Merge branch 'dev' into remove-watermark-option

modules/api/api.py

@@ -6,7 +6,6 @@ import uvicorn
 import gradio as gr
 from threading import Lock
 from io import BytesIO
-from gradio.processing_utils import decode_base64_to_file
 from fastapi import APIRouter, Depends, FastAPI, Request, Response
 from fastapi.security import HTTPBasic, HTTPBasicCredentials
 from fastapi.exceptions import HTTPException
@@ -272,7 +271,9 @@ class Api:
                     raise HTTPException(status_code=422, detail=f"Cannot have a selectable script in the always on scripts params")
                 # always on script with no arg should always run so you don't really need to add them to the requests
                 if "args" in request.alwayson_scripts[alwayson_script_name]:
-                    script_args[alwayson_script.args_from:alwayson_script.args_to] = request.alwayson_scripts[alwayson_script_name]["args"]
+                    # min between arg length in scriptrunner and arg length in the request
+                    for idx in range(0, min((alwayson_script.args_to - alwayson_script.args_from), len(request.alwayson_scripts[alwayson_script_name]["args"]))):
+                        script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx]
         return script_args
 
     def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
@@ -395,16 +396,11 @@ class Api:
     def extras_batch_images_api(self, req: ExtrasBatchImagesRequest):
         reqDict = setUpscalers(req)
 
-        def prepareFiles(file):
-            file = decode_base64_to_file(file.data, file_path=file.name)
-            file.orig_name = file.name
-            return file
-
-        reqDict['image_folder'] = list(map(prepareFiles, reqDict['imageList']))
-        reqDict.pop('imageList')
+        image_list = reqDict.pop('imageList', [])
+        image_folder = [decode_base64_to_image(x.data) for x in image_list]
 
         with self.queue_lock:
-            result = postprocessing.run_extras(extras_mode=1, image="", input_dir="", output_dir="", save_output=False, **reqDict)
+            result = postprocessing.run_extras(extras_mode=1, image_folder=image_folder, image="", input_dir="", output_dir="", save_output=False, **reqDict)
 
         return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
 

modules/devices.py

@@ -92,14 +92,18 @@ def cond_cast_float(input):
 
 
 def randn(seed, shape):
+    from modules.shared import opts
+
     torch.manual_seed(seed)
-    if device.type == 'mps':
+    if opts.randn_source == "CPU" or device.type == 'mps':
         return torch.randn(shape, device=cpu).to(device)
     return torch.randn(shape, device=device)
 
 
 def randn_without_seed(shape):
-    if device.type == 'mps':
+    from modules.shared import opts
+
+    if opts.randn_source == "CPU" or device.type == 'mps':
         return torch.randn(shape, device=cpu).to(device)
     return torch.randn(shape, device=device)
 

modules/extensions.py

@@ -15,7 +15,12 @@ if not os.path.exists(extensions_dir):
 
 
 def active():
-    return [x for x in extensions if x.enabled]
+    if shared.opts.disable_all_extensions == "all":
+        return []
+    elif shared.opts.disable_all_extensions == "extra":
+        return [x for x in extensions if x.enabled and x.is_builtin]
+    else:
+        return [x for x in extensions if x.enabled]
 
 
 class Extension:
@@ -97,6 +102,11 @@ def list_extensions():
     if not os.path.isdir(extensions_dir):
         return
 
+    if shared.opts.disable_all_extensions == "all":
+        print("*** \"Disable all extensions\" option was set, will not load any extensions ***")
+    elif shared.opts.disable_all_extensions == "extra":
+        print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
+
     extension_paths = []
     for dirname in [extensions_dir, extensions_builtin_dir]:
         if not os.path.isdir(dirname):
@@ -112,4 +122,3 @@ def list_extensions():
     for dirname, path, is_builtin in extension_paths:
         extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)
         extensions.append(extension)
-

modules/extra_networks_hypernet.py

@@ -9,7 +9,7 @@ class ExtraNetworkHypernet(extra_networks.ExtraNetwork):
     def activate(self, p, params_list):
         additional = shared.opts.sd_hypernetwork
 
-        if additional != "" and additional in shared.hypernetworks and len([x for x in params_list if x.items[0] == additional]) == 0:
+        if additional != "None" and additional in shared.hypernetworks and len([x for x in params_list if x.items[0] == additional]) == 0:
             p.all_prompts = [x + f"<hypernet:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
             params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
 

modules/generation_parameters_copypaste.py

@@ -284,6 +284,10 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
 
     restore_old_hires_fix_params(res)
 
+    # Missing RNG means the default was set, which is GPU RNG
+    if "RNG" not in res:
+        res["RNG"] = "GPU"
+
     return res
 
 
@@ -304,6 +308,8 @@ infotext_to_setting_name_mapping = [
     ('UniPC skip type', 'uni_pc_skip_type'),
     ('UniPC order', 'uni_pc_order'),
     ('UniPC lower order final', 'uni_pc_lower_order_final'),
+    ('RNG', 'randn_source'),
+    ('NGMS', 's_min_uncond'),
 ]
 
 

modules/hypernetworks/hypernetwork.py

@@ -312,7 +312,7 @@ class Hypernetwork:
 
 def list_hypernetworks(path):
     res = {}
-    for filename in sorted(glob.iglob(os.path.join(path, '**/*.pt'), recursive=True)):
+    for filename in sorted(glob.iglob(os.path.join(path, '**/*.pt'), recursive=True), key=str.lower):
         name = os.path.splitext(os.path.basename(filename))[0]
         # Prevent a hypothetical "None.pt" from being listed.
         if name != "None":

modules/images.py

@@ -318,6 +318,7 @@ re_nonletters = re.compile(r'[\s' + string.punctuation + ']+')
 re_pattern = re.compile(r"(.*?)(?:\[([^\[\]]+)\]|$)")
 re_pattern_arg = re.compile(r"(.*)<([^>]*)>$")
 max_filename_part_length = 128
+NOTHING_AND_SKIP_PREVIOUS_TEXT = object()
 
 
 def sanitize_filename_part(text, replace_spaces=True):
@@ -352,6 +353,10 @@ class FilenameGenerator:
         'prompt_no_styles': lambda self: self.prompt_no_style(),
         'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),
         'prompt_words': lambda self: self.prompt_words(),
+        'batch_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 else self.p.batch_index + 1,
+        'generation_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.n_iter == 1 and self.p.batch_size == 1 else self.p.iteration * self.p.batch_size + self.p.batch_index + 1,
+        'hasprompt': lambda self, *args: self.hasprompt(*args),  # accepts formats:[hasprompt<prompt1|default><prompt2>..]
+        'clip_skip': lambda self: opts.data["CLIP_stop_at_last_layers"],
     }
     default_time_format = '%Y%m%d%H%M%S'
 
@@ -360,6 +365,22 @@ class FilenameGenerator:
         self.seed = seed
         self.prompt = prompt
         self.image = image
+        
+    def hasprompt(self, *args):
+        lower = self.prompt.lower()
+        if self.p is None or self.prompt is None:
+            return None
+        outres = ""
+        for arg in args:
+            if arg != "":
+                division = arg.split("|")
+                expected = division[0].lower()
+                default = division[1] if len(division) > 1 else ""
+                if lower.find(expected) >= 0:
+                    outres = f'{outres}{expected}'
+                else:
+                    outres = outres if default == "" else f'{outres}{default}'
+        return sanitize_filename_part(outres)
 
     def prompt_no_style(self):
         if self.p is None or self.prompt is None:
@@ -403,9 +424,9 @@ class FilenameGenerator:
 
         for m in re_pattern.finditer(x):
             text, pattern = m.groups()
-            res += text
 
             if pattern is None:
+                res += text
                 continue
 
             pattern_args = []
@@ -426,11 +447,13 @@ class FilenameGenerator:
                     print(f"Error adding [{pattern}] to filename", file=sys.stderr)
                     print(traceback.format_exc(), file=sys.stderr)
 
-                if replacement is not None:
-                    res += str(replacement)
+                if replacement == NOTHING_AND_SKIP_PREVIOUS_TEXT:
+                    continue
+                elif replacement is not None:
+                    res += text + str(replacement)
                     continue
 
-            res += f'[{pattern}]'
+            res += f'{text}[{pattern}]'
 
         return res
 

modules/img2img.py

@@ -151,13 +151,14 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         override_settings=override_settings,
     )
 
-    p.scripts = modules.scripts.scripts_txt2img
+    p.scripts = modules.scripts.scripts_img2img
     p.script_args = args
 
     if shared.cmd_opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
-    p.extra_generation_params["Mask blur"] = mask_blur
+    if mask:
+        p.extra_generation_params["Mask blur"] = mask_blur
 
     if is_batch:
         assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"

modules/interrogate.py

@@ -32,7 +32,7 @@ def download_default_clip_interrogate_categories(content_dir):
     category_types = ["artists", "flavors", "mediums", "movements"]
 
     try:
-        os.makedirs(tmpdir)
+        os.makedirs(tmpdir, exist_ok=True)
         for category_type in category_types:
             torch.hub.download_url_to_file(f"https://raw.githubusercontent.com/pharmapsychotic/clip-interrogator/main/clip_interrogator/data/{category_type}.txt", os.path.join(tmpdir, f"{category_type}.txt"))
         os.rename(tmpdir, content_dir)
@@ -41,7 +41,7 @@ def download_default_clip_interrogate_categories(content_dir):
         errors.display(e, "downloading default CLIP interrogate categories")
     finally:
         if os.path.exists(tmpdir):
-            os.remove(tmpdir)
+            os.removedirs(tmpdir)
 
 
 class InterrogateModels:

modules/lowvram.py

@@ -55,12 +55,12 @@ def setup_for_low_vram(sd_model, use_medvram):
     if hasattr(sd_model.cond_stage_model, 'model'):
         sd_model.cond_stage_model.transformer = sd_model.cond_stage_model.model
 
-    # remove four big modules, cond, first_stage, depth (if applicable), and unet from the model and then
+    # remove several big modules: cond, first_stage, depth/embedder (if applicable), and unet from the model and then
     # 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, getattr(sd_model, 'depth_model', None), sd_model.model
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.model = None, None, None, None
+    stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, getattr(sd_model, 'depth_model', None), getattr(sd_model, 'embedder', None), sd_model.model
+    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = None, None, None, None, None
     sd_model.to(devices.device)
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.model = stored
+    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = stored
 
     # register hooks for those the first three models
     sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
@@ -69,6 +69,8 @@ def setup_for_low_vram(sd_model, use_medvram):
     sd_model.first_stage_model.decode = first_stage_model_decode_wrap
     if sd_model.depth_model:
         sd_model.depth_model.register_forward_pre_hook(send_me_to_gpu)
+    if sd_model.embedder:
+        sd_model.embedder.register_forward_pre_hook(send_me_to_gpu)
     parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
 
     if hasattr(sd_model.cond_stage_model, 'model'):

modules/postprocessing.py

@@ -18,9 +18,15 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
 
     if extras_mode == 1:
         for img in image_folder:
-            image = Image.open(img)
+            if isinstance(img, Image.Image):
+                image = img
+                fn = ''
+            else:
+                image = Image.open(os.path.abspath(img.name))
+                fn = os.path.splitext(img.orig_name)[0]
+
             image_data.append(image)
-            image_names.append(os.path.splitext(img.orig_name)[0])
+            image_names.append(fn)
     elif extras_mode == 2:
         assert not shared.cmd_opts.hide_ui_dir_config, '--hide-ui-dir-config option must be disabled'
         assert input_dir, 'input directory not selected'

modules/processing.py

@@ -3,6 +3,7 @@ import math
 import os
 import sys
 import warnings
+import hashlib
 
 import torch
 import numpy as np
@@ -78,28 +79,34 @@ def apply_overlay(image, paste_loc, index, overlays):
 
 
 def txt2img_image_conditioning(sd_model, x, width, height):
-    if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
-        # Dummy zero conditioning if we're not using inpainting model.
+    if sd_model.model.conditioning_key in {'hybrid', 'concat'}: # Inpainting models
+
+        # 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 = sd_model.get_first_stage_encoding(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)
+
+        return image_conditioning
+
+    elif sd_model.model.conditioning_key == "crossattn-adm": # UnCLIP models
+
+        return x.new_zeros(x.shape[0], 2*sd_model.noise_augmentor.time_embed.dim, dtype=x.dtype, device=x.device)
+
+    else:
+        # Dummy zero conditioning if we're not using inpainting or unclip models.
         # 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.
         return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
 
-    # 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 = sd_model.get_first_stage_encoding(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)
-
-    return image_conditioning
-
 
 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_name: str = None, 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 = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
+    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_name: str = None, 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 = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
         if sampler_index is not None:
             print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
 
@@ -134,6 +141,7 @@ class StableDiffusionProcessing:
         self.denoising_strength: float = denoising_strength
         self.sampler_noise_scheduler_override = None
         self.ddim_discretize = ddim_discretize or opts.ddim_discretize
+        self.s_min_uncond = s_min_uncond or opts.s_min_uncond
         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
@@ -156,6 +164,8 @@ class StableDiffusionProcessing:
         self.all_seeds = None
         self.all_subseeds = None
         self.iteration = 0
+        self.is_hr_pass = False
+        
 
     @property
     def sd_model(self):
@@ -190,6 +200,14 @@ class StableDiffusionProcessing:
 
         return conditioning_image
 
+    def unclip_image_conditioning(self, source_image):
+        c_adm = self.sd_model.embedder(source_image)
+        if self.sd_model.noise_augmentor is not None:
+            noise_level = 0 # TODO: Allow other noise levels?
+            c_adm, noise_level_emb = self.sd_model.noise_augmentor(c_adm, noise_level=repeat(torch.tensor([noise_level]).to(c_adm.device), '1 -> b', b=c_adm.shape[0]))
+            c_adm = torch.cat((c_adm, noise_level_emb), 1)
+        return c_adm
+
     def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None):
         self.is_using_inpainting_conditioning = True
 
@@ -241,6 +259,9 @@ class StableDiffusionProcessing:
         if self.sampler.conditioning_key in {'hybrid', 'concat'}:
             return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
 
+        if self.sampler.conditioning_key == "crossattn-adm":
+            return self.unclip_image_conditioning(source_image)
+
         # Dummy zero conditioning if we're not using inpainting or depth model.
         return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
 
@@ -459,6 +480,9 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None,
         "Clip skip": None if clip_skip <= 1 else clip_skip,
         "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta,
+        "Init image hash": getattr(p, 'init_img_hash', None),
+        "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
+        "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
     }
 
     generation_params.update(p.extra_generation_params)
@@ -622,8 +646,14 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     processed = Processed(p, [], p.seed, "")
                     file.write(processed.infotext(p, 0))
 
-            uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc)
-            c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c)
+            step_multiplier = 1
+            if not shared.opts.dont_fix_second_order_samplers_schedule:
+                try:
+                    step_multiplier = 2 if sd_samplers.all_samplers_map.get(p.sampler_name).aliases[0] in ['k_dpmpp_2s_a', 'k_dpmpp_2s_a_ka', 'k_dpmpp_sde', 'k_dpmpp_sde_ka', 'k_dpm_2', 'k_dpm_2_a', 'k_heun'] else 1
+                except:
+                    pass
+            uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc)
+            c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps * step_multiplier, cached_c)
 
             if len(model_hijack.comments) > 0:
                 for comment in model_hijack.comments:
@@ -653,6 +683,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 p.scripts.postprocess_batch(p, x_samples_ddim, batch_number=n)
 
             for i, x_sample in enumerate(x_samples_ddim):
+                p.batch_index = i
+
                 x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
                 x_sample = x_sample.astype(np.uint8)
 
@@ -689,9 +721,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     image.info["parameters"] = text
                 output_images.append(image)
 
-                if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay:
+                if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay and any([opts.save_mask, opts.save_mask_composite, opts.return_mask, opts.return_mask_composite]):
                     image_mask = p.mask_for_overlay.convert('RGB')
-                    image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), p.mask_for_overlay.convert('L')).convert('RGBA')
+                    image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
 
                     if opts.save_mask:
                         images.save_image(image_mask, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask")
@@ -701,7 +733,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
                     if opts.return_mask:
                         output_images.append(image_mask)
-                    
+
                     if opts.return_mask_composite:
                         output_images.append(image_mask_composite)
 
@@ -854,6 +886,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         if not self.enable_hr:
             return samples
 
+        self.is_hr_pass = True
+
         target_width = self.hr_upscale_to_x
         target_height = self.hr_upscale_to_y
 
@@ -923,6 +957,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
 
+        self.is_hr_pass = False
+
         return samples
 
 
@@ -990,6 +1026,12 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             self.color_corrections = []
         imgs = []
         for img in self.init_images:
+
+            # Save init image
+            if opts.save_init_img:
+                self.init_img_hash = hashlib.md5(img.tobytes()).hexdigest()
+                images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False)
+
             image = images.flatten(img, opts.img2img_background_color)
 
             if crop_region is None and self.resize_mode != 3:

modules/safe.py

@@ -1,6 +1,5 @@
 # this code is adapted from the script contributed by anon from /h/
 
-import io
 import pickle
 import collections
 import sys
@@ -12,11 +11,9 @@ import _codecs
 import zipfile
 import re
 
-
 # PyTorch 1.13 and later have _TypedStorage renamed to TypedStorage
 TypedStorage = torch.storage.TypedStorage if hasattr(torch.storage, 'TypedStorage') else torch.storage._TypedStorage
 
-
 def encode(*args):
     out = _codecs.encode(*args)
     return out
@@ -27,7 +24,7 @@ class RestrictedUnpickler(pickle.Unpickler):
 
     def persistent_load(self, saved_id):
         assert saved_id[0] == 'storage'
-        return TypedStorage()
+        return TypedStorage(_internal=True)
 
     def find_class(self, module, name):
         if self.extra_handler is not None:

modules/sd_models.py

@@ -122,7 +122,7 @@ def list_models():
     elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:
         print(f"Checkpoint in --ckpt argument not found (Possible it was moved to {model_path}: {cmd_ckpt}", file=sys.stderr)
 
-    for filename in model_list:
+    for filename in sorted(model_list, key=str.lower):
         checkpoint_info = CheckpointInfo(filename)
         checkpoint_info.register()
 
@@ -383,6 +383,14 @@ def repair_config(sd_config):
     elif shared.cmd_opts.upcast_sampling:
         sd_config.model.params.unet_config.params.use_fp16 = True
 
+    if getattr(sd_config.model.params.first_stage_config.params.ddconfig, "attn_type", None) == "vanilla-xformers" and not shared.xformers_available:
+        sd_config.model.params.first_stage_config.params.ddconfig.attn_type = "vanilla"
+
+    # For UnCLIP-L, override the hardcoded karlo directory
+    if hasattr(sd_config.model.params, "noise_aug_config") and hasattr(sd_config.model.params.noise_aug_config.params, "clip_stats_path"):
+        karlo_path = os.path.join(paths.models_path, 'karlo')
+        sd_config.model.params.noise_aug_config.params.clip_stats_path = sd_config.model.params.noise_aug_config.params.clip_stats_path.replace("checkpoints/karlo_models", karlo_path)
+
 
 sd1_clip_weight = 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight'
 sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight'

modules/sd_models_config.py

@@ -14,6 +14,8 @@ config_sd2 = os.path.join(sd_repo_configs_path, "v2-inference.yaml")
 config_sd2v = os.path.join(sd_repo_configs_path, "v2-inference-v.yaml")
 config_sd2_inpainting = os.path.join(sd_repo_configs_path, "v2-inpainting-inference.yaml")
 config_depth_model = os.path.join(sd_repo_configs_path, "v2-midas-inference.yaml")
+config_unclip = os.path.join(sd_repo_configs_path, "v2-1-stable-unclip-l-inference.yaml")
+config_unopenclip = os.path.join(sd_repo_configs_path, "v2-1-stable-unclip-h-inference.yaml")
 config_inpainting = os.path.join(sd_configs_path, "v1-inpainting-inference.yaml")
 config_instruct_pix2pix = os.path.join(sd_configs_path, "instruct-pix2pix.yaml")
 config_alt_diffusion = os.path.join(sd_configs_path, "alt-diffusion-inference.yaml")
@@ -65,9 +67,14 @@ def is_using_v_parameterization_for_sd2(state_dict):
 def guess_model_config_from_state_dict(sd, filename):
     sd2_cond_proj_weight = sd.get('cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight', None)
     diffusion_model_input = sd.get('model.diffusion_model.input_blocks.0.0.weight', None)
+    sd2_variations_weight = sd.get('embedder.model.ln_final.weight', None)
 
     if sd.get('depth_model.model.pretrained.act_postprocess3.0.project.0.bias', None) is not None:
         return config_depth_model
+    elif sd2_variations_weight is not None and sd2_variations_weight.shape[0] == 768:
+        return config_unclip
+    elif sd2_variations_weight is not None and sd2_variations_weight.shape[0] == 1024:
+        return config_unopenclip
 
     if sd2_cond_proj_weight is not None and sd2_cond_proj_weight.shape[1] == 1024:
         if diffusion_model_input.shape[1] == 9:

modules/sd_samplers_common.py

@@ -60,3 +60,13 @@ def store_latent(decoded):
 
 class InterruptedException(BaseException):
     pass
+
+
+if opts.randn_source == "CPU":
+    import torchsde._brownian.brownian_interval
+
+    def torchsde_randn(size, dtype, device, seed):
+        generator = torch.Generator(devices.cpu).manual_seed(int(seed))
+        return torch.randn(size, dtype=dtype, device=devices.cpu, generator=generator).to(device)
+
+    torchsde._brownian.brownian_interval._randn = torchsde_randn

modules/sd_samplers_compvis.py

@@ -70,8 +70,13 @@ class VanillaStableDiffusionSampler:
 
         # Have to unwrap the inpainting conditioning here to perform pre-processing
         image_conditioning = None
+        uc_image_conditioning = None
         if isinstance(cond, dict):
-            image_conditioning = cond["c_concat"][0]
+            if self.conditioning_key == "crossattn-adm":
+                image_conditioning = cond["c_adm"]
+                uc_image_conditioning = unconditional_conditioning["c_adm"]
+            else:
+                image_conditioning = cond["c_concat"][0]
             cond = cond["c_crossattn"][0]
             unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
 
@@ -98,8 +103,12 @@ class VanillaStableDiffusionSampler:
         # 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]}
+            if self.conditioning_key == "crossattn-adm":
+                cond = {"c_adm": image_conditioning, "c_crossattn": [cond]}
+                unconditional_conditioning = {"c_adm": uc_image_conditioning, "c_crossattn": [unconditional_conditioning]}
+            else:
+                cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
+                unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
 
         return x, ts, cond, unconditional_conditioning
 
@@ -176,8 +185,12 @@ class VanillaStableDiffusionSampler:
 
         # 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]}
+            if self.conditioning_key == "crossattn-adm":
+                conditioning = {"c_adm": image_conditioning, "c_crossattn": [conditioning]}
+                unconditional_conditioning = {"c_adm": torch.zeros_like(image_conditioning), "c_crossattn": [unconditional_conditioning]}
+            else:
+                conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
+                unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
 
         samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
 
@@ -195,8 +208,12 @@ class VanillaStableDiffusionSampler:
         # Wrap the conditioning models with additional image conditioning for inpainting model
         # dummy_for_plms is needed because PLMS code checks the first item in the dict to have the right shape
         if image_conditioning is not None:
-            conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
-            unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
+            if self.conditioning_key == "crossattn-adm":
+                conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_adm": image_conditioning}
+                unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_adm": torch.zeros_like(image_conditioning)}
+            else:
+                conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
+                unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
 
         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])
 

modules/sd_samplers_kdiffusion.py

@@ -76,7 +76,7 @@ class CFGDenoiser(torch.nn.Module):
 
         return denoised
 
-    def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
+    def forward(self, x, sigma, uncond, cond, cond_scale, s_min_uncond, image_cond):
         if state.interrupted or state.skipped:
             raise sd_samplers_common.InterruptedException
 
@@ -92,14 +92,21 @@ class CFGDenoiser(torch.nn.Module):
         batch_size = len(conds_list)
         repeats = [len(conds_list[i]) for i in range(batch_size)]
 
+        if shared.sd_model.model.conditioning_key == "crossattn-adm":
+            image_uncond = torch.zeros_like(image_cond)
+            make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm} 
+        else:
+            image_uncond = image_cond
+            make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]} 
+
         if not is_edit_model:
             x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
             sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
-            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
+            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_uncond])
         else:
             x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x] + [x])
             sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma] + [sigma])
-            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond] + [torch.zeros_like(self.init_latent)])
+            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_uncond] + [torch.zeros_like(self.init_latent)])
 
         denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps, tensor, uncond)
         cfg_denoiser_callback(denoiser_params)
@@ -108,21 +115,30 @@ class CFGDenoiser(torch.nn.Module):
         sigma_in = denoiser_params.sigma
         tensor = denoiser_params.text_cond
         uncond = denoiser_params.text_uncond
+        skip_uncond = False
 
-        if tensor.shape[1] == uncond.shape[1]:
-            if not is_edit_model:
-                cond_in = torch.cat([tensor, uncond])
-            else:
+        # alternating uncond allows for higher thresholds without the quality loss normally expected from raising it
+        if self.step % 2 and s_min_uncond > 0 and sigma[0] < s_min_uncond and not is_edit_model:
+            skip_uncond = True
+            x_in = x_in[:-batch_size]
+            sigma_in = sigma_in[:-batch_size]
+
+        if tensor.shape[1] == uncond.shape[1] or skip_uncond:
+            if is_edit_model:
                 cond_in = torch.cat([tensor, uncond, uncond])
+            elif skip_uncond:
+                cond_in = tensor
+            else:
+                cond_in = torch.cat([tensor, uncond])
 
             if shared.batch_cond_uncond:
-                x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
+                x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict([cond_in], 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={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
+                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict([cond_in[a:b]], 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
@@ -135,9 +151,15 @@ class CFGDenoiser(torch.nn.Module):
                 else:
                     c_crossattn = torch.cat([tensor[a:b]], uncond)
 
-                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": c_crossattn, "c_concat": [image_cond_in[a:b]]})
+                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b]))
 
-            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]:]]})
+            if not skip_uncond:
+                x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=make_condition_dict([uncond], image_cond_in[-uncond.shape[0]:]))
+
+        denoised_image_indexes = [x[0][0] for x in conds_list]
+        if skip_uncond:
+            fake_uncond = torch.cat([x_out[i:i+1] for i in denoised_image_indexes])
+            x_out = torch.cat([x_out, fake_uncond])  # we skipped uncond denoising, so we put cond-denoised image to where the uncond-denoised image should be
 
         denoised_params = CFGDenoisedParams(x_out, state.sampling_step, state.sampling_steps)
         cfg_denoised_callback(denoised_params)
@@ -145,20 +167,21 @@ class CFGDenoiser(torch.nn.Module):
         devices.test_for_nans(x_out, "unet")
 
         if opts.live_preview_content == "Prompt":
-            sd_samplers_common.store_latent(x_out[0:uncond.shape[0]])
+            sd_samplers_common.store_latent(torch.cat([x_out[i:i+1] for i in denoised_image_indexes]))
         elif opts.live_preview_content == "Negative prompt":
             sd_samplers_common.store_latent(x_out[-uncond.shape[0]:])
 
-        if not is_edit_model:
-            denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
-        else:
+        if is_edit_model:
             denoised = self.combine_denoised_for_edit_model(x_out, cond_scale)
+        elif skip_uncond:
+            denoised = self.combine_denoised(x_out, conds_list, uncond, 1.0)
+        else:
+            denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
 
         if self.mask is not None:
             denoised = self.init_latent * self.mask + self.nmask * denoised
 
         self.step += 1
-
         return denoised
 
 
@@ -183,7 +206,7 @@ class TorchHijack:
             if noise.shape == x.shape:
                 return noise
 
-        if x.device.type == 'mps':
+        if opts.randn_source == "CPU" or x.device.type == 'mps':
             return torch.randn_like(x, device=devices.cpu).to(x.device)
         else:
             return torch.randn_like(x)
@@ -203,6 +226,7 @@ class KDiffusionSampler:
         self.eta = None
         self.config = None
         self.last_latent = None
+        self.s_min_uncond = None
 
         self.conditioning_key = sd_model.model.conditioning_key
 
@@ -237,6 +261,7 @@ class KDiffusionSampler:
         self.model_wrap_cfg.step = 0
         self.model_wrap_cfg.image_cfg_scale = getattr(p, 'image_cfg_scale', None)
         self.eta = p.eta if p.eta is not None else opts.eta_ancestral
+        self.s_min_uncond = getattr(p, 's_min_uncond', 0.0)
 
         k_diffusion.sampling.torch = TorchHijack(self.sampler_noises if self.sampler_noises is not None else [])
 
@@ -319,6 +344,7 @@ class KDiffusionSampler:
             'image_cond': image_conditioning, 
             'uncond': unconditional_conditioning, 
             'cond_scale': p.cfg_scale,
+            's_min_uncond': self.s_min_uncond
         }
 
         samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
@@ -352,7 +378,8 @@ class KDiffusionSampler:
             'cond': conditioning, 
             'image_cond': image_conditioning, 
             'uncond': unconditional_conditioning, 
-            'cond_scale': p.cfg_scale
+            'cond_scale': p.cfg_scale,
+            's_min_uncond': self.s_min_uncond
         }, disable=False, callback=self.callback_state, **extra_params_kwargs))
 
         return samples

modules/shared.py

@@ -4,6 +4,7 @@ import json
 import os
 import sys
 import time
+import requests
 
 from PIL import Image
 import gradio as gr
@@ -39,6 +40,7 @@ restricted_opts = {
     "outdir_grids",
     "outdir_txt2img_grids",
     "outdir_save",
+    "outdir_init_images"
 }
 
 ui_reorder_categories = [
@@ -54,6 +56,21 @@ ui_reorder_categories = [
     "scripts",
 ]
 
+# https://huggingface.co/datasets/freddyaboulton/gradio-theme-subdomains/resolve/main/subdomains.json
+gradio_hf_hub_themes = [
+    "gradio/glass",
+    "gradio/monochrome",
+    "gradio/seafoam",
+    "gradio/soft",
+    "freddyaboulton/dracula_revamped",
+    "gradio/dracula_test",
+    "abidlabs/dracula_test",
+    "abidlabs/pakistan",
+    "dawood/microsoft_windows",
+    "ysharma/steampunk"
+]
+
+
 cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen or cmd_opts.server_name) and not cmd_opts.enable_insecure_extension_access
 
 devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_esrgan, devices.device_codeformer = \
@@ -252,6 +269,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
     "use_original_name_batch": OptionInfo(True, "Use original name for output filename during batch process in extras tab"),
     "use_upscaler_name_as_suffix": OptionInfo(False, "Use upscaler name as filename suffix in the extras tab"),
     "save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"),
+    "save_init_img": OptionInfo(False, "Save init images when using img2img"),
 
     "temp_dir":  OptionInfo("", "Directory for temporary images; leave empty for default"),
     "clean_temp_dir_at_start": OptionInfo(False, "Cleanup non-default temporary directory when starting webui"),
@@ -267,6 +285,7 @@ options_templates.update(options_section(('saving-paths', "Paths for saving"), {
     "outdir_txt2img_grids": OptionInfo("outputs/txt2img-grids", 'Output directory for txt2img grids', component_args=hide_dirs),
     "outdir_img2img_grids": OptionInfo("outputs/img2img-grids", 'Output directory for img2img grids', component_args=hide_dirs),
     "outdir_save": OptionInfo("log/images", "Directory for saving images using the Save button", component_args=hide_dirs),
+    "outdir_init_images": OptionInfo("outputs/init-images", "Directory for saving init images when using img2img", component_args=hide_dirs),
 }))
 
 options_templates.update(options_section(('saving-to-dirs', "Saving to a directory"), {
@@ -282,6 +301,8 @@ options_templates.update(options_section(('upscaling', "Upscaling"), {
     "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
     "realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": shared_items.realesrgan_models_names()}),
     "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in sd_upscalers]}),
+    "SCUNET_tile": OptionInfo(256, "Tile size for SCUNET upscalers. 0 = no tiling.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+    "SCUNET_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for SCUNET upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}),
 }))
 
 options_templates.update(options_section(('face-restoration', "Face restoration"), {
@@ -330,6 +351,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }),
     "CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
     "upcast_attn": OptionInfo(False, "Upcast cross attention layer to float32"),
+    "randn_source": OptionInfo("GPU", "Random number generator source. Changes seeds drastically. Use CPU to produce the same picture across different vidocard vendors.", gr.Radio, {"choices": ["GPU", "CPU"]}),
 }))
 
 options_templates.update(options_section(('compatibility', "Compatibility"), {
@@ -337,6 +359,7 @@ options_templates.update(options_section(('compatibility', "Compatibility"), {
     "use_old_karras_scheduler_sigmas": OptionInfo(False, "Use old karras scheduler sigmas (0.1 to 10)."),
     "no_dpmpp_sde_batch_determinism": OptionInfo(False, "Do not make DPM++ SDE deterministic across different batch sizes."),
     "use_old_hires_fix_width_height": OptionInfo(False, "For hires fix, use width/height sliders to set final resolution rather than first pass (disables Upscale by, Resize width/height to)."),
+    "dont_fix_second_order_samplers_schedule": OptionInfo(False, "Do not fix prompt schedule for second order samplers."),
 }))
 
 options_templates.update(options_section(('interrogate', "Interrogate Options"), {
@@ -360,7 +383,7 @@ options_templates.update(options_section(('extra_networks', "Extra Networks"), {
     "extra_networks_card_width": OptionInfo(0, "Card width for Extra Networks (px)"),
     "extra_networks_card_height": OptionInfo(0, "Card height for Extra Networks (px)"),
     "extra_networks_add_text_separator": OptionInfo(" ", "Extra text to add before <...> when adding extra network to prompt"),
-    "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": [""] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
+    "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
 }))
 
 options_templates.update(options_section(('ui', "User interface"), {
@@ -381,11 +404,13 @@ options_templates.update(options_section(('ui', "User interface"), {
     "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row"),
     "keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
     "keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
+    "keyedit_delimiters": OptionInfo(".,\/!?%^*;:{}=`~()", "Ctrl+up/down word delimiters"),
     "quicksettings": OptionInfo("sd_model_checkpoint", "Quicksettings list"),
     "hidden_tabs": OptionInfo([], "Hidden UI tabs (requires restart)", ui_components.DropdownMulti, lambda: {"choices": [x for x in tab_names]}),
     "ui_reorder": OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order"),
     "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order"),
     "localization": OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
+    "gradio_theme": OptionInfo("Default", "Gradio theme (requires restart)", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + gradio_hf_hub_themes})
 }))
 
 options_templates.update(options_section(('ui', "Live previews"), {
@@ -404,6 +429,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
     "eta_ancestral": OptionInfo(1.0, "eta (noise multiplier) for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
     "ddim_discretize": OptionInfo('uniform', "img2img DDIM discretize", gr.Radio, {"choices": ['uniform', 'quad']}),
     's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
+    's_min_uncond': OptionInfo(0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 4.0, "step": 0.01}),
     's_tmin':  OptionInfo(0.0, "sigma tmin",  gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
     's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
     'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}),
@@ -421,7 +447,8 @@ options_templates.update(options_section(('postprocessing', "Postprocessing"), {
 }))
 
 options_templates.update(options_section((None, "Hidden options"), {
-    "disabled_extensions": OptionInfo([], "Disable those extensions"),
+    "disabled_extensions": OptionInfo([], "Disable these extensions"),
+    "disable_all_extensions": OptionInfo("none", "Disable all extensions (preserves the list of disabled extensions)", gr.Radio, {"choices": ["none", "extra", "all"]}),
     "sd_checkpoint_hash": OptionInfo("", "SHA256 hash of the current checkpoint"),
 }))
 
@@ -598,6 +625,24 @@ clip_model = None
 
 progress_print_out = sys.stdout
 
+gradio_theme = gr.themes.Base()
+
+
+def reload_gradio_theme(theme_name=None):
+    global gradio_theme
+    if not theme_name:
+        theme_name = opts.gradio_theme
+
+    if theme_name == "Default":
+        gradio_theme = gr.themes.Default()
+    else:
+        try:
+            gradio_theme = gr.themes.ThemeClass.from_hub(theme_name)
+        except requests.exceptions.ConnectionError:
+            print("Can't access HuggingFace Hub, falling back to default Gradio theme")
+            gradio_theme = gr.themes.Default()
+
+
 
 class TotalTQDM:
     def __init__(self):

modules/styles.py

@@ -72,16 +72,14 @@ class StyleDatabase:
         return apply_styles_to_prompt(prompt, [self.styles.get(x, self.no_style).negative_prompt for x in styles])
 
     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")
+        # Always keep a backup file around
+        if os.path.exists(path):
+            shutil.copy(path, path + ".bak")
+
+        fd = os.open(path, os.O_RDWR|os.O_CREAT)
         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)
             writer.writeheader()
             writer.writerows(style._asdict() for k,     style in self.styles.items())
-
-        # Always keep a backup file around
-        if os.path.exists(path):
-            shutil.move(path, path + ".bak")
-        shutil.move(temp_path, path)

modules/textual_inversion/textual_inversion.py

@@ -233,6 +233,12 @@ class EmbeddingDatabase:
             self.load_from_dir(embdir)
             embdir.update()
 
+        # re-sort word_embeddings because load_from_dir may not load in alphabetic order.
+        # using a temporary copy so we don't reinitialize self.word_embeddings in case other objects have a reference to it.
+        sorted_word_embeddings = {e.name: e for e in sorted(self.word_embeddings.values(), key=lambda e: e.name.lower())}
+        self.word_embeddings.clear()
+        self.word_embeddings.update(sorted_word_embeddings)
+
         displayed_embeddings = (tuple(self.word_embeddings.keys()), tuple(self.skipped_embeddings.keys()))
         if self.previously_displayed_embeddings != displayed_embeddings:
             self.previously_displayed_embeddings = displayed_embeddings

modules/ui.py

@@ -70,17 +70,6 @@ def gr_show(visible=True):
 sample_img2img = "assets/stable-samples/img2img/sketch-mountains-input.jpg"
 sample_img2img = sample_img2img if os.path.exists(sample_img2img) else None
 
-css_hide_progressbar = """
-.wrap .m-12 svg { display:none!important; }
-.wrap .m-12::before { content:"Loading..." }
-.wrap .z-20 svg { display:none!important; }
-.wrap .z-20::before { content:"Loading..." }
-.wrap.cover-bg .z-20::before { content:"" }
-.progress-bar { display:none!important; }
-.meta-text { display:none!important; }
-.meta-text-center { display:none!important; }
-"""
-
 # Using constants for these since the variation selector isn't visible.
 # Important that they exactly match script.js for tooltip to work.
 random_symbol = '\U0001f3b2\ufe0f'  # 🎲️
@@ -182,8 +171,8 @@ def create_seed_inputs(target_interface):
     with FormRow(elem_id=target_interface + '_seed_row', variant="compact"):
         seed = (gr.Textbox if cmd_opts.use_textbox_seed else gr.Number)(label='Seed', value=-1, elem_id=target_interface + '_seed')
         seed.style(container=False)
-        random_seed = ToolButton(random_symbol, elem_id=target_interface + '_random_seed')
-        reuse_seed = ToolButton(reuse_symbol, elem_id=target_interface + '_reuse_seed')
+        random_seed = ToolButton(random_symbol, elem_id=target_interface + '_random_seed', label='Random seed')
+        reuse_seed = ToolButton(reuse_symbol, elem_id=target_interface + '_reuse_seed', label='Reuse seed')
 
         seed_checkbox = gr.Checkbox(label='Extra', elem_id=target_interface + '_subseed_show', value=False)
 
@@ -479,7 +468,7 @@ def create_ui():
                                 height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
 
                             with gr.Column(elem_id="txt2img_dimensions_row", scale=1, elem_classes="dimensions-tools"):
-                                res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn")
+                                res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn", label="Switch dims")
 
                             if opts.dimensions_and_batch_together:
                                 with gr.Column(elem_id="txt2img_column_batch"):
@@ -1215,7 +1204,7 @@ def create_ui():
 
             with gr.Column(elem_id='ti_gallery_container'):
                 ti_output = gr.Text(elem_id="ti_output", value="", show_label=False)
-                ti_gallery = gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery').style(grid=4)
+                ti_gallery = gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery').style(columns=4)
                 ti_progress = gr.HTML(elem_id="ti_progress", value="")
                 ti_outcome = gr.HTML(elem_id="ti_error", value="")
 
@@ -1566,22 +1555,6 @@ def create_ui():
         (train_interface, "Train", "ti"),
     ]
 
-    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(data_path, "user.css")):
-        with open(os.path.join(data_path, "user.css"), "r", encoding="utf8") as file:
-            css += file.read() + "\n"
-
-    if not cmd_opts.no_progressbar_hiding:
-        css += css_hide_progressbar
-
     interfaces += script_callbacks.ui_tabs_callback()
     interfaces += [(settings_interface, "Settings", "settings")]
 
@@ -1592,7 +1565,7 @@ def create_ui():
     for _interface, label, _ifid in interfaces:
         shared.tab_names.append(label)
 
-    with gr.Blocks(css=css, analytics_enabled=False, title="Stable Diffusion") as demo:
+    with gr.Blocks(theme=shared.gradio_theme, analytics_enabled=False, title="Stable Diffusion") as demo:
         with gr.Row(elem_id="quicksettings", variant="compact"):
             for i, k, item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])):
                 component = create_setting_component(k, is_quicksettings=True)
@@ -1655,6 +1628,7 @@ def create_ui():
             fn=get_settings_values,
             inputs=[],
             outputs=[component_dict[k] for k in component_keys],
+            queue=False,
         )
 
         def modelmerger(*args):
@@ -1731,7 +1705,7 @@ def create_ui():
                 if init_field is not None:
                     init_field(saved_value)
 
-        if type(x) in [gr.Slider, gr.Radio, gr.Checkbox, gr.Textbox, gr.Number, gr.Dropdown] and x.visible:
+        if type(x) in [gr.Slider, gr.Radio, gr.Checkbox, gr.Textbox, gr.Number, gr.Dropdown, ToolButton] and x.visible:
             apply_field(x, 'visible')
 
         if type(x) == gr.Slider:
@@ -1777,25 +1751,60 @@ def create_ui():
     return demo
 
 
-def reload_javascript():
+def webpath(fn):
+    if fn.startswith(script_path):
+        web_path = os.path.relpath(fn, script_path).replace('\\', '/')
+    else:
+        web_path = os.path.abspath(fn)
+
+    return f'file={web_path}?{os.path.getmtime(fn)}'
+
+
+def javascript_html():
     script_js = os.path.join(script_path, "script.js")
-    head = f'<script type="text/javascript" src="file={os.path.abspath(script_js)}?{os.path.getmtime(script_js)}"></script>\n'
+    head = f'<script type="text/javascript" src="{webpath(script_js)}"></script>\n'
 
     inline = f"{localization.localization_js(shared.opts.localization)};"
     if cmd_opts.theme is not None:
         inline += f"set_theme('{cmd_opts.theme}');"
 
     for script in modules.scripts.list_scripts("javascript", ".js"):
-        head += f'<script type="text/javascript" src="file={script.path}?{os.path.getmtime(script.path)}"></script>\n'
+        head += f'<script type="text/javascript" src="{webpath(script.path)}"></script>\n'
 
     for script in modules.scripts.list_scripts("javascript", ".mjs"):
-        head += f'<script type="module" src="file={script.path}?{os.path.getmtime(script.path)}"></script>\n'
+        head += f'<script type="module" src="{webpath(script.path)}"></script>\n'
 
     head += f'<script type="text/javascript">{inline}</script>\n'
 
+    return head
+
+
+def css_html():
+    head = ""
+
+    def stylesheet(fn):
+        return f'<link rel="stylesheet" property="stylesheet" href="{webpath(fn)}">'
+
+    for cssfile in modules.scripts.list_files_with_name("style.css"):
+        if not os.path.isfile(cssfile):
+            continue
+
+        head += stylesheet(cssfile)
+
+    if os.path.exists(os.path.join(data_path, "user.css")):
+        head += stylesheet(os.path.join(data_path, "user.css"))
+
+    return head
+
+
+def reload_javascript():
+    js = javascript_html()
+    css = css_html()
+
     def template_response(*args, **kwargs):
         res = shared.GradioTemplateResponseOriginal(*args, **kwargs)
-        res.body = res.body.replace(b'</head>', f'{head}</head>'.encode("utf8"))
+        res.body = res.body.replace(b'</head>', f'{js}</head>'.encode("utf8"))
+        res.body = res.body.replace(b'</body>', f'{css}</body>'.encode("utf8"))
         res.init_headers()
         return res
 

modules/ui_common.py

@@ -125,7 +125,7 @@ Requested path was: {f}
 
     with gr.Column(variant='panel', elem_id=f"{tabname}_results"):
         with gr.Group(elem_id=f"{tabname}_gallery_container"):
-            result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery").style(grid=4)
+            result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery").style(columns=4)
 
         generation_info = None
         with gr.Column():

modules/ui_components.py

@@ -62,3 +62,13 @@ class DropdownMulti(FormComponent, gr.Dropdown):
 
     def get_block_name(self):
         return "dropdown"
+
+
+class DropdownEditable(FormComponent, gr.Dropdown):
+    """Same as gr.Dropdown but allows editing value"""
+    def __init__(self, **kwargs):
+        super().__init__(allow_custom_value=True, **kwargs)
+
+    def get_block_name(self):
+        return "dropdown"
+

modules/ui_extensions.py

@@ -21,7 +21,7 @@ def check_access():
     assert not shared.cmd_opts.disable_extension_access, "extension access disabled because of command line flags"
 
 
-def apply_and_restart(disable_list, update_list):
+def apply_and_restart(disable_list, update_list, disable_all):
     check_access()
 
     disabled = json.loads(disable_list)
@@ -43,6 +43,7 @@ def apply_and_restart(disable_list, update_list):
             print(traceback.format_exc(), file=sys.stderr)
 
     shared.opts.disabled_extensions = disabled
+    shared.opts.disable_all_extensions = disable_all
     shared.opts.save(shared.config_filename)
 
     shared.state.interrupt()
@@ -99,9 +100,13 @@ def extension_table():
         else:
             ext_status = ext.status
 
+        style = ""
+        if shared.opts.disable_all_extensions == "extra" and not ext.is_builtin or shared.opts.disable_all_extensions == "all":
+            style = ' style="color: var(--primary-400)"'
+
         code += f"""
             <tr>
-                <td><label><input class="gr-check-radio gr-checkbox" name="enable_{html.escape(ext.name)}" type="checkbox" {'checked="checked"' if ext.enabled else ''}>{html.escape(ext.name)}</label></td>
+                <td><label{style}><input class="gr-check-radio gr-checkbox" name="enable_{html.escape(ext.name)}" type="checkbox" {'checked="checked"' if ext.enabled else ''}>{html.escape(ext.name)}</label></td>
                 <td>{remote}</td>
                 <td>{ext.version}</td>
                 <td{' class="extension_status"' if ext.remote is not None else ''}>{ext_status}</td>
@@ -124,7 +129,7 @@ def normalize_git_url(url):
     return url
 
 
-def install_extension_from_url(dirname, url):
+def install_extension_from_url(dirname, url, branch_name=None):
     check_access()
 
     assert url, 'No URL specified'
@@ -145,10 +150,17 @@ def install_extension_from_url(dirname, url):
 
     try:
         shutil.rmtree(tmpdir, True)
-        with git.Repo.clone_from(url, tmpdir) as repo:
-            repo.remote().fetch()
-            for submodule in repo.submodules:
-                submodule.update()
+        if not branch_name:
+            # if no branch is specified, use the default branch
+            with git.Repo.clone_from(url, tmpdir) as repo:
+                repo.remote().fetch()
+                for submodule in repo.submodules:
+                    submodule.update()
+        else:
+            with git.Repo.clone_from(url, tmpdir, branch=branch_name) as repo:
+                repo.remote().fetch()
+                for submodule in repo.submodules:
+                    submodule.update()
         try:
             os.rename(tmpdir, target_dir)
         except OSError as err:
@@ -294,16 +306,24 @@ def create_ui():
                 with gr.Row(elem_id="extensions_installed_top"):
                     apply = gr.Button(value="Apply and restart UI", variant="primary")
                     check = gr.Button(value="Check for updates")
+                    extensions_disable_all = gr.Radio(label="Disable all extensions", choices=["none", "extra", "all"], value=shared.opts.disable_all_extensions, elem_id="extensions_disable_all")
                     extensions_disabled_list = gr.Text(elem_id="extensions_disabled_list", visible=False).style(container=False)
                     extensions_update_list = gr.Text(elem_id="extensions_update_list", visible=False).style(container=False)
 
-                info = gr.HTML()
+                html = ""
+                if shared.opts.disable_all_extensions != "none":
+                    html = """
+<span style="color: var(--primary-400);">
+    "Disable all extensions" was set, change it to "none" to load all extensions again
+</span>
+                    """
+                info = gr.HTML(html)
                 extensions_table = gr.HTML(lambda: extension_table())
 
                 apply.click(
                     fn=apply_and_restart,
                     _js="extensions_apply",
-                    inputs=[extensions_disabled_list, extensions_update_list],
+                    inputs=[extensions_disabled_list, extensions_update_list, extensions_disable_all],
                     outputs=[],
                 )
 
@@ -363,13 +383,14 @@ def create_ui():
 
             with gr.TabItem("Install from URL"):
                 install_url = gr.Text(label="URL for extension's git repository")
+                install_branch = gr.Text(label="Specific branch name", placeholder="Leave empty for default main branch")
                 install_dirname = gr.Text(label="Local directory name", placeholder="Leave empty for auto")
                 install_button = gr.Button(value="Install", variant="primary")
                 install_result = gr.HTML(elem_id="extension_install_result")
 
                 install_button.click(
                     fn=modules.ui.wrap_gradio_call(install_extension_from_url, extra_outputs=[gr.update()]),
-                    inputs=[install_dirname, install_url],
+                    inputs=[install_dirname, install_url, install_branch],
                     outputs=[extensions_table, install_result],
                 )
 

modules/ui_postprocessing.py

@@ -13,7 +13,7 @@ def create_ui():
                     extras_image = gr.Image(label="Source", source="upload", interactive=True, type="pil", elem_id="extras_image")
 
                 with gr.TabItem('Batch Process', elem_id="extras_batch_process_tab") as tab_batch:
-                    image_batch = gr.File(label="Batch Process", file_count="multiple", interactive=True, type="file", elem_id="extras_image_batch")
+                    image_batch = gr.Files(label="Batch Process", interactive=True, elem_id="extras_image_batch")
 
                 with gr.TabItem('Batch from Directory', elem_id="extras_batch_directory_tab") as tab_batch_dir:
                     extras_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, placeholder="A directory on the same machine where the server is running.", elem_id="extras_batch_input_dir")