Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -44,7 +44,7 @@ body:
     id: commit
     attributes:
       label: Commit where the problem happens
-      description: Which commit are you running ? (copy the **Commit hash** shown in the cmd/terminal when you launch the UI)
+      description: Which commit are you running ? (Do not write *Latest version/repo/commit*, as this means nothing and will have changed by the time we read your issue. Rather, copy the **Commit hash** shown in the cmd/terminal when you launch the UI)
     validations:
       required: true
   - type: dropdown

README.md

@@ -72,7 +72,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
 - DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args)
 - [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
-- History tab: view, direct and delete images conveniently within the UI
+- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
 - Generate forever option
 - Training tab
      - hypernetworks and embeddings options
@@ -95,6 +95,16 @@ git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-grad
 After running this command, make sure that you have `aesthetic-gradients` dir in webui's `extensions` directory and restart
 the UI. The interface for Aesthetic Gradients should appear exactly the same as it was.
 
+## Where is History/Image browser?!?!
+Image browser is now an extension. You can install it using git:
+
+```commandline
+git clone https://github.com/yfszzx/stable-diffusion-webui-images-browser extensions/images-browser
+```
+
+After running this command, make sure that you have `images-browser` dir in webui's `extensions` directory and restart
+the UI. The interface for Image browser should appear exactly the same as it was.
+
 ## Installation and Running
 Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
 

javascript/hints.js

@@ -62,8 +62,8 @@ titles = {
 
     "Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
 
-    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.",
+    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
     "Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
 
     "Loopback": "Process an image, use it as an input, repeat.",

javascript/localization.js

@@ -108,6 +108,9 @@ function processNode(node){
 
 function dumpTranslations(){
     dumped = {}
+    if (localization.rtl) {
+        dumped.rtl = true
+    }
 
     Object.keys(original_lines).forEach(function(text){
         if(dumped[text] !== undefined)  return
@@ -129,6 +132,24 @@ onUiUpdate(function(m){
 
 document.addEventListener("DOMContentLoaded", function() {
     processNode(gradioApp())
+
+    if (localization.rtl) {  // if the language is from right to left,
+        (new MutationObserver((mutations, observer) => { // wait for the style to load
+            mutations.forEach(mutation => {
+                mutation.addedNodes.forEach(node => {
+                    if (node.tagName === 'STYLE') {
+                        observer.disconnect();
+
+                        for (const x of node.sheet.rules) {  // find all rtl media rules
+                            if (Array.from(x.media || []).includes('rtl')) {
+                                x.media.appendMedium('all');  // enable them
+                            }
+                        }
+                    }
+                })
+            });
+        })).observe(gradioApp(), { childList: true });
+    }
 })
 
 function download_localization() {

modules/api/api.py

@@ -54,7 +54,7 @@ class Api:
         
         b64images = list(map(encode_pil_to_base64, processed.images))
         
-        return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.info)
+        return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
     def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
         sampler_index = sampler_to_index(img2imgreq.sampler_index)
@@ -93,8 +93,12 @@ class Api:
             processed = process_images(p)
         
         b64images = list(map(encode_pil_to_base64, processed.images))
+
+        if (not img2imgreq.include_init_images):
+            img2imgreq.init_images = None
+            img2imgreq.mask = None
        
-        return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.info)
+        return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
 
     def extras_single_image_api(self, req: ExtrasSingleImageRequest):
         reqDict = setUpscalers(req)

modules/api/models.py

@@ -31,6 +31,7 @@ class ModelDef(BaseModel):
     field_alias: str
     field_type: Any
     field_value: Any
+    field_exclude: bool = False
 
 
 class PydanticModelGenerator:
@@ -78,7 +79,8 @@ class PydanticModelGenerator:
                 field=underscore(fields["key"]), 
                 field_alias=fields["key"], 
                 field_type=fields["type"],
-                field_value=fields["default"]))
+                field_value=fields["default"],
+                field_exclude=fields["exclude"] if "exclude" in fields else False))
 
     def generate_model(self):
         """
@@ -86,7 +88,7 @@ class PydanticModelGenerator:
         from the json and overrides provided at initialization
         """
         fields = {
-            d.field: (d.field_type, Field(default=d.field_value, alias=d.field_alias)) for d in self._model_def
+            d.field: (d.field_type, Field(default=d.field_value, alias=d.field_alias, exclude=d.field_exclude)) for d in self._model_def
         }
         DynamicModel = create_model(self._model_name, **fields)
         DynamicModel.__config__.allow_population_by_field_name = True
@@ -102,7 +104,7 @@ StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
 StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
     "StableDiffusionProcessingImg2Img", 
     StableDiffusionProcessingImg2Img,
-    [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}]
+    [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}]
 ).generate_model()
 
 class TextToImageResponse(BaseModel):

modules/devices.py

@@ -45,7 +45,7 @@ def enable_tf32():
 
 errors.run(enable_tf32, "Enabling TF32")
 
-device = device_interrogate = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = None
+device = device_interrogate = device_gfpgan = device_swinir = device_esrgan = device_scunet = device_codeformer = None
 dtype = torch.float16
 dtype_vae = torch.float16
 
@@ -81,3 +81,7 @@ def autocast(disable=False):
         return contextlib.nullcontext()
 
     return torch.autocast("cuda")
+
+# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
+def mps_contiguous(input_tensor, device): return input_tensor.contiguous() if device.type == 'mps' else input_tensor
+def mps_contiguous_to(input_tensor, device): return mps_contiguous(input_tensor, device).to(device)

modules/esrgan_model.py

@@ -190,7 +190,7 @@ def upscale_without_tiling(model, img):
     img = img[:, :, ::-1]
     img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(devices.device_esrgan)
+    img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_esrgan)
     with torch.no_grad():
         output = model(img)
     output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/hypernetworks/hypernetwork.py

@@ -5,6 +5,7 @@ import html
 import os
 import sys
 import traceback
+import inspect
 
 import modules.textual_inversion.dataset
 import torch
@@ -15,10 +16,12 @@ from modules import devices, processing, sd_models, shared
 from modules.textual_inversion import textual_inversion
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 from torch import einsum
+from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_
 
 from collections import defaultdict, deque
 from statistics import stdev, mean
 
+
 class HypernetworkModule(torch.nn.Module):
     multiplier = 1.0
     activation_dict = {
@@ -26,9 +29,12 @@ class HypernetworkModule(torch.nn.Module):
         "leakyrelu": torch.nn.LeakyReLU,
         "elu": torch.nn.ELU,
         "swish": torch.nn.Hardswish,
+        "tanh": torch.nn.Tanh,
+        "sigmoid": torch.nn.Sigmoid,
     }
+    activation_dict.update({cls_name.lower(): cls_obj for cls_name, cls_obj in inspect.getmembers(torch.nn.modules.activation) if inspect.isclass(cls_obj) and cls_obj.__module__ == 'torch.nn.modules.activation'})
 
-    def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, add_layer_norm=False, use_dropout=False):
+    def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, weight_init='Normal', add_layer_norm=False, use_dropout=False):
         super().__init__()
 
         assert layer_structure is not None, "layer_structure must not be None"
@@ -65,9 +71,24 @@ class HypernetworkModule(torch.nn.Module):
         else:
             for layer in self.linear:
                 if type(layer) == torch.nn.Linear or type(layer) == torch.nn.LayerNorm:
-                    layer.weight.data.normal_(mean=0.0, std=0.01)
-                    layer.bias.data.zero_()
-
+                    w, b = layer.weight.data, layer.bias.data
+                    if weight_init == "Normal" or type(layer) == torch.nn.LayerNorm:
+                        normal_(w, mean=0.0, std=0.01)
+                        normal_(b, mean=0.0, std=0.005)
+                    elif weight_init == 'XavierUniform':
+                        xavier_uniform_(w)
+                        zeros_(b)
+                    elif weight_init == 'XavierNormal':
+                        xavier_normal_(w)
+                        zeros_(b)
+                    elif weight_init == 'KaimingUniform':
+                        kaiming_uniform_(w, nonlinearity='leaky_relu' if 'leakyrelu' == activation_func else 'relu')
+                        zeros_(b)
+                    elif weight_init == 'KaimingNormal':
+                        kaiming_normal_(w, nonlinearity='leaky_relu' if 'leakyrelu' == activation_func else 'relu')
+                        zeros_(b)
+                    else:
+                        raise KeyError(f"Key {weight_init} is not defined as initialization!")
         self.to(devices.device)
 
     def fix_old_state_dict(self, state_dict):
@@ -105,7 +126,7 @@ class Hypernetwork:
     filename = None
     name = None
 
-    def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, add_layer_norm=False, use_dropout=False):
+    def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False):
         self.filename = None
         self.name = name
         self.layers = {}
@@ -114,13 +135,14 @@ class Hypernetwork:
         self.sd_checkpoint_name = None
         self.layer_structure = layer_structure
         self.activation_func = activation_func
+        self.weight_init = weight_init
         self.add_layer_norm = add_layer_norm
         self.use_dropout = use_dropout
 
         for size in enable_sizes or []:
             self.layers[size] = (
-                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
-                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
+                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
+                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
             )
 
     def weights(self):
@@ -144,6 +166,7 @@ class Hypernetwork:
         state_dict['layer_structure'] = self.layer_structure
         state_dict['activation_func'] = self.activation_func
         state_dict['is_layer_norm'] = self.add_layer_norm
+        state_dict['weight_initialization'] = self.weight_init
         state_dict['use_dropout'] = self.use_dropout
         state_dict['sd_checkpoint'] = self.sd_checkpoint
         state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name
@@ -158,15 +181,21 @@ class Hypernetwork:
         state_dict = torch.load(filename, map_location='cpu')
 
         self.layer_structure = state_dict.get('layer_structure', [1, 2, 1])
+        print(self.layer_structure)
         self.activation_func = state_dict.get('activation_func', None)
+        print(f"Activation function is {self.activation_func}")
+        self.weight_init = state_dict.get('weight_initialization', 'Normal')
+        print(f"Weight initialization is {self.weight_init}")
         self.add_layer_norm = state_dict.get('is_layer_norm', False)
+        print(f"Layer norm is set to {self.add_layer_norm}")
         self.use_dropout = state_dict.get('use_dropout', False)
+        print(f"Dropout usage is set to {self.use_dropout}" )
 
         for size, sd in state_dict.items():
             if type(size) == int:
                 self.layers[size] = (
-                    HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
-                    HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.add_layer_norm, self.use_dropout),
+                    HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
+                    HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),
                 )
 
         self.name = state_dict.get('name', self.name)
@@ -458,7 +487,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
 
             if image is not None:
                 shared.state.current_image = image
-                last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename)
+                last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
                 last_saved_image += f", prompt: {preview_text}"
 
         shared.state.job_no = hypernetwork.step

modules/hypernetworks/ui.py

@@ -8,8 +8,9 @@ import modules.textual_inversion.textual_inversion
 from modules import devices, sd_hijack, shared
 from modules.hypernetworks import hypernetwork
 
+keys = list(hypernetwork.HypernetworkModule.activation_dict.keys())
 
-def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, add_layer_norm=False, use_dropout=False):
+def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False):
     # Remove illegal characters from name.
     name = "".join( x for x in name if (x.isalnum() or x in "._- "))
 
@@ -25,6 +26,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
         enable_sizes=[int(x) for x in enable_sizes],
         layer_structure=layer_structure,
         activation_func=activation_func,
+        weight_init=weight_init,
         add_layer_norm=add_layer_norm,
         use_dropout=use_dropout,
     )

modules/images.py

@@ -16,7 +16,7 @@ from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
 from fonts.ttf import Roboto
 import string
 
-from modules import sd_samplers, shared
+from modules import sd_samplers, shared, script_callbacks
 from modules.shared import opts, cmd_opts
 
 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
@@ -277,7 +277,7 @@ invalid_filename_chars = '<>:"/\\|?*\n'
 invalid_filename_prefix = ' '
 invalid_filename_postfix = ' .'
 re_nonletters = re.compile(r'[\s' + string.punctuation + ']+')
-re_pattern = re.compile(r"([^\[\]]+|\[([^]]+)]|[\[\]]*)")
+re_pattern = re.compile(r"(.*?)(?:\[([^\[\]]+)\]|$)")
 re_pattern_arg = re.compile(r"(.*)<([^>]*)>$")
 max_filename_part_length = 128
 
@@ -343,8 +343,11 @@ class FilenameGenerator:
     def datetime(self, *args):
         time_datetime = datetime.datetime.now()
 
-        time_format = args[0] if len(args) > 0 else self.default_time_format
-        time_zone = pytz.timezone(args[1]) if len(args) > 1 else None
+        time_format = args[0] if len(args) > 0 and args[0] != "" else self.default_time_format
+        try:
+            time_zone = pytz.timezone(args[1]) if len(args) > 1 else None
+        except pytz.exceptions.UnknownTimeZoneError as _:
+            time_zone = None
 
         time_zone_time = time_datetime.astimezone(time_zone)
         try:
@@ -359,9 +362,9 @@ class FilenameGenerator:
 
         for m in re_pattern.finditer(x):
             text, pattern = m.groups()
+            res += text
 
             if pattern is None:
-                res += text
                 continue
 
             pattern_args = []
@@ -382,12 +385,9 @@ class FilenameGenerator:
                     print(f"Error adding [{pattern}] to filename", file=sys.stderr)
                     print(traceback.format_exc(), file=sys.stderr)
 
-                if replacement is None:
-                    res += f'[{pattern}]'
-                else:
+                if replacement is not None:
                     res += str(replacement)
-
-                continue
+                    continue
 
             res += f'[{pattern}]'
 
@@ -451,17 +451,6 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     """
     namegen = FilenameGenerator(p, seed, prompt)
 
-    if extension == 'png' and opts.enable_pnginfo and info is not None:
-        pnginfo = PngImagePlugin.PngInfo()
-
-        if existing_info is not None:
-            for k, v in existing_info.items():
-                pnginfo.add_text(k, str(v))
-
-        pnginfo.add_text(pnginfo_section_name, info)
-    else:
-        pnginfo = None
-
     if save_to_dirs is None:
         save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)
 
@@ -474,8 +463,10 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     if forced_filename is None:
         if short_filename or seed is None:
             file_decoration = ""
-        else:
+        elif opts.save_to_dirs:
             file_decoration = opts.samples_filename_pattern or "[seed]"
+        else:
+            file_decoration = opts.samples_filename_pattern or "[seed]-[prompt_spaces]"
 
         add_number = opts.save_images_add_number or file_decoration == ''
 
@@ -487,19 +478,27 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         if add_number:
             basecount = get_next_sequence_number(path, basename)
             fullfn = None
-            fullfn_without_extension = None
             for i in range(500):
                 fn = f"{basecount + i:05}" if basename == '' else f"{basename}-{basecount + i:04}"
                 fullfn = os.path.join(path, f"{fn}{file_decoration}.{extension}")
-                fullfn_without_extension = os.path.join(path, f"{fn}{file_decoration}")
                 if not os.path.exists(fullfn):
                     break
         else:
             fullfn = os.path.join(path, f"{file_decoration}.{extension}")
-            fullfn_without_extension = os.path.join(path, file_decoration)
     else:
         fullfn = os.path.join(path, f"{forced_filename}.{extension}")
-        fullfn_without_extension = os.path.join(path, forced_filename)
+
+    pnginfo = existing_info or {}
+    if info is not None:
+        pnginfo[pnginfo_section_name] = info
+
+    params = script_callbacks.ImageSaveParams(image, p, fullfn, pnginfo)
+    script_callbacks.before_image_saved_callback(params)
+
+    image = params.image
+    fullfn = params.filename
+    info = params.pnginfo.get(pnginfo_section_name, None)
+    fullfn_without_extension, extension = os.path.splitext(params.filename)
 
     def exif_bytes():
         return piexif.dump({
@@ -508,12 +507,20 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
             },
         })
 
-    if extension.lower() in ("jpg", "jpeg", "webp"):
+    if extension.lower() == '.png':
+        pnginfo_data = PngImagePlugin.PngInfo()
+        for k, v in params.pnginfo.items():
+            pnginfo_data.add_text(k, str(v))
+
+        image.save(fullfn, quality=opts.jpeg_quality, pnginfo=pnginfo_data)
+
+    elif extension.lower() in (".jpg", ".jpeg", ".webp"):
         image.save(fullfn, quality=opts.jpeg_quality)
+
         if opts.enable_pnginfo and info is not None:
             piexif.insert(exif_bytes(), fullfn)
     else:
-        image.save(fullfn, quality=opts.jpeg_quality, pnginfo=pnginfo)
+        image.save(fullfn, quality=opts.jpeg_quality)
 
     target_side_length = 4000
     oversize = image.width > target_side_length or image.height > target_side_length
@@ -536,6 +543,8 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     else:
         txt_fullfn = None
 
+    script_callbacks.image_saved_callback(params)
+
     return fullfn, txt_fullfn
 
 

modules/img2img.py

@@ -39,6 +39,8 @@ def process_batch(p, input_dir, output_dir, args):
             break
 
         img = Image.open(image)
+        # Use the EXIF orientation of photos taken by smartphones.
+        img = ImageOps.exif_transpose(img) 
         p.init_images = [img] * p.batch_size
 
         proc = modules.scripts.scripts_img2img.run(p, *args)
@@ -61,19 +63,25 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
     is_batch = mode == 2
 
     if is_inpaint:
+        # Drawn mask
         if mask_mode == 0:
             image = init_img_with_mask['image']
             mask = init_img_with_mask['mask']
             alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')
             mask = ImageChops.lighter(alpha_mask, mask.convert('L')).convert('L')
             image = image.convert('RGB')
+        # Uploaded mask
         else:
             image = init_img_inpaint
             mask = init_mask_inpaint
+    # No mask
     else:
         image = init_img
         mask = None
 
+    # Use the EXIF orientation of photos taken by smartphones.
+    image = ImageOps.exif_transpose(image) 
+
     assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]'
 
     p = StableDiffusionProcessingImg2Img(

modules/processing.py

@@ -77,9 +77,8 @@ def get_correct_sampler(p):
 class StableDiffusionProcessing():
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
-    
     """
-    def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str="", styles: List[str]=None, seed: int=-1, subseed: int=-1, subseed_strength: float=0, seed_resize_from_h: int=-1, seed_resize_from_w: int=-1, seed_enable_extras: bool=True, sampler_index: int=0, batch_size: int=1, n_iter: int=1, steps:int =50, cfg_scale:float=7.0, width:int=512, height:int=512, restore_faces:bool=False, tiling:bool=False, do_not_save_samples:bool=False, do_not_save_grid:bool=False, extra_generation_params: Dict[Any,Any]=None, overlay_images: Any=None, negative_prompt: str=None, eta: float =None, do_not_reload_embeddings: bool=False, denoising_strength: float = 0, ddim_discretize: str = "uniform", s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0):
+    def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_index: int = 0, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None):
         self.sd_model = sd_model
         self.outpath_samples: str = outpath_samples
         self.outpath_grids: str = outpath_grids
@@ -109,13 +108,14 @@ class StableDiffusionProcessing():
         self.do_not_reload_embeddings = do_not_reload_embeddings
         self.paste_to = None
         self.color_corrections = None
-        self.denoising_strength: float = 0
+        self.denoising_strength: float = denoising_strength
         self.sampler_noise_scheduler_override = None
-        self.ddim_discretize = opts.ddim_discretize
+        self.ddim_discretize = ddim_discretize or opts.ddim_discretize
         self.s_churn = s_churn or opts.s_churn
         self.s_tmin = s_tmin or opts.s_tmin
         self.s_tmax = s_tmax or float('inf')  # not representable as a standard ui option
         self.s_noise = s_noise or opts.s_noise
+        self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
 
         if not seed_enable_extras:
             self.subseed = -1
@@ -129,7 +129,6 @@ class StableDiffusionProcessing():
         self.all_seeds = None
         self.all_subseeds = None
 
-
     def init(self, all_prompts, all_seeds, all_subseeds):
         pass
 
@@ -351,6 +350,22 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration
 
 
 def process_images(p: StableDiffusionProcessing) -> Processed:
+    stored_opts = {k: opts.data[k] for k in p.override_settings.keys()}
+
+    try:
+        for k, v in p.override_settings.items():
+            opts.data[k] = v  # we don't call onchange for simplicity which makes changing model, hypernet impossible
+
+        res = process_images_inner(p)
+
+    finally:
+        for k, v in stored_opts.items():
+            opts.data[k] = v
+
+    return res
+
+
+def process_images_inner(p: StableDiffusionProcessing) -> Processed:
     """this is the main loop that both txt2img and img2img use; it calls func_init once inside all the scopes and func_sample once per batch"""
 
     if type(p.prompt) == list:

modules/script_callbacks.py

+import sys
+import traceback
+from collections import namedtuple
+import inspect
 
+
+def report_exception(c, job):
+    print(f"Error executing callback {job} for {c.script}", file=sys.stderr)
+    print(traceback.format_exc(), file=sys.stderr)
+
+
+class ImageSaveParams:
+    def __init__(self, image, p, filename, pnginfo):
+        self.image = image
+        """the PIL image itself"""
+
+        self.p = p
+        """p object with processing parameters; either StableDiffusionProcessing or an object with same fields"""
+
+        self.filename = filename
+        """name of file that the image would be saved to"""
+
+        self.pnginfo = pnginfo
+        """dictionary with parameters for image's PNG info data; infotext will have the key 'parameters'"""
+
+
+ScriptCallback = namedtuple("ScriptCallback", ["script", "callback"])
 callbacks_model_loaded = []
 callbacks_ui_tabs = []
 callbacks_ui_settings = []
+callbacks_before_image_saved = []
+callbacks_image_saved = []
 
 
 def clear_callbacks():
     callbacks_model_loaded.clear()
     callbacks_ui_tabs.clear()
+    callbacks_ui_settings.clear()
+    callbacks_before_image_saved.clear()
+    callbacks_image_saved.clear()
 
 
 def model_loaded_callback(sd_model):
-    for callback in callbacks_model_loaded:
-        callback(sd_model)
+    for c in callbacks_model_loaded:
+        try:
+            c.callback(sd_model)
+        except Exception:
+            report_exception(c, 'model_loaded_callback')
 
 
 def ui_tabs_callback():
     res = []
     
-    for callback in callbacks_ui_tabs:
-        res += callback() or []
+    for c in callbacks_ui_tabs:
+        try:
+            res += c.callback() or []
+        except Exception:
+            report_exception(c, 'ui_tabs_callback')
 
     return res
 
 
 def ui_settings_callback():
-    for callback in callbacks_ui_settings:
-        callback()
+    for c in callbacks_ui_settings:
+        try:
+            c.callback()
+        except Exception:
+            report_exception(c, 'ui_settings_callback')
+
+
+def before_image_saved_callback(params: ImageSaveParams):
+    for c in callbacks_image_saved:
+        try:
+            c.callback(params)
+        except Exception:
+            report_exception(c, 'before_image_saved_callback')
+
+
+def image_saved_callback(params: ImageSaveParams):
+    for c in callbacks_image_saved:
+        try:
+            c.callback(params)
+        except Exception:
+            report_exception(c, 'image_saved_callback')
+
+
+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'
+
+    callbacks.append(ScriptCallback(filename, fun))
 
 
 def on_model_loaded(callback):
     """register a function to be called when the stable diffusion model is created; the model is
     passed as an argument"""
-    callbacks_model_loaded.append(callback)
+    add_callback(callbacks_model_loaded, callback)
 
 
 def on_ui_tabs(callback):
@@ -44,10 +107,26 @@ def on_ui_tabs(callback):
     title is tab text displayed to user in the UI
     elem_id is HTML id for the tab
     """
-    callbacks_ui_tabs.append(callback)
+    add_callback(callbacks_ui_tabs, callback)
 
 
 def on_ui_settings(callback):
     """register a function to be called before UI settings are populated; add your settings
     by using shared.opts.add_option(shared.OptionInfo(...)) """
-    callbacks_ui_settings.append(callback)
+    add_callback(callbacks_ui_settings, callback)
+
+
+def on_before_image_saved(callback):
+    """register a function to be called before an image is saved to a file.
+    The callback is called with one argument:
+        - params: ImageSaveParams - parameters the image is to be saved with. You can change fields in this object.
+    """
+    add_callback(callbacks_before_image_saved, callback)
+
+
+def on_image_saved(callback):
+    """register a function to be called after an image is saved to a file.
+    The callback is called with one argument:
+        - params: ImageSaveParams - parameters the image was saved with. Changing fields in this object does nothing.
+    """
+    add_callback(callbacks_image_saved, callback)

modules/scunet_model.py

@@ -54,9 +54,8 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         img = img[:, :, ::-1]
         img = np.moveaxis(img, 2, 0) / 255
         img = torch.from_numpy(img).float()
-        img = img.unsqueeze(0).to(device)
+        img = devices.mps_contiguous_to(img.unsqueeze(0), device)
 
-        img = img.to(device)
         with torch.no_grad():
             output = model(img)
         output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/sd_samplers.py

@@ -228,7 +228,7 @@ class VanillaStableDiffusionSampler:
             unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
             
             
-        samples = self.launch_sampling(steps, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
+        samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
 
         return samples
 
@@ -429,7 +429,7 @@ class KDiffusionSampler:
         self.model_wrap_cfg.init_latent = x
         self.last_latent = x
 
-        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
+        samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
             'cond': conditioning, 
             'image_cond': image_conditioning, 
             'uncond': unconditional_conditioning, 

modules/shared.py

@@ -58,7 +58,7 @@ parser.add_argument("--opt-split-attention", action='store_true', help="force-en
 parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
 parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
-parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
 parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
@@ -84,7 +84,7 @@ parser.add_argument("--ui-debug-mode", action='store_true', help="Don't load mod
 parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)
 
 cmd_opts = parser.parse_args()
-restricted_opts = [
+restricted_opts = {
     "samples_filename_pattern",
     "directories_filename_pattern",
     "outdir_samples",
@@ -94,10 +94,10 @@ restricted_opts = [
     "outdir_grids",
     "outdir_txt2img_grids",
     "outdir_save",
-]
+}
 
-devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_bsrgan, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
-(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'])
+devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_swinir, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
+(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'])
 
 device = devices.device
 weight_load_location = None if cmd_opts.lowram else "cpu"

modules/swinir_model.py

@@ -7,8 +7,8 @@ from PIL import Image
 from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
-from modules import modelloader
-from modules.shared import cmd_opts, opts, device
+from modules import modelloader, devices
+from modules.shared import cmd_opts, opts
 from modules.swinir_model_arch import SwinIR as net
 from modules.swinir_model_arch_v2 import Swin2SR as net2
 from modules.upscaler import Upscaler, UpscalerData
@@ -42,7 +42,7 @@ class UpscalerSwinIR(Upscaler):
         model = self.load_model(model_file)
         if model is None:
             return img
-        model = model.to(device)
+        model = model.to(devices.device_swinir)
         img = upscale(img, model)
         try:
             torch.cuda.empty_cache()
@@ -111,7 +111,7 @@ def upscale(
     img = img[:, :, ::-1]
     img = np.moveaxis(img, 2, 0) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(device)
+    img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_swinir)
     with torch.no_grad(), precision_scope("cuda"):
         _, _, h_old, w_old = img.size()
         h_pad = (h_old // window_size + 1) * window_size - h_old
@@ -139,8 +139,8 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
     stride = tile - tile_overlap
     h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
     w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
-    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=device).type_as(img)
-    W = torch.zeros_like(E, dtype=torch.half, device=device)
+    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=devices.device_swinir).type_as(img)
+    W = torch.zeros_like(E, dtype=torch.half, device=devices.device_swinir)
 
     with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
         for h_idx in h_idx_list:

modules/textual_inversion/preprocess.py

@@ -7,12 +7,14 @@ import tqdm
 import time
 
 from modules import shared, images
+from modules.paths import models_path
 from modules.shared import opts, cmd_opts
+from modules.textual_inversion import autocrop
 if cmd_opts.deepdanbooru:
     import modules.deepbooru as deepbooru
 
 
-def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2):
+def preprocess(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
     try:
         if process_caption:
             shared.interrogator.load()
@@ -22,7 +24,7 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce
             db_opts[deepbooru.OPT_INCLUDE_RANKS] = False
             deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, db_opts)
 
-        preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio)
+        preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug)
 
     finally:
 
@@ -34,7 +36,7 @@ def preprocess(process_src, process_dst, process_width, process_height, preproce
 
 
 
-def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2):
+def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False):
     width = process_width
     height = process_height
     src = os.path.abspath(process_src)
@@ -113,6 +115,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
                 splitted = image.crop((0, y, to_w, y + to_h))
             yield splitted
 
+
     for index, imagefile in enumerate(tqdm.tqdm(files)):
         subindex = [0]
         filename = os.path.join(src, imagefile)
@@ -137,11 +140,36 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre
             ratio = (img.height * width) / (img.width * height)
             inverse_xy = True
 
+        process_default_resize = True
+
         if process_split and ratio < 1.0 and ratio <= split_threshold:
             for splitted in split_pic(img, inverse_xy):
                 save_pic(splitted, index, existing_caption=existing_caption)
-        else:
+            process_default_resize = False
+
+        if process_focal_crop and img.height != img.width:
+
+            dnn_model_path = None
+            try:
+                dnn_model_path = autocrop.download_and_cache_models(os.path.join(models_path, "opencv"))
+            except Exception as e:
+                print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e)
+
+            autocrop_settings = autocrop.Settings(
+                crop_width = width,
+                crop_height = height,
+                face_points_weight = process_focal_crop_face_weight,
+                entropy_points_weight = process_focal_crop_entropy_weight,
+                corner_points_weight = process_focal_crop_edges_weight,
+                annotate_image = process_focal_crop_debug,
+                dnn_model_path = dnn_model_path,
+            )
+            for focal in autocrop.crop_image(img, autocrop_settings):
+                save_pic(focal, index, existing_caption=existing_caption)
+            process_default_resize = False
+
+        if process_default_resize:
             img = images.resize_image(1, img, width, height)
             save_pic(img, index, existing_caption=existing_caption)
 
-        shared.state.nextjob()
+        shared.state.nextjob()
\ No newline at end of file

modules/textual_inversion/textual_inversion.py

@@ -10,7 +10,7 @@ import csv
 
 from PIL import Image, PngImagePlugin
 
-from modules import shared, devices, sd_hijack, processing, sd_models
+from modules import shared, devices, sd_hijack, processing, sd_models, images
 import modules.textual_inversion.dataset
 from modules.textual_inversion.learn_schedule import LearnRateScheduler
 
@@ -157,6 +157,9 @@ def create_embedding(name, num_vectors_per_token, overwrite_old, init_text='*'):
     cond_model = shared.sd_model.cond_stage_model
     embedding_layer = cond_model.wrapped.transformer.text_model.embeddings
 
+    with devices.autocast():
+        cond_model([""])  # will send cond model to GPU if lowvram/medvram is active
+
     ids = cond_model.tokenizer(init_text, max_length=num_vectors_per_token, return_tensors="pt", add_special_tokens=False)["input_ids"]
     embedded = embedding_layer.token_embedding.wrapped(ids.to(devices.device)).squeeze(0)
     vec = torch.zeros((num_vectors_per_token, embedded.shape[1]), device=devices.device)
@@ -164,6 +167,8 @@ def create_embedding(name, num_vectors_per_token, overwrite_old, init_text='*'):
     for i in range(num_vectors_per_token):
         vec[i] = embedded[i * int(embedded.shape[0]) // num_vectors_per_token]
 
+    # Remove illegal characters from name.
+    name = "".join( x for x in name if (x.isalnum() or x in "._- "))
     fn = os.path.join(shared.cmd_opts.embeddings_dir, f"{name}.pt")
     if not overwrite_old:
         assert not os.path.exists(fn), f"file {fn} already exists"
@@ -244,6 +249,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
 
     last_saved_file = "<none>"
     last_saved_image = "<none>"
+    forced_filename = "<none>"
     embedding_yet_to_be_embedded = False
 
     ititial_step = embedding.step or 0
@@ -283,7 +289,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
         pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{len(ds)}]loss: {losses.mean():.7f}")
 
         if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
-            last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.pt')
+            # Before saving, change name to match current checkpoint.
+            embedding.name = f'{embedding_name}-{embedding.step}'
+            last_saved_file = os.path.join(embedding_dir, f'{embedding.name}.pt')
             embedding.save(last_saved_file)
             embedding_yet_to_be_embedded = True
 
@@ -293,8 +301,8 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
         })
 
         if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0:
-            last_saved_image = os.path.join(images_dir, f'{embedding_name}-{embedding.step}.png')
-
+            forced_filename = f'{embedding_name}-{embedding.step}'
+            last_saved_image = os.path.join(images_dir, forced_filename)
             p = processing.StableDiffusionProcessingTxt2Img(
                 sd_model=shared.sd_model,
                 do_not_save_grid=True,
@@ -350,8 +358,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
                 captioned_image.save(last_saved_image_chunks, "PNG", pnginfo=info)
                 embedding_yet_to_be_embedded = False
 
-            image.save(last_saved_image)
-
+            last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
             last_saved_image += f", prompt: {preview_text}"
 
         shared.state.job_no = embedding.step
@@ -371,6 +378,9 @@ Last saved image: {html.escape(last_saved_image)}<br/>
     embedding.sd_checkpoint = checkpoint.hash
     embedding.sd_checkpoint_name = checkpoint.model_name
     embedding.cached_checksum = None
+    # Before saving for the last time, change name back to base name (as opposed to the save_embedding_every step-suffixed naming convention).
+    embedding.name = embedding_name
+    filename = os.path.join(shared.cmd_opts.embedding_dir, f'{embedding.name}.pt')
     embedding.save(filename)
 
     return embedding, filename

modules/ui.py

@@ -1238,7 +1238,8 @@ def create_ui(wrap_gradio_gpu_call):
                     new_hypernetwork_name = gr.Textbox(label="Name")
                     new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "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="relu", label="Select activation function of hypernetwork", choices=["linear", "relu", "leakyrelu", "elu", "swish"])
+                    new_hypernetwork_activation_func = gr.Dropdown(value="relu", label="Select activation function of hypernetwork", choices=modules.hypernetworks.ui.keys)
+                    new_hypernetwork_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization. relu-like - Kaiming, sigmoid-like - Xavier is recommended", 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")
@@ -1260,6 +1261,7 @@ def create_ui(wrap_gradio_gpu_call):
                     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 if cmd_opts.deepdanbooru else False)
 
@@ -1267,6 +1269,12 @@ def create_ui(wrap_gradio_gpu_call):
                         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)
 
+                    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')
+
                     with gr.Row():
                         with gr.Column(scale=3):
                             gr.HTML(value="")
@@ -1280,6 +1288,12 @@ def create_ui(wrap_gradio_gpu_call):
                         outputs=[process_split_extra_row],
                     )
 
+                    process_focal_crop.change(
+                        fn=lambda show: gr_show(show),
+                        inputs=[process_focal_crop],
+                        outputs=[process_focal_crop_row],
+                    )
+
                 with gr.Tab(label="Train"):
                     gr.HTML(value="<p style='margin-bottom: 0.7em'>Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images <a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\" style=\"font-weight:bold;\">[wiki]</a></p>")
                     with gr.Row():
@@ -1342,6 +1356,7 @@ def create_ui(wrap_gradio_gpu_call):
                 overwrite_old_hypernetwork,
                 new_hypernetwork_layer_structure,
                 new_hypernetwork_activation_func,
+                new_hypernetwork_initialization_option,
                 new_hypernetwork_add_layer_norm,
                 new_hypernetwork_use_dropout
             ],
@@ -1367,6 +1382,11 @@ def create_ui(wrap_gradio_gpu_call):
                 process_caption_deepbooru,
                 process_split_threshold,
                 process_overlap_ratio,
+                process_focal_crop,
+                process_focal_crop_face_weight,
+                process_focal_crop_entropy_weight,
+                process_focal_crop_edges_weight,
+                process_focal_crop_debug,
             ],
             outputs=[
                 ti_output,

requirements.txt

@@ -8,6 +8,8 @@ gradio==3.5
 invisible-watermark
 numpy
 omegaconf
+opencv-python
+requests
 piexif
 Pillow
 pytorch_lightning

scripts/prompts_from_file.py

 import copy
 import math
 import os
+import random
 import sys
 import traceback
 import shlex
@@ -81,32 +82,34 @@ def cmdargs(line):
     return res
 
 
+def load_prompt_file(file):
+    if (file is None):
+        lines = []
+    else:
+        lines = [x.strip() for x in file.decode('utf8', errors='ignore').split("\n")]
+
+    return None, "\n".join(lines), gr.update(lines=7)
+
 class Script(scripts.Script):
     def title(self):
         return "Prompts from file or textbox"
 
     def ui(self, is_img2img):
-        # This checkbox would look nicer as two tabs, but there are two problems:
-        # 1) There is a bug in Gradio 3.3 that prevents visibility from working on Tabs
-        # 2) Even with Gradio 3.3.1, returning a control (like Tabs) that can't be used as input
-        #    causes a AttributeError: 'Tabs' object has no attribute 'preprocess' assert,
-        #    due to the way Script assumes all controls returned can be used as inputs.
-        # Therefore, there's no good way to use grouping components right now,
-        # so we will use a checkbox! :)
-        checkbox_txt = gr.Checkbox(label="Show Textbox", value=False)
-        file = gr.File(label="File with inputs", type='bytes')
-        prompt_txt = gr.TextArea(label="Prompts")
-        checkbox_txt.change(fn=lambda x: [gr.File.update(visible = not x), gr.TextArea.update(visible = x)], inputs=[checkbox_txt], outputs=[file, prompt_txt])
-        return [checkbox_txt, file, prompt_txt]
-
-    def on_show(self, checkbox_txt, file, prompt_txt):
-        return [ gr.Checkbox.update(visible = True), gr.File.update(visible = not checkbox_txt), gr.TextArea.update(visible = checkbox_txt) ]
-
-    def run(self, p, checkbox_txt, data: bytes, prompt_txt: str):
-        if checkbox_txt:
-            lines = [x.strip() for x in prompt_txt.splitlines()]
-        else:
-            lines = [x.strip() for x in data.decode('utf8', errors='ignore').split("\n")]
+        checkbox_iterate = gr.Checkbox(label="Iterate seed every line", value=False)
+
+        prompt_txt = gr.Textbox(label="List of prompt inputs", lines=1)
+        file = gr.File(label="Upload prompt inputs", type='bytes')
+
+        file.change(fn=load_prompt_file, inputs=[file], outputs=[file, prompt_txt, prompt_txt])
+
+        # We start at one line. When the text changes, we jump to seven lines, or two lines if no \n.
+        # We don't shrink back to 1, because that causes the control to ignore [enter], and it may
+        # be unclear to the user that shift-enter is needed.
+        prompt_txt.change(lambda tb: gr.update(lines=7) if ("\n" in tb) else gr.update(lines=2), inputs=[prompt_txt], outputs=[prompt_txt])
+        return [checkbox_iterate, file, prompt_txt]
+
+    def run(self, p, checkbox_iterate, file, prompt_txt: str):
+        lines = [x.strip() for x in prompt_txt.splitlines()]
         lines = [x for x in lines if len(x) > 0]
 
         p.do_not_save_grid = True
@@ -134,6 +137,9 @@ class Script(scripts.Script):
             jobs.append(args)
 
         print(f"Will process {len(lines)} lines in {job_count} jobs.")
+        if (checkbox_iterate and p.seed == -1):
+            p.seed = int(random.randrange(4294967294))
+
         state.job_count = job_count
 
         images = []
@@ -146,5 +152,9 @@ class Script(scripts.Script):
 
             proc = process_images(copy_p)
             images += proc.images
+            
+            if (checkbox_iterate):
+                p.seed = p.seed + (p.batch_size * p.n_iter)
+
 
-        return Processed(p, images, p.seed, "")
+        return Processed(p, images, p.seed, "")
\ No newline at end of file

style.css

@@ -515,3 +515,77 @@ img2maskimg, #img2maskimg > .h-60, #img2maskimg > .h-60 > div, #img2maskimg > .h
     max-height: 480px !important;
     min-height: 480px !important;
 }
+
+/* The following handles localization for right-to-left (RTL) languages like Arabic.
+The rtl media type will only be activated by the logic in javascript/localization.js.
+If you change anything above, you need to make sure it is RTL compliant by just running
+your changes through converters like https://cssjanus.github.io/ or https://rtlcss.com/.
+Then, you will need to add the RTL counterpart only if needed in the rtl section below.*/
+@media rtl {
+    /* this part was manualy added */
+    :host {
+        direction: rtl;
+    }
+    .output-html:has(.performance), .gr-text-input {
+        direction: ltr;
+    }
+    .gr-radio, .gr-checkbox{
+        margin-left: 0.25em;
+    }
+
+    /* this part was automatically generated with few manual modifications */
+    .performance .time {
+        margin-right: unset;
+        margin-left: 0;
+    }
+    .justify-center.overflow-x-scroll {
+        justify-content: right;
+    }
+    .justify-center.overflow-x-scroll button:first-of-type {
+        margin-left: unset;
+        margin-right: auto;
+    }
+    .justify-center.overflow-x-scroll button:last-of-type {
+        margin-right: unset;
+        margin-left: auto;
+    }
+    #settings fieldset span.text-gray-500, #settings .gr-block.gr-box span.text-gray-500, #settings label.block span{
+        margin-right: unset;
+        margin-left: 8em;
+    }
+    #txt2img_progressbar, #img2img_progressbar, #ti_progressbar{
+        right: unset;
+        left: 0;
+    }
+    .progressDiv .progress{
+        padding: 0 0 0 8px;
+        text-align: left;
+    }
+    #lightboxModal{
+        left: unset;
+        right: 0;
+    }
+    .modalPrev, .modalNext{
+        border-radius: 3px 0 0 3px;
+    }
+    .modalNext {
+        right: unset;
+        left: 0;
+        border-radius: 0 3px 3px 0;
+    }
+    #imageARPreview{
+        left:unset;
+        right:0px;
+    }
+    #txt2img_skip, #img2img_skip{
+        right: unset;
+        left: 0px;
+    }
+    #context-menu{
+        box-shadow:-1px 1px 2px #CE6400;
+    }
+    .gr-box > div > div > input.gr-text-input{
+        right: unset;
+        left: 0.5em;
+    }
+}