removed aesthetic gradients as built-in

added support for extensions

modules/aesthetic_clip.py

@@ -1,241 +0,0 @@
-import copy
-import itertools
-import os
-from pathlib import Path
-import html
-import gc
-
-import gradio as gr
-import torch
-from PIL import Image
-from torch import optim
-
-from modules import shared
-from transformers import CLIPModel, CLIPProcessor, CLIPTokenizer
-from tqdm.auto import tqdm, trange
-from modules.shared import opts, device
-
-
-def get_all_images_in_folder(folder):
-    return [os.path.join(folder, f) for f in os.listdir(folder) if
-            os.path.isfile(os.path.join(folder, f)) and check_is_valid_image_file(f)]
-
-
-def check_is_valid_image_file(filename):
-    return filename.lower().endswith(('.png', '.jpg', '.jpeg', ".gif", ".tiff", ".webp"))
-
-
-def batched(dataset, total, n=1):
-    for ndx in range(0, total, n):
-        yield [dataset.__getitem__(i) for i in range(ndx, min(ndx + n, total))]
-
-
-def iter_to_batched(iterable, n=1):
-    it = iter(iterable)
-    while True:
-        chunk = tuple(itertools.islice(it, n))
-        if not chunk:
-            return
-        yield chunk
-
-
-def create_ui():
-    import modules.ui
-
-    with gr.Group():
-        with gr.Accordion("Open for Clip Aesthetic!", open=False):
-            with gr.Row():
-                aesthetic_weight = gr.Slider(minimum=0, maximum=1, step=0.01, label="Aesthetic weight",
-                                             value=0.9)
-                aesthetic_steps = gr.Slider(minimum=0, maximum=50, step=1, label="Aesthetic steps", value=5)
-
-            with gr.Row():
-                aesthetic_lr = gr.Textbox(label='Aesthetic learning rate',
-                                          placeholder="Aesthetic learning rate", value="0.0001")
-                aesthetic_slerp = gr.Checkbox(label="Slerp interpolation", value=False)
-                aesthetic_imgs = gr.Dropdown(sorted(shared.aesthetic_embeddings.keys()),
-                                             label="Aesthetic imgs embedding",
-                                             value="None")
-
-                modules.ui.create_refresh_button(aesthetic_imgs, shared.update_aesthetic_embeddings, lambda: {"choices": sorted(shared.aesthetic_embeddings.keys())}, "refresh_aesthetic_embeddings")
-
-            with gr.Row():
-                aesthetic_imgs_text = gr.Textbox(label='Aesthetic text for imgs',
-                                                 placeholder="This text is used to rotate the feature space of the imgs embs",
-                                                 value="")
-                aesthetic_slerp_angle = gr.Slider(label='Slerp angle', minimum=0, maximum=1, step=0.01,
-                                                  value=0.1)
-                aesthetic_text_negative = gr.Checkbox(label="Is negative text", value=False)
-
-    return aesthetic_weight, aesthetic_steps, aesthetic_lr, aesthetic_slerp, aesthetic_imgs, aesthetic_imgs_text, aesthetic_slerp_angle, aesthetic_text_negative
-
-
-aesthetic_clip_model = None
-
-
-def aesthetic_clip():
-    global aesthetic_clip_model
-
-    if aesthetic_clip_model is None or aesthetic_clip_model.name_or_path != shared.sd_model.cond_stage_model.wrapped.transformer.name_or_path:
-        aesthetic_clip_model = CLIPModel.from_pretrained(shared.sd_model.cond_stage_model.wrapped.transformer.name_or_path)
-        aesthetic_clip_model.cpu()
-
-    return aesthetic_clip_model
-
-
-def generate_imgs_embd(name, folder, batch_size):
-    model = aesthetic_clip().to(device)
-    processor = CLIPProcessor.from_pretrained(model.name_or_path)
-
-    with torch.no_grad():
-        embs = []
-        for paths in tqdm(iter_to_batched(get_all_images_in_folder(folder), batch_size),
-                          desc=f"Generating embeddings for {name}"):
-            if shared.state.interrupted:
-                break
-            inputs = processor(images=[Image.open(path) for path in paths], return_tensors="pt").to(device)
-            outputs = model.get_image_features(**inputs).cpu()
-            embs.append(torch.clone(outputs))
-            inputs.to("cpu")
-            del inputs, outputs
-
-        embs = torch.cat(embs, dim=0).mean(dim=0, keepdim=True)
-
-        # The generated embedding will be located here
-        path = str(Path(shared.cmd_opts.aesthetic_embeddings_dir) / f"{name}.pt")
-        torch.save(embs, path)
-
-        model.cpu()
-        del processor
-        del embs
-        gc.collect()
-        torch.cuda.empty_cache()
-        res = f"""
-        Done generating embedding for {name}!
-        Aesthetic embedding saved to {html.escape(path)}
-        """
-        shared.update_aesthetic_embeddings()
-        return gr.Dropdown.update(choices=sorted(shared.aesthetic_embeddings.keys()), label="Imgs embedding",
-                                  value="None"), \
-               gr.Dropdown.update(choices=sorted(shared.aesthetic_embeddings.keys()),
-                                  label="Imgs embedding",
-                                  value="None"), res, ""
-
-
-def slerp(low, high, val):
-    low_norm = low / torch.norm(low, dim=1, keepdim=True)
-    high_norm = high / torch.norm(high, dim=1, keepdim=True)
-    omega = torch.acos((low_norm * high_norm).sum(1))
-    so = torch.sin(omega)
-    res = (torch.sin((1.0 - val) * omega) / so).unsqueeze(1) * low + (torch.sin(val * omega) / so).unsqueeze(1) * high
-    return res
-
-
-class AestheticCLIP:
-    def __init__(self):
-        self.skip = False
-        self.aesthetic_steps = 0
-        self.aesthetic_weight = 0
-        self.aesthetic_lr = 0
-        self.slerp = False
-        self.aesthetic_text_negative = ""
-        self.aesthetic_slerp_angle = 0
-        self.aesthetic_imgs_text = ""
-
-        self.image_embs_name = None
-        self.image_embs = None
-        self.load_image_embs(None)
-
-    def set_aesthetic_params(self, p, aesthetic_lr=0, aesthetic_weight=0, aesthetic_steps=0, image_embs_name=None,
-                             aesthetic_slerp=True, aesthetic_imgs_text="",
-                             aesthetic_slerp_angle=0.15,
-                             aesthetic_text_negative=False):
-        self.aesthetic_imgs_text = aesthetic_imgs_text
-        self.aesthetic_slerp_angle = aesthetic_slerp_angle
-        self.aesthetic_text_negative = aesthetic_text_negative
-        self.slerp = aesthetic_slerp
-        self.aesthetic_lr = aesthetic_lr
-        self.aesthetic_weight = aesthetic_weight
-        self.aesthetic_steps = aesthetic_steps
-        self.load_image_embs(image_embs_name)
-
-        if self.image_embs_name is not None:
-            p.extra_generation_params.update({
-                "Aesthetic LR": aesthetic_lr,
-                "Aesthetic weight": aesthetic_weight,
-                "Aesthetic steps": aesthetic_steps,
-                "Aesthetic embedding": self.image_embs_name,
-                "Aesthetic slerp": aesthetic_slerp,
-                "Aesthetic text": aesthetic_imgs_text,
-                "Aesthetic text negative": aesthetic_text_negative,
-                "Aesthetic slerp angle": aesthetic_slerp_angle,
-            })
-
-    def set_skip(self, skip):
-        self.skip = skip
-
-    def load_image_embs(self, image_embs_name):
-        if image_embs_name is None or len(image_embs_name) == 0 or image_embs_name == "None":
-            image_embs_name = None
-            self.image_embs_name = None
-        if image_embs_name is not None and self.image_embs_name != image_embs_name:
-            self.image_embs_name = image_embs_name
-            self.image_embs = torch.load(shared.aesthetic_embeddings[self.image_embs_name], map_location=device)
-            self.image_embs /= self.image_embs.norm(dim=-1, keepdim=True)
-            self.image_embs.requires_grad_(False)
-
-    def __call__(self, z, remade_batch_tokens):
-        if not self.skip and self.aesthetic_steps != 0 and self.aesthetic_lr != 0 and self.aesthetic_weight != 0 and self.image_embs_name is not None:
-            tokenizer = shared.sd_model.cond_stage_model.tokenizer
-            if not opts.use_old_emphasis_implementation:
-                remade_batch_tokens = [
-                    [tokenizer.bos_token_id] + x[:75] + [tokenizer.eos_token_id] for x in
-                    remade_batch_tokens]
-
-            tokens = torch.asarray(remade_batch_tokens).to(device)
-
-            model = copy.deepcopy(aesthetic_clip()).to(device)
-            model.requires_grad_(True)
-            if self.aesthetic_imgs_text is not None and len(self.aesthetic_imgs_text) > 0:
-                text_embs_2 = model.get_text_features(
-                    **tokenizer([self.aesthetic_imgs_text], padding=True, return_tensors="pt").to(device))
-                if self.aesthetic_text_negative:
-                    text_embs_2 = self.image_embs - text_embs_2
-                    text_embs_2 /= text_embs_2.norm(dim=-1, keepdim=True)
-                img_embs = slerp(self.image_embs, text_embs_2, self.aesthetic_slerp_angle)
-            else:
-                img_embs = self.image_embs
-
-            with torch.enable_grad():
-
-                # We optimize the model to maximize the similarity
-                optimizer = optim.Adam(
-                    model.text_model.parameters(), lr=self.aesthetic_lr
-                )
-
-                for _ in trange(self.aesthetic_steps, desc="Aesthetic optimization"):
-                    text_embs = model.get_text_features(input_ids=tokens)
-                    text_embs = text_embs / text_embs.norm(dim=-1, keepdim=True)
-                    sim = text_embs @ img_embs.T
-                    loss = -sim
-                    optimizer.zero_grad()
-                    loss.mean().backward()
-                    optimizer.step()
-
-                zn = model.text_model(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
-                if opts.CLIP_stop_at_last_layers > 1:
-                    zn = zn.hidden_states[-opts.CLIP_stop_at_last_layers]
-                    zn = model.text_model.final_layer_norm(zn)
-                else:
-                    zn = zn.last_hidden_state
-                model.cpu()
-                del model
-                gc.collect()
-                torch.cuda.empty_cache()
-            zn = torch.concat([zn[77 * i:77 * (i + 1)] for i in range(max(z.shape[1] // 77, 1))], 1)
-            if self.slerp:
-                z = slerp(z, zn, self.aesthetic_weight)
-            else:
-                z = z * (1 - self.aesthetic_weight) + zn * self.aesthetic_weight
-
-        return z

modules/img2img.py

@@ -56,7 +56,7 @@ def process_batch(p, input_dir, output_dir, args):
                 processed_image.save(os.path.join(output_dir, filename))
 
 
-def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, init_img_with_mask, init_img_inpaint, init_mask_inpaint, mask_mode, steps: int, sampler_index: int, mask_blur: int, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, aesthetic_lr=0, aesthetic_weight=0, aesthetic_steps=0, aesthetic_imgs=None, aesthetic_slerp=False, aesthetic_imgs_text="", aesthetic_slerp_angle=0.15, aesthetic_text_negative=False, *args):
+def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, init_img_with_mask, init_img_inpaint, init_mask_inpaint, mask_mode, steps: int, sampler_index: int, mask_blur: int, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):
     is_inpaint = mode == 1
     is_batch = mode == 2
 
@@ -109,7 +109,8 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
         inpainting_mask_invert=inpainting_mask_invert,
     )
 
-    shared.aesthetic_clip.set_aesthetic_params(p, float(aesthetic_lr), float(aesthetic_weight), int(aesthetic_steps), aesthetic_imgs, aesthetic_slerp, aesthetic_imgs_text, aesthetic_slerp_angle, aesthetic_text_negative)
+    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)

modules/processing.py

@@ -104,6 +104,12 @@ 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
@@ -350,32 +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
@@ -387,9 +396,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             if state.interrupted:
                 break
 
-            prompts = all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
+            prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
-            seeds = all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
+            seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
-            subseeds = all_subseeds[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
@@ -490,10 +499,10 @@ 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):

modules/script_callbacks.py

@@ -0,0 +1,42 @@
+
+callbacks_model_loaded = []
+callbacks_ui_tabs = []
+
+
+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 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)
+

modules/scripts.py

@@ -1,86 +1,153 @@
 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
+    def run(self, p, *args):
-    # self, the model object "p" (a StableDiffusionProcessing class, see
+        """
-    # processing.py), and the parameters returned by the ui method.
+        This function is called if the script has been selected in the script dropdown.
-    # Custom functions can be defined here, and additional libraries can be imported 
+        It must do all processing and return the Processed object with results, same as
-    # to be used in processing. The return value should be a Processed object, which is
+        one returned by processing.process_images.
-    # what is returned by the process_images method.
+
-    def run(self, *args):
+        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.
+    def process(self, p, *args):
-    # 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 
+        This function is called before processing begins for AlwaysVisible scripts.
-    # your description as the value.
+        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):
+def list_scripts(scriptdirname, extension):
-    if not os.path.exists(basedir):
+    scripts_list = []
-        return
 
+    basedir = os.path.join(paths.script_path, scriptdirname)
+    if os.path.exists(basedir):
         for filename in sorted(os.listdir(basedir)):
-        path = os.path.join(basedir, filename)
+            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)
+            if not os.path.isdir(dirpath):
                 continue
 
-        if not os.path.isfile(path):
+            for filename in sorted(os.listdir(os.path.join(dirpath, scriptdirname))):
-            continue
+                scripts_list.append(ScriptFile(dirpath, filename, os.path.join(dirpath, scriptdirname, 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 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')
+            compiled = compile(text, scriptfile.path, 'exec')
-            module = ModuleType(filename)
+            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:
@@ -96,56 +163,80 @@ 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):
+            visibility = script.show(is_img2img)
-                continue
 
+            if visibility == AlwaysVisible:
                 self.scripts.append(script)
+                self.alwayson_scripts.append(script)
+                script.alwayson = True
 
-        self.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"] + self.titles, value="None", type="index")
+        self.titles = [wrap_call(script.title, script.filename, "title") or f"{script.filename} [error]" for script in self.selectable_scripts]
-        dropdown.save_to_config = True
-        inputs = [dropdown]
 
-        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)
+                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):
+            if 0 < script_index <= len(self.selectable_scripts):
-                script = self.scripts[script_index-1]
+                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.scripts[script_index]
+            script = self.selectable_scripts[script_index]
             for i in range(script.args_from, script.args_to):
                 inputs[i].visible = True
 
@@ -164,7 +255,7 @@ 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
@@ -176,6 +267,15 @@ class ScriptRunner:
 
         return processed
 
+    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):
         for si, script in list(enumerate(self.scripts)):
             with open(script.filename, "r", encoding="utf8") as file:
@@ -197,19 +297,21 @@ 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()
 
 
-def reload_scripts(basedir):
+def reload_scripts():
     global scripts_txt2img, scripts_img2img
 
-    scripts_data.clear()
+    load_scripts()
-    load_scripts(basedir)
 
     scripts_txt2img = ScriptRunner()
     scripts_img2img = ScriptRunner()
+

modules/sd_hijack.py

@@ -332,7 +332,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
                     multipliers.append([1.0] * 75)
 
             z1 = self.process_tokens(tokens, multipliers)
-            z1 = shared.aesthetic_clip(z1, remade_batch_tokens)
             z = z1 if z is None else torch.cat((z, z1), axis=-2)
 
             remade_batch_tokens = rem_tokens

modules/sd_models.py

@@ -7,7 +7,7 @@ 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
 
@@ -238,6 +238,9 @@ def load_model(checkpoint_info=None):
     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
@@ -252,7 +255,7 @@ def reload_model_weights(sd_model, info=None):
 
     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(checkpoint_info)
+        load_model(checkpoint_info)
         return shared.sd_model
 
     if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:

modules/shared.py

@@ -31,7 +31,6 @@ parser.add_argument("--no-half-vae", action='store_true', help="do not switch th
 parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
 parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
 parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
-parser.add_argument("--aesthetic_embeddings-dir", type=str, default=os.path.join(models_path, 'aesthetic_embeddings'), help="aesthetic_embeddings directory(default: aesthetic_embeddings)")
 parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
 parser.add_argument("--localizations-dir", type=str, default=os.path.join(script_path, 'localizations'), help="localizations directory")
 parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
@@ -109,21 +108,6 @@ os.makedirs(cmd_opts.hypernetwork_dir, exist_ok=True)
 hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
 loaded_hypernetwork = None
 
-
-os.makedirs(cmd_opts.aesthetic_embeddings_dir, exist_ok=True)
-aesthetic_embeddings = {}
-
-
-def update_aesthetic_embeddings():
-    global aesthetic_embeddings
-    aesthetic_embeddings = {f.replace(".pt", ""): os.path.join(cmd_opts.aesthetic_embeddings_dir, f) for f in
-                            os.listdir(cmd_opts.aesthetic_embeddings_dir) if f.endswith(".pt")}
-    aesthetic_embeddings = OrderedDict(**{"None": None}, **aesthetic_embeddings)
-
-
-update_aesthetic_embeddings()
-
-
 def reload_hypernetworks():
     global hypernetworks
 
@@ -415,9 +399,6 @@ sd_model = None
 
 clip_model = None
 
-from modules.aesthetic_clip import AestheticCLIP
-aesthetic_clip = AestheticCLIP()
-
 progress_print_out = sys.stdout
 
 

modules/txt2img.py

@@ -7,7 +7,7 @@ import modules.processing as processing
 from modules.ui import plaintext_to_html
 
 
-def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, firstphase_width: int, firstphase_height: int, aesthetic_lr=0, aesthetic_weight=0, aesthetic_steps=0, aesthetic_imgs=None, aesthetic_slerp=False, aesthetic_imgs_text="", aesthetic_slerp_angle=0.15, aesthetic_text_negative=False, *args):
+def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, firstphase_width: int, firstphase_height: int, *args):
     p = StableDiffusionProcessingTxt2Img(
         sd_model=shared.sd_model,
         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -36,7 +36,8 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
         firstphase_height=firstphase_height if enable_hr else None,
     )
 
-    shared.aesthetic_clip.set_aesthetic_params(p, float(aesthetic_lr), float(aesthetic_weight), int(aesthetic_steps), aesthetic_imgs, aesthetic_slerp, aesthetic_imgs_text, aesthetic_slerp_angle, aesthetic_text_negative)
+    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)

modules/ui.py

@@ -23,10 +23,10 @@ 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, aesthetic_embeddings
+from modules.shared import opts, cmd_opts, restricted_opts
 
 if cmd_opts.deepdanbooru:
     from modules.deepbooru import get_deepbooru_tags
@@ -44,7 +44,6 @@ from modules.images import save_image
 import modules.textual_inversion.ui
 import modules.hypernetworks.ui
 
-import modules.aesthetic_clip as aesthetic_clip
 import modules.images_history as img_his
 
 
@@ -662,8 +661,6 @@ def create_ui(wrap_gradio_gpu_call):
 
                 seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs()
 
-                aesthetic_weight, aesthetic_steps, aesthetic_lr, aesthetic_slerp, aesthetic_imgs, aesthetic_imgs_text, aesthetic_slerp_angle, aesthetic_text_negative = aesthetic_clip.create_ui()
-
                 with gr.Group():
                     custom_inputs = modules.scripts.scripts_txt2img.setup_ui(is_img2img=False)
 
@@ -718,14 +715,6 @@ def create_ui(wrap_gradio_gpu_call):
                     denoising_strength,
                     firstphase_width,
                     firstphase_height,
-                    aesthetic_lr,
-                    aesthetic_weight,
-                    aesthetic_steps,
-                    aesthetic_imgs,
-                    aesthetic_slerp,
-                    aesthetic_imgs_text,
-                    aesthetic_slerp_angle,
-                    aesthetic_text_negative
                 ] + custom_inputs,
 
                 outputs=[
@@ -804,14 +793,7 @@ 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"),
-                (aesthetic_lr, "Aesthetic LR"),
+                *modules.scripts.scripts_txt2img.infotext_fields
-                (aesthetic_weight, "Aesthetic weight"),
-                (aesthetic_steps, "Aesthetic steps"),
-                (aesthetic_imgs, "Aesthetic embedding"),
-                (aesthetic_slerp, "Aesthetic slerp"),
-                (aesthetic_imgs_text, "Aesthetic text"),
-                (aesthetic_text_negative, "Aesthetic text negative"),
-                (aesthetic_slerp_angle, "Aesthetic slerp angle"),
             ]
 
             txt2img_preview_params = [
@@ -896,8 +878,6 @@ def create_ui(wrap_gradio_gpu_call):
 
                 seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs()
 
-                aesthetic_weight_im, aesthetic_steps_im, aesthetic_lr_im, aesthetic_slerp_im, aesthetic_imgs_im, aesthetic_imgs_text_im, aesthetic_slerp_angle_im, aesthetic_text_negative_im = aesthetic_clip.create_ui()
-
                 with gr.Group():
                     custom_inputs = modules.scripts.scripts_img2img.setup_ui(is_img2img=True)
 
@@ -988,14 +968,6 @@ def create_ui(wrap_gradio_gpu_call):
                     inpainting_mask_invert,
                     img2img_batch_input_dir,
                     img2img_batch_output_dir,
-                    aesthetic_lr_im,
-                    aesthetic_weight_im,
-                    aesthetic_steps_im,
-                    aesthetic_imgs_im,
-                    aesthetic_slerp_im,
-                    aesthetic_imgs_text_im,
-                    aesthetic_slerp_angle_im,
-                    aesthetic_text_negative_im,
                 ] + custom_inputs,
                 outputs=[
                     img2img_gallery,
@@ -1087,14 +1059,7 @@ 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"),
-                (aesthetic_lr_im, "Aesthetic LR"),
+                *modules.scripts.scripts_img2img.infotext_fields
-                (aesthetic_weight_im, "Aesthetic weight"),
-                (aesthetic_steps_im, "Aesthetic steps"),
-                (aesthetic_imgs_im, "Aesthetic embedding"),
-                (aesthetic_slerp_im, "Aesthetic slerp"),
-                (aesthetic_imgs_text_im, "Aesthetic text"),
-                (aesthetic_text_negative_im, "Aesthetic text negative"),
-                (aesthetic_slerp_angle_im, "Aesthetic slerp angle"),
             ]
             token_button.click(fn=update_token_counter, inputs=[img2img_prompt, steps], outputs=[token_counter])
 
@@ -1217,9 +1182,9 @@ def create_ui(wrap_gradio_gpu_call):
         )
     #images history
     images_history_switch_dict = {
-        "fn":modules.generation_parameters_copypaste.connect_paste,
+        "fn": modules.generation_parameters_copypaste.connect_paste,
-        "t2i":txt2img_paste_fields,
+        "t2i": txt2img_paste_fields,
-        "i2i":img2img_paste_fields
+        "i2i": img2img_paste_fields
     }
 
     images_history = img_his.create_history_tabs(gr, opts, cmd_opts, wrap_gradio_call(modules.extras.run_pnginfo), images_history_switch_dict)
@@ -1264,18 +1229,6 @@ def create_ui(wrap_gradio_gpu_call):
                         with gr.Column():
                             create_embedding = gr.Button(value="Create embedding", variant='primary')
 
-                with gr.Tab(label="Create aesthetic images embedding"):
-
-                    new_embedding_name_ae = gr.Textbox(label="Name")
-                    process_src_ae = gr.Textbox(label='Source directory')
-                    batch_ae = gr.Slider(minimum=1, maximum=1024, step=1, label="Batch size", value=256)
-                    with gr.Row():
-                        with gr.Column(scale=3):
-                            gr.HTML(value="")
-
-                        with gr.Column():
-                            create_embedding_ae = gr.Button(value="Create images embedding", variant='primary')
-
                 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"])
@@ -1375,21 +1328,6 @@ def create_ui(wrap_gradio_gpu_call):
             ]
         )
 
-        create_embedding_ae.click(
-            fn=aesthetic_clip.generate_imgs_embd,
-            inputs=[
-                new_embedding_name_ae,
-                process_src_ae,
-                batch_ae
-            ],
-            outputs=[
-                aesthetic_imgs,
-                aesthetic_imgs_im,
-                ti_output,
-                ti_outcome,
-            ]
-        )
-
         create_hypernetwork.click(
             fn=modules.hypernetworks.ui.create_hypernetwork,
             inputs=[
@@ -1580,10 +1518,10 @@ Requested path was: {f}
         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:
@@ -1692,9 +1630,12 @@ Requested path was: {f}
         (images_history, "Image Browser", "images_history"),
         (modelmerger_interface, "Checkpoint Merger", "modelmerger"),
         (train_interface, "Train", "ti"),
-        (settings_interface, "Settings", "settings"),
     ]
 
+    interfaces += script_callbacks.ui_tabs_callback()
+
+    interfaces += [(settings_interface, "Settings", "settings")]
+
     with open(os.path.join(script_path, "style.css"), "r", encoding="utf8") as file:
         css = file.read()
 

webui.py

@@ -71,6 +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()
@@ -79,9 +80,9 @@ 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)
@@ -145,7 +146,7 @@ def webui():
         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')