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

Custom Width and Height

Browse source
This commit is contained in:
alg-wiki 2022-10-10 22:35:35 +09:00
parent 4ee7519fc2
commit 04c745ea4f
No known key found for this signature in database
GPG key ID: 9D27E57D1F43E750
4 changed files with 26 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
modules/textual_inversion/dataset.py
View file

@ -15,13 +15,12 @@ re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
class PersonalizedBase(Dataset):
def __init__(self, data_root, size, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
self.placeholder_token = placeholder_token
self.size = size
self.width = size
self.height = size
self.width = width
self.height = height
self.flip = transforms.RandomHorizontalFlip(p=flip_p)
self.dataset = []

19
modules/textual_inversion/preprocess.py
View file

@ -7,8 +7,9 @@ import tqdm
from modules import shared, images
def preprocess(process_src, process_dst, process_size, process_flip, process_split, process_caption):
size = process_size
def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption):
width = process_width
height = process_height
src = os.path.abspath(process_src)
dst = os.path.abspath(process_dst)
@ -55,23 +56,23 @@ def preprocess(process_src, process_dst, process_size, process_flip, process_spl
is_wide = ratio < 1 / 1.35
if process_split and is_tall:
img = img.resize((size, size * img.height // img.width))
img = img.resize((width, height * img.height // img.width))
top = img.crop((0, 0, size, size))
top = img.crop((0, 0, width, height))
save_pic(top, index)
bot = img.crop((0, img.height - size, size, img.height))
bot = img.crop((0, img.height - height, width, img.height))
save_pic(bot, index)
elif process_split and is_wide:
img = img.resize((size * img.width // img.height, size))
img = img.resize((width * img.width // img.height, height))
left = img.crop((0, 0, size, size))
left = img.crop((0, 0, width, height))
save_pic(left, index)
right = img.crop((img.width - size, 0, img.width, size))
right = img.crop((img.width - width, 0, img.width, height))
save_pic(right, index)
else:
img = images.resize_image(1, img, size, size)
img = images.resize_image(1, img, width, height)
save_pic(img, index)
shared.state.nextjob()

11
modules/textual_inversion/textual_inversion.py
View file

@ -6,7 +6,6 @@ import torch
import tqdm
import html
import datetime
import math
from modules import shared, devices, sd_hijack, processing, sd_models
@ -157,7 +156,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
return fn
def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_size, steps, num_repeats, create_image_every, save_embedding_every, template_file):
def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file):
assert embedding_name, 'embedding not selected'
shared.state.textinfo = "Initializing textual inversion training..."
@ -183,7 +182,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
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, size=training_size, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
hijack = sd_hijack.model_hijack
@ -227,7 +226,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
loss.backward()
optimizer.step()
epoch_num = math.floor(embedding.step / epoch_len)
epoch_num = embedding.step // epoch_len
epoch_step = embedding.step - (epoch_num * epoch_len) + 1
pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{epoch_len}]loss: {losses.mean():.7f}")
@ -243,8 +242,8 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
sd_model=shared.sd_model,
prompt=text,
steps=20,
height=training_size,
width=training_size,
height=training_height,
width=training_width,
do_not_save_grid=True,
do_not_save_samples=True,
)

12
modules/ui.py
View file

@ -1029,7 +1029,8 @@ def create_ui(wrap_gradio_gpu_call):
process_src = gr.Textbox(label='Source directory')
process_dst = gr.Textbox(label='Destination directory')
process_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512)
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)
with gr.Row():
process_flip = gr.Checkbox(label='Create flipped copies')
@ -1050,7 +1051,8 @@ def create_ui(wrap_gradio_gpu_call):
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")
template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"))
training_size = gr.Slider(minimum=64, maximum=2048, step=64, label="Size (width and height)", value=512)
training_width = gr.Slider(minimum=64, maximum=2048, step=64, label="Width", value=512)
training_height = gr.Slider(minimum=64, maximum=2048, step=64, label="Height", value=512)
steps = gr.Number(label='Max steps', value=100000, precision=0)
num_repeats = gr.Number(label='Number of repeats for a single input image per epoch', value=100, precision=0)
create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
@ -1095,7 +1097,8 @@ def create_ui(wrap_gradio_gpu_call):
inputs=[
process_src,
process_dst,
process_size,
process_width,
process_height,
process_flip,
process_split,
process_caption,
@ -1114,7 +1117,8 @@ def create_ui(wrap_gradio_gpu_call):
learn_rate,
dataset_directory,
log_directory,
training_size,
training_width,
training_height,
steps,
num_repeats,
create_image_every,