Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_opt

modules/api/api.py

@@ -100,6 +100,7 @@ class Api:
         self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem])
         self.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str])
         self.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem])
+        self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse)
         self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
         self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse)
         self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse)
@@ -121,7 +122,6 @@ class Api:
 
     def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
         populate = txt2imgreq.copy(update={ # Override __init__ params
-            "sd_model": shared.sd_model,
             "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index),
             "do_not_save_samples": True,
             "do_not_save_grid": True
@@ -129,15 +129,14 @@ class Api:
         )
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
-        p = StableDiffusionProcessingTxt2Img(**vars(populate))
-        # Override object param
-
-        shared.state.begin()
 
         with self.queue_lock:
-            processed = process_images(p)
+            p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **vars(populate))
+
+            shared.state.begin()
+            processed = process_images(p)
+            shared.state.end()
 
-        shared.state.end()
 
         b64images = list(map(encode_pil_to_base64, processed.images))
 
@@ -153,7 +152,6 @@ class Api:
             mask = decode_base64_to_image(mask)
 
         populate = img2imgreq.copy(update={ # Override __init__ params
-            "sd_model": shared.sd_model,
             "sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index),
             "do_not_save_samples": True,
             "do_not_save_grid": True,
@@ -165,16 +163,14 @@ class Api:
 
         args = vars(populate)
         args.pop('include_init_images', None)  # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine.
-        p = StableDiffusionProcessingImg2Img(**args)
-
-        p.init_images = [decode_base64_to_image(x) for x in init_images]
-
-        shared.state.begin()
 
         with self.queue_lock:
-            processed = process_images(p)
+            p = StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)
+            p.init_images = [decode_base64_to_image(x) for x in init_images]
 
-        shared.state.end()
+            shared.state.begin()
+            processed = process_images(p)
+            shared.state.end()
 
         b64images = list(map(encode_pil_to_base64, processed.images))
 
@@ -332,6 +328,26 @@ class Api:
     def get_artists(self):
         return [{"name":x[0], "score":x[1], "category":x[2]} for x in shared.artist_db.artists]
 
+    def get_embeddings(self):
+        db = sd_hijack.model_hijack.embedding_db
+
+        def convert_embedding(embedding):
+            return {
+                "step": embedding.step,
+                "sd_checkpoint": embedding.sd_checkpoint,
+                "sd_checkpoint_name": embedding.sd_checkpoint_name,
+                "shape": embedding.shape,
+                "vectors": embedding.vectors,
+            }
+
+        def convert_embeddings(embeddings):
+            return {embedding.name: convert_embedding(embedding) for embedding in embeddings.values()}
+
+        return {
+            "loaded": convert_embeddings(db.word_embeddings),
+            "skipped": convert_embeddings(db.skipped_embeddings),
+        }
+
     def refresh_checkpoints(self):
         shared.refresh_checkpoints()
 

modules/api/models.py

@@ -249,3 +249,13 @@ class ArtistItem(BaseModel):
     score: float = Field(title="Score")
     category: str = Field(title="Category")
 
+class EmbeddingItem(BaseModel):
+    step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available")
+    sd_checkpoint: Optional[str] = Field(title="SD Checkpoint", description="The hash of the checkpoint this embedding was trained on, if available")
+    sd_checkpoint_name: Optional[str] = Field(title="SD Checkpoint Name", description="The name of the checkpoint this embedding was trained on, if available. Note that this is the name that was used by the trainer; for a stable identifier, use `sd_checkpoint` instead")
+    shape: int = Field(title="Shape", description="The length of each individual vector in the embedding")
+    vectors: int = Field(title="Vectors", description="The number of vectors in the embedding")
+
+class EmbeddingsResponse(BaseModel):
+    loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model")
+    skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")

modules/extras.py

@@ -303,6 +303,8 @@ def run_modelmerger(primary_model_name, secondary_model_name, tertiary_model_nam
                 theta_0[key][:, 0:4, :, :] = theta_func2(a[:, 0:4, :, :], b, multiplier)
                 result_is_inpainting_model = True
             else:
+                assert a.shape == b.shape, f'Incompatible shapes for layer {key}: A is {a.shape}, and B is {b.shape}'
+
                 theta_0[key] = theta_func2(a, b, multiplier)
 
             if save_as_half:

modules/generation_parameters_copypaste.py

@@ -1,12 +1,13 @@
 import base64
 import io
+import math
 import os
 import re
 from pathlib import Path
 
 import gradio as gr
 from modules.shared import script_path
-from modules import shared
+from modules import shared, ui_tempdir
 import tempfile
 from PIL import Image
 
@@ -36,9 +37,12 @@ def quote(text):
 
 
 def image_from_url_text(filedata):
-    if type(filedata) == dict and filedata["is_file"]:
+    if type(filedata) == list and len(filedata) > 0 and type(filedata[0]) == dict and filedata[0].get("is_file", False):
+        filedata = filedata[0]
+
+    if type(filedata) == dict and filedata.get("is_file", False):
         filename = filedata["name"]
-        is_in_right_dir = any(Path(temp_dir).resolve() in Path(filename).resolve().parents for temp_dir in shared.demo.temp_dirs)
+        is_in_right_dir = ui_tempdir.check_tmp_file(shared.demo, filename)
         assert is_in_right_dir, 'trying to open image file outside of allowed directories'
 
         return Image.open(filename)
@@ -93,7 +97,7 @@ def integrate_settings_paste_fields(component_dict):
 def create_buttons(tabs_list):
     buttons = {}
     for tab in tabs_list:
-        buttons[tab] = gr.Button(f"Send to {tab}")
+        buttons[tab] = gr.Button(f"Send to {tab}", elem_id=f"{tab}_tab")
     return buttons
 
 
@@ -102,35 +106,57 @@ def bind_buttons(buttons, send_image, send_generate_info):
     bind_list.append([buttons, send_image, send_generate_info])
 
 
+def send_image_and_dimensions(x):
+    if isinstance(x, Image.Image):
+        img = x
+    else:
+        img = image_from_url_text(x)
+
+    if shared.opts.send_size and isinstance(img, Image.Image):
+        w = img.width
+        h = img.height
+    else:
+        w = gr.update()
+        h = gr.update()
+
+    return img, w, h
+
+
 def run_bind():
-    for buttons, send_image, send_generate_info in bind_list:
+    for buttons, source_image_component, send_generate_info in bind_list:
         for tab in buttons:
             button = buttons[tab]
-            if send_image and paste_fields[tab]["init_img"]:
-                if type(send_image) == gr.Gallery:
-                    button.click(
-                        fn=lambda x: image_from_url_text(x),
-                        _js="extract_image_from_gallery",
-                        inputs=[send_image],
-                        outputs=[paste_fields[tab]["init_img"]],
-                    )
-                else:
-                    button.click(
-                        fn=lambda x: x,
-                        inputs=[send_image],
-                        outputs=[paste_fields[tab]["init_img"]],
-                    )
+            destination_image_component = paste_fields[tab]["init_img"]
+            fields = paste_fields[tab]["fields"]
 
-            if send_generate_info and paste_fields[tab]["fields"] is not None:
+            destination_width_component = next(iter([field for field, name in fields if name == "Size-1"] if fields else []), None)
+            destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
+
+            if source_image_component and destination_image_component:
+                if isinstance(source_image_component, gr.Gallery):
+                    func = send_image_and_dimensions if destination_width_component else image_from_url_text
+                    jsfunc = "extract_image_from_gallery"
+                else:
+                    func = send_image_and_dimensions if destination_width_component else lambda x: x
+                    jsfunc = None
+
+                button.click(
+                    fn=func,
+                    _js=jsfunc,
+                    inputs=[source_image_component],
+                    outputs=[destination_image_component, destination_width_component, destination_height_component] if destination_width_component else [destination_image_component],
+                )
+
+            if send_generate_info and fields is not None:
                 if send_generate_info in paste_fields:
-                    paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] +  (['Size-1', 'Size-2'] if shared.opts.send_size else []) + (["Seed"] if shared.opts.send_seed else [])
+                    paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] + (["Seed"] if shared.opts.send_seed else [])
                     button.click(
                         fn=lambda *x: x,
                         inputs=[field for field, name in paste_fields[send_generate_info]["fields"] if name in paste_field_names],
-                        outputs=[field for field, name in paste_fields[tab]["fields"] if name in paste_field_names],
+                        outputs=[field for field, name in fields if name in paste_field_names],
                     )
                 else:
-                    connect_paste(button, paste_fields[tab]["fields"], send_generate_info)
+                    connect_paste(button, fields, send_generate_info)
 
             button.click(
                 fn=None,
@@ -164,6 +190,35 @@ def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
     return None
 
 
+def restore_old_hires_fix_params(res):
+    """for infotexts that specify old First pass size parameter, convert it into
+    width, height, and hr scale"""
+
+    firstpass_width = res.get('First pass size-1', None)
+    firstpass_height = res.get('First pass size-2', None)
+
+    if firstpass_width is None or firstpass_height is None:
+        return
+
+    firstpass_width, firstpass_height = int(firstpass_width), int(firstpass_height)
+    width = int(res.get("Size-1", 512))
+    height = int(res.get("Size-2", 512))
+
+    if firstpass_width == 0 or firstpass_height == 0:
+        # old algorithm for auto-calculating first pass size
+        desired_pixel_count = 512 * 512
+        actual_pixel_count = width * height
+        scale = math.sqrt(desired_pixel_count / actual_pixel_count)
+        firstpass_width = math.ceil(scale * width / 64) * 64
+        firstpass_height = math.ceil(scale * height / 64) * 64
+
+    hr_scale = width / firstpass_width if firstpass_width > 0 else height / firstpass_height
+
+    res['Size-1'] = firstpass_width
+    res['Size-2'] = firstpass_height
+    res['Hires upscale'] = hr_scale
+
+
 def parse_generation_parameters(x: str):
     """parses generation parameters string, the one you see in text field under the picture in UI:
 ```
@@ -221,6 +276,8 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         hypernet_hash = res.get("Hypernet hash", None)
         res["Hypernet"] = find_hypernetwork_key(hypernet_name, hypernet_hash)
 
+    restore_old_hires_fix_params(res)
+
     return res
 
 

modules/images.py

@@ -39,11 +39,14 @@ def image_grid(imgs, batch_size=1, rows=None):
 
     cols = math.ceil(len(imgs) / rows)
 
-    w, h = imgs[0].size
-    grid = Image.new('RGB', size=(cols * w, rows * h), color='black')
+    params = script_callbacks.ImageGridLoopParams(imgs, cols, rows)
+    script_callbacks.image_grid_callback(params)
 
-    for i, img in enumerate(imgs):
-        grid.paste(img, box=(i % cols * w, i // cols * h))
+    w, h = imgs[0].size
+    grid = Image.new('RGB', size=(params.cols * w, params.rows * h), color='black')
+
+    for i, img in enumerate(params.imgs):
+        grid.paste(img, box=(i % params.cols * w, i // params.cols * h))
 
     return grid
 
@@ -227,16 +230,32 @@ def draw_prompt_matrix(im, width, height, all_prompts):
     return draw_grid_annotations(im, width, height, hor_texts, ver_texts)
 
 
-def resize_image(resize_mode, im, width, height):
+def resize_image(resize_mode, im, width, height, upscaler_name=None):
+    """
+    Resizes an image with the specified resize_mode, width, and height.
+
+    Args:
+        resize_mode: The mode to use when resizing the image.
+            0: Resize the image to the specified width and height.
+            1: Resize the image to fill the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, cropping the excess.
+            2: Resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, filling empty with data from image.
+        im: The image to resize.
+        width: The width to resize the image to.
+        height: The height to resize the image to.
+        upscaler_name: The name of the upscaler to use. If not provided, defaults to opts.upscaler_for_img2img.
+    """
+
+    upscaler_name = upscaler_name or opts.upscaler_for_img2img
+
     def resize(im, w, h):
-        if opts.upscaler_for_img2img is None or opts.upscaler_for_img2img == "None" or im.mode == 'L':
+        if upscaler_name is None or upscaler_name == "None" or im.mode == 'L':
             return im.resize((w, h), resample=LANCZOS)
 
         scale = max(w / im.width, h / im.height)
 
         if scale > 1.0:
-            upscalers = [x for x in shared.sd_upscalers if x.name == opts.upscaler_for_img2img]
-            assert len(upscalers) > 0, f"could not find upscaler named {opts.upscaler_for_img2img}"
+            upscalers = [x for x in shared.sd_upscalers if x.name == upscaler_name]
+            assert len(upscalers) > 0, f"could not find upscaler named {upscaler_name}"
 
             upscaler = upscalers[0]
             im = upscaler.scaler.upscale(im, scale, upscaler.data_path)
@@ -525,6 +544,9 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
             image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality, pnginfo=pnginfo_data)
 
         elif extension.lower() in (".jpg", ".jpeg", ".webp"):
+            if image_to_save.mode == 'RGBA':
+                image_to_save = image_to_save.convert("RGB")
+
             image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)
 
             if opts.enable_pnginfo and info is not None:

modules/img2img.py

@@ -162,4 +162,4 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
     if opts.do_not_show_images:
         processed.images = []
 
-    return processed.images, generation_info_js, plaintext_to_html(processed.info)
+    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)

modules/interrogate.py

@@ -135,7 +135,7 @@ class InterrogateModels:
         return caption[0]
 
     def interrogate(self, pil_image):
-        res = None
+        res = ""
 
         try:
 

modules/memmon.py

@@ -71,10 +71,13 @@ class MemUsageMonitor(threading.Thread):
     def read(self):
         if not self.disabled:
             free, total = torch.cuda.mem_get_info()
+            self.data["free"] = free
             self.data["total"] = total
 
             torch_stats = torch.cuda.memory_stats(self.device)
+            self.data["active"] = torch_stats["active.all.current"]
             self.data["active_peak"] = torch_stats["active_bytes.all.peak"]
+            self.data["reserved"] = torch_stats["reserved_bytes.all.current"]
             self.data["reserved_peak"] = torch_stats["reserved_bytes.all.peak"]
             self.data["system_peak"] = total - self.data["min_free"]
 

modules/modelloader.py

@@ -123,6 +123,23 @@ def move_files(src_path: str, dest_path: str, ext_filter: str = None):
         pass
 
 
+builtin_upscaler_classes = []
+forbidden_upscaler_classes = set()
+
+
+def list_builtin_upscalers():
+    load_upscalers()
+
+    builtin_upscaler_classes.clear()
+    builtin_upscaler_classes.extend(Upscaler.__subclasses__())
+
+
+def forbid_loaded_nonbuiltin_upscalers():
+    for cls in Upscaler.__subclasses__():
+        if cls not in builtin_upscaler_classes:
+            forbidden_upscaler_classes.add(cls)
+
+
 def load_upscalers():
     # We can only do this 'magic' method to dynamically load upscalers if they are referenced,
     # so we'll try to import any _model.py files before looking in __subclasses__
@@ -139,6 +156,9 @@ def load_upscalers():
     datas = []
     commandline_options = vars(shared.cmd_opts)
     for cls in Upscaler.__subclasses__():
+        if cls in forbidden_upscaler_classes:
+            continue
+
         name = cls.__name__
         cmd_name = f"{name.lower().replace('upscaler', '')}_models_path"
         scaler = cls(commandline_options.get(cmd_name, None))

modules/processing.py

@@ -239,7 +239,7 @@ class StableDiffusionProcessing():
 
 
 class Processed:
-    def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None):
+    def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None, comments=""):
         self.images = images_list
         self.prompt = p.prompt
         self.negative_prompt = p.negative_prompt
@@ -247,6 +247,7 @@ class Processed:
         self.subseed = subseed
         self.subseed_strength = p.subseed_strength
         self.info = info
+        self.comments = comments
         self.width = p.width
         self.height = p.height
         self.sampler_name = p.sampler_name
@@ -646,7 +647,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
     devices.torch_gc()
 
-    res = Processed(p, output_images, p.all_seeds[0], infotext() + "".join(["\n\n" + x for x in comments]), subseed=p.all_subseeds[0], index_of_first_image=index_of_first_image, infotexts=infotexts)
+    res = Processed(p, output_images, p.all_seeds[0], infotext(), comments="".join(["\n\n" + x for x in comments]), subseed=p.all_subseeds[0], index_of_first_image=index_of_first_image, infotexts=infotexts)
 
     if p.scripts is not None:
         p.scripts.postprocess(p, res)
@@ -657,14 +658,18 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     sampler = None
 
-    def __init__(self, enable_hr: bool=False, denoising_strength: float=0.75, firstphase_width: int=0, firstphase_height: int=0, **kwargs):
+    def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, **kwargs):
         super().__init__(**kwargs)
         self.enable_hr = enable_hr
         self.denoising_strength = denoising_strength
-        self.firstphase_width = firstphase_width
-        self.firstphase_height = firstphase_height
-        self.truncate_x = 0
-        self.truncate_y = 0
+        self.hr_scale = hr_scale
+        self.hr_upscaler = hr_upscaler
+
+        if firstphase_width != 0 or firstphase_height != 0:
+            print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
+            self.hr_scale = self.width / firstphase_width
+            self.width = firstphase_width
+            self.height = firstphase_height
 
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
@@ -673,47 +678,29 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             else:
                 state.job_count = state.job_count * 2
 
-            self.extra_generation_params["First pass size"] = f"{self.firstphase_width}x{self.firstphase_height}"
-
-            if self.firstphase_width == 0 or self.firstphase_height == 0:
-                desired_pixel_count = 512 * 512
-                actual_pixel_count = self.width * self.height
-                scale = math.sqrt(desired_pixel_count / actual_pixel_count)
-                self.firstphase_width = math.ceil(scale * self.width / 64) * 64
-                self.firstphase_height = math.ceil(scale * self.height / 64) * 64
-                firstphase_width_truncated = int(scale * self.width)
-                firstphase_height_truncated = int(scale * self.height)
-
-            else:
-
-                width_ratio = self.width / self.firstphase_width
-                height_ratio = self.height / self.firstphase_height
-
-                if width_ratio > height_ratio:
-                    firstphase_width_truncated = self.firstphase_width
-                    firstphase_height_truncated = self.firstphase_width * self.height / self.width
-                else:
-                    firstphase_width_truncated = self.firstphase_height * self.width / self.height
-                    firstphase_height_truncated = self.firstphase_height
-
-            self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f
-            self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f
+            self.extra_generation_params["Hires upscale"] = self.hr_scale
+            if self.hr_upscaler is not None:
+                self.extra_generation_params["Hires upscaler"] = self.hr_upscaler
 
     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
+        latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest")
+        if self.enable_hr and latent_scale_mode is None:
+            assert len([x for x in shared.sd_upscalers if x.name == self.hr_upscaler]) > 0, f"could not find upscaler named {self.hr_upscaler}"
+
+        x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
+
         if not self.enable_hr:
-            x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-            samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
             return samples
 
-        x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x, self.firstphase_width, self.firstphase_height))
+        target_width = int(self.width * self.hr_scale)
+        target_height = int(self.height * self.hr_scale)
 
-        samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
-
-        """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
         def save_intermediate(image, index):
+            """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
+
             if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix:
                 return
 
@@ -722,11 +709,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
             images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
 
-        if opts.use_scale_latent_for_hires_fix:
+        if latent_scale_mode is not None:
             for i in range(samples.shape[0]):
                 save_intermediate(samples, i)
 
-            samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
+            samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode)
 
             # Avoid making the inpainting conditioning unless necessary as
             # this does need some extra compute to decode / encode the image again.
@@ -746,7 +733,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
                 save_intermediate(image, i)
 
-                image = images.resize_image(0, image, self.width, self.height)
+                image = images.resize_image(0, image, target_width, target_height, upscaler_name=self.hr_upscaler)
                 image = np.array(image).astype(np.float32) / 255.0
                 image = np.moveaxis(image, 2, 0)
                 batch_images.append(image)
@@ -763,7 +750,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
-        noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+        noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, p=self)
 
         # GC now before running the next img2img to prevent running out of memory
         x = None

modules/script_callbacks.py

@@ -51,6 +51,13 @@ class UiTrainTabParams:
         self.txt2img_preview_params = txt2img_preview_params
 
 
+class ImageGridLoopParams:
+    def __init__(self, imgs, cols, rows):
+        self.imgs = imgs
+        self.cols = cols
+        self.rows = rows
+
+
 ScriptCallback = namedtuple("ScriptCallback", ["script", "callback"])
 callback_map = dict(
     callbacks_app_started=[],
@@ -63,6 +70,7 @@ callback_map = dict(
     callbacks_cfg_denoiser=[],
     callbacks_before_component=[],
     callbacks_after_component=[],
+    callbacks_image_grid=[],
 )
 
 
@@ -155,6 +163,14 @@ def after_component_callback(component, **kwargs):
             report_exception(c, 'after_component_callback')
 
 
+def image_grid_callback(params: ImageGridLoopParams):
+    for c in callback_map['callbacks_image_grid']:
+        try:
+            c.callback(params)
+        except Exception:
+            report_exception(c, 'image_grid')
+
+
 def add_callback(callbacks, fun):
     stack = [x for x in inspect.stack() if x.filename != __file__]
     filename = stack[0].filename if len(stack) > 0 else 'unknown file'
@@ -255,3 +271,11 @@ def on_before_component(callback):
 def on_after_component(callback):
     """register a function to be called after a component is created. See on_before_component for more."""
     add_callback(callback_map['callbacks_after_component'], callback)
+
+
+def on_image_grid(callback):
+    """register a function to be called before making an image grid.
+    The callback is called with one argument:
+       - params: ImageGridLoopParams - parameters to be used for grid creation. Can be modified.
+    """
+    add_callback(callback_map['callbacks_image_grid'], callback)

modules/sd_hijack.py

@@ -5,7 +5,7 @@ import modules.textual_inversion.textual_inversion
 from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint
 from modules.hypernetworks import hypernetwork
 from modules.shared import cmd_opts
-from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet
+from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
 
 import ldm.modules.attention
 import ldm.modules.diffusionmodules.model
@@ -65,6 +65,7 @@ def fix_checkpoint():
     ldm.modules.diffusionmodules.openaimodel.ResBlock.forward = sd_hijack_checkpoint.ResBlock_forward
     ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward = sd_hijack_checkpoint.AttentionBlock_forward
 
+
 class StableDiffusionModelHijack:
     fixes = None
     comments = []
@@ -75,17 +76,25 @@ class StableDiffusionModelHijack:
     embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir)
 
     def hijack(self, m):
-        if type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
+
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+            model_embeddings = m.cond_stage_model.roberta.embeddings
+            model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
+            m.cond_stage_model = sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords(m.cond_stage_model, self)
+
+        elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
             model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
             model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self)
             m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
+
         elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder:
             m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
             m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
 
-        self.clip = m.cond_stage_model
-
         apply_optimizations()
+
+        self.clip = m.cond_stage_model
+        
         fix_checkpoint()
 
         def flatten(el):
@@ -98,7 +107,11 @@ class StableDiffusionModelHijack:
         self.layers = flatten(m)
 
     def undo_hijack(self, m):
-        if type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
+
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+            m.cond_stage_model = m.cond_stage_model.wrapped 
+
+        elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
             m.cond_stage_model = m.cond_stage_model.wrapped
 
             model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
@@ -126,8 +139,8 @@ class StableDiffusionModelHijack:
 
     def tokenize(self, text):
         _, remade_batch_tokens, _, _, _, token_count = self.clip.process_text([text])
-        return remade_batch_tokens[0], token_count, sd_hijack_clip.get_target_prompt_token_count(token_count)
 
+        return remade_batch_tokens[0], token_count, sd_hijack_clip.get_target_prompt_token_count(token_count)
 
 
 class EmbeddingsWithFixes(torch.nn.Module):

modules/sd_hijack_clip.py

@@ -5,7 +5,6 @@ import torch
 from modules import prompt_parser, devices
 from modules.shared import opts
 
-
 def get_target_prompt_token_count(token_count):
     return math.ceil(max(token_count, 1) / 75) * 75
 
@@ -254,10 +253,13 @@ class FrozenCLIPEmbedderWithCustomWords(FrozenCLIPEmbedderWithCustomWordsBase):
     def __init__(self, wrapped, hijack):
         super().__init__(wrapped, hijack)
         self.tokenizer = wrapped.tokenizer
-        self.comma_token = [v for k, v in self.tokenizer.get_vocab().items() if k == ',</w>'][0]
+
+        vocab = self.tokenizer.get_vocab()
+
+        self.comma_token = vocab.get(',</w>', None)
 
         self.token_mults = {}
-        tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k]
+        tokens_with_parens = [(k, v) for k, v in vocab.items() if '(' in k or ')' in k or '[' in k or ']' in k]
         for text, ident in tokens_with_parens:
             mult = 1.0
             for c in text:
@@ -296,6 +298,6 @@ class FrozenCLIPEmbedderWithCustomWords(FrozenCLIPEmbedderWithCustomWordsBase):
     def encode_embedding_init_text(self, init_text, nvpt):
         embedding_layer = self.wrapped.transformer.text_model.embeddings
         ids = self.wrapped.tokenizer(init_text, max_length=nvpt, return_tensors="pt", add_special_tokens=False)["input_ids"]
-        embedded = embedding_layer.token_embedding.wrapped(ids.to(devices.device)).squeeze(0)
+        embedded = embedding_layer.token_embedding.wrapped(ids.to(embedding_layer.token_embedding.wrapped.weight.device)).squeeze(0)
 
         return embedded

modules/sd_hijack_inpainting.py

@@ -12,191 +12,6 @@ from ldm.models.diffusion.ddpm import LatentDiffusion
 from ldm.models.diffusion.plms import PLMSSampler
 from ldm.models.diffusion.ddim import DDIMSampler, noise_like
 
-# =================================================================================================
-# Monkey patch DDIMSampler methods from RunwayML repo directly.
-# Adapted from:
-# https://github.com/runwayml/stable-diffusion/blob/main/ldm/models/diffusion/ddim.py
-# =================================================================================================
-@torch.no_grad()
-def sample_ddim(self,
-            S,
-            batch_size,
-            shape,
-            conditioning=None,
-            callback=None,
-            normals_sequence=None,
-            img_callback=None,
-            quantize_x0=False,
-            eta=0.,
-            mask=None,
-            x0=None,
-            temperature=1.,
-            noise_dropout=0.,
-            score_corrector=None,
-            corrector_kwargs=None,
-            verbose=True,
-            x_T=None,
-            log_every_t=100,
-            unconditional_guidance_scale=1.,
-            unconditional_conditioning=None,
-            # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
-            **kwargs
-            ):
-    if conditioning is not None:
-        if isinstance(conditioning, dict):
-            ctmp = conditioning[list(conditioning.keys())[0]]
-            while isinstance(ctmp, list):
-                ctmp = ctmp[0]
-            cbs = ctmp.shape[0]
-            if cbs != batch_size:
-                print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
-        else:
-            if conditioning.shape[0] != batch_size:
-                print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
-
-    self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
-    # sampling
-    C, H, W = shape
-    size = (batch_size, C, H, W)
-    print(f'Data shape for DDIM sampling is {size}, eta {eta}')
-
-    samples, intermediates = self.ddim_sampling(conditioning, size,
-                                                callback=callback,
-                                                img_callback=img_callback,
-                                                quantize_denoised=quantize_x0,
-                                                mask=mask, x0=x0,
-                                                ddim_use_original_steps=False,
-                                                noise_dropout=noise_dropout,
-                                                temperature=temperature,
-                                                score_corrector=score_corrector,
-                                                corrector_kwargs=corrector_kwargs,
-                                                x_T=x_T,
-                                                log_every_t=log_every_t,
-                                                unconditional_guidance_scale=unconditional_guidance_scale,
-                                                unconditional_conditioning=unconditional_conditioning,
-                                                )
-    return samples, intermediates
-
-@torch.no_grad()
-def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
-                    temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
-                    unconditional_guidance_scale=1., unconditional_conditioning=None):
-    b, *_, device = *x.shape, x.device
-
-    if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
-        e_t = self.model.apply_model(x, t, c)
-    else:
-        x_in = torch.cat([x] * 2)
-        t_in = torch.cat([t] * 2)
-        if isinstance(c, dict):
-            assert isinstance(unconditional_conditioning, dict)
-            c_in = dict()
-            for k in c:
-                if isinstance(c[k], list):
-                    c_in[k] = [
-                        torch.cat([unconditional_conditioning[k][i], c[k][i]])
-                        for i in range(len(c[k]))
-                    ]
-                else:
-                    c_in[k] = torch.cat([unconditional_conditioning[k], c[k]])
-        else:
-            c_in = torch.cat([unconditional_conditioning, c])
-        e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
-        e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
-
-    if score_corrector is not None:
-        assert self.model.parameterization == "eps"
-        e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
-
-    alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
-    alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
-    sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
-    sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
-    # select parameters corresponding to the currently considered timestep
-    a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
-    a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
-    sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
-    sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
-
-    # current prediction for x_0
-    pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
-    if quantize_denoised:
-        pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
-    # direction pointing to x_t
-    dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
-    noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
-    if noise_dropout > 0.:
-        noise = torch.nn.functional.dropout(noise, p=noise_dropout)
-    x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
-    return x_prev, pred_x0
-
-
-# =================================================================================================
-# Monkey patch PLMSSampler methods.
-# This one was not actually patched correctly in the RunwayML repo, but we can replicate the changes.
-# Adapted from:
-# https://github.com/CompVis/stable-diffusion/blob/main/ldm/models/diffusion/plms.py
-# =================================================================================================
-@torch.no_grad()
-def sample_plms(self,
-            S,
-            batch_size,
-            shape,
-            conditioning=None,
-            callback=None,
-            normals_sequence=None,
-            img_callback=None,
-            quantize_x0=False,
-            eta=0.,
-            mask=None,
-            x0=None,
-            temperature=1.,
-            noise_dropout=0.,
-            score_corrector=None,
-            corrector_kwargs=None,
-            verbose=True,
-            x_T=None,
-            log_every_t=100,
-            unconditional_guidance_scale=1.,
-            unconditional_conditioning=None,
-            # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
-            **kwargs
-            ):
-    if conditioning is not None:
-        if isinstance(conditioning, dict):
-            ctmp = conditioning[list(conditioning.keys())[0]]
-            while isinstance(ctmp, list):
-                ctmp = ctmp[0]
-            cbs = ctmp.shape[0]
-            if cbs != batch_size:
-                print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
-        else:
-            if conditioning.shape[0] != batch_size:
-                print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
-
-    self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
-    # sampling
-    C, H, W = shape
-    size = (batch_size, C, H, W)
-    print(f'Data shape for PLMS sampling is {size}')
-
-    samples, intermediates = self.plms_sampling(conditioning, size,
-                                                callback=callback,
-                                                img_callback=img_callback,
-                                                quantize_denoised=quantize_x0,
-                                                mask=mask, x0=x0,
-                                                ddim_use_original_steps=False,
-                                                noise_dropout=noise_dropout,
-                                                temperature=temperature,
-                                                score_corrector=score_corrector,
-                                                corrector_kwargs=corrector_kwargs,
-                                                x_T=x_T,
-                                                log_every_t=log_every_t,
-                                                unconditional_guidance_scale=unconditional_guidance_scale,
-                                                unconditional_conditioning=unconditional_conditioning,
-                                                )
-    return samples, intermediates
-
 
 @torch.no_grad()
 def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
@@ -280,44 +95,6 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F
 
     return x_prev, pred_x0, e_t
 
-# =================================================================================================
-# Monkey patch LatentInpaintDiffusion to load the checkpoint with a proper config.
-# Adapted from:
-# https://github.com/runwayml/stable-diffusion/blob/main/ldm/models/diffusion/ddpm.py
-# =================================================================================================
-
-@torch.no_grad()
-def get_unconditional_conditioning(self, batch_size, null_label=None):
-    if null_label is not None:
-        xc = null_label
-        if isinstance(xc, ListConfig):
-            xc = list(xc)
-        if isinstance(xc, dict) or isinstance(xc, list):
-            c = self.get_learned_conditioning(xc)
-        else:
-            if hasattr(xc, "to"):
-                xc = xc.to(self.device)
-            c = self.get_learned_conditioning(xc)
-    else:
-        # todo: get null label from cond_stage_model
-        raise NotImplementedError()
-    c = repeat(c, "1 ... -> b ...", b=batch_size).to(self.device)
-    return c
-
-
-class LatentInpaintDiffusion(LatentDiffusion):
-    def __init__(
-        self,
-        concat_keys=("mask", "masked_image"),
-        masked_image_key="masked_image",
-        *args,
-        **kwargs,
-    ):
-        super().__init__(*args, **kwargs)
-        self.masked_image_key = masked_image_key
-        assert self.masked_image_key in concat_keys
-        self.concat_keys = concat_keys
-
 
 def should_hijack_inpainting(checkpoint_info):
     ckpt_basename = os.path.basename(checkpoint_info.filename).lower()
@@ -326,15 +103,6 @@ def should_hijack_inpainting(checkpoint_info):
 
 
 def do_inpainting_hijack():
-    # most of this stuff seems to no longer be needed because it is already included into SD2.0
     # p_sample_plms is needed because PLMS can't work with dicts as conditionings
-    # this file should be cleaned up later if everything turns out to work fine
-
-    # ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning
-    # ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion
-
-    # ldm.models.diffusion.ddim.DDIMSampler.p_sample_ddim = p_sample_ddim
-    # ldm.models.diffusion.ddim.DDIMSampler.sample = sample_ddim
 
     ldm.models.diffusion.plms.PLMSSampler.p_sample_plms = p_sample_plms
-    # ldm.models.diffusion.plms.PLMSSampler.sample = sample_plms

modules/sd_hijack_xlmr.py

@@ -0,0 +1,34 @@
+import open_clip.tokenizer
+import torch
+
+from modules import sd_hijack_clip, devices
+from modules.shared import opts
+
+
+class FrozenXLMREmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords):
+    def __init__(self, wrapped, hijack):
+        super().__init__(wrapped, hijack)
+
+        self.id_start = wrapped.config.bos_token_id
+        self.id_end = wrapped.config.eos_token_id
+        self.id_pad = wrapped.config.pad_token_id
+
+        self.comma_token = self.tokenizer.get_vocab().get(',', None)  # alt diffusion doesn't have </w> bits for comma
+
+    def encode_with_transformers(self, tokens):
+        # there's no CLIP Skip here because all hidden layers have size of 1024 and the last one uses a
+        # trained layer to transform those 1024 into 768 for unet; so you can't choose which transformer
+        # layer to work with - you have to use the last
+
+        attention_mask = (tokens != self.id_pad).to(device=tokens.device, dtype=torch.int64)
+        features = self.wrapped(input_ids=tokens, attention_mask=attention_mask)
+        z = features['projection_state']
+
+        return z
+
+    def encode_embedding_init_text(self, init_text, nvpt):
+        embedding_layer = self.wrapped.roberta.embeddings
+        ids = self.wrapped.tokenizer(init_text, max_length=nvpt, return_tensors="pt", add_special_tokens=False)["input_ids"]
+        embedded = embedding_layer.token_embedding.wrapped(ids.to(devices.device)).squeeze(0)
+
+        return embedded

modules/sd_models.py

@@ -228,6 +228,8 @@ def load_model_weights(model, checkpoint_info, vae_file="auto"):
     model.sd_model_checkpoint = checkpoint_file
     model.sd_checkpoint_info = checkpoint_info
 
+    model.logvar = model.logvar.to(devices.device)  # fix for training
+
     sd_vae.delete_base_vae()
     sd_vae.clear_loaded_vae()
     vae_file = sd_vae.resolve_vae(checkpoint_file, vae_file=vae_file)
@@ -322,9 +324,12 @@ def load_model(checkpoint_info=None):
     sd_model.eval()
     shared.sd_model = sd_model
 
+    sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)  # Reload embeddings after model load as they may or may not fit the model
+
     script_callbacks.model_loaded_callback(sd_model)
 
     print("Model loaded.")
+
     return sd_model
 
 

modules/sd_samplers.py

@@ -465,7 +465,9 @@ class KDiffusionSampler:
         if p.sampler_noise_scheduler_override:
             sigmas = p.sampler_noise_scheduler_override(steps)
         elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
-            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=0.1, sigma_max=10, device=shared.device)
+            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
+
+            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
         else:
             sigmas = self.model_wrap.get_sigmas(steps)
 

modules/sd_vae.py

@@ -1,5 +1,6 @@
 import torch
 import os
+import collections
 from collections import namedtuple
 from modules import shared, devices, script_callbacks
 from modules.paths import models_path
@@ -30,6 +31,7 @@ base_vae = None
 loaded_vae_file = None
 checkpoint_info = None
 
+checkpoints_loaded = collections.OrderedDict()
 
 def get_base_vae(model):
     if base_vae is not None and checkpoint_info == model.sd_checkpoint_info and model:
@@ -149,13 +151,30 @@ def load_vae(model, vae_file=None):
     global first_load, vae_dict, vae_list, loaded_vae_file
     # save_settings = False
 
+    cache_enabled = shared.opts.sd_vae_checkpoint_cache > 0
+
     if vae_file:
-        assert os.path.isfile(vae_file), f"VAE file doesn't exist: {vae_file}"
-        print(f"Loading VAE weights from: {vae_file}")
-        store_base_vae(model)
-        vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
-        vae_dict_1 = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
-        _load_vae_dict(model, vae_dict_1)
+        if cache_enabled and vae_file in checkpoints_loaded:
+            # use vae checkpoint cache
+            print(f"Loading VAE weights [{get_filename(vae_file)}] from cache")
+            store_base_vae(model)
+            _load_vae_dict(model, checkpoints_loaded[vae_file])
+        else:
+            assert os.path.isfile(vae_file), f"VAE file doesn't exist: {vae_file}"
+            print(f"Loading VAE weights from: {vae_file}")
+            store_base_vae(model)
+            vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
+            vae_dict_1 = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
+            _load_vae_dict(model, vae_dict_1)
+
+            if cache_enabled:
+                # cache newly loaded vae
+                checkpoints_loaded[vae_file] = vae_dict_1.copy()
+
+        # clean up cache if limit is reached
+        if cache_enabled:
+            while len(checkpoints_loaded) > shared.opts.sd_vae_checkpoint_cache + 1: # we need to count the current model
+                checkpoints_loaded.popitem(last=False)  # LRU
 
         # If vae used is not in dict, update it
         # It will be removed on refresh though

modules/shared.py

@@ -23,7 +23,7 @@ demo = None
 sd_model_file = os.path.join(script_path, 'model.ckpt')
 default_sd_model_file = sd_model_file
 parser = argparse.ArgumentParser()
-parser.add_argument("--config", type=str, default=os.path.join(script_path, "v1-inference.yaml"), help="path to config which constructs model",)
+parser.add_argument("--config", type=str, default=os.path.join(script_path, "configs/v1-inference.yaml"), help="path to config which constructs model",)
 parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
 parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to directory with stable diffusion checkpoints")
 parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
@@ -113,6 +113,17 @@ restricted_opts = {
     "outdir_save",
 }
 
+ui_reorder_categories = [
+    "sampler",
+    "dimensions",
+    "cfg",
+    "seed",
+    "checkboxes",
+    "hires_fix",
+    "batch",
+    "scripts",
+]
+
 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 = \
@@ -172,7 +183,7 @@ class State:
     def dict(self):
         obj = {
             "skipped": self.skipped,
-            "interrupted": self.skipped,
+            "interrupted": self.interrupted,
             "job": self.job,
             "job_count": self.job_count,
             "job_no": self.job_no,
@@ -331,7 +342,6 @@ 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": realesrgan_models_names()}),
     "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in sd_upscalers]}),
-    "use_scale_latent_for_hires_fix": OptionInfo(False, "Upscale latent space image when doing hires. fix"),
 }))
 
 options_templates.update(options_section(('face-restoration', "Face restoration"), {
@@ -360,6 +370,7 @@ options_templates.update(options_section(('training', "Training"), {
 options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": list_checkpoint_tiles()}, refresh=refresh_checkpoints),
     "sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
+    "sd_vae_checkpoint_cache": OptionInfo(0, "VAE Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
     "sd_vae": OptionInfo("auto", "SD VAE", gr.Dropdown, lambda: {"choices": sd_vae.vae_list}, refresh=sd_vae.refresh_vae_list),
     "sd_vae_as_default": OptionInfo(False, "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them"),
     "sd_hypernetwork": OptionInfo("None", "Hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
@@ -371,13 +382,17 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "img2img_background_color": OptionInfo("#ffffff", "With img2img, fill image's transparent parts with this color.", gr.ColorPicker, {}),
     "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."),
     "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),
-    "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
     "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
     "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}),
     "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
 }))
 
+options_templates.update(options_section(('compatibility', "Compatibility"), {
+    "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
+    "use_old_karras_scheduler_sigmas": OptionInfo(False, "Use old karras scheduler sigmas (0.1 to 10)."),
+}))
+
 options_templates.update(options_section(('interrogate', "Interrogate Options"), {
     "interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"),
     "interrogate_use_builtin_artists": OptionInfo(True, "Interrogate: use artists from artists.csv"),
@@ -409,7 +424,10 @@ options_templates.update(options_section(('ui', "User interface"), {
     "js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
     "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
     "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
+    "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group"),
+    "dimensions_and_batch_together": OptionInfo(True, "Show Witdth/Height and Batch sliders in same row"),
     'quicksettings': OptionInfo("sd_model_checkpoint", "Quicksettings list"),
+    'ui_reorder': OptionInfo(", ".join(ui_reorder_categories), "txt2img/ing2img UI item 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)),
 }))
 
@@ -543,6 +561,12 @@ opts = Options()
 if os.path.exists(config_filename):
     opts.load(config_filename)
 
+latent_upscale_default_mode = "Latent"
+latent_upscale_modes = {
+    "Latent": "bilinear",
+    "Latent (nearest)": "nearest",
+}
+
 sd_upscalers = []
 
 sd_model = None

modules/textual_inversion/textual_inversion.py

@@ -23,6 +23,8 @@ class Embedding:
         self.vec = vec
         self.name = name
         self.step = step
+        self.shape = None
+        self.vectors = 0
         self.cached_checksum = None
         self.sd_checkpoint = None
         self.sd_checkpoint_name = None
@@ -57,8 +59,10 @@ class EmbeddingDatabase:
     def __init__(self, embeddings_dir):
         self.ids_lookup = {}
         self.word_embeddings = {}
+        self.skipped_embeddings = {}
         self.dir_mtime = None
         self.embeddings_dir = embeddings_dir
+        self.expected_shape = -1
 
     def register_embedding(self, embedding, model):
 
@@ -75,20 +79,24 @@ class EmbeddingDatabase:
 
         return embedding
 
-    def load_textual_inversion_embeddings(self):
+    def get_expected_shape(self):
+        vec = shared.sd_model.cond_stage_model.encode_embedding_init_text(",", 1)
+        return vec.shape[1]
+
+    def load_textual_inversion_embeddings(self, force_reload = False):
         mt = os.path.getmtime(self.embeddings_dir)
-        if self.dir_mtime is not None and mt <= self.dir_mtime:
+        if not force_reload and self.dir_mtime is not None and mt <= self.dir_mtime:
             return
 
         self.dir_mtime = mt
         self.ids_lookup.clear()
         self.word_embeddings.clear()
+        self.skipped_embeddings.clear()
+        self.expected_shape = self.get_expected_shape()
 
         def process_file(path, filename):
             name = os.path.splitext(filename)[0]
 
-            data = []
-
             if os.path.splitext(filename.upper())[-1] in ['.PNG', '.WEBP', '.JXL', '.AVIF']:
                 embed_image = Image.open(path)
                 if hasattr(embed_image, 'text') and 'sd-ti-embedding' in embed_image.text:
@@ -122,7 +130,13 @@ class EmbeddingDatabase:
             embedding.step = data.get('step', None)
             embedding.sd_checkpoint = data.get('sd_checkpoint', None)
             embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
-            self.register_embedding(embedding, shared.sd_model)
+            embedding.vectors = vec.shape[0]
+            embedding.shape = vec.shape[-1]
+
+            if self.expected_shape == -1 or self.expected_shape == embedding.shape:
+                self.register_embedding(embedding, shared.sd_model)
+            else:
+                self.skipped_embeddings[name] = embedding
 
         for fn in os.listdir(self.embeddings_dir):
             try:
@@ -137,8 +151,9 @@ class EmbeddingDatabase:
                 print(traceback.format_exc(), file=sys.stderr)
                 continue
 
-        print(f"Loaded a total of {len(self.word_embeddings)} textual inversion embeddings.")
-        print("Embeddings:", ', '.join(self.word_embeddings.keys()))
+        print(f"Textual inversion embeddings loaded({len(self.word_embeddings)}): {', '.join(self.word_embeddings.keys())}")
+        if len(self.skipped_embeddings) > 0:
+            print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings.keys())}")
 
     def find_embedding_at_position(self, tokens, offset):
         token = tokens[offset]
@@ -267,7 +282,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
         return embedding, filename
     scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
 
-   # dataset loading may take a while, so input validations and early returns should be done before this
+    # dataset loading may take a while, so input validations and early returns should be done before this
     shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
     old_parallel_processing_allowed = shared.parallel_processing_allowed
 
@@ -295,7 +310,6 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
     loss_step = 0
     _loss_step = 0 #internal
 
-
     last_saved_file = "<none>"
     last_saved_image = "<none>"
     forced_filename = "<none>"

modules/txt2img.py

@@ -8,7 +8,7 @@ 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, *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, hr_scale: float, hr_upscaler: str, *args):
     p = StableDiffusionProcessingTxt2Img(
         sd_model=shared.sd_model,
         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -33,8 +33,8 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
         tiling=tiling,
         enable_hr=enable_hr,
         denoising_strength=denoising_strength if enable_hr else None,
-        firstphase_width=firstphase_width if enable_hr else None,
-        firstphase_height=firstphase_height if enable_hr else None,
+        hr_scale=hr_scale,
+        hr_upscaler=hr_upscaler,
     )
 
     p.scripts = modules.scripts.scripts_txt2img
@@ -59,4 +59,4 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
     if opts.do_not_show_images:
         processed.images = []
 
-    return processed.images, generation_info_js, plaintext_to_html(processed.info)
+    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)

modules/ui.py

@@ -20,6 +20,7 @@ from PIL import Image, PngImagePlugin
 from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call
 
 from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru
+from modules.ui_components import FormRow, FormGroup, ToolButton
 from modules.paths import script_path
 
 from modules.shared import opts, cmd_opts, restricted_opts
@@ -80,7 +81,6 @@ css_hide_progressbar = """
 # Important that they exactly match script.js for tooltip to work.
 random_symbol = '\U0001f3b2\ufe0f'  # 🎲️
 reuse_symbol = '\u267b\ufe0f'  # ♻️
-art_symbol = '\U0001f3a8'  # 🎨
 paste_symbol = '\u2199\ufe0f'  # ↙
 folder_symbol = '\U0001f4c2'  # 📂
 refresh_symbol = '\U0001f504'  # 🔄
@@ -159,7 +159,7 @@ def save_files(js_data, images, do_make_zip, index):
                     zip_file.writestr(filenames[i], f.read())
         fullfns.insert(0, zip_filepath)
 
-    return gr.File.update(value=fullfns, visible=True), '', '', plaintext_to_html(f"Saved: {filenames[0]}")
+    return gr.File.update(value=fullfns, visible=True), plaintext_to_html(f"Saved: {filenames[0]}")
 
 
 
@@ -234,13 +234,6 @@ def check_progress_call_initial(id_part):
     return check_progress_call(id_part)
 
 
-def roll_artist(prompt):
-    allowed_cats = set([x for x in shared.artist_db.categories() if len(opts.random_artist_categories)==0 or x in opts.random_artist_categories])
-    artist = random.choice([x for x in shared.artist_db.artists if x.category in allowed_cats])
-
-    return prompt + ", " + artist.name if prompt != '' else artist.name
-
-
 def visit(x, func, path=""):
     if hasattr(x, 'children'):
         for c in x.children:
@@ -280,35 +273,31 @@ def interrogate_deepbooru(image):
     return gr_show(True) if prompt is None else prompt
 
 
-def create_seed_inputs():
-    with gr.Row():
-        with gr.Box():
-            with gr.Row(elem_id='seed_row'):
-                seed = (gr.Textbox if cmd_opts.use_textbox_seed else gr.Number)(label='Seed', value=-1)
-                seed.style(container=False)
-                random_seed = gr.Button(random_symbol, elem_id='random_seed')
-                reuse_seed = gr.Button(reuse_symbol, elem_id='reuse_seed')
+def create_seed_inputs(target_interface):
+    with FormRow(elem_id=target_interface + '_seed_row'):
+        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 = gr.Button(random_symbol, elem_id=target_interface + '_random_seed')
+        reuse_seed = gr.Button(reuse_symbol, elem_id=target_interface + '_reuse_seed')
 
-        with gr.Box(elem_id='subseed_show_box'):
-            seed_checkbox = gr.Checkbox(label='Extra', elem_id='subseed_show', value=False)
+        with gr.Group(elem_id=target_interface + '_subseed_show_box'):
+            seed_checkbox = gr.Checkbox(label='Extra', elem_id=target_interface + '_subseed_show', value=False)
 
     # Components to show/hide based on the 'Extra' checkbox
     seed_extras = []
 
-    with gr.Row(visible=False) as seed_extra_row_1:
+    with FormRow(visible=False, elem_id=target_interface + '_subseed_row') as seed_extra_row_1:
         seed_extras.append(seed_extra_row_1)
-        with gr.Box():
-            with gr.Row(elem_id='subseed_row'):
-                subseed = gr.Number(label='Variation seed', value=-1)
-                subseed.style(container=False)
-                random_subseed = gr.Button(random_symbol, elem_id='random_subseed')
-                reuse_subseed = gr.Button(reuse_symbol, elem_id='reuse_subseed')
-        subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01)
+        subseed = gr.Number(label='Variation seed', value=-1, elem_id=target_interface + '_subseed')
+        subseed.style(container=False)
+        random_subseed = gr.Button(random_symbol, elem_id=target_interface + '_random_subseed')
+        reuse_subseed = gr.Button(reuse_symbol, elem_id=target_interface + '_reuse_subseed')
+        subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=target_interface + '_subseed_strength')
 
-    with gr.Row(visible=False) as seed_extra_row_2:
+    with FormRow(visible=False) as seed_extra_row_2:
         seed_extras.append(seed_extra_row_2)
-        seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0)
-        seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0)
+        seed_resize_from_w = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from width", value=0, elem_id=target_interface + '_seed_resize_from_w')
+        seed_resize_from_h = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize seed from height", value=0, elem_id=target_interface + '_seed_resize_from_h')
 
     random_seed.click(fn=lambda: -1, show_progress=False, inputs=[], outputs=[seed])
     random_subseed.click(fn=lambda: -1, show_progress=False, inputs=[], outputs=[subseed])
@@ -403,7 +392,6 @@ def create_toprow(is_img2img):
                         )
 
         with gr.Column(scale=1, elem_id="roll_col"):
-            roll = gr.Button(value=art_symbol, elem_id="roll", visible=len(shared.artist_db.artists) > 0)
             paste = gr.Button(value=paste_symbol, elem_id="paste")
             save_style = gr.Button(value=save_style_symbol, elem_id="style_create")
             prompt_style_apply = gr.Button(value=apply_style_symbol, elem_id="style_apply")
@@ -452,7 +440,7 @@ def create_toprow(is_img2img):
                     prompt_style2 = gr.Dropdown(label="Style 2", elem_id=f"{id_part}_style2_index", choices=[k for k, v in shared.prompt_styles.styles.items()], value=next(iter(shared.prompt_styles.styles.keys())))
                     prompt_style2.save_to_config = True
 
-    return prompt, roll, prompt_style, negative_prompt, prompt_style2, submit, button_interrogate, button_deepbooru, prompt_style_apply, save_style, paste, token_counter, token_button
+    return prompt, prompt_style, negative_prompt, prompt_style2, submit, button_interrogate, button_deepbooru, prompt_style_apply, save_style, paste, token_counter, token_button
 
 
 def setup_progressbar(progressbar, preview, id_part, textinfo=None):
@@ -500,7 +488,7 @@ def apply_setting(key, value):
         return
 
     valtype = type(opts.data_labels[key].default)
-    oldval = opts.data[key]
+    oldval = opts.data.get(key, None)
     opts.data[key] = valtype(value) if valtype != type(None) else value
     if oldval != value and opts.data_labels[key].onchange is not None:
         opts.data_labels[key].onchange()
@@ -532,7 +520,7 @@ def create_refresh_button(refresh_component, refresh_method, refreshed_args, ele
 
         return gr.update(**(args or {}))
 
-    refresh_button = gr.Button(value=refresh_symbol, elem_id=elem_id)
+    refresh_button = ToolButton(value=refresh_symbol, elem_id=elem_id)
     refresh_button.click(
         fn=refresh,
         inputs=[],
@@ -570,13 +558,14 @@ Requested path was: {f}
 
             generation_info = None
             with gr.Column():
-                with gr.Row():
+                with gr.Row(elem_id=f"image_buttons_{tabname}"):
+                    open_folder_button = gr.Button(folder_symbol, elem_id="hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder')
+
                     if tabname != "extras":
                         save = gr.Button('Save', elem_id=f'save_{tabname}')
+                        save_zip = gr.Button('Zip', elem_id=f'save_zip_{tabname}')
 
                     buttons = parameters_copypaste.create_buttons(["img2img", "inpaint", "extras"])
-                    button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder'
-                    open_folder_button = gr.Button(folder_symbol, elem_id=button_id)
 
                 open_folder_button.click(
                     fn=lambda: open_folder(opts.outdir_samples or outdir),
@@ -585,14 +574,13 @@ Requested path was: {f}
                 )
 
                 if tabname != "extras":
-                    with gr.Row():
-                        do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
-
                     with gr.Row():
                         download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
 
                     with gr.Group():
                         html_info = gr.HTML()
+                        html_log = gr.HTML()
+
                         generation_info = gr.Textbox(visible=False)
                         if tabname == 'txt2img' or tabname == 'img2img':
                             generation_info_button = gr.Button(visible=False, elem_id=f"{tabname}_generation_info_button")
@@ -606,25 +594,61 @@ Requested path was: {f}
 
                         save.click(
                             fn=wrap_gradio_call(save_files),
-                            _js="(x, y, z, w) => [x, y, z, selected_gallery_index()]",
+                            _js="(x, y, z, w) => [x, y, false, selected_gallery_index()]",
                             inputs=[
                                 generation_info,
                                 result_gallery,
-                                do_make_zip,
+                                html_info,
                                 html_info,
                             ],
                             outputs=[
                                 download_files,
-                                html_info,
-                                html_info,
-                                html_info,
+                                html_log,
                             ]
                         )
+
+                        save_zip.click(
+                            fn=wrap_gradio_call(save_files),
+                            _js="(x, y, z, w) => [x, y, true, selected_gallery_index()]",
+                            inputs=[
+                                generation_info,
+                                result_gallery,
+                                html_info,
+                                html_info,
+                            ],
+                            outputs=[
+                                download_files,
+                                html_log,
+                            ]
+                        )
+
                 else:
                     html_info_x = gr.HTML()
                     html_info = gr.HTML()
+                    html_log = gr.HTML()
+
                 parameters_copypaste.bind_buttons(buttons, result_gallery, "txt2img" if tabname == "txt2img" else None)
-                return result_gallery, generation_info if tabname != "extras" else html_info_x, html_info
+                return result_gallery, generation_info if tabname != "extras" else html_info_x, html_info, html_log
+
+
+def create_sampler_and_steps_selection(choices, tabname):
+    if opts.samplers_in_dropdown:
+        with FormRow(elem_id=f"sampler_selection_{tabname}"):
+            sampler_index = gr.Dropdown(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
+            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+    else:
+        with FormGroup(elem_id=f"sampler_selection_{tabname}"):
+            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+            sampler_index = gr.Radio(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
+
+    return steps, sampler_index
+
+
+def ordered_ui_categories():
+    user_order = {x.strip(): i for i, x in enumerate(shared.opts.ui_reorder.split(","))}
+
+    for i, category in sorted(enumerate(shared.ui_reorder_categories), key=lambda x: user_order.get(x[1], x[0] + 1000)):
+        yield category
 
 
 def create_ui():
@@ -639,14 +663,11 @@ def create_ui():
     modules.scripts.scripts_txt2img.initialize_scripts(is_img2img=False)
 
     with gr.Blocks(analytics_enabled=False) as txt2img_interface:
-        txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _,txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)
+        txt2img_prompt, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _,txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, token_counter, token_button = create_toprow(is_img2img=False)
 
         dummy_component = gr.Label(visible=False)
         txt_prompt_img = gr.File(label="", elem_id="txt2img_prompt_image", file_count="single", type="bytes", visible=False)
 
-
-
-
         with gr.Row(elem_id='txt2img_progress_row'):
             with gr.Column(scale=1):
                 pass
@@ -658,42 +679,57 @@ def create_ui():
 
         with gr.Row().style(equal_height=False):
             with gr.Column(variant='panel', elem_id="txt2img_settings"):
-                steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
-                sampler_index = gr.Radio(label='Sampling method', elem_id="txt2img_sampling", choices=[x.name for x in samplers], value=samplers[0].name, type="index")
+                for category in ordered_ui_categories():
+                    if category == "sampler":
+                        steps, sampler_index = create_sampler_and_steps_selection(samplers, "txt2img")
 
-                with gr.Group():
-                    width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
-                    height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
+                    elif category == "dimensions":
+                        with FormRow():
+                            with gr.Column(elem_id="txt2img_column_size", scale=4):
+                                width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width")
+                                height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
 
-                with gr.Row():
-                    restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1)
-                    tiling = gr.Checkbox(label='Tiling', value=False)
-                    enable_hr = gr.Checkbox(label='Highres. fix', value=False)
+                            if opts.dimensions_and_batch_together:
+                                with gr.Column(elem_id="txt2img_column_batch"):
+                                    batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
+                                    batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
 
-                with gr.Row(visible=False) as hr_options:
-                    firstphase_width = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass width", value=0)
-                    firstphase_height = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass height", value=0)
-                    denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7)
+                    elif category == "cfg":
+                        cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
 
-                with gr.Row(equal_height=True):
-                    batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)
-                    batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)
+                    elif category == "seed":
+                        seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('txt2img')
 
-                cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0)
+                    elif category == "checkboxes":
+                        with FormRow(elem_id="txt2img_checkboxes"):
+                            restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
+                            tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
+                            enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
 
-                seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs()
+                    elif category == "hires_fix":
+                        with FormRow(visible=False, elem_id="txt2img_hires_fix") as hr_options:
+                            hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
+                            hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
+                            denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
 
-                with gr.Group():
-                    custom_inputs = modules.scripts.scripts_txt2img.setup_ui()
+                    elif category == "batch":
+                        if not opts.dimensions_and_batch_together:
+                            with FormRow(elem_id="txt2img_column_batch"):
+                                batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
+                                batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
 
-            txt2img_gallery, generation_info, html_info = create_output_panel("txt2img", opts.outdir_txt2img_samples)
+                    elif category == "scripts":
+                        with FormGroup(elem_id="txt2img_script_container"):
+                            custom_inputs = modules.scripts.scripts_txt2img.setup_ui()
+
+            txt2img_gallery, generation_info, html_info, html_log = create_output_panel("txt2img", opts.outdir_txt2img_samples)
             parameters_copypaste.bind_buttons({"txt2img": txt2img_paste}, None, txt2img_prompt)
 
             connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
             connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
 
             txt2img_args = dict(
-                fn=wrap_gradio_gpu_call(modules.txt2img.txt2img),
+                fn=wrap_gradio_gpu_call(modules.txt2img.txt2img, extra_outputs=[None, '', '']),
                 _js="submit",
                 inputs=[
                     txt2img_prompt,
@@ -713,14 +749,15 @@ def create_ui():
                     width,
                     enable_hr,
                     denoising_strength,
-                    firstphase_width,
-                    firstphase_height,
+                    hr_scale,
+                    hr_upscaler,
                 ] + custom_inputs,
 
                 outputs=[
                     txt2img_gallery,
                     generation_info,
-                    html_info
+                    html_info,
+                    html_log,
                 ],
                 show_progress=False,
             )
@@ -745,17 +782,6 @@ def create_ui():
                 outputs=[hr_options],
             )
 
-            roll.click(
-                fn=roll_artist,
-                _js="update_txt2img_tokens",
-                inputs=[
-                    txt2img_prompt,
-                ],
-                outputs=[
-                    txt2img_prompt,
-                ]
-            )
-
             txt2img_paste_fields = [
                 (txt2img_prompt, "Prompt"),
                 (txt2img_negative_prompt, "Negative prompt"),
@@ -774,8 +800,8 @@ def create_ui():
                 (denoising_strength, "Denoising strength"),
                 (enable_hr, lambda d: "Denoising strength" in d),
                 (hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
-                (firstphase_width, "First pass size-1"),
-                (firstphase_height, "First pass size-2"),
+                (hr_scale, "Hires upscale"),
+                (hr_upscaler, "Hires upscaler"),
                 *modules.scripts.scripts_txt2img.infotext_fields
             ]
             parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields)
@@ -797,8 +823,7 @@ def create_ui():
     modules.scripts.scripts_img2img.initialize_scripts(is_img2img=True)
 
     with gr.Blocks(analytics_enabled=False) as img2img_interface:
-        img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste,token_counter, token_button = create_toprow(is_img2img=True)
-
+        img2img_prompt, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste,token_counter, token_button = create_toprow(is_img2img=True)
 
         with gr.Row(elem_id='img2img_progress_row'):
             img2img_prompt_img = gr.File(label="", elem_id="img2img_prompt_image", file_count="single", type="bytes", visible=False)
@@ -811,14 +836,14 @@ def create_ui():
                 img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)
                 setup_progressbar(progressbar, img2img_preview, 'img2img')
 
-        with gr.Row().style(equal_height=False):
+        with FormRow().style(equal_height=False):
             with gr.Column(variant='panel', elem_id="img2img_settings"):
 
                 with gr.Tabs(elem_id="mode_img2img") as tabs_img2img_mode:
-                    with gr.TabItem('img2img', id='img2img'):
+                    with gr.TabItem('img2img', id='img2img', elem_id="img2img_img2img_tab"):
                         init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_img2img_tool, image_mode="RGBA").style(height=480)
 
-                    with gr.TabItem('Inpaint', id='inpaint'):
+                    with gr.TabItem('Inpaint', id='inpaint', elem_id="img2img_inpaint_tab"):
                         init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_inpaint_tool, image_mode="RGBA").style(height=480)
                         init_img_with_mask_orig = gr.State(None)
 
@@ -836,54 +861,72 @@ def create_ui():
                         init_img_inpaint = gr.Image(label="Image for img2img", show_label=False, source="upload", interactive=True, type="pil", visible=False, elem_id="img_inpaint_base")
                         init_mask_inpaint = gr.Image(label="Mask", source="upload", interactive=True, type="pil", visible=False, elem_id="img_inpaint_mask")
 
-                        with gr.Row():
-                            mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4)
-                            mask_alpha = gr.Slider(label="Mask transparency", interactive=use_color_sketch, visible=use_color_sketch)
+                        with FormRow():
+                            mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4, elem_id="img2img_mask_blur")
+                            mask_alpha = gr.Slider(label="Mask transparency", interactive=use_color_sketch, visible=use_color_sketch, elem_id="img2img_mask_alpha")
 
-                        with gr.Row():
-                            mask_mode = gr.Radio(label="Mask mode", show_label=False, choices=["Draw mask", "Upload mask"], type="index", value="Draw mask", elem_id="mask_mode")
-                            inpainting_mask_invert = gr.Radio(label='Masking mode', show_label=False, choices=['Inpaint masked', 'Inpaint not masked'], value='Inpaint masked', type="index")
+                        with FormRow():
+                            mask_mode = gr.Radio(label="Mask source", choices=["Draw mask", "Upload mask"], type="index", value="Draw mask", elem_id="mask_mode")
+                            inpainting_mask_invert = gr.Radio(label='Mask mode', choices=['Inpaint masked', 'Inpaint not masked'], value='Inpaint masked', type="index", elem_id="img2img_mask_mode")
 
-                        inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='original', type="index")
+                        with FormRow():
+                            inpainting_fill = gr.Radio(label='Masked content', choices=['fill', 'original', 'latent noise', 'latent nothing'], value='original', type="index", elem_id="img2img_inpainting_fill")
 
-                        with gr.Row():
-                            inpaint_full_res = gr.Checkbox(label='Inpaint at full resolution', value=False)
-                            inpaint_full_res_padding = gr.Slider(label='Inpaint at full resolution padding, pixels', minimum=0, maximum=256, step=4, value=32)
+                        with FormRow():
+                            with gr.Column():
+                                inpaint_full_res = gr.Radio(label="Inpaint area", choices=["Whole picture", "Only masked"], type="index", value="Whole picture", elem_id="img2img_inpaint_full_res")
 
-                    with gr.TabItem('Batch img2img', id='batch'):
+                            with gr.Column(scale=4):
+                                inpaint_full_res_padding = gr.Slider(label='Only masked padding, pixels', minimum=0, maximum=256, step=4, value=32, elem_id="img2img_inpaint_full_res_padding")
+
+                    with gr.TabItem('Batch img2img', id='batch', elem_id="img2img_batch_tab"):
                         hidden = '<br>Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else ''
                         gr.HTML(f"<p class=\"text-gray-500\">Process images in a directory on the same machine where the server is running.<br>Use an empty output directory to save pictures normally instead of writing to the output directory.{hidden}</p>")
-                        img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs)
-                        img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs)
+                        img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, elem_id="img2img_batch_input_dir")
+                        img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, elem_id="img2img_batch_output_dir")
 
-                with gr.Row():
-                    resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", show_label=False, choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
+                with FormRow():
+                    resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
 
-                steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
-                sampler_index = gr.Radio(label='Sampling method', choices=[x.name for x in samplers_for_img2img], value=samplers_for_img2img[0].name, type="index")
+                for category in ordered_ui_categories():
+                    if category == "sampler":
+                        steps, sampler_index = create_sampler_and_steps_selection(samplers_for_img2img, "img2img")
 
-                with gr.Group():
-                    width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
-                    height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
+                    elif category == "dimensions":
+                        with FormRow():
+                            with gr.Column(elem_id="img2img_column_size", scale=4):
+                                width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
+                                height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
 
-                with gr.Row():
-                    restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1)
-                    tiling = gr.Checkbox(label='Tiling', value=False)
+                            if opts.dimensions_and_batch_together:
+                                with gr.Column(elem_id="img2img_column_batch"):
+                                    batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
+                                    batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
 
-                with gr.Row():
-                    batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)
-                    batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)
+                    elif category == "cfg":
+                        with FormGroup():
+                            cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
+                            denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
 
-                with gr.Group():
-                    cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0)
-                    denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75)
+                    elif category == "seed":
+                        seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('img2img')
 
-                seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs()
+                    elif category == "checkboxes":
+                        with FormRow(elem_id="img2img_checkboxes"):
+                            restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="img2img_restore_faces")
+                            tiling = gr.Checkbox(label='Tiling', value=False, elem_id="img2img_tiling")
 
-                with gr.Group():
-                    custom_inputs = modules.scripts.scripts_img2img.setup_ui()
+                    elif category == "batch":
+                        if not opts.dimensions_and_batch_together:
+                            with FormRow(elem_id="img2img_column_batch"):
+                                batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
+                                batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
 
-            img2img_gallery, generation_info, html_info = create_output_panel("img2img", opts.outdir_img2img_samples)
+                    elif category == "scripts":
+                        with FormGroup(elem_id="img2img_script_container"):
+                            custom_inputs = modules.scripts.scripts_img2img.setup_ui()
+
+            img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples)
             parameters_copypaste.bind_buttons({"img2img": img2img_paste}, None, img2img_prompt)
 
             connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
@@ -915,7 +958,7 @@ def create_ui():
             )
 
             img2img_args = dict(
-                fn=wrap_gradio_gpu_call(modules.img2img.img2img),
+                fn=wrap_gradio_gpu_call(modules.img2img.img2img, extra_outputs=[None, '', '']),
                 _js="submit_img2img",
                 inputs=[
                     dummy_component,
@@ -954,7 +997,8 @@ def create_ui():
                 outputs=[
                     img2img_gallery,
                     generation_info,
-                    html_info
+                    html_info,
+                    html_log,
                 ],
                 show_progress=False,
             )
@@ -974,18 +1018,6 @@ def create_ui():
                 outputs=[img2img_prompt],
             )
 
-
-            roll.click(
-                fn=roll_artist,
-                _js="update_img2img_tokens",
-                inputs=[
-                    img2img_prompt,
-                ],
-                outputs=[
-                    img2img_prompt,
-                ]
-            )
-
             prompts = [(txt2img_prompt, txt2img_negative_prompt), (img2img_prompt, img2img_negative_prompt)]
             style_dropdowns = [(txt2img_prompt_style, txt2img_prompt_style2), (img2img_prompt_style, img2img_prompt_style2)]
             style_js_funcs = ["update_txt2img_tokens", "update_img2img_tokens"]
@@ -1038,50 +1070,50 @@ def create_ui():
         with gr.Row().style(equal_height=False):
             with gr.Column(variant='panel'):
                 with gr.Tabs(elem_id="mode_extras"):
-                    with gr.TabItem('Single Image'):
-                        extras_image = gr.Image(label="Source", source="upload", interactive=True, type="pil")
+                    with gr.TabItem('Single Image', elem_id="extras_single_tab"):
+                        extras_image = gr.Image(label="Source", source="upload", interactive=True, type="pil", elem_id="extras_image")
 
-                    with gr.TabItem('Batch Process'):
-                        image_batch = gr.File(label="Batch Process", file_count="multiple", interactive=True, type="file")
+                    with gr.TabItem('Batch Process', elem_id="extras_batch_process_tab"):
+                        image_batch = gr.File(label="Batch Process", file_count="multiple", interactive=True, type="file", elem_id="extras_image_batch")
 
-                    with gr.TabItem('Batch from Directory'):
-                        extras_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, placeholder="A directory on the same machine where the server is running.")
-                        extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.")
-                        show_extras_results = gr.Checkbox(label='Show result images', value=True)
+                    with gr.TabItem('Batch from Directory', elem_id="extras_batch_directory_tab"):
+                        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")
+                        extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.", elem_id="extras_batch_output_dir")
+                        show_extras_results = gr.Checkbox(label='Show result images', value=True, elem_id="extras_show_extras_results")
 
                 submit = gr.Button('Generate', elem_id="extras_generate", variant='primary')
 
                 with gr.Tabs(elem_id="extras_resize_mode"):
-                    with gr.TabItem('Scale by'):
-                        upscaling_resize = gr.Slider(minimum=1.0, maximum=8.0, step=0.05, label="Resize", value=4)
-                    with gr.TabItem('Scale to'):
+                    with gr.TabItem('Scale by', elem_id="extras_scale_by_tab"):
+                        upscaling_resize = gr.Slider(minimum=1.0, maximum=8.0, step=0.05, label="Resize", value=4, elem_id="extras_upscaling_resize")
+                    with gr.TabItem('Scale to', elem_id="extras_scale_to_tab"):
                         with gr.Group():
                             with gr.Row():
-                                upscaling_resize_w = gr.Number(label="Width", value=512, precision=0)
-                                upscaling_resize_h = gr.Number(label="Height", value=512, precision=0)
-                            upscaling_crop = gr.Checkbox(label='Crop to fit', value=True)
+                                upscaling_resize_w = gr.Number(label="Width", value=512, precision=0, elem_id="extras_upscaling_resize_w")
+                                upscaling_resize_h = gr.Number(label="Height", value=512, precision=0, elem_id="extras_upscaling_resize_h")
+                            upscaling_crop = gr.Checkbox(label='Crop to fit', value=True, elem_id="extras_upscaling_crop")
 
                 with gr.Group():
                     extras_upscaler_1 = gr.Radio(label='Upscaler 1', elem_id="extras_upscaler_1", choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index")
 
                 with gr.Group():
                     extras_upscaler_2 = gr.Radio(label='Upscaler 2', elem_id="extras_upscaler_2", choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name, type="index")
-                    extras_upscaler_2_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Upscaler 2 visibility", value=1)
+                    extras_upscaler_2_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Upscaler 2 visibility", value=1, elem_id="extras_upscaler_2_visibility")
 
                 with gr.Group():
-                    gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="GFPGAN visibility", value=0, interactive=modules.gfpgan_model.have_gfpgan)
+                    gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="GFPGAN visibility", value=0, interactive=modules.gfpgan_model.have_gfpgan, elem_id="extras_gfpgan_visibility")
 
                 with gr.Group():
-                    codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer visibility", value=0, interactive=modules.codeformer_model.have_codeformer)
-                    codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer weight (0 = maximum effect, 1 = minimum effect)", value=0, interactive=modules.codeformer_model.have_codeformer)
+                    codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer visibility", value=0, interactive=modules.codeformer_model.have_codeformer, elem_id="extras_codeformer_visibility")
+                    codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer weight (0 = maximum effect, 1 = minimum effect)", value=0, interactive=modules.codeformer_model.have_codeformer, elem_id="extras_codeformer_weight")
 
                 with gr.Group():
-                    upscale_before_face_fix = gr.Checkbox(label='Upscale Before Restoring Faces', value=False)
+                    upscale_before_face_fix = gr.Checkbox(label='Upscale Before Restoring Faces', value=False, elem_id="extras_upscale_before_face_fix")
 
-            result_images, html_info_x, html_info = create_output_panel("extras", opts.outdir_extras_samples)
+            result_images, html_info_x, html_info, html_log = create_output_panel("extras", opts.outdir_extras_samples)
 
         submit.click(
-            fn=wrap_gradio_gpu_call(modules.extras.run_extras),
+            fn=wrap_gradio_gpu_call(modules.extras.run_extras, extra_outputs=[None, '']),
             _js="get_extras_tab_index",
             inputs=[
                 dummy_component,
@@ -1123,7 +1155,7 @@ def create_ui():
 
             with gr.Column(variant='panel'):
                 html = gr.HTML()
-                generation_info = gr.Textbox(visible=False)
+                generation_info = gr.Textbox(visible=False, elem_id="pnginfo_generation_info")
                 html2 = gr.HTML()
                 with gr.Row():
                     buttons = parameters_copypaste.create_buttons(["txt2img", "img2img", "inpaint", "extras"])
@@ -1142,23 +1174,27 @@ def create_ui():
 
                 with gr.Row():
                     primary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_primary_model_name", label="Primary model (A)")
+                    create_refresh_button(primary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_A")
+
                     secondary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_secondary_model_name", label="Secondary model (B)")
+                    create_refresh_button(secondary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_B")
+
                     tertiary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_tertiary_model_name", label="Tertiary model (C)")
-                custom_name = gr.Textbox(label="Custom Name (Optional)")
-                interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3)
-                interp_method = gr.Radio(choices=["Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method")
+                    create_refresh_button(tertiary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_C")
+
+                custom_name = gr.Textbox(label="Custom Name (Optional)", elem_id="modelmerger_custom_name")
+                interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3, elem_id="modelmerger_interp_amount")
+                interp_method = gr.Radio(choices=["Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
 
                 with gr.Row():
-                    checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="ckpt", label="Checkpoint format")
-                    save_as_half = gr.Checkbox(value=False, label="Save as float16")
+                    checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="ckpt", label="Checkpoint format", elem_id="modelmerger_checkpoint_format")
+                    save_as_half = gr.Checkbox(value=False, label="Save as float16", elem_id="modelmerger_save_as_half")
 
                 modelmerger_merge = gr.Button(elem_id="modelmerger_merge", label="Merge", variant='primary')
 
             with gr.Column(variant='panel'):
                 submit_result = gr.Textbox(elem_id="modelmerger_result", show_label=False)
 
-    sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings()
-
     with gr.Blocks(analytics_enabled=False) as train_interface:
         with gr.Row().style(equal_height=False):
             gr.HTML(value="<p style='margin-bottom: 0.7em'>See <b><a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\">wiki</a></b> for detailed explanation.</p>")
@@ -1167,58 +1203,58 @@ def create_ui():
             with gr.Tabs(elem_id="train_tabs"):
 
                 with gr.Tab(label="Create embedding"):
-                    new_embedding_name = gr.Textbox(label="Name")
-                    initialization_text = gr.Textbox(label="Initialization text", value="*")
-                    nvpt = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1)
-                    overwrite_old_embedding = gr.Checkbox(value=False, label="Overwrite Old Embedding")
+                    new_embedding_name = gr.Textbox(label="Name", elem_id="train_new_embedding_name")
+                    initialization_text = gr.Textbox(label="Initialization text", value="*", elem_id="train_initialization_text")
+                    nvpt = gr.Slider(label="Number of vectors per token", minimum=1, maximum=75, step=1, value=1, elem_id="train_nvpt")
+                    overwrite_old_embedding = gr.Checkbox(value=False, label="Overwrite Old Embedding", elem_id="train_overwrite_old_embedding")
 
                     with gr.Row():
                         with gr.Column(scale=3):
                             gr.HTML(value="")
 
                         with gr.Column():
-                            create_embedding = gr.Button(value="Create embedding", variant='primary')
+                            create_embedding = gr.Button(value="Create embedding", variant='primary', elem_id="train_create_embedding")
 
                 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", "1024", "320", "640", "1280"])
-                    new_hypernetwork_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'")
-                    new_hypernetwork_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork. Recommended : Swish / Linear(none)", choices=modules.hypernetworks.ui.keys)
-                    new_hypernetwork_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization. Recommended: Kaiming for relu-like, Xavier for sigmoid-like, Normal otherwise", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"])
-                    new_hypernetwork_add_layer_norm = gr.Checkbox(label="Add layer normalization")
-                    new_hypernetwork_use_dropout = gr.Checkbox(label="Use dropout")
-                    overwrite_old_hypernetwork = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork")
+                    new_hypernetwork_name = gr.Textbox(label="Name", elem_id="train_new_hypernetwork_name")
+                    new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "1024", "320", "640", "1280"], elem_id="train_new_hypernetwork_sizes")
+                    new_hypernetwork_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'", elem_id="train_new_hypernetwork_layer_structure")
+                    new_hypernetwork_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork. Recommended : Swish / Linear(none)", choices=modules.hypernetworks.ui.keys, elem_id="train_new_hypernetwork_activation_func")
+                    new_hypernetwork_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization. Recommended: Kaiming for relu-like, Xavier for sigmoid-like, Normal otherwise", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"], elem_id="train_new_hypernetwork_initialization_option")
+                    new_hypernetwork_add_layer_norm = gr.Checkbox(label="Add layer normalization", elem_id="train_new_hypernetwork_add_layer_norm")
+                    new_hypernetwork_use_dropout = gr.Checkbox(label="Use dropout", elem_id="train_new_hypernetwork_use_dropout")
+                    overwrite_old_hypernetwork = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork", elem_id="train_overwrite_old_hypernetwork")
 
                     with gr.Row():
                         with gr.Column(scale=3):
                             gr.HTML(value="")
 
                         with gr.Column():
-                            create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary')
+                            create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary', elem_id="train_create_hypernetwork")
 
                 with gr.Tab(label="Preprocess images"):
-                    process_src = gr.Textbox(label='Source directory')
-                    process_dst = gr.Textbox(label='Destination directory')
-                    process_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
-                    process_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
-                    preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"])
+                    process_src = gr.Textbox(label='Source directory', elem_id="train_process_src")
+                    process_dst = gr.Textbox(label='Destination directory', elem_id="train_process_dst")
+                    process_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_process_width")
+                    process_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_process_height")
+                    preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"], elem_id="train_preprocess_txt_action")
 
                     with gr.Row():
-                        process_flip = gr.Checkbox(label='Create flipped copies')
-                        process_split = gr.Checkbox(label='Split oversized images')
-                        process_focal_crop = gr.Checkbox(label='Auto focal point crop')
-                        process_caption = gr.Checkbox(label='Use BLIP for caption')
-                        process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True)
+                        process_flip = gr.Checkbox(label='Create flipped copies', elem_id="train_process_flip")
+                        process_split = gr.Checkbox(label='Split oversized images', elem_id="train_process_split")
+                        process_focal_crop = gr.Checkbox(label='Auto focal point crop', elem_id="train_process_focal_crop")
+                        process_caption = gr.Checkbox(label='Use BLIP for caption', elem_id="train_process_caption")
+                        process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True, elem_id="train_process_caption_deepbooru")
 
                     with gr.Row(visible=False) as process_split_extra_row:
-                        process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05)
-                        process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05)
+                        process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_split_threshold")
+                        process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="train_process_overlap_ratio")
 
                     with gr.Row(visible=False) as process_focal_crop_row:
-                        process_focal_crop_face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05)
-                        process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05)
-                        process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05)
-                        process_focal_crop_debug = gr.Checkbox(label='Create debug image')
+                        process_focal_crop_face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_face_weight")
+                        process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight")
+                        process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight")
+                        process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
 
                     with gr.Row():
                         with gr.Column(scale=3):
@@ -1226,8 +1262,8 @@ def create_ui():
 
                         with gr.Column():
                             with gr.Row():
-                                interrupt_preprocessing = gr.Button("Interrupt")
-                            run_preprocess = gr.Button(value="Preprocess", variant='primary')
+                                interrupt_preprocessing = gr.Button("Interrupt", elem_id="train_interrupt_preprocessing")
+                            run_preprocess = gr.Button(value="Preprocess", variant='primary', elem_id="train_run_preprocess")
 
                     process_split.change(
                         fn=lambda show: gr_show(show),
@@ -1250,31 +1286,31 @@ def create_ui():
                         train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', elem_id="train_hypernetwork", choices=[x for x in shared.hypernetworks.keys()])
                         create_refresh_button(train_hypernetwork_name, shared.reload_hypernetworks, lambda: {"choices": sorted([x for x in shared.hypernetworks.keys()])}, "refresh_train_hypernetwork_name")
                     with gr.Row():
-                        embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005")
-                        hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001")
+                        embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005", elem_id="train_embedding_learn_rate")
+                        hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001", elem_id="train_hypernetwork_learn_rate")
 
-                    batch_size = gr.Number(label='Batch size', value=1, precision=0)
-                    gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0)
-                    dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images")
-                    log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion")
-                    template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"))
-                    training_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512)
-                    training_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512)
-                    steps = gr.Number(label='Max steps', value=100000, precision=0)
-                    create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0)
-                    save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0)
-                    save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True)
-                    preview_from_txt2img = gr.Checkbox(label='Read parameters (prompt, etc...) from txt2img tab when making previews', value=False)
+                    batch_size = gr.Number(label='Batch size', value=1, precision=0, elem_id="train_batch_size")
+                    gradient_step = gr.Number(label='Gradient accumulation steps', value=1, precision=0, elem_id="train_gradient_step")
+                    dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images", elem_id="train_dataset_directory")
+                    log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion", elem_id="train_log_directory")
+                    template_file = gr.Textbox(label='Prompt template file', value=os.path.join(script_path, "textual_inversion_templates", "style_filewords.txt"), elem_id="train_template_file")
+                    training_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_training_width")
+                    training_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_training_height")
+                    steps = gr.Number(label='Max steps', value=100000, precision=0, elem_id="train_steps")
+                    create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_create_image_every")
+                    save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_save_embedding_every")
+                    save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True, elem_id="train_save_image_with_stored_embedding")
+                    preview_from_txt2img = gr.Checkbox(label='Read parameters (prompt, etc...) from txt2img tab when making previews', value=False, elem_id="train_preview_from_txt2img")
                     with gr.Row():
-                        shuffle_tags = gr.Checkbox(label="Shuffle tags by ',' when creating prompts.", value=False)
-                        tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts.", value=0)
+                        shuffle_tags = gr.Checkbox(label="Shuffle tags by ',' when creating prompts.", value=False, elem_id="train_shuffle_tags")
+                        tag_drop_out = gr.Slider(minimum=0, maximum=1, step=0.1, label="Drop out tags when creating prompts.", value=0, elem_id="train_tag_drop_out")
                     with gr.Row():
-                        latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'])
+                        latent_sampling_method = gr.Radio(label='Choose latent sampling method', value="once", choices=['once', 'deterministic', 'random'], elem_id="train_latent_sampling_method")
 
                     with gr.Row():
-                        interrupt_training = gr.Button(value="Interrupt")
-                        train_hypernetwork = gr.Button(value="Train Hypernetwork", variant='primary')
-                        train_embedding = gr.Button(value="Train Embedding", variant='primary')
+                        interrupt_training = gr.Button(value="Interrupt", elem_id="train_interrupt_training")
+                        train_hypernetwork = gr.Button(value="Train Hypernetwork", variant='primary', elem_id="train_train_hypernetwork")
+                        train_embedding = gr.Button(value="Train Embedding", variant='primary', elem_id="train_train_embedding")
 
                 params = script_callbacks.UiTrainTabParams(txt2img_preview_params)
 
@@ -1447,7 +1483,7 @@ def create_ui():
                 res = comp(label=info.label, value=fun(), elem_id=elem_id, **(args or {}))
                 create_refresh_button(res, info.refresh, info.component_args, "refresh_" + key)
             else:
-                with gr.Row(variant="compact"):
+                with FormRow():
                     res = comp(label=info.label, value=fun(), elem_id=elem_id, **(args or {}))
                     create_refresh_button(res, info.refresh, info.component_args, "refresh_" + key)
         else:
@@ -1492,41 +1528,36 @@ def create_ui():
         return gr.update(value=value), opts.dumpjson()
 
     with gr.Blocks(analytics_enabled=False) as settings_interface:
-        settings_submit = gr.Button(value="Apply settings", variant='primary')
-        result = gr.HTML()
+        with gr.Row():
+            with gr.Column(scale=6):
+                settings_submit = gr.Button(value="Apply settings", variant='primary', elem_id="settings_submit")
+            with gr.Column():
+                restart_gradio = gr.Button(value='Reload UI', variant='primary', elem_id="settings_restart_gradio")
 
-        settings_cols = 3
-        items_per_col = int(len(opts.data_labels) * 0.9 / settings_cols)
+        result = gr.HTML(elem_id="settings_result")
 
         quicksettings_names = [x.strip() for x in opts.quicksettings.split(",")]
-        quicksettings_names = set(x for x in quicksettings_names if x != 'quicksettings')
+        quicksettings_names = {x: i for i, x in enumerate(quicksettings_names) if x != 'quicksettings'}
 
         quicksettings_list = []
 
-        cols_displayed = 0
-        items_displayed = 0
         previous_section = None
-        column = None
-        with gr.Row(elem_id="settings").style(equal_height=False):
+        current_tab = None
+        with gr.Tabs(elem_id="settings"):
             for i, (k, item) in enumerate(opts.data_labels.items()):
                 section_must_be_skipped = item.section[0] is None
 
                 if previous_section != item.section and not section_must_be_skipped:
-                    if cols_displayed < settings_cols and (items_displayed >= items_per_col or previous_section is None):
-                        if column is not None:
-                            column.__exit__()
+                    elem_id, text = item.section
 
-                        column = gr.Column(variant='panel')
-                        column.__enter__()
+                    if current_tab is not None:
+                        current_tab.__exit__()
 
-                        items_displayed = 0
-                        cols_displayed += 1
+                    current_tab = gr.TabItem(elem_id="settings_{}".format(elem_id), label=text)
+                    current_tab.__enter__()
 
                     previous_section = item.section
 
-                    elem_id, text = item.section
-                    gr.HTML(elem_id="settings_header_text_{}".format(elem_id), value='<h1 class="gr-button-lg">{}</h1>'.format(text))
-
                 if k in quicksettings_names and not shared.cmd_opts.freeze_settings:
                     quicksettings_list.append((i, k, item))
                     components.append(dummy_component)
@@ -1536,15 +1567,21 @@ def create_ui():
                     component = create_setting_component(k)
                     component_dict[k] = component
                     components.append(component)
-                    items_displayed += 1
 
-        with gr.Row():
-            request_notifications = gr.Button(value='Request browser notifications', elem_id="request_notifications")
-            download_localization = gr.Button(value='Download localization template', elem_id="download_localization")
+            if current_tab is not None:
+                current_tab.__exit__()
 
-        with gr.Row():
-            reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary')
-            restart_gradio = gr.Button(value='Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)', variant='primary')
+            with gr.TabItem("Actions"):
+                request_notifications = gr.Button(value='Request browser notifications', elem_id="request_notifications")
+                download_localization = gr.Button(value='Download localization template', elem_id="download_localization")
+                reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary', elem_id="settings_reload_script_bodies")
+
+            if os.path.exists("html/licenses.html"):
+                with open("html/licenses.html", encoding="utf8") as file:
+                    with gr.TabItem("Licenses"):
+                        gr.HTML(file.read(), elem_id="licenses")
+
+            gr.Button(value="Show all pages", elem_id="settings_show_all_pages")
 
         request_notifications.click(
             fn=lambda: None,
@@ -1581,9 +1618,6 @@ def create_ui():
             outputs=[],
         )
 
-        if column is not None:
-            column.__exit__()
-
     interfaces = [
         (txt2img_interface, "txt2img", "txt2img"),
         (img2img_interface, "img2img", "img2img"),
@@ -1617,7 +1651,7 @@ def create_ui():
 
     with gr.Blocks(css=css, analytics_enabled=False, title="Stable Diffusion") as demo:
         with gr.Row(elem_id="quicksettings"):
-            for i, k, item in quicksettings_list:
+            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)
                 component_dict[k] = component
 
@@ -1632,6 +1666,10 @@ def create_ui():
         if os.path.exists(os.path.join(script_path, "notification.mp3")):
             audio_notification = gr.Audio(interactive=False, value=os.path.join(script_path, "notification.mp3"), elem_id="audio_notification", visible=False)
 
+        if os.path.exists("html/footer.html"):
+            with open("html/footer.html", encoding="utf8") as file:
+                gr.HTML(file.read(), elem_id="footer")
+
         text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False)
         settings_submit.click(
             fn=wrap_gradio_call(run_settings, extra_outputs=[gr.update()]),
@@ -1666,7 +1704,7 @@ def create_ui():
                 print("Error loading/saving model file:", file=sys.stderr)
                 print(traceback.format_exc(), file=sys.stderr)
                 modules.sd_models.list_models()  # to remove the potentially missing models from the list
-                return ["Error loading/saving model file. It doesn't exist or the name contains illegal characters"] + [gr.Dropdown.update(choices=modules.sd_models.checkpoint_tiles()) for _ in range(3)]
+                return [f"Error merging checkpoints: {e}"] + [gr.Dropdown.update(choices=modules.sd_models.checkpoint_tiles()) for _ in range(4)]
             return results
 
         modelmerger_merge.click(

modules/ui_components.py

@@ -0,0 +1,25 @@
+import gradio as gr
+
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+    """Small button with single emoji as text, fits inside gradio forms"""
+
+    def __init__(self, **kwargs):
+        super().__init__(variant="tool", **kwargs)
+
+    def get_block_name(self):
+        return "button"
+
+
+class FormRow(gr.Row, gr.components.FormComponent):
+    """Same as gr.Row but fits inside gradio forms"""
+
+    def get_block_name(self):
+        return "row"
+
+
+class FormGroup(gr.Group, gr.components.FormComponent):
+    """Same as gr.Row but fits inside gradio forms"""
+
+    def get_block_name(self):
+        return "group"

modules/ui_tempdir.py

@@ -1,6 +1,7 @@
 import os
 import tempfile
 from collections import namedtuple
+from pathlib import Path
 
 import gradio as gr
 
@@ -12,10 +13,29 @@ from modules import shared
 Savedfile = namedtuple("Savedfile", ["name"])
 
 
+def register_tmp_file(gradio, filename):
+    if hasattr(gradio, 'temp_file_sets'):  # gradio 3.15
+        gradio.temp_file_sets[0] = gradio.temp_file_sets[0] | {os.path.abspath(filename)}
+
+    if hasattr(gradio, 'temp_dirs'):  # gradio 3.9
+        gradio.temp_dirs = gradio.temp_dirs | {os.path.abspath(os.path.dirname(filename))}
+
+
+def check_tmp_file(gradio, filename):
+    if hasattr(gradio, 'temp_file_sets'):
+        return any([filename in fileset for fileset in gradio.temp_file_sets])
+
+    if hasattr(gradio, 'temp_dirs'):
+        return any(Path(temp_dir).resolve() in Path(filename).resolve().parents for temp_dir in gradio.temp_dirs)
+
+    return False
+
+
 def save_pil_to_file(pil_image, dir=None):
     already_saved_as = getattr(pil_image, 'already_saved_as', None)
     if already_saved_as and os.path.isfile(already_saved_as):
-        shared.demo.temp_dirs = shared.demo.temp_dirs | {os.path.abspath(os.path.dirname(already_saved_as))}
+        register_tmp_file(shared.demo, already_saved_as)
+
         file_obj = Savedfile(already_saved_as)
         return file_obj
 
@@ -44,7 +64,7 @@ def on_tmpdir_changed():
 
     os.makedirs(shared.opts.temp_dir, exist_ok=True)
 
-    shared.demo.temp_dirs = shared.demo.temp_dirs | {os.path.abspath(shared.opts.temp_dir)}
+    register_tmp_file(shared.demo, os.path.join(shared.opts.temp_dir, "x"))
 
 
 def cleanup_tmpdr():

modules/upscaler.py

@@ -53,10 +53,10 @@ class Upscaler:
     def do_upscale(self, img: PIL.Image, selected_model: str):
         return img
 
-    def upscale(self, img: PIL.Image, scale: int, selected_model: str = None):
+    def upscale(self, img: PIL.Image, scale, selected_model: str = None):
         self.scale = scale
-        dest_w = img.width * scale
-        dest_h = img.height * scale
+        dest_w = int(img.width * scale)
+        dest_h = int(img.height * scale)
 
         for i in range(3):
             shape = (img.width, img.height)

modules/xlmr.py

@@ -0,0 +1,137 @@
+from transformers import BertPreTrainedModel,BertModel,BertConfig
+import torch.nn as nn
+import torch
+from transformers.models.xlm_roberta.configuration_xlm_roberta import XLMRobertaConfig
+from transformers import XLMRobertaModel,XLMRobertaTokenizer
+from typing import Optional
+
+class BertSeriesConfig(BertConfig):
+    def __init__(self, vocab_size=30522, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act="gelu", hidden_dropout_prob=0.1, attention_probs_dropout_prob=0.1, max_position_embeddings=512, type_vocab_size=2, initializer_range=0.02, layer_norm_eps=1e-12, pad_token_id=0, position_embedding_type="absolute", use_cache=True, classifier_dropout=None,project_dim=512, pooler_fn="average",learn_encoder=False,model_type='bert',**kwargs):
+
+        super().__init__(vocab_size, hidden_size, num_hidden_layers, num_attention_heads, intermediate_size, hidden_act, hidden_dropout_prob, attention_probs_dropout_prob, max_position_embeddings, type_vocab_size, initializer_range, layer_norm_eps, pad_token_id, position_embedding_type, use_cache, classifier_dropout, **kwargs)
+        self.project_dim = project_dim
+        self.pooler_fn = pooler_fn
+        self.learn_encoder = learn_encoder
+
+class RobertaSeriesConfig(XLMRobertaConfig):
+    def __init__(self, pad_token_id=1, bos_token_id=0, eos_token_id=2,project_dim=512,pooler_fn='cls',learn_encoder=False, **kwargs):
+        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
+        self.project_dim = project_dim
+        self.pooler_fn = pooler_fn
+        self.learn_encoder = learn_encoder
+
+
+class BertSeriesModelWithTransformation(BertPreTrainedModel):
+
+    _keys_to_ignore_on_load_unexpected = [r"pooler"]
+    _keys_to_ignore_on_load_missing = [r"position_ids", r"predictions.decoder.bias"]
+    config_class = BertSeriesConfig
+
+    def __init__(self, config=None, **kargs):
+        # modify initialization for autoloading 
+        if config is None:
+            config = XLMRobertaConfig()
+            config.attention_probs_dropout_prob= 0.1
+            config.bos_token_id=0
+            config.eos_token_id=2
+            config.hidden_act='gelu'
+            config.hidden_dropout_prob=0.1
+            config.hidden_size=1024
+            config.initializer_range=0.02
+            config.intermediate_size=4096
+            config.layer_norm_eps=1e-05
+            config.max_position_embeddings=514
+
+            config.num_attention_heads=16
+            config.num_hidden_layers=24
+            config.output_past=True
+            config.pad_token_id=1
+            config.position_embedding_type= "absolute"
+
+            config.type_vocab_size= 1
+            config.use_cache=True
+            config.vocab_size= 250002
+            config.project_dim = 768
+            config.learn_encoder = False
+        super().__init__(config)
+        self.roberta = XLMRobertaModel(config)
+        self.transformation = nn.Linear(config.hidden_size,config.project_dim)
+        self.pre_LN=nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.tokenizer = XLMRobertaTokenizer.from_pretrained('xlm-roberta-large')
+        self.pooler = lambda x: x[:,0]
+        self.post_init()
+
+    def encode(self,c):
+        device = next(self.parameters()).device
+        text = self.tokenizer(c,
+                        truncation=True,
+                        max_length=77,
+                        return_length=False,
+                        return_overflowing_tokens=False,
+                        padding="max_length",
+                        return_tensors="pt")
+        text["input_ids"] = torch.tensor(text["input_ids"]).to(device)
+        text["attention_mask"] = torch.tensor(
+            text['attention_mask']).to(device)
+        features = self(**text)
+        return features['projection_state'] 
+
+    def forward(
+        self,
+        input_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        token_type_ids: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.Tensor] = None,
+        head_mask: Optional[torch.Tensor] = None,
+        inputs_embeds: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        output_attentions: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+    ) :
+        r"""
+        """
+
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+
+        outputs = self.roberta(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            position_ids=position_ids,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            encoder_hidden_states=encoder_hidden_states,
+            encoder_attention_mask=encoder_attention_mask,
+            output_attentions=output_attentions,
+            output_hidden_states=True,
+            return_dict=return_dict,
+        )
+
+        # last module outputs
+        sequence_output = outputs[0]
+
+
+        # project every module
+        sequence_output_ln = self.pre_LN(sequence_output)
+
+        # pooler
+        pooler_output = self.pooler(sequence_output_ln)
+        pooler_output = self.transformation(pooler_output)
+        projection_state = self.transformation(outputs.last_hidden_state)
+
+        return {
+            'pooler_output':pooler_output,
+            'last_hidden_state':outputs.last_hidden_state,
+            'hidden_states':outputs.hidden_states,
+            'attentions':outputs.attentions,
+            'projection_state':projection_state,
+            'sequence_out': sequence_output
+        }
+
+
+class RobertaSeriesModelWithTransformation(BertSeriesModelWithTransformation):
+    base_model_prefix = 'roberta'
+    config_class= RobertaSeriesConfig