removed aesthetic gradients as built-in

added support for extensions

.gitignore

@@ -27,4 +27,4 @@ __pycache__
 notification.mp3
 /SwinIR
 /textual_inversion
-.vscode
\ No newline at end of file
+.vscode

modules/images_history.py

@@ -310,7 +310,7 @@ def show_images_history(gr, opts, tabname, run_pnginfo, switch_dict):
                         forward = gr.Button('Prev batch')
                         backward = gr.Button('Next batch')
                 with gr.Column(scale=3):
-                    load_info =  gr.HTML(visible=not custom_dir)   
+                    load_info =     gr.HTML(visible=not custom_dir)
             with gr.Row(visible=False) as warning:                 
                 warning_box = gr.Textbox("Message", interactive=False)                        
 

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]
-            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
@@ -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

+
+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/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"),
-                (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"),
+                *modules.scripts.scripts_txt2img.infotext_fields
             ]
 
             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"),
-                (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"),
+                *modules.scripts.scripts_img2img.infotext_fields
             ]
             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,
-        "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, 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')