbeddingEncoder(json.JSONEncoder):
@ -133,7 +134,7 @@ def caption_image_overlay(srcimage, title, footerLeft, footerMid, footerRight, t
from math import cos
image = srcimage.copy()
fontsize = 32
if textfont is None:
try:
textfont = ImageFont.truetype(opts.font or Roboto, fontsize)
@ -150,7 +151,7 @@ def caption_image_overlay(srcimage, title, footerLeft, footerMid, footerRight, t
image = Image.alpha_composite(image.convert('RGBA'), gradient.resize(image.size))
draw = ImageDraw.Draw(image)
fontsize = 32
font = ImageFont.truetype(textfont, fontsize)
padding = 10

85
modules/textual_inversion/preprocess.py
View file

@ -1,5 +1,6 @@
import os
from PIL import Image, ImageOps
import math
import platform
import sys
import tqdm
@ -11,7 +12,7 @@ if cmd_opts.deepdanbooru:
import modules.deepbooru as deepbooru
def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2):
try:
if process_caption:
shared.interrogator.load()
@ -21,7 +22,7 @@ def preprocess(process_src, process_dst, process_width, process_height, process_
db_opts[deepbooru.OPT_INCLUDE_RANKS] = False
deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, db_opts)
preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru)
preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio)
finally:
@ -33,11 +34,13 @@ def preprocess(process_src, process_dst, process_width, process_height, process_
def preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2):
width = process_width
height = process_height
src = os.path.abspath(process_src)
dst = os.path.abspath(process_dst)
split_threshold = max(0.0, min(1.0, split_threshold))
overlap_ratio = max(0.0, min(0.9, overlap_ratio))
assert src != dst, 'same directory specified as source and destination'
@ -48,7 +51,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro
shared.state.textinfo = "Preprocessing..."
shared.state.job_count = len(files)
def save_pic_with_caption(image, index):
def save_pic_with_caption(image, index, existing_caption=None):
caption = ""
if process_caption:
@ -66,17 +69,49 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro
basename = f"{index:05}-{subindex[0]}-{filename_part}"
image.save(os.path.join(dst, f"{basename}.png"))
if preprocess_txt_action == 'prepend' and existing_caption:
caption = existing_caption + ' ' + caption
elif preprocess_txt_action == 'append' and existing_caption:
caption = caption + ' ' + existing_caption
elif preprocess_txt_action == 'copy' and existing_caption:
caption = existing_caption
caption = caption.strip()
if len(caption) > 0:
with open(os.path.join(dst, f"{basename}.txt"), "w", encoding="utf8") as file:
file.write(caption)
subindex[0] += 1
def save_pic(image, index):
save_pic_with_caption(image, index)
def save_pic(image, index, existing_caption=None):
save_pic_with_caption(image, index, existing_caption=existing_caption)
if process_flip:
save_pic_with_caption(ImageOps.mirror(image), index)
save_pic_with_caption(ImageOps.mirror(image), index, existing_caption=existing_caption)
def split_pic(image, inverse_xy):
if inverse_xy:
from_w, from_h = image.height, image.width
to_w, to_h = height, width
else:
from_w, from_h = image.width, image.height
to_w, to_h = width, height
h = from_h * to_w // from_w
if inverse_xy:
image = image.resize((h, to_w))
else:
image = image.resize((to_w, h))
split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio)))
y_step = (h - to_h) / (split_count - 1)
for i in range(split_count):
y = int(y_step * i)
if inverse_xy:
splitted = image.crop((y, 0, y + to_h, to_w))
else:
splitted = image.crop((0, y, to_w, y + to_h))
yield splitted
for index, imagefile in enumerate(tqdm.tqdm(files)):
subindex = [0]
@ -86,31 +121,27 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pro
except Exception:
continue
existing_caption = None
existing_caption_filename = os.path.splitext(filename)[0] + '.txt'
if os.path.exists(existing_caption_filename):
with open(existing_caption_filename, 'r', encoding="utf8") as file:
existing_caption = file.read()
if shared.state.interrupted:
break
ratio = img.height / img.width
is_tall = ratio > 1.35
is_wide = ratio < 1 / 1.35
if img.height > img.width:
ratio = (img.width * height) / (img.height * width)
inverse_xy = False
else:
ratio = (img.height * width) / (img.width * height)
inverse_xy = True
if process_split and is_tall:
img = img.resize((width, height * img.height // img.width))
top = img.crop((0, 0, width, height))
save_pic(top, index)
bot = img.crop((0, img.height - height, width, img.height))
save_pic(bot, index)
elif process_split and is_wide:
img = img.resize((width * img.width // img.height, height))
left = img.crop((0, 0, width, height))
save_pic(left, index)
right = img.crop((img.width - width, 0, img.width, height))
save_pic(right, index)
if process_split and ratio < 1.0 and ratio <= split_threshold:
for splitted in split_pic(img, inverse_xy):
save_pic(splitted, index, existing_caption=existing_caption)
else:
img = images.resize_image(1, img, width, height)
save_pic(img, index)
save_pic(img, index, existing_caption=existing_caption)
shared.state.nextjob()

6
modules/textual_inversion/textual_inversion.py
View file

@ -153,7 +153,7 @@ class EmbeddingDatabase:
return None, None
def create_embedding(name, num_vectors_per_token, init_text='*'):
def create_embedding(name, num_vectors_per_token, overwrite_old, init_text='*'):
cond_model = shared.sd_model.cond_stage_model
embedding_layer = cond_model.wrapped.transformer.text_model.embeddings
@ -165,7 +165,8 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
vec[i] = embedded[i * int(embedded.shape[0]) // num_vectors_per_token]
fn = os.path.join(shared.cmd_opts.embeddings_dir, f"{name}.pt")
assert not os.path.exists(fn), f"file {fn} already exists"
if not overwrite_old:
assert not os.path.exists(fn), f"file {fn} already exists"
embedding = Embedding(vec, name)
embedding.step = 0
@ -275,6 +276,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
loss.backward()
optimizer.step()
epoch_num = embedding.step // len(ds)
epoch_step = embedding.step - (epoch_num * len(ds)) + 1

4
modules/textual_inversion/ui.py
View file

@ -7,8 +7,8 @@ import modules.textual_inversion.preprocess
from modules import sd_hijack, shared
def create_embedding(name, initialization_text, nvpt):
filename = modules.textual_inversion.textual_inversion.create_embedding(name, nvpt, init_text=initialization_text)
def create_embedding(name, initialization_text, nvpt, overwrite_old):
filename = modules.textual_inversion.textual_inversion.create_embedding(name, nvpt, overwrite_old, init_text=initialization_text)
sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings()

7
modules/txt2img.py
View file

@ -1,5 +1,6 @@
import modules.scripts
from modules.processing import StableDiffusionProcessing, Processed, StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
from modules.processing import StableDiffusionProcessing, Processed, StableDiffusionProcessingTxt2Img, \
StableDiffusionProcessingImg2Img, process_images
from modules.shared import opts, cmd_opts
import modules.shared as shared
import modules.processing as processing
@ -35,6 +36,9 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
firstphase_height=firstphase_height if enable_hr else None,
)
p.scripts = modules.scripts.scripts_txt2img
p.script_args = args
if cmd_opts.enable_console_prompts:
print(f"\ntxt2img: {prompt}", file=shared.progress_print_out)
@ -53,4 +57,3 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
processed.images = []
return processed.images, generation_info_js, plaintext_to_html(processed.info)

247
modules/ui.py
View file

@ -5,43 +5,54 @@ import json
import math
import mimetypes
import os
import platform
import random
import subprocess as sp
import sys
import tempfile
import time
import traceback
import platform
import subprocess as sp
from functools import reduce
from functools import partial, reduce
import gradio as gr
import gradio.routes
import gradio.utils
import numpy as np
import piexif
import torch
from PIL import Image, PngImagePlugin
import piexif
import gradio as gr
import gradio.utils
import gradio.routes
from modules import sd_hijack, sd_models, localization
from modules import sd_hijack, sd_models, localization, script_callbacks
from modules.paths import script_path
from modules.shared import opts, cmd_opts, restricted_opts
if cmd_opts.deepdanbooru:
from modules.deepbooru import get_deepbooru_tags
import modules.shared as shared
from modules.sd_samplers import samplers, samplers_for_img2img
from modules.sd_hijack import model_hijack
import modules.ldsr_model
import modules.scripts
import modules.gfpgan_model
import modules.codeformer_model
import modules.styles
import modules.generation_parameters_copypaste
from modules import prompt_parser
from modules.images import save_image
import modules.textual_inversion.ui
import modules.gfpgan_model
import modules.hypernetworks.ui
import modules.images_history as img_his
import modules.ldsr_model
import modules.scripts
import modules.shared as shared
import modules.styles
import modules.textual_inversion.ui
from modules import prompt_parser
from modules.images import save_image
from modules.sd_hijack import model_hijack
from modules.sd_samplers import samplers, samplers_for_img2img
import modules.textual_inversion.ui
import modules.hypernetworks.ui
import modules.images_history as img_his
# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
mimetypes.init()
@ -261,6 +272,24 @@ def wrap_gradio_call(func, extra_outputs=None):
return f
def calc_time_left(progress, threshold, label, force_display):
if progress == 0:
return ""
else:
time_since_start = time.time() - shared.state.time_start
eta = (time_since_start/progress)
eta_relative = eta-time_since_start
if (eta_relative > threshold and progress > 0.02) or force_display:
if eta_relative > 3600:
return label + time.strftime('%H:%M:%S', time.gmtime(eta_relative))
elif eta_relative > 60:
return label + time.strftime('%M:%S', time.gmtime(eta_relative))
else:
return label + time.strftime('%Ss', time.gmtime(eta_relative))
else:
return ""
def check_progress_call(id_part):
if shared.state.job_count == 0:
return "", gr_show(False), gr_show(False), gr_show(False)
@ -272,11 +301,15 @@ def check_progress_call(id_part):
if shared.state.sampling_steps > 0:
progress += 1 / shared.state.job_count * shared.state.sampling_step / shared.state.sampling_steps
time_left = calc_time_left( progress, 1, " ETA: ", shared.state.time_left_force_display )
if time_left != "":
shared.state.time_left_force_display = True
progress = min(progress, 1)
progressbar = ""
if opts.show_progressbar:
progressbar = f"""<div class='progressDiv'><div class='progress' style="width:{progress * 100}%">{str(int(progress*100))+"%" if progress > 0.01 else ""}</div></div>"""
progressbar = f"""<div class='progressDiv'><div class='progress' style="overflow:visible;width:{progress * 100}%;white-space:nowrap;">{"&nbsp;" * 2 + str(int(progress*100))+"%" + time_left if progress > 0.01 else ""}</div></div>"""
image = gr_show(False)
preview_visibility = gr_show(False)
@ -285,7 +318,10 @@ def check_progress_call(id_part):
if shared.parallel_processing_allowed:
if shared.state.sampling_step - shared.state.current_image_sampling_step >= opts.show_progress_every_n_steps and shared.state.current_latent is not None:
shared.state.current_image = modules.sd_samplers.sample_to_image(shared.state.current_latent)
if opts.show_progress_grid:
shared.state.current_image = modules.sd_samplers.samples_to_image_grid(shared.state.current_latent)
else:
shared.state.current_image = modules.sd_samplers.sample_to_image(shared.state.current_latent)
shared.state.current_image_sampling_step = shared.state.sampling_step
image = shared.state.current_image
@ -308,6 +344,8 @@ def check_progress_call_initial(id_part):
shared.state.current_latent = None
shared.state.current_image = None
shared.state.textinfo = None
shared.state.time_start = time.time()
shared.state.time_left_force_display = False
return check_progress_call(id_part)
@ -458,14 +496,14 @@ def create_toprow(is_img2img):
with gr.Row():
with gr.Column(scale=80):
with gr.Row():
prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=2,
prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=2,
placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)"
)
with gr.Row():
with gr.Column(scale=80):
with gr.Row():
negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=2,
negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=2,
placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)"
)
@ -542,6 +580,13 @@ def apply_setting(key, value):
if value is None:
return gr.update()
if shared.cmd_opts.freeze_settings:
return gr.update()
# dont allow model to be swapped when model hash exists in prompt
if key == "sd_model_checkpoint" and opts.disable_weights_auto_swap:
return gr.update()
if key == "sd_model_checkpoint":
ckpt_info = sd_models.get_closet_checkpoint_match(value)
@ -564,27 +609,29 @@ def apply_setting(key, value):
return value
def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
def refresh():
refresh_method()
args = refreshed_args() if callable(refreshed_args) else refreshed_args
for k, v in args.items():
setattr(refresh_component, k, v)
return gr.update(**(args or {}))
refresh_button = gr.Button(value=refresh_symbol, elem_id=elem_id)
refresh_button.click(
fn=refresh,
inputs=[],
outputs=[refresh_component]
)
return refresh_button
def create_ui(wrap_gradio_gpu_call):
import modules.img2img
import modules.txt2img
def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
def refresh():
refresh_method()
args = refreshed_args() if callable(refreshed_args) else refreshed_args
for k, v in args.items():
setattr(refresh_component, k, v)
return gr.update(**(args or {}))
refresh_button = gr.Button(value=refresh_symbol, elem_id=elem_id)
refresh_button.click(
fn = refresh,
inputs = [],
outputs = [refresh_component]
)
return refresh_button
with gr.Blocks(analytics_enabled=False) as txt2img_interface:
txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)
@ -682,6 +729,7 @@ def create_ui(wrap_gradio_gpu_call):
firstphase_width,
firstphase_height,
] + custom_inputs,
outputs=[
txt2img_gallery,
generation_info,
@ -758,6 +806,7 @@ def create_ui(wrap_gradio_gpu_call):
(hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
(firstphase_width, "First pass size-1"),
(firstphase_height, "First pass size-2"),
*modules.scripts.scripts_txt2img.infotext_fields
]
txt2img_preview_params = [
@ -825,8 +874,8 @@ def create_ui(wrap_gradio_gpu_call):
sampler_index = gr.Radio(label='Sampling method', choices=[x.name for x in samplers_for_img2img], value=samplers_for_img2img[0].name, type="index")
with gr.Group():
width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512, elem_id="img2img_width")
height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512, elem_id="img2img_height")
with gr.Row():
restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1)
@ -1023,6 +1072,7 @@ def create_ui(wrap_gradio_gpu_call):
(seed_resize_from_w, "Seed resize from-1"),
(seed_resize_from_h, "Seed resize from-2"),
(denoising_strength, "Denoising strength"),
*modules.scripts.scripts_img2img.infotext_fields
]
token_button.click(fn=update_token_counter, inputs=[img2img_prompt, steps], outputs=[token_counter])
@ -1145,12 +1195,12 @@ def create_ui(wrap_gradio_gpu_call):
)
#images history
images_history_switch_dict = {
"fn":modules.generation_parameters_copypaste.connect_paste,
"t2i":txt2img_paste_fields,
"i2i":img2img_paste_fields
"fn": modules.generation_parameters_copypaste.connect_paste,
"t2i": txt2img_paste_fields,
"i2i": img2img_paste_fields
}
images_history = img_his.create_history_tabs(gr, opts, wrap_gradio_call(modules.extras.run_pnginfo), images_history_switch_dict)
images_history = img_his.create_history_tabs(gr, opts, cmd_opts, wrap_gradio_call(modules.extras.run_pnginfo), images_history_switch_dict)
with gr.Blocks() as modelmerger_interface:
with gr.Row().style(equal_height=False):
@ -1183,6 +1233,7 @@ def create_ui(wrap_gradio_gpu_call):
new_embedding_name = gr.Textbox(label="Name")
initialization_text = gr.Textbox(label="Initialization text", value="*")
nvpt = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1)
overwrite_old_embedding = gr.Checkbox(value=False, label="Overwrite Old Embedding")
with gr.Row():
with gr.Column(scale=3):
@ -1194,6 +1245,11 @@ def create_ui(wrap_gradio_gpu_call):
with gr.Tab(label="Create hypernetwork"):
new_hypernetwork_name = gr.Textbox(label="Name")
new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "320", "640", "1280"])
new_hypernetwork_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'")
new_hypernetwork_activation_func = gr.Dropdown(value="relu", label="Select activation function of hypernetwork", choices=["linear", "relu", "leakyrelu", "elu", "swish"])
new_hypernetwork_add_layer_norm = gr.Checkbox(label="Add layer normalization")
new_hypernetwork_use_dropout = gr.Checkbox(label="Use dropout")
overwrite_old_hypernetwork = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork")
with gr.Row():
with gr.Column(scale=3):
@ -1207,13 +1263,18 @@ def create_ui(wrap_gradio_gpu_call):
process_dst = gr.Textbox(label='Destination directory')
process_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
process_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"])
with gr.Row():
process_flip = gr.Checkbox(label='Create flipped copies')
process_split = gr.Checkbox(label='Split oversized images into two')
process_split = gr.Checkbox(label='Split oversized images')
process_caption = gr.Checkbox(label='Use BLIP for caption')
process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True if cmd_opts.deepdanbooru else False)
with gr.Row(visible=False) as process_split_extra_row:
process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05)
process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05)
with gr.Row():
with gr.Column(scale=3):
gr.HTML(value="")
@ -1221,15 +1282,24 @@ def create_ui(wrap_gradio_gpu_call):
with gr.Column():
run_preprocess = gr.Button(value="Preprocess", variant='primary')
process_split.change(
fn=lambda show: gr_show(show),
inputs=[process_split],
outputs=[process_split_extra_row],
)
with gr.Tab(label="Train"):
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding; must specify a directory with a set of 1:1 ratio images</p>")
gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images <a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\" style=\"font-weight:bold;\">[wiki]</a></p>")
with gr.Row():
train_embedding_name = gr.Dropdown(label='Embedding', elem_id="train_embedding", choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys()))
create_refresh_button(train_embedding_name, sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings, lambda: {"choices": sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())}, "refresh_train_embedding_name")
with gr.Row():
train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', elem_id="train_hypernetwork", choices=[x for x in shared.hypernetworks.keys()])
create_refresh_button(train_hypernetwork_name, shared.reload_hypernetworks, lambda: {"choices": sorted([x for x in shared.hypernetworks.keys()])}, "refresh_train_hypernetwork_name")
learn_rate = gr.Textbox(label='Learning rate', placeholder="Learning rate", value="0.005")
with gr.Row():
embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005")
hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001")
batch_size = gr.Number(label='Batch size', value=1, precision=0)
dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")
@ -1263,6 +1333,7 @@ def create_ui(wrap_gradio_gpu_call):
new_embedding_name,
initialization_text,
nvpt,
overwrite_old_embedding,
],
outputs=[
train_embedding_name,
@ -1276,6 +1347,11 @@ def create_ui(wrap_gradio_gpu_call):
inputs=[
new_hypernetwork_name,
new_hypernetwork_sizes,
overwrite_old_hypernetwork,
new_hypernetwork_layer_structure,
new_hypernetwork_activation_func,
new_hypernetwork_add_layer_norm,
new_hypernetwork_use_dropout
],
outputs=[
train_hypernetwork_name,
@ -1292,10 +1368,13 @@ def create_ui(wrap_gradio_gpu_call):
process_dst,
process_width,
process_height,
preprocess_txt_action,
process_flip,
process_split,
process_caption,
process_caption_deepbooru
process_caption_deepbooru,
process_split_threshold,
process_overlap_ratio,
],
outputs=[
ti_output,
@ -1308,7 +1387,7 @@ def create_ui(wrap_gradio_gpu_call):
_js="start_training_textual_inversion",
inputs=[
train_embedding_name,
learn_rate,
embedding_learn_rate,
batch_size,
dataset_directory,
log_directory,
@ -1333,10 +1412,12 @@ def create_ui(wrap_gradio_gpu_call):
_js="start_training_textual_inversion",
inputs=[
train_hypernetwork_name,
learn_rate,
hypernetwork_learn_rate,
batch_size,
dataset_directory,
log_directory,
training_width,
training_height,
steps,
create_image_every,
save_embedding_every,
@ -1395,6 +1476,9 @@ def create_ui(wrap_gradio_gpu_call):
components = []
component_dict = {}
script_callbacks.ui_settings_callback()
opts.reorder()
def open_folder(f):
if not os.path.exists(f):
print(f'Folder "{f}" does not exist. After you create an image, the folder will be created.')
@ -1420,6 +1504,8 @@ Requested path was: {f}
def run_settings(*args):
changed = 0
assert not shared.cmd_opts.freeze_settings, "changing settings is disabled"
for key, value, comp in zip(opts.data_labels.keys(), args, components):
if comp != dummy_component and not opts.same_type(value, opts.data_labels[key].default):
return f"Bad value for setting {key}: {value}; expecting {type(opts.data_labels[key].default).__name__}", opts.dumpjson()
@ -1449,13 +1535,15 @@ Requested path was: {f}
return f'{changed} settings changed.', opts.dumpjson()
def run_settings_single(value, key):
assert not shared.cmd_opts.freeze_settings, "changing settings is disabled"
if not opts.same_type(value, opts.data_labels[key].default):
return gr.update(visible=True), opts.dumpjson()
oldval = opts.data.get(key, None)
if cmd_opts.hide_ui_dir_config and key in restricted_opts:
return gr.update(value=oldval), opts.dumpjson()
oldval = opts.data.get(key, None)
opts.data[key] = value
if oldval != value:
@ -1498,9 +1586,10 @@ Requested path was: {f}
previous_section = item.section
gr.HTML(elem_id="settings_header_text_{}".format(item.section[0]), value='<h1 class="gr-button-lg">{}</h1>'.format(item.section[1]))
elem_id, text = item.section
gr.HTML(elem_id="settings_header_text_{}".format(elem_id), value='<h1 class="gr-button-lg">{}</h1>'.format(text))
if k in quicksettings_names:
if k in quicksettings_names and not shared.cmd_opts.freeze_settings:
quicksettings_list.append((i, k, item))
components.append(dummy_component)
else:
@ -1533,6 +1622,7 @@ Requested path was: {f}
def reload_scripts():
modules.scripts.reload_script_body_only()
reload_javascript() # need to refresh the html page
reload_script_bodies.click(
fn=reload_scripts,
@ -1560,19 +1650,27 @@ Requested path was: {f}
(img2img_interface, "img2img", "img2img"),
(extras_interface, "Extras", "extras"),
(pnginfo_interface, "PNG Info", "pnginfo"),
(images_history, "History", "images_history"),
(images_history, "Image Browser", "images_history"),
(modelmerger_interface, "Checkpoint Merger", "modelmerger"),
(train_interface, "Train", "ti"),
(settings_interface, "Settings", "settings"),
]
with open(os.path.join(script_path, "style.css"), "r", encoding="utf8") as file:
css = file.read()
interfaces += script_callbacks.ui_tabs_callback()
interfaces += [(settings_interface, "Settings", "settings")]
css = ""
for cssfile in modules.scripts.list_files_with_name("style.css"):
if not os.path.isfile(cssfile):
continue
with open(cssfile, "r", encoding="utf8") as file:
css += file.read() + "\n"
if os.path.exists(os.path.join(script_path, "user.css")):
with open(os.path.join(script_path, "user.css"), "r", encoding="utf8") as file:
usercss = file.read()
css += usercss
css += file.read() + "\n"
if not cmd_opts.no_progressbar_hiding:
css += css_hide_progressbar
@ -1733,7 +1831,7 @@ Requested path was: {f}
print(traceback.format_exc(), file=sys.stderr)
def loadsave(path, x):
def apply_field(obj, field, condition=None):
def apply_field(obj, field, condition=None, init_field=None):
key = path + "/" + field
if getattr(obj,'custom_script_source',None) is not None:
@ -1749,6 +1847,8 @@ Requested path was: {f}
print(f'Warning: Bad ui setting value: {key}: {saved_value}; Default value "{getattr(obj, field)}" will be used instead.')
else:
setattr(obj, field, saved_value)
if init_field is not None:
init_field(saved_value)
if type(x) in [gr.Slider, gr.Radio, gr.Checkbox, gr.Textbox, gr.Number] and x.visible:
apply_field(x, 'visible')
@ -1774,7 +1874,8 @@ Requested path was: {f}
# Since there are many dropdowns that shouldn't be saved,
# we only mark dropdowns that should be saved.
if type(x) == gr.Dropdown and getattr(x, 'save_to_config', False):
apply_field(x, 'value', lambda val: val in x.choices)
apply_field(x, 'value', lambda val: val in x.choices, getattr(x, 'init_field', None))
apply_field(x, 'visible')
visit(txt2img_interface, loadsave, "txt2img")
visit(img2img_interface, loadsave, "img2img")
@ -1788,23 +1889,29 @@ Requested path was: {f}
return demo
with open(os.path.join(script_path, "script.js"), "r", encoding="utf8") as jsfile:
javascript = f'<script>{jsfile.read()}</script>'
def load_javascript(raw_response):
with open(os.path.join(script_path, "script.js"), "r", encoding="utf8") as jsfile:
javascript = f'<script>{jsfile.read()}</script>'
jsdir = os.path.join(script_path, "javascript")
for filename in sorted(os.listdir(jsdir)):
with open(os.path.join(jsdir, filename), "r", encoding="utf8") as jsfile:
javascript += f"\n<script>{jsfile.read()}</script>"
scripts_list = modules.scripts.list_scripts("javascript", ".js")
for basedir, filename, path in scripts_list:
with open(path, "r", encoding="utf8") as jsfile:
javascript += f"\n<!-- {filename} --><script>{jsfile.read()}</script>"
javascript += f"\n<script>{localization.localization_js(shared.opts.localization)}</script>"
if cmd_opts.theme is not None:
javascript += f"\n<script>set_theme('{cmd_opts.theme}');</script>\n"
javascript += f"\n<script>{localization.localization_js(shared.opts.localization)}</script>"
if 'gradio_routes_templates_response' not in globals():
def template_response(*args, **kwargs):
res = gradio_routes_templates_response(*args, **kwargs)
res.body = res.body.replace(b'</head>', f'{javascript}</head>'.encode("utf8"))
res = raw_response(*args, **kwargs)
res.body = res.body.replace(
b'</head>', f'{javascript}</head>'.encode("utf8"))
res.init_headers()
return res
gradio_routes_templates_response = gradio.routes.templates.TemplateResponse
gradio.routes.templates.TemplateResponse = template_response
reload_javascript = partial(load_javascript, gradio.routes.templates.TemplateResponse)
reload_javascript()

1
requirements.txt
View file

@ -23,3 +23,4 @@ resize-right
torchdiffeq
kornia
lark
inflection

1
requirements_versions.txt
View file

@ -22,3 +22,4 @@ resize-right==0.0.2
torchdiffeq==0.2.3
kornia==0.6.7
lark==1.1.2
inflection==0.5.1

8
scripts/img2imgalt.py
View file

@ -34,6 +34,9 @@ def find_noise_for_image(p, cond, uncond, cfg_scale, steps):
sigma_in = torch.cat([sigmas[i] * s_in] * 2)
cond_in = torch.cat([uncond, cond])
image_conditioning = torch.cat([p.image_conditioning] * 2)
cond_in = {"c_concat": [image_conditioning], "c_crossattn": [cond_in]}
c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)]
t = dnw.sigma_to_t(sigma_in)
@ -78,6 +81,9 @@ def find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg_scale, steps):
sigma_in = torch.cat([sigmas[i - 1] * s_in] * 2)
cond_in = torch.cat([uncond, cond])
image_conditioning = torch.cat([p.image_conditioning] * 2)
cond_in = {"c_concat": [image_conditioning], "c_crossattn": [cond_in]}
c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)]
if i == 1:
@ -194,7 +200,7 @@ class Script(scripts.Script):
p.seed = p.seed + 1
return sampler.sample_img2img(p, p.init_latent, noise_dt, conditioning, unconditional_conditioning)
return sampler.sample_img2img(p, p.init_latent, noise_dt, conditioning, unconditional_conditioning, image_conditioning=p.image_conditioning)
p.sample = sample_extra

127
scripts/outpainting_mk_2.py
View file

@ -172,54 +172,54 @@ class Script(scripts.Script):
if down > 0:
down = target_h - init_img.height - up
init_image = p.init_images[0]
state.job_count = (1 if left > 0 else 0) + (1 if right > 0 else 0) + (1 if up > 0 else 0) + (1 if down > 0 else 0)
def expand(init, expand_pixels, is_left=False, is_right=False, is_top=False, is_bottom=False):
def expand(init, count, expand_pixels, is_left=False, is_right=False, is_top=False, is_bottom=False):
is_horiz = is_left or is_right
is_vert = is_top or is_bottom
pixels_horiz = expand_pixels if is_horiz else 0
pixels_vert = expand_pixels if is_vert else 0
res_w = init.width + pixels_horiz
res_h = init.height + pixels_vert
process_res_w = math.ceil(res_w / 64) * 64
process_res_h = math.ceil(res_h / 64) * 64
images_to_process = []
output_images = []
for n in range(count):
res_w = init[n].width + pixels_horiz
res_h = init[n].height + pixels_vert
process_res_w = math.ceil(res_w / 64) * 64
process_res_h = math.ceil(res_h / 64) * 64
img = Image.new("RGB", (process_res_w, process_res_h))
img.paste(init, (pixels_horiz if is_left else 0, pixels_vert if is_top else 0))
mask = Image.new("RGB", (process_res_w, process_res_h), "white")
draw = ImageDraw.Draw(mask)
draw.rectangle((
expand_pixels + mask_blur if is_left else 0,
expand_pixels + mask_blur if is_top else 0,
mask.width - expand_pixels - mask_blur if is_right else res_w,
mask.height - expand_pixels - mask_blur if is_bottom else res_h,
), fill="black")
img = Image.new("RGB", (process_res_w, process_res_h))
img.paste(init[n], (pixels_horiz if is_left else 0, pixels_vert if is_top else 0))
mask = Image.new("RGB", (process_res_w, process_res_h), "white")
draw = ImageDraw.Draw(mask)
draw.rectangle((
expand_pixels + mask_blur if is_left else 0,
expand_pixels + mask_blur if is_top else 0,
mask.width - expand_pixels - mask_blur if is_right else res_w,
mask.height - expand_pixels - mask_blur if is_bottom else res_h,
), fill="black")
np_image = (np.asarray(img) / 255.0).astype(np.float64)
np_mask = (np.asarray(mask) / 255.0).astype(np.float64)
noised = get_matched_noise(np_image, np_mask, noise_q, color_variation)
out = Image.fromarray(np.clip(noised * 255., 0., 255.).astype(np.uint8), mode="RGB")
np_image = (np.asarray(img) / 255.0).astype(np.float64)
np_mask = (np.asarray(mask) / 255.0).astype(np.float64)
noised = get_matched_noise(np_image, np_mask, noise_q, color_variation)
output_images.append(Image.fromarray(np.clip(noised * 255., 0., 255.).astype(np.uint8), mode="RGB"))
target_width = min(process_width, init.width + pixels_horiz) if is_horiz else img.width
target_height = min(process_height, init.height + pixels_vert) if is_vert else img.height
target_width = min(process_width, init[n].width + pixels_horiz) if is_horiz else img.width
target_height = min(process_height, init[n].height + pixels_vert) if is_vert else img.height
p.width = target_width if is_horiz else img.width
p.height = target_height if is_vert else img.height
crop_region = (
0 if is_left else out.width - target_width,
0 if is_top else out.height - target_height,
target_width if is_left else out.width,
target_height if is_top else out.height,
)
crop_region = (
0 if is_left else output_images[n].width - target_width,
0 if is_top else output_images[n].height - target_height,
target_width if is_left else output_images[n].width,
target_height if is_top else output_images[n].height,
)
mask = mask.crop(crop_region)
p.image_mask = mask
image_to_process = out.crop(crop_region)
mask = mask.crop(crop_region)
image_to_process = output_images[n].crop(crop_region)
images_to_process.append(image_to_process)
p.width = target_width if is_horiz else img.width
p.height = target_height if is_vert else img.height
p.init_images = [image_to_process]
p.image_mask = mask
p.init_images = images_to_process
latent_mask = Image.new("RGB", (p.width, p.height), "white")
draw = ImageDraw.Draw(latent_mask)
@ -232,31 +232,52 @@ class Script(scripts.Script):
p.latent_mask = latent_mask
proc = process_images(p)
proc_img = proc.images[0]
if initial_seed_and_info[0] is None:
initial_seed_and_info[0] = proc.seed
initial_seed_and_info[1] = proc.info
out.paste(proc_img, (0 if is_left else out.width - proc_img.width, 0 if is_top else out.height - proc_img.height))
out = out.crop((0, 0, res_w, res_h))
return out
for n in range(count):
output_images[n].paste(proc.images[n], (0 if is_left else output_images[n].width - proc.images[n].width, 0 if is_top else output_images[n].height - proc.images[n].height))
output_images[n] = output_images[n].crop((0, 0, res_w, res_h))
img = init_image
return output_images
if left > 0:
img = expand(img, left, is_left=True)
if right > 0:
img = expand(img, right, is_right=True)
if up > 0:
img = expand(img, up, is_top=True)
if down > 0:
img = expand(img, down, is_bottom=True)
batch_count = p.n_iter
batch_size = p.batch_size
p.n_iter = 1
state.job_count = batch_count * ((1 if left > 0 else 0) + (1 if right > 0 else 0) + (1 if up > 0 else 0) + (1 if down > 0 else 0))
all_processed_images = []
res = Processed(p, [img], initial_seed_and_info[0], initial_seed_and_info[1])
for i in range(batch_count):
imgs = [init_img] * batch_size
state.job = f"Batch {i + 1} out of {batch_count}"
if left > 0:
imgs = expand(imgs, batch_size, left, is_left=True)
if right > 0:
imgs = expand(imgs, batch_size, right, is_right=True)
if up > 0:
imgs = expand(imgs, batch_size, up, is_top=True)
if down > 0:
imgs = expand(imgs, batch_size, down, is_bottom=True)
all_processed_images += imgs
all_images = all_processed_images
combined_grid_image = images.image_grid(all_processed_images)
unwanted_grid_because_of_img_count = len(all_processed_images) < 2 and opts.grid_only_if_multiple
if opts.return_grid and not unwanted_grid_because_of_img_count:
all_images = [combined_grid_image] + all_processed_images
res = Processed(p, all_images, initial_seed_and_info[0], initial_seed_and_info[1])
if opts.samples_save:
images.save_image(img, p.outpath_samples, "", res.seed, p.prompt, opts.grid_format, info=res.info, p=p)
for img in all_processed_images:
images.save_image(img, p.outpath_samples, "", res.seed, p.prompt, opts.grid_format, info=res.info, p=p)
if opts.grid_save and not unwanted_grid_because_of_img_count:
images.save_image(combined_grid_image, p.outpath_grids, "grid", res.seed, p.prompt, opts.grid_format, info=res.info, short_filename=not opts.grid_extended_filename, grid=True, p=p)
return res

1
scripts/xy_grid.py
View file

@ -89,6 +89,7 @@ def apply_checkpoint(p, x, xs):
if info is None:
raise RuntimeError(f"Unknown checkpoint: {x}")
modules.sd_models.reload_model_weights(shared.sd_model, info)
p.sd_model = shared.sd_model
def confirm_checkpoints(p, xs):

9
style.css
View file

@ -34,9 +34,10 @@
.performance {
font-size: 0.85em;
color: #444;
display: flex;
justify-content: space-between;
white-space: nowrap;
}
.performance p{
display: inline-block;
}
.performance .time {
@ -44,8 +45,6 @@
}
.performance .vram {
margin-left: 0;
text-align: right;
}
#txt2img_generate, #img2img_generate {

2
webui.bat
View file

@ -33,7 +33,7 @@ goto :launch
:skip_venv
:launch
%PYTHON% launch.py
%PYTHON% launch.py %*
pause
exit /b

68
webui.py
View file

@ -4,7 +4,7 @@ import time
import importlib
import signal
import threading
from fastapi import FastAPI
from fastapi.middleware.gzip import GZipMiddleware
from modules.paths import script_path
@ -31,7 +31,6 @@ from modules.paths import script_path
from modules.shared import cmd_opts
import modules.hypernetworks.hypernetwork
queue_lock = threading.Lock()
@ -72,6 +71,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs)
def initialize():
modelloader.cleanup_models()
modules.sd_models.setup_model()
@ -80,17 +80,13 @@ def initialize():
shared.face_restorers.append(modules.face_restoration.FaceRestoration())
modelloader.load_upscalers()
modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
modules.scripts.load_scripts()
shared.sd_model = modules.sd_models.load_model()
modules.sd_models.load_model()
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model)))
shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
shared.opts.onchange("sd_hypernetwork_strength", modules.hypernetworks.hypernetwork.apply_strength)
def webui():
initialize()
# make the program just exit at ctrl+c without waiting for anything
def sigint_handler(sig, frame):
print(f'Interrupted with signal {sig} in {frame}')
@ -98,10 +94,38 @@ def webui():
signal.signal(signal.SIGINT, sigint_handler)
while 1:
def create_api(app):
from modules.api.api import Api
api = Api(app, queue_lock)
return api
def wait_on_server(demo=None):
while 1:
time.sleep(0.5)
if demo and getattr(demo, 'do_restart', False):
time.sleep(0.5)
demo.close()
time.sleep(0.5)
break
def api_only():
initialize()
app = FastAPI()
app.add_middleware(GZipMiddleware, minimum_size=1000)
api = create_api(app)
api.launch(server_name="0.0.0.0" if cmd_opts.listen else "127.0.0.1", port=cmd_opts.port if cmd_opts.port else 7861)
def webui():
launch_api = cmd_opts.api
initialize()
while 1:
demo = modules.ui.create_ui(wrap_gradio_gpu_call=wrap_gradio_gpu_call)
app, local_url, share_url = demo.launch(
share=cmd_opts.share,
server_name="0.0.0.0" if cmd_opts.listen else None,
@ -111,21 +135,20 @@ def webui():
inbrowser=cmd_opts.autolaunch,
prevent_thread_lock=True
)
# after initial launch, disable --autolaunch for subsequent restarts
cmd_opts.autolaunch = False
app.add_middleware(GZipMiddleware, minimum_size=1000)
while 1:
time.sleep(0.5)
if getattr(demo, 'do_restart', False):
time.sleep(0.5)
demo.close()
time.sleep(0.5)
break
if (launch_api):
create_api(app)
wait_on_server(demo)
sd_samplers.set_samplers()
print('Reloading Custom Scripts')
modules.scripts.reload_scripts(os.path.join(script_path, "scripts"))
modules.scripts.reload_scripts()
print('Reloading modules: modules.ui')
importlib.reload(modules.ui)
print('Refreshing Model List')
@ -133,5 +156,10 @@ def webui():
print('Restarting Gradio')
task = []
if __name__ == "__main__":
webui()
if cmd_opts.nowebui:
api_only()
else:
webui()

2
webui.sh
View file

@ -138,4 +138,4 @@ fi
printf "\n%s\n" "${delimiter}"
printf "Launching launch.py..."
printf "\n%s\n" "${delimiter}"
"${python_cmd}" "${LAUNCH_SCRIPT}"
"${python_cmd}" "${LAUNCH_SCRIPT}" "$@"