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

.eslintrc.js

@@ -78,6 +78,8 @@ module.exports = {
         //extraNetworks.js
         requestGet: "readonly",
         popup: "readonly",
+        // profilerVisualization.js
+        createVisualizationTable: "readonly",
         // from python
         localization: "readonly",
         // progrssbar.js
@@ -86,8 +88,6 @@ module.exports = {
         // imageviewer.js
         modalPrevImage: "readonly",
         modalNextImage: "readonly",
-        // token-counters.js
-        setupTokenCounters: "readonly",
         // localStorage.js
         localSet: "readonly",
         localGet: "readonly",

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -91,7 +91,7 @@ body:
     id: logs
     attributes:
       label: Console logs
-      description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occured. If it's very long, provide a link to pastebin or similar service.
+      description: Please provide **full** cmd/terminal logs from the moment you started UI to the end of it, after the bug occurred. If it's very long, provide a link to pastebin or similar service.
       render: Shell
     validations:
       required: true

.github/workflows/on_pull_request.yaml

@@ -11,8 +11,8 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+        uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: 3.11
           # NB: there's no cache: pip here since we're not installing anything
@@ -20,7 +20,7 @@ jobs:
           #     not to have GHA download an (at the time of writing) 4 GB cache
           #     of PyTorch and other dependencies.
       - name: Install Ruff
-        run: pip install ruff==0.1.6
+        run: pip install ruff==0.3.3
       - name: Run Ruff
         run: ruff .
   lint-js:
@@ -29,9 +29,9 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Install Node.js
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18
       - run: npm i --ci

.github/workflows/run_tests.yaml

@@ -11,15 +11,21 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Set up Python 3.10
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.10.6
           cache: pip
           cache-dependency-path: |
             **/requirements*txt
             launch.py
+      - name: Cache models
+        id: cache-models
+        uses: actions/cache@v4
+        with:
+          path: models
+          key: "2023-12-30"
       - name: Install test dependencies
         run: pip install wait-for-it -r requirements-test.txt
         env:
@@ -33,6 +39,8 @@ jobs:
           TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
           WEBUI_LAUNCH_LIVE_OUTPUT: "1"
           PYTHONUNBUFFERED: "1"
+      - name: Print installed packages
+        run: pip freeze
       - name: Start test server
         run: >
           python -m coverage run
@@ -49,7 +57,7 @@ jobs:
           2>&1 | tee output.txt &
       - name: Run tests
         run: |
-          wait-for-it --service 127.0.0.1:7860 -t 600
+          wait-for-it --service 127.0.0.1:7860 -t 20
           python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
       - name: Kill test server
         if: always()
@@ -60,13 +68,13 @@ jobs:
           python -m coverage report -i
           python -m coverage html -i
       - name: Upload main app output
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         if: always()
         with:
           name: output
           path: output.txt
       - name: Upload coverage HTML
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         if: always()
         with:
           name: htmlcov

.gitignore

@@ -2,6 +2,7 @@ __pycache__
 *.ckpt
 *.safetensors
 *.pth
+.DS_Store
 /ESRGAN/*
 /SwinIR/*
 /repositories
@@ -37,3 +38,7 @@ notification.mp3
 /node_modules
 /package-lock.json
 /.coverage*
+/test/test_outputs
+/cache
+trace.json
+/sysinfo-????-??-??-??-??.json

README.md

 # Stable Diffusion web UI
-A browser interface based on Gradio library for Stable Diffusion.
+A web interface for Stable Diffusion, implemented using Gradio library.
 
 ![](screenshot.png)
 
@@ -78,7 +78,7 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Clip skip
 - Hypernetworks
 - Loras (same as Hypernetworks but more pretty)
-- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt 
+- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
 - Can select to load a different VAE from settings screen
 - Estimated completion time in progress bar
 - API
@@ -98,6 +98,7 @@ Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-di
 - [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended)
 - [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
 - [Intel CPUs, Intel GPUs (both integrated and discrete)](https://github.com/openvinotoolkit/stable-diffusion-webui/wiki/Installation-on-Intel-Silicon) (external wiki page)
+- [Ascend NPUs](https://github.com/wangshuai09/stable-diffusion-webui/wiki/Install-and-run-on-Ascend-NPUs) (external wiki page)
 
 Alternatively, use online services (like Google Colab):
 
@@ -121,16 +122,38 @@ Alternatively, use online services (like Google Colab):
 # Debian-based:
 sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
 # Red Hat-based:
-sudo dnf install wget git python3 gperftools-libs libglvnd-glx 
+sudo dnf install wget git python3 gperftools-libs libglvnd-glx
 # openSUSE-based:
 sudo zypper install wget git python3 libtcmalloc4 libglvnd
 # Arch-based:
 sudo pacman -S wget git python3
 ```
+If your system is very new, you need to install python3.11 or python3.10:
+```bash
+# Ubuntu 24.04
+sudo add-apt-repository ppa:deadsnakes/ppa
+sudo apt update
+sudo apt install python3.11
+
+# Manjaro/Arch
+sudo pacman -S yay
+yay -S python311 # do not confuse with python3.11 package
+
+# Only for 3.11
+# Then set up env variable in launch script
+export python_cmd="python3.11"
+# or in webui-user.sh
+python_cmd="python3.11"
+```
 2. Navigate to the directory you would like the webui to be installed and execute the following command:
 ```bash
 wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
 ```
+Or just clone the repo wherever you want:
+```bash
+git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
+```
+
 3. Run `webui.sh`.
 4. Check `webui-user.sh` for options.
 ### Installation on Apple Silicon
@@ -149,13 +172,14 @@ For the purposes of getting Google and other search engines to crawl the wiki, h
 ## Credits
 Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
 
-- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
+- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers, https://github.com/mcmonkey4eva/sd3-ref
 - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
-- GFPGAN - https://github.com/TencentARC/GFPGAN.git
-- CodeFormer - https://github.com/sczhou/CodeFormer
-- ESRGAN - https://github.com/xinntao/ESRGAN
-- SwinIR - https://github.com/JingyunLiang/SwinIR
-- Swin2SR - https://github.com/mv-lab/swin2sr
+- Spandrel - https://github.com/chaiNNer-org/spandrel implementing
+  - GFPGAN - https://github.com/TencentARC/GFPGAN.git
+  - CodeFormer - https://github.com/sczhou/CodeFormer
+  - ESRGAN - https://github.com/xinntao/ESRGAN
+  - SwinIR - https://github.com/JingyunLiang/SwinIR
+  - Swin2SR - https://github.com/mv-lab/swin2sr
 - LDSR - https://github.com/Hafiidz/latent-diffusion
 - MiDaS - https://github.com/isl-org/MiDaS
 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion

_typos.toml

+[default.extend-words]
+# Part of "RGBa" (Pillow's pre-multiplied alpha RGB mode)
+Ba = "Ba"
+# HSA is something AMD uses for their GPUs
+HSA = "HSA"

configs/alt-diffusion-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/alt-diffusion-m18-inference.yaml

@@ -41,7 +41,7 @@ model:
         use_linear_in_transformer: True
         transformer_depth: 1
         context_dim: 1024
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/instruct-pix2pix.yaml

@@ -45,7 +45,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/sd3-inference.yaml

+model:
+  target: modules.models.sd3.sd3_model.SD3Inferencer
+  params:
+    shift: 3
+    state_dict: null

configs/sd_xl_inpaint.yaml

+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: False
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          attn_type: vanilla-xformers
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult: [1, 2, 4, 4]
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity

configs/v1-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/v1-inpainting-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

extensions-builtin/LDSR/sd_hijack_ddpm_v1.py

@@ -301,7 +301,7 @@ class DDPMV1(pl.LightningModule):
         elif self.parameterization == "x0":
             target = x_start
         else:
-            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+            raise NotImplementedError(f"Parameterization {self.parameterization} not yet supported")
 
         loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
 
@@ -572,7 +572,7 @@ class LatentDiffusionV1(DDPMV1):
         :param h: height
         :param w: width
         :return: normalized distance to image border,
-         wtith min distance = 0 at border and max dist = 0.5 at image center
+         with min distance = 0 at border and max dist = 0.5 at image center
         """
         lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
         arr = self.meshgrid(h, w) / lower_right_corner
@@ -880,7 +880,7 @@ class LatentDiffusionV1(DDPMV1):
     def apply_model(self, x_noisy, t, cond, return_ids=False):
 
         if isinstance(cond, dict):
-            # hybrid case, cond is exptected to be a dict
+            # hybrid case, cond is expected to be a dict
             pass
         else:
             if not isinstance(cond, list):
@@ -916,7 +916,7 @@ class LatentDiffusionV1(DDPMV1):
                 cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
 
             elif self.cond_stage_key == 'coordinates_bbox':
-                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+                assert 'original_image_size' in self.split_input_params, 'BoundingBoxRescaling is missing original_image_size'
 
                 # assuming padding of unfold is always 0 and its dilation is always 1
                 n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
@@ -926,7 +926,7 @@ class LatentDiffusionV1(DDPMV1):
                 num_downs = self.first_stage_model.encoder.num_resolutions - 1
                 rescale_latent = 2 ** (num_downs)
 
-                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # get top left positions of patches as conforming for the bbbox tokenizer, therefore we
                 # need to rescale the tl patch coordinates to be in between (0,1)
                 tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
                                          rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)

extensions-builtin/Lora/extra_networks_lora.py

@@ -9,6 +9,8 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
         self.errors = {}
         """mapping of network names to the number of errors the network had during operation"""
 
+    remove_symbols = str.maketrans('', '', ":,")
+
     def activate(self, p, params_list):
         additional = shared.opts.sd_lora
 
@@ -43,22 +45,15 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
         networks.load_networks(names, te_multipliers, unet_multipliers, dyn_dims)
 
         if shared.opts.lora_add_hashes_to_infotext:
-            network_hashes = []
-            for item in networks.loaded_networks:
-                shorthash = item.network_on_disk.shorthash
-                if not shorthash:
-                    continue
-
-                alias = item.mentioned_name
-                if not alias:
-                    continue
+            if not getattr(p, "is_hr_pass", False) or not hasattr(p, "lora_hashes"):
+                p.lora_hashes = {}
 
-                alias = alias.replace(":", "").replace(",", "")
-
-                network_hashes.append(f"{alias}: {shorthash}")
+            for item in networks.loaded_networks:
+                if item.network_on_disk.shorthash and item.mentioned_name:
+                    p.lora_hashes[item.mentioned_name.translate(self.remove_symbols)] = item.network_on_disk.shorthash
 
-            if network_hashes:
-                p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
+            if p.lora_hashes:
+                p.extra_generation_params["Lora hashes"] = ', '.join(f'{k}: {v}' for k, v in p.lora_hashes.items())
 
     def deactivate(self, p):
         if self.errors:

extensions-builtin/Lora/lyco_helpers.py

@@ -30,7 +30,7 @@ def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
     In LoRA with Kroneckor Product, first value is a value for weight scale.
     secon value is a value for weight.
 
-    Becuase of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
+    Because of non-commutative property, A⊗B ≠ B⊗A. Meaning of two matrices is slightly different.
 
     examples)
     factor

extensions-builtin/Lora/network.py

@@ -3,7 +3,11 @@ import os
 from collections import namedtuple
 import enum
 
+import torch.nn as nn
+import torch.nn.functional as F
+
 from modules import sd_models, cache, errors, hashes, shared
+import modules.models.sd3.mmdit
 
 NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
 
@@ -26,7 +30,6 @@ class NetworkOnDisk:
 
         def read_metadata():
             metadata = sd_models.read_metadata_from_safetensors(filename)
-            metadata.pop('ssmd_cover_images', None)  # those are cover images, and they are too big to display in UI as text
 
             return metadata
 
@@ -112,14 +115,49 @@ class NetworkModule:
         self.sd_key = weights.sd_key
         self.sd_module = weights.sd_module
 
-        if hasattr(self.sd_module, 'weight'):
+        if isinstance(self.sd_module, modules.models.sd3.mmdit.QkvLinear):
+            s = self.sd_module.weight.shape
+            self.shape = (s[0] // 3, s[1])
+        elif hasattr(self.sd_module, 'weight'):
             self.shape = self.sd_module.weight.shape
+        elif isinstance(self.sd_module, nn.MultiheadAttention):
+            # For now, only self-attn use Pytorch's MHA
+            # So assume all qkvo proj have same shape
+            self.shape = self.sd_module.out_proj.weight.shape
+        else:
+            self.shape = None
+
+        self.ops = None
+        self.extra_kwargs = {}
+        if isinstance(self.sd_module, nn.Conv2d):
+            self.ops = F.conv2d
+            self.extra_kwargs = {
+                'stride': self.sd_module.stride,
+                'padding': self.sd_module.padding
+            }
+        elif isinstance(self.sd_module, nn.Linear):
+            self.ops = F.linear
+        elif isinstance(self.sd_module, nn.LayerNorm):
+            self.ops = F.layer_norm
+            self.extra_kwargs = {
+                'normalized_shape': self.sd_module.normalized_shape,
+                'eps': self.sd_module.eps
+            }
+        elif isinstance(self.sd_module, nn.GroupNorm):
+            self.ops = F.group_norm
+            self.extra_kwargs = {
+                'num_groups': self.sd_module.num_groups,
+                'eps': self.sd_module.eps
+            }
 
         self.dim = None
         self.bias = weights.w.get("bias")
         self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
         self.scale = weights.w["scale"].item() if "scale" in weights.w else None
 
+        self.dora_scale = weights.w.get("dora_scale", None)
+        self.dora_norm_dims = len(self.shape) - 1
+
     def multiplier(self):
         if 'transformer' in self.sd_key[:20]:
             return self.network.te_multiplier
@@ -134,10 +172,31 @@ class NetworkModule:
 
         return 1.0
 
+    def apply_weight_decompose(self, updown, orig_weight):
+        # Match the device/dtype
+        orig_weight = orig_weight.to(updown.dtype)
+        dora_scale = self.dora_scale.to(device=orig_weight.device, dtype=updown.dtype)
+        updown = updown.to(orig_weight.device)
+
+        merged_scale1 = updown + orig_weight
+        merged_scale1_norm = (
+            merged_scale1.transpose(0, 1)
+            .reshape(merged_scale1.shape[1], -1)
+            .norm(dim=1, keepdim=True)
+            .reshape(merged_scale1.shape[1], *[1] * self.dora_norm_dims)
+            .transpose(0, 1)
+        )
+
+        dora_merged = (
+            merged_scale1 * (dora_scale / merged_scale1_norm)
+        )
+        final_updown = dora_merged - orig_weight
+        return final_updown
+
     def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
         if self.bias is not None:
             updown = updown.reshape(self.bias.shape)
-            updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown += self.bias.to(orig_weight.device, dtype=updown.dtype)
             updown = updown.reshape(output_shape)
 
         if len(output_shape) == 4:
@@ -149,11 +208,21 @@ class NetworkModule:
         if ex_bias is not None:
             ex_bias = ex_bias * self.multiplier()
 
-        return updown * self.calc_scale() * self.multiplier(), ex_bias
+        updown = updown * self.calc_scale()
+
+        if self.dora_scale is not None:
+            updown = self.apply_weight_decompose(updown, orig_weight)
+
+        return updown * self.multiplier(), ex_bias
 
     def calc_updown(self, target):
         raise NotImplementedError()
 
     def forward(self, x, y):
-        raise NotImplementedError()
+        """A general forward implementation for all modules"""
+        if self.ops is None:
+            raise NotImplementedError()
+        else:
+            updown, ex_bias = self.calc_updown(self.sd_module.weight)
+            return y + self.ops(x, weight=updown, bias=ex_bias, **self.extra_kwargs)
 

extensions-builtin/Lora/network_full.py

@@ -18,9 +18,9 @@ class NetworkModuleFull(network.NetworkModule):
 
     def calc_updown(self, orig_weight):
         output_shape = self.weight.shape
-        updown = self.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+        updown = self.weight.to(orig_weight.device)
         if self.ex_bias is not None:
-            ex_bias = self.ex_bias.to(orig_weight.device, dtype=orig_weight.dtype)
+            ex_bias = self.ex_bias.to(orig_weight.device)
         else:
             ex_bias = None
 

extensions-builtin/Lora/network_glora.py

@@ -22,12 +22,12 @@ class NetworkModuleGLora(network.NetworkModule):
         self.w2b = weights.w["b2.weight"]
 
     def calc_updown(self, orig_weight):
-        w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+        w1a = self.w1a.to(orig_weight.device)
+        w1b = self.w1b.to(orig_weight.device)
+        w2a = self.w2a.to(orig_weight.device)
+        w2b = self.w2b.to(orig_weight.device)
 
         output_shape = [w1a.size(0), w1b.size(1)]
-        updown = ((w2b @ w1b) + ((orig_weight @ w2a) @ w1a))
+        updown = ((w2b @ w1b) + ((orig_weight.to(dtype = w1a.dtype) @ w2a) @ w1a))
 
         return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_hada.py

@@ -27,16 +27,16 @@ class NetworkModuleHada(network.NetworkModule):
         self.t2 = weights.w.get("hada_t2")
 
     def calc_updown(self, orig_weight):
-        w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-        w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+        w1a = self.w1a.to(orig_weight.device)
+        w1b = self.w1b.to(orig_weight.device)
+        w2a = self.w2a.to(orig_weight.device)
+        w2b = self.w2b.to(orig_weight.device)
 
         output_shape = [w1a.size(0), w1b.size(1)]
 
         if self.t1 is not None:
             output_shape = [w1a.size(1), w1b.size(1)]
-            t1 = self.t1.to(orig_weight.device, dtype=orig_weight.dtype)
+            t1 = self.t1.to(orig_weight.device)
             updown1 = lyco_helpers.make_weight_cp(t1, w1a, w1b)
             output_shape += t1.shape[2:]
         else:
@@ -45,7 +45,7 @@ class NetworkModuleHada(network.NetworkModule):
             updown1 = lyco_helpers.rebuild_conventional(w1a, w1b, output_shape)
 
         if self.t2 is not None:
-            t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
+            t2 = self.t2.to(orig_weight.device)
             updown2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
         else:
             updown2 = lyco_helpers.rebuild_conventional(w2a, w2b, output_shape)

extensions-builtin/Lora/network_ia3.py

@@ -17,7 +17,7 @@ class NetworkModuleIa3(network.NetworkModule):
         self.on_input = weights.w["on_input"].item()
 
     def calc_updown(self, orig_weight):
-        w = self.w.to(orig_weight.device, dtype=orig_weight.dtype)
+        w = self.w.to(orig_weight.device)
 
         output_shape = [w.size(0), orig_weight.size(1)]
         if self.on_input:

extensions-builtin/Lora/network_lokr.py

@@ -37,22 +37,22 @@ class NetworkModuleLokr(network.NetworkModule):
 
     def calc_updown(self, orig_weight):
         if self.w1 is not None:
-            w1 = self.w1.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1 = self.w1.to(orig_weight.device)
         else:
-            w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
-            w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1a = self.w1a.to(orig_weight.device)
+            w1b = self.w1b.to(orig_weight.device)
             w1 = w1a @ w1b
 
         if self.w2 is not None:
-            w2 = self.w2.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2 = self.w2.to(orig_weight.device)
         elif self.t2 is None:
-            w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-            w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w2a = self.w2a.to(orig_weight.device)
+            w2b = self.w2b.to(orig_weight.device)
             w2 = w2a @ w2b
         else:
-            t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
-            w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
-            w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+            t2 = self.t2.to(orig_weight.device)
+            w2a = self.w2a.to(orig_weight.device)
+            w2b = self.w2b.to(orig_weight.device)
             w2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
 
         output_shape = [w1.size(0) * w2.size(0), w1.size(1) * w2.size(1)]

extensions-builtin/Lora/network_lora.py

 import torch
 
 import lyco_helpers
+import modules.models.sd3.mmdit
 import network
 from modules import devices
 
@@ -10,6 +11,13 @@ class ModuleTypeLora(network.ModuleType):
         if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
             return NetworkModuleLora(net, weights)
 
+        if all(x in weights.w for x in ["lora_A.weight", "lora_B.weight"]):
+            w = weights.w.copy()
+            weights.w.clear()
+            weights.w.update({"lora_up.weight": w["lora_B.weight"], "lora_down.weight": w["lora_A.weight"]})
+
+            return NetworkModuleLora(net, weights)
+
         return None
 
 
@@ -29,7 +37,7 @@ class NetworkModuleLora(network.NetworkModule):
         if weight is None and none_ok:
             return None
 
-        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention]
+        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention, modules.models.sd3.mmdit.QkvLinear]
         is_conv = type(self.sd_module) in [torch.nn.Conv2d]
 
         if is_linear:
@@ -61,13 +69,13 @@ class NetworkModuleLora(network.NetworkModule):
         return module
 
     def calc_updown(self, orig_weight):
-        up = self.up_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
-        down = self.down_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+        up = self.up_model.weight.to(orig_weight.device)
+        down = self.down_model.weight.to(orig_weight.device)
 
         output_shape = [up.size(0), down.size(1)]
         if self.mid_model is not None:
             # cp-decomposition
-            mid = self.mid_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+            mid = self.mid_model.weight.to(orig_weight.device)
             updown = lyco_helpers.rebuild_cp_decomposition(up, down, mid)
             output_shape += mid.shape[2:]
         else:

extensions-builtin/Lora/network_norm.py

@@ -18,10 +18,10 @@ class NetworkModuleNorm(network.NetworkModule):
 
     def calc_updown(self, orig_weight):
         output_shape = self.w_norm.shape
-        updown = self.w_norm.to(orig_weight.device, dtype=orig_weight.dtype)
+        updown = self.w_norm.to(orig_weight.device)
 
         if self.b_norm is not None:
-            ex_bias = self.b_norm.to(orig_weight.device, dtype=orig_weight.dtype)
+            ex_bias = self.b_norm.to(orig_weight.device)
         else:
             ex_bias = None
 

extensions-builtin/Lora/network_oft.py

 import torch
 import network
-from lyco_helpers import factorization
 from einops import rearrange
 
 
@@ -22,16 +21,17 @@ class NetworkModuleOFT(network.NetworkModule):
         self.org_module: list[torch.Module] = [self.sd_module]
 
         self.scale = 1.0
+        self.is_R = False
+        self.is_boft = False
 
-        # kohya-ss
+        # kohya-ss/New LyCORIS OFT/BOFT
         if "oft_blocks" in weights.w.keys():
-            self.is_kohya = True
             self.oft_blocks = weights.w["oft_blocks"] # (num_blocks, block_size, block_size)
-            self.alpha = weights.w["alpha"] # alpha is constraint
+            self.alpha = weights.w.get("alpha", None) # alpha is constraint
             self.dim = self.oft_blocks.shape[0] # lora dim
-        # LyCORIS
+        # Old LyCORIS OFT
         elif "oft_diag" in weights.w.keys():
-            self.is_kohya = False
+            self.is_R = True
             self.oft_blocks = weights.w["oft_diag"]
             # self.alpha is unused
             self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
@@ -47,36 +47,72 @@ class NetworkModuleOFT(network.NetworkModule):
         elif is_other_linear:
             self.out_dim = self.sd_module.embed_dim
 
-        if self.is_kohya:
-            self.constraint = self.alpha * self.out_dim
-            self.num_blocks = self.dim
-            self.block_size = self.out_dim // self.dim
-        else:
+        # LyCORIS BOFT
+        if self.oft_blocks.dim() == 4:
+            self.is_boft = True
+        self.rescale = weights.w.get('rescale', None)
+        if self.rescale is not None and not is_other_linear:
+            self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1))
+
+        self.num_blocks = self.dim
+        self.block_size = self.out_dim // self.dim
+        self.constraint = (0 if self.alpha is None else self.alpha) * self.out_dim
+        if self.is_R:
             self.constraint = None
-            self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
+            self.block_size = self.dim
+            self.num_blocks = self.out_dim // self.dim
+        elif self.is_boft:
+            self.boft_m = self.oft_blocks.shape[0]
+            self.num_blocks = self.oft_blocks.shape[1]
+            self.block_size = self.oft_blocks.shape[2]
+            self.boft_b = self.block_size
 
     def calc_updown(self, orig_weight):
-        oft_blocks = self.oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
-        eye = torch.eye(self.block_size, device=self.oft_blocks.device)
-
-        if self.is_kohya:
-            block_Q = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
-            norm_Q = torch.norm(block_Q.flatten())
-            new_norm_Q = torch.clamp(norm_Q, max=self.constraint)
-            block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
+        oft_blocks = self.oft_blocks.to(orig_weight.device)
+        eye = torch.eye(self.block_size, device=oft_blocks.device)
+
+        if not self.is_R:
+            block_Q = oft_blocks - oft_blocks.transpose(-1, -2) # ensure skew-symmetric orthogonal matrix
+            if self.constraint != 0:
+                norm_Q = torch.norm(block_Q.flatten())
+                new_norm_Q = torch.clamp(norm_Q, max=self.constraint.to(oft_blocks.device))
+                block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
             oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse())
 
-        R = oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
-
-        # This errors out for MultiheadAttention, might need to be handled up-stream
-        merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
-        merged_weight = torch.einsum(
-            'k n m, k n ... -> k m ...',
-            R,
-            merged_weight
-        )
-        merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
-
-        updown = merged_weight.to(orig_weight.device, dtype=orig_weight.dtype) - orig_weight
+        R = oft_blocks.to(orig_weight.device)
+
+        if not self.is_boft:
+            # This errors out for MultiheadAttention, might need to be handled up-stream
+            merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
+            merged_weight = torch.einsum(
+                'k n m, k n ... -> k m ...',
+                R,
+                merged_weight
+            )
+            merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
+        else:
+            # TODO: determine correct value for scale
+            scale = 1.0
+            m = self.boft_m
+            b = self.boft_b
+            r_b = b // 2
+            inp = orig_weight
+            for i in range(m):
+                bi = R[i] # b_num, b_size, b_size
+                if i == 0:
+                    # Apply multiplier/scale and rescale into first weight
+                    bi = bi * scale + (1 - scale) * eye
+                inp = rearrange(inp, "(c g k) ... -> (c k g) ...", g=2, k=2**i * r_b)
+                inp = rearrange(inp, "(d b) ... -> d b ...", b=b)
+                inp = torch.einsum("b i j, b j ... -> b i ...", bi, inp)
+                inp = rearrange(inp, "d b ... -> (d b) ...")
+                inp = rearrange(inp, "(c k g) ... -> (c g k) ...", g=2, k=2**i * r_b)
+            merged_weight = inp
+
+        # Rescale mechanism
+        if self.rescale is not None:
+            merged_weight = self.rescale.to(merged_weight) * merged_weight
+
+        updown = merged_weight.to(orig_weight.device) - orig_weight.to(merged_weight.dtype)
         output_shape = orig_weight.shape
         return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/preload.py

 import os
 from modules import paths
+from modules.paths_internal import normalized_filepath
 
 
 def preload(parser):
-    parser.add_argument("--lora-dir", type=str, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
-    parser.add_argument("--lyco-dir-backcompat", type=str, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))
+    parser.add_argument("--lora-dir", type=normalized_filepath, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
+    parser.add_argument("--lyco-dir-backcompat", type=normalized_filepath, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))

extensions-builtin/Lora/scripts/lora_script.py

@@ -36,9 +36,12 @@ shared.options_templates.update(shared.options_section(('extra_networks', "Extra
     "sd_lora": shared.OptionInfo("None", "Add network to prompt", gr.Dropdown, lambda: {"choices": ["None", *networks.available_networks]}, refresh=networks.list_available_networks),
     "lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to Lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
     "lora_add_hashes_to_infotext": shared.OptionInfo(True, "Add Lora hashes to infotext"),
+    "lora_bundled_ti_to_infotext": shared.OptionInfo(True, "Add Lora name as TI hashes for bundled Textual Inversion").info('"Add Textual Inversion hashes to infotext" needs to be enabled'),
     "lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
     "lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
     "lora_in_memory_limit": shared.OptionInfo(0, "Number of Lora networks to keep cached in memory", gr.Number, {"precision": 0}),
+    "lora_not_found_warning_console": shared.OptionInfo(False, "Lora not found warning in console"),
+    "lora_not_found_gradio_warning": shared.OptionInfo(False, "Lora not found warning popup in webui"),
 }))
 
 

extensions-builtin/Lora/ui_edit_user_metadata.py

@@ -21,10 +21,12 @@ re_comma = re.compile(r" *, *")
 def build_tags(metadata):
     tags = {}
 
-    for _, tags_dict in metadata.get("ss_tag_frequency", {}).items():
-        for tag, tag_count in tags_dict.items():
-            tag = tag.strip()
-            tags[tag] = tags.get(tag, 0) + int(tag_count)
+    ss_tag_frequency = metadata.get("ss_tag_frequency", {})
+    if ss_tag_frequency is not None and hasattr(ss_tag_frequency, 'items'):
+        for _, tags_dict in ss_tag_frequency.items():
+            for tag, tag_count in tags_dict.items():
+                tag = tag.strip()
+                tags[tag] = tags.get(tag, 0) + int(tag_count)
 
     if tags and is_non_comma_tagset(tags):
         new_tags = {}
@@ -54,12 +56,13 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
         self.slider_preferred_weight = None
         self.edit_notes = None
 
-    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, notes):
+    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, negative_text, notes):
         user_metadata = self.get_user_metadata(name)
         user_metadata["description"] = desc
         user_metadata["sd version"] = sd_version
         user_metadata["activation text"] = activation_text
         user_metadata["preferred weight"] = preferred_weight
+        user_metadata["negative text"] = negative_text
         user_metadata["notes"] = notes
 
         self.write_user_metadata(name, user_metadata)
@@ -127,6 +130,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
             gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
             user_metadata.get('activation text', ''),
             float(user_metadata.get('preferred weight', 0.0)),
+            user_metadata.get('negative text', ''),
             gr.update(visible=True if tags else False),
             gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
         ]
@@ -147,6 +151,8 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
 
             v = random.random() * max_count
             if count > v:
+                for x in "({[]})":
+                    tag = tag.replace(x, '\\' + x)
                 res.append(tag)
 
         return ", ".join(sorted(res))
@@ -162,7 +168,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
         self.taginfo = gr.HighlightedText(label="Training dataset tags")
         self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
         self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
-
+        self.edit_negative_text = gr.Text(label='Negative prompt', info="Will be added to negative prompts")
         with gr.Row() as row_random_prompt:
             with gr.Column(scale=8):
                 random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
@@ -198,6 +204,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
             self.taginfo,
             self.edit_activation_text,
             self.slider_preferred_weight,
+            self.edit_negative_text,
             row_random_prompt,
             random_prompt,
         ]
@@ -211,7 +218,9 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor)
             self.select_sd_version,
             self.edit_activation_text,
             self.slider_preferred_weight,
+            self.edit_negative_text,
             self.edit_notes,
         ]
 
+
         self.setup_save_handler(self.button_save, self.save_lora_user_metadata, edited_components)

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -24,13 +24,16 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
 
         alias = lora_on_disk.get_alias()
 
+        search_terms = [self.search_terms_from_path(lora_on_disk.filename)]
+        if lora_on_disk.hash:
+            search_terms.append(lora_on_disk.hash)
         item = {
             "name": name,
             "filename": lora_on_disk.filename,
             "shorthash": lora_on_disk.shorthash,
-            "preview": self.find_preview(path),
+            "preview": self.find_preview(path) or self.find_embedded_preview(path, name, lora_on_disk.metadata),
             "description": self.find_description(path),
-            "search_term": self.search_terms_from_path(lora_on_disk.filename) + " " + (lora_on_disk.hash or ""),
+            "search_terms": search_terms,
             "local_preview": f"{path}.{shared.opts.samples_format}",
             "metadata": lora_on_disk.metadata,
             "sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
@@ -45,6 +48,11 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         if activation_text:
             item["prompt"] += " + " + quote_js(" " + activation_text)
 
+        negative_prompt = item["user_metadata"].get("negative text")
+        item["negative_prompt"] = quote_js("")
+        if negative_prompt:
+            item["negative_prompt"] = quote_js('(' + negative_prompt + ':1)')
+
         sd_version = item["user_metadata"].get("sd version")
         if sd_version in network.SdVersion.__members__:
             item["sd_version"] = sd_version
@@ -52,7 +60,7 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         else:
             sd_version = lora_on_disk.sd_version
 
-        if shared.opts.lora_show_all or not enable_filter:
+        if shared.opts.lora_show_all or not enable_filter or not shared.sd_model:
             pass
         elif sd_version == network.SdVersion.Unknown:
             model_version = network.SdVersion.SDXL if shared.sd_model.is_sdxl else network.SdVersion.SD2 if shared.sd_model.is_sd2 else network.SdVersion.SD1

extensions-builtin/ScuNET/scripts/scunet_model.py

 import sys
 
 import PIL.Image
-import numpy as np
-import torch
-from tqdm import tqdm
 
 import modules.upscaler
-from modules import devices, modelloader, script_callbacks, errors
-from scunet_model_arch import SCUNet
-
-from modules.modelloader import load_file_from_url
-from modules.shared import opts
+from modules import devices, errors, modelloader, script_callbacks, shared, upscaler_utils
 
 
 class UpscalerScuNET(modules.upscaler.Upscaler):
@@ -42,100 +35,37 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
             scalers.append(scaler_data2)
         self.scalers = scalers
 
-    @staticmethod
-    @torch.no_grad()
-    def tiled_inference(img, model):
-        # test the image tile by tile
-        h, w = img.shape[2:]
-        tile = opts.SCUNET_tile
-        tile_overlap = opts.SCUNET_tile_overlap
-        if tile == 0:
-            return model(img)
-
-        device = devices.get_device_for('scunet')
-        assert tile % 8 == 0, "tile size should be a multiple of window_size"
-        sf = 1
-
-        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(1, 3, h * sf, w * sf, dtype=img.dtype, device=device)
-        W = torch.zeros_like(E, dtype=devices.dtype, device=device)
-
-        with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="ScuNET tiles") as pbar:
-            for h_idx in h_idx_list:
-
-                for w_idx in w_idx_list:
-
-                    in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
-
-                    out_patch = model(in_patch)
-                    out_patch_mask = torch.ones_like(out_patch)
-
-                    E[
-                        ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                    ].add_(out_patch)
-                    W[
-                        ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                    ].add_(out_patch_mask)
-                    pbar.update(1)
-        output = E.div_(W)
-
-        return output
-
     def do_upscale(self, img: PIL.Image.Image, selected_file):
-
         devices.torch_gc()
-
         try:
             model = self.load_model(selected_file)
         except Exception as e:
             print(f"ScuNET: Unable to load model from {selected_file}: {e}", file=sys.stderr)
             return img
 
-        device = devices.get_device_for('scunet')
-        tile = opts.SCUNET_tile
-        h, w = img.height, img.width
-        np_img = np.array(img)
-        np_img = np_img[:, :, ::-1]  # RGB to BGR
-        np_img = np_img.transpose((2, 0, 1)) / 255  # HWC to CHW
-        torch_img = torch.from_numpy(np_img).float().unsqueeze(0).to(device)  # type: ignore
-
-        if tile > h or tile > w:
-            _img = torch.zeros(1, 3, max(h, tile), max(w, tile), dtype=torch_img.dtype, device=torch_img.device)
-            _img[:, :, :h, :w] = torch_img # pad image
-            torch_img = _img
-
-        torch_output = self.tiled_inference(torch_img, model).squeeze(0)
-        torch_output = torch_output[:, :h * 1, :w * 1] # remove padding, if any
-        np_output: np.ndarray = torch_output.float().cpu().clamp_(0, 1).numpy()
-        del torch_img, torch_output
+        img = upscaler_utils.upscale_2(
+            img,
+            model,
+            tile_size=shared.opts.SCUNET_tile,
+            tile_overlap=shared.opts.SCUNET_tile_overlap,
+            scale=1,  # ScuNET is a denoising model, not an upscaler
+            desc='ScuNET',
+        )
         devices.torch_gc()
-
-        output = np_output.transpose((1, 2, 0))  # CHW to HWC
-        output = output[:, :, ::-1]  # BGR to RGB
-        return PIL.Image.fromarray((output * 255).astype(np.uint8))
+        return img
 
     def load_model(self, path: str):
         device = devices.get_device_for('scunet')
         if path.startswith("http"):
             # TODO: this doesn't use `path` at all?
-            filename = load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
+            filename = modelloader.load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name=f"{self.name}.pth")
         else:
             filename = path
-        model = SCUNet(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
-        model.load_state_dict(torch.load(filename), strict=True)
-        model.eval()
-        for _, v in model.named_parameters():
-            v.requires_grad = False
-        model = model.to(device)
-
-        return model
+        return modelloader.load_spandrel_model(filename, device=device, expected_architecture='SCUNet')
 
 
 def on_ui_settings():
     import gradio as gr
-    from modules import shared
 
     shared.opts.add_option("SCUNET_tile", shared.OptionInfo(256, "Tile size for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")).info("0 = no tiling"))
     shared.opts.add_option("SCUNET_tile_overlap", shared.OptionInfo(8, "Tile overlap for SCUNET upscalers.", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, section=('upscaling', "Upscaling")).info("Low values = visible seam"))

extensions-builtin/SwinIR/scripts/swinir_model.py

+import logging
 import sys
-import platform
 
-import numpy as np
 import torch
 from PIL import Image
-from tqdm import tqdm
 
-from modules import modelloader, devices, script_callbacks, shared
-from modules.shared import opts, state
-from swinir_model_arch import SwinIR
-from swinir_model_arch_v2 import Swin2SR
+from modules import devices, modelloader, script_callbacks, shared, upscaler_utils
 from modules.upscaler import Upscaler, UpscalerData
 
 SWINIR_MODEL_URL = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth"
 
-device_swinir = devices.get_device_for('swinir')
+logger = logging.getLogger(__name__)
 
 
 class UpscalerSwinIR(Upscaler):
@@ -37,26 +32,28 @@ class UpscalerSwinIR(Upscaler):
             scalers.append(model_data)
         self.scalers = scalers
 
-    def do_upscale(self, img, model_file):
-        use_compile = hasattr(opts, 'SWIN_torch_compile') and opts.SWIN_torch_compile \
-            and int(torch.__version__.split('.')[0]) >= 2 and platform.system() != "Windows"
-        current_config = (model_file, opts.SWIN_tile)
+    def do_upscale(self, img: Image.Image, model_file: str) -> Image.Image:
+        current_config = (model_file, shared.opts.SWIN_tile)
 
-        if use_compile and self._cached_model_config == current_config:
+        if self._cached_model_config == current_config:
             model = self._cached_model
         else:
-            self._cached_model = None
             try:
                 model = self.load_model(model_file)
             except Exception as e:
                 print(f"Failed loading SwinIR model {model_file}: {e}", file=sys.stderr)
                 return img
-            model = model.to(device_swinir, dtype=devices.dtype)
-            if use_compile:
-                model = torch.compile(model)
-                self._cached_model = model
-                self._cached_model_config = current_config
-        img = upscale(img, model)
+            self._cached_model = model
+            self._cached_model_config = current_config
+
+        img = upscaler_utils.upscale_2(
+            img,
+            model,
+            tile_size=shared.opts.SWIN_tile,
+            tile_overlap=shared.opts.SWIN_tile_overlap,
+            scale=model.scale,
+            desc="SwinIR",
+        )
         devices.torch_gc()
         return img
 
@@ -69,115 +66,22 @@ class UpscalerSwinIR(Upscaler):
             )
         else:
             filename = path
-        if filename.endswith(".v2.pth"):
-            model = Swin2SR(
-                upscale=scale,
-                in_chans=3,
-                img_size=64,
-                window_size=8,
-                img_range=1.0,
-                depths=[6, 6, 6, 6, 6, 6],
-                embed_dim=180,
-                num_heads=[6, 6, 6, 6, 6, 6],
-                mlp_ratio=2,
-                upsampler="nearest+conv",
-                resi_connection="1conv",
-            )
-            params = None
-        else:
-            model = SwinIR(
-                upscale=scale,
-                in_chans=3,
-                img_size=64,
-                window_size=8,
-                img_range=1.0,
-                depths=[6, 6, 6, 6, 6, 6, 6, 6, 6],
-                embed_dim=240,
-                num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8],
-                mlp_ratio=2,
-                upsampler="nearest+conv",
-                resi_connection="3conv",
-            )
-            params = "params_ema"
 
-        pretrained_model = torch.load(filename)
-        if params is not None:
-            model.load_state_dict(pretrained_model[params], strict=True)
-        else:
-            model.load_state_dict(pretrained_model, strict=True)
-        return model
-
-
-def upscale(
-        img,
-        model,
-        tile=None,
-        tile_overlap=None,
-        window_size=8,
-        scale=4,
-):
-    tile = tile or opts.SWIN_tile
-    tile_overlap = tile_overlap or opts.SWIN_tile_overlap
-
-
-    img = np.array(img)
-    img = img[:, :, ::-1]
-    img = np.moveaxis(img, 2, 0) / 255
-    img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(device_swinir, dtype=devices.dtype)
-    with torch.no_grad(), devices.autocast():
-        _, _, h_old, w_old = img.size()
-        h_pad = (h_old // window_size + 1) * window_size - h_old
-        w_pad = (w_old // window_size + 1) * window_size - w_old
-        img = torch.cat([img, torch.flip(img, [2])], 2)[:, :, : h_old + h_pad, :]
-        img = torch.cat([img, torch.flip(img, [3])], 3)[:, :, :, : w_old + w_pad]
-        output = inference(img, model, tile, tile_overlap, window_size, scale)
-        output = output[..., : h_old * scale, : w_old * scale]
-        output = output.data.squeeze().float().cpu().clamp_(0, 1).numpy()
-        if output.ndim == 3:
-            output = np.transpose(
-                output[[2, 1, 0], :, :], (1, 2, 0)
-            )  # CHW-RGB to HCW-BGR
-        output = (output * 255.0).round().astype(np.uint8)  # float32 to uint8
-        return Image.fromarray(output, "RGB")
-
-
-def inference(img, model, tile, tile_overlap, window_size, scale):
-    # test the image tile by tile
-    b, c, h, w = img.size()
-    tile = min(tile, h, w)
-    assert tile % window_size == 0, "tile size should be a multiple of window_size"
-    sf = 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=devices.dtype, device=device_swinir).type_as(img)
-    W = torch.zeros_like(E, dtype=devices.dtype, device=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:
-            if state.interrupted or state.skipped:
-                break
-
-            for w_idx in w_idx_list:
-                if state.interrupted or state.skipped:
-                    break
-
-                in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
-                out_patch = model(in_patch)
-                out_patch_mask = torch.ones_like(out_patch)
-
-                E[
-                ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                ].add_(out_patch)
-                W[
-                ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
-                ].add_(out_patch_mask)
-                pbar.update(1)
-    output = E.div_(W)
-
-    return output
+        model_descriptor = modelloader.load_spandrel_model(
+            filename,
+            device=self._get_device(),
+            prefer_half=(devices.dtype == torch.float16),
+            expected_architecture="SwinIR",
+        )
+        if getattr(shared.opts, 'SWIN_torch_compile', False):
+            try:
+                model_descriptor.model.compile()
+            except Exception:
+                logger.warning("Failed to compile SwinIR model, fallback to JIT", exc_info=True)
+        return model_descriptor
+
+    def _get_device(self):
+        return devices.get_device_for('swinir')
 
 
 def on_ui_settings():
@@ -185,8 +89,7 @@ def on_ui_settings():
 
     shared.opts.add_option("SWIN_tile", shared.OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}, section=('upscaling', "Upscaling")))
     shared.opts.add_option("SWIN_tile_overlap", shared.OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}, section=('upscaling', "Upscaling")))
-    if int(torch.__version__.split('.')[0]) >= 2 and platform.system() != "Windows":    # torch.compile() require pytorch 2.0 or above, and not on Windows
-        shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
+    shared.opts.add_option("SWIN_torch_compile", shared.OptionInfo(False, "Use torch.compile to accelerate SwinIR.", gr.Checkbox, {"interactive": True}, section=('upscaling', "Upscaling")).info("Takes longer on first run"))
 
 
 script_callbacks.on_ui_settings(on_ui_settings)

extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js

@@ -29,6 +29,7 @@ onUiLoaded(async() => {
     });
 
     function getActiveTab(elements, all = false) {
+        if (!elements.img2imgTabs) return null;
         const tabs = elements.img2imgTabs.querySelectorAll("button");
 
         if (all) return tabs;
@@ -43,6 +44,7 @@ onUiLoaded(async() => {
     // Get tab ID
     function getTabId(elements) {
         const activeTab = getActiveTab(elements);
+        if (!activeTab) return null;
         return tabNameToElementId[activeTab.innerText];
     }
 
@@ -218,6 +220,8 @@ onUiLoaded(async() => {
         canvas_hotkey_fullscreen: "KeyS",
         canvas_hotkey_move: "KeyF",
         canvas_hotkey_overlap: "KeyO",
+        canvas_hotkey_shrink_brush: "KeyQ",
+        canvas_hotkey_grow_brush: "KeyW",
         canvas_disabled_functions: [],
         canvas_show_tooltip: true,
         canvas_auto_expand: true,
@@ -227,6 +231,8 @@ onUiLoaded(async() => {
     const functionMap = {
         "Zoom": "canvas_hotkey_zoom",
         "Adjust brush size": "canvas_hotkey_adjust",
+        "Hotkey shrink brush": "canvas_hotkey_shrink_brush",
+        "Hotkey enlarge brush": "canvas_hotkey_grow_brush",
         "Moving canvas": "canvas_hotkey_move",
         "Fullscreen": "canvas_hotkey_fullscreen",
         "Reset Zoom": "canvas_hotkey_reset",
@@ -248,6 +254,7 @@ onUiLoaded(async() => {
     let isMoving = false;
     let mouseX, mouseY;
     let activeElement;
+    let interactedWithAltKey = false;
 
     const elements = Object.fromEntries(
         Object.keys(elementIDs).map(id => [
@@ -273,7 +280,7 @@ onUiLoaded(async() => {
         const targetElement = gradioApp().querySelector(elemId);
 
         if (!targetElement) {
-            console.log("Element not found");
+            console.log("Element not found", elemId);
             return;
         }
 
@@ -288,7 +295,7 @@ onUiLoaded(async() => {
 
         // Create tooltip
         function createTooltip() {
-            const toolTipElemnt =
+            const toolTipElement =
                 targetElement.querySelector(".image-container");
             const tooltip = document.createElement("div");
             tooltip.className = "canvas-tooltip";
@@ -351,7 +358,7 @@ onUiLoaded(async() => {
             tooltip.appendChild(tooltipContent);
 
             // Add a hint element to the target element
-            toolTipElemnt.appendChild(tooltip);
+            toolTipElement.appendChild(tooltip);
         }
 
         //Show tool tip if setting enable
@@ -361,9 +368,9 @@ onUiLoaded(async() => {
 
         // In the course of research, it was found that the tag img is very harmful when zooming and creates white canvases. This hack allows you to almost never think about this problem, it has no effect on webui.
         function fixCanvas() {
-            const activeTab = getActiveTab(elements).textContent.trim();
+            const activeTab = getActiveTab(elements)?.textContent.trim();
 
-            if (activeTab !== "img2img") {
+            if (activeTab && activeTab !== "img2img") {
                 const img = targetElement.querySelector(`${elemId} img`);
 
                 if (img && img.style.display !== "none") {
@@ -504,6 +511,10 @@ onUiLoaded(async() => {
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
                 e.preventDefault();
 
+                if (hotkeysConfig.canvas_hotkey_zoom === "Alt") {
+                    interactedWithAltKey = true;
+                }
+
                 let zoomPosX, zoomPosY;
                 let delta = 0.2;
                 if (elemData[elemId].zoomLevel > 7) {
@@ -686,7 +697,9 @@ onUiLoaded(async() => {
             const hotkeyActions = {
                 [hotkeysConfig.canvas_hotkey_reset]: resetZoom,
                 [hotkeysConfig.canvas_hotkey_overlap]: toggleOverlap,
-                [hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen
+                [hotkeysConfig.canvas_hotkey_fullscreen]: fitToScreen,
+                [hotkeysConfig.canvas_hotkey_shrink_brush]: () => adjustBrushSize(elemId, 10),
+                [hotkeysConfig.canvas_hotkey_grow_brush]: () => adjustBrushSize(elemId, -10)
             };
 
             const action = hotkeyActions[event.code];
@@ -777,23 +790,29 @@ onUiLoaded(async() => {
         targetElement.addEventListener("mouseleave", handleMouseLeave);
 
         // Reset zoom when click on another tab
-        elements.img2imgTabs.addEventListener("click", resetZoom);
-        elements.img2imgTabs.addEventListener("click", () => {
-            // targetElement.style.width = "";
-            if (parseInt(targetElement.style.width) > 865) {
-                setTimeout(fitToElement, 0);
-            }
-        });
+        if (elements.img2imgTabs) {
+            elements.img2imgTabs.addEventListener("click", resetZoom);
+            elements.img2imgTabs.addEventListener("click", () => {
+                // targetElement.style.width = "";
+                if (parseInt(targetElement.style.width) > 865) {
+                    setTimeout(fitToElement, 0);
+                }
+            });
+        }
 
         targetElement.addEventListener("wheel", e => {
             // change zoom level
-            const operation = e.deltaY > 0 ? "-" : "+";
+            const operation = (e.deltaY || -e.wheelDelta) > 0 ? "-" : "+";
             changeZoomLevel(operation, e);
 
             // Handle brush size adjustment with ctrl key pressed
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
                 e.preventDefault();
 
+                if (hotkeysConfig.canvas_hotkey_adjust === "Alt") {
+                    interactedWithAltKey = true;
+                }
+
                 // Increase or decrease brush size based on scroll direction
                 adjustBrushSize(elemId, e.deltaY);
             }
@@ -833,6 +852,20 @@ onUiLoaded(async() => {
         document.addEventListener("keydown", handleMoveKeyDown);
         document.addEventListener("keyup", handleMoveKeyUp);
 
+
+        // Prevent firefox from opening main menu when alt is used as a hotkey for zoom or brush size
+        function handleAltKeyUp(e) {
+            if (e.key !== "Alt" || !interactedWithAltKey) {
+                return;
+            }
+
+            e.preventDefault();
+            interactedWithAltKey = false;
+        }
+
+        document.addEventListener("keyup", handleAltKeyUp);
+
+
         // Detect zoom level and update the pan speed.
         function updatePanPosition(movementX, movementY) {
             let panSpeed = 2;

extensions-builtin/canvas-zoom-and-pan/scripts/hotkey_config.py

@@ -4,12 +4,14 @@ from modules import shared
 shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas Hotkeys"), {
     "canvas_hotkey_zoom": shared.OptionInfo("Alt", "Zoom canvas", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
     "canvas_hotkey_adjust": shared.OptionInfo("Ctrl", "Adjust brush size", gr.Radio, {"choices": ["Shift","Ctrl", "Alt"]}).info("If you choose 'Shift' you cannot scroll horizontally, 'Alt' can cause a little trouble in firefox"),
+    "canvas_hotkey_shrink_brush": shared.OptionInfo("Q", "Shrink the brush size"),
+    "canvas_hotkey_grow_brush": shared.OptionInfo("W", "Enlarge the brush size"),
     "canvas_hotkey_move": shared.OptionInfo("F", "Moving the canvas").info("To work correctly in firefox, turn off 'Automatically search the page text when typing' in the browser settings"),
     "canvas_hotkey_fullscreen": shared.OptionInfo("S", "Fullscreen Mode, maximizes the picture so that it fits into the screen and stretches it to its full width "),
-    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas positon"),
-    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, neededs for testing"),
+    "canvas_hotkey_reset": shared.OptionInfo("R", "Reset zoom and canvas position"),
+    "canvas_hotkey_overlap": shared.OptionInfo("O", "Toggle overlap").info("Technical button, needed for testing"),
     "canvas_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
     "canvas_auto_expand": shared.OptionInfo(True, "Automatically expands an image that does not fit completely in the canvas area, similar to manually pressing the S and R buttons"),
     "canvas_blur_prompt": shared.OptionInfo(False, "Take the focus off the prompt when working with a canvas"),
-    "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size", "Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
+    "canvas_disabled_functions": shared.OptionInfo(["Overlap"], "Disable function that you don't use", gr.CheckboxGroup, {"choices": ["Zoom","Adjust brush size","Hotkey enlarge brush","Hotkey shrink brush","Moving canvas","Fullscreen","Reset Zoom","Overlap"]}),
 }))

extensions-builtin/extra-options-section/scripts/extra_options_section.py

 import math
 
 import gradio as gr
-from modules import scripts, shared, ui_components, ui_settings, generation_parameters_copypaste
+from modules import scripts, shared, ui_components, ui_settings, infotext_utils, errors
 from modules.ui_components import FormColumn
 
 
@@ -25,7 +25,7 @@ class ExtraOptionsSection(scripts.Script):
         extra_options = shared.opts.extra_options_img2img if is_img2img else shared.opts.extra_options_txt2img
         elem_id_tabname = "extra_options_" + ("img2img" if is_img2img else "txt2img")
 
-        mapping = {k: v for v, k in generation_parameters_copypaste.infotext_to_setting_name_mapping}
+        mapping = {k: v for v, k in infotext_utils.infotext_to_setting_name_mapping}
 
         with gr.Blocks() as interface:
             with gr.Accordion("Options", open=False, elem_id=elem_id_tabname) if shared.opts.extra_options_accordion and extra_options else gr.Group(elem_id=elem_id_tabname):
@@ -42,7 +42,11 @@ class ExtraOptionsSection(scripts.Script):
                             setting_name = extra_options[index]
 
                             with FormColumn():
-                                comp = ui_settings.create_setting_component(setting_name)
+                                try:
+                                    comp = ui_settings.create_setting_component(setting_name)
+                                except KeyError:
+                                    errors.report(f"Can't add extra options for {setting_name} in ui")
+                                    continue
 
                             self.comps.append(comp)
                             self.setting_names.append(setting_name)

extensions-builtin/hypertile/scripts/hypertile_script.py

 import hypertile
 from modules import scripts, script_callbacks, shared
-from scripts.hypertile_xyz import add_axis_options
 
 
 class ScriptHypertile(scripts.Script):
@@ -93,7 +92,6 @@ def on_ui_settings():
         "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile U-Net max depth").info("larger = more neural network layers affected; minor effect on performance"),
         "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-Net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile U-Net max tile size").info("larger = worse performance"),
         "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-Net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile U-Net swap size"),
-
         "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE", infotext="Hypertile VAE").info("minimal change in the generated picture"),
         "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile VAE max depth"),
         "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile VAE max tile size"),
@@ -105,5 +103,20 @@ def on_ui_settings():
         shared.opts.add_option(name, opt)
 
 
+def add_axis_options():
+    xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
+    xyz_grid.axis_options.extend([
+        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet_secondpass', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_unet"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] Unet Max Depth'), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_unet"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] Unet Max Tile Size')),
+        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_unet"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] Unet Swap Size')),
+        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, xyz_grid.apply_override('hypertile_enable_vae', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_vae"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] VAE Max Depth'), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_vae"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] VAE Max Tile Size')),
+        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_vae"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] VAE Swap Size')),
+    ])
+
+
 script_callbacks.on_ui_settings(on_ui_settings)
 script_callbacks.on_before_ui(add_axis_options)

extensions-builtin/hypertile/scripts/hypertile_xyz.py

-from modules import scripts
-from modules.shared import opts
-
-xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
-
-def int_applier(value_name:str, min_range:int = -1, max_range:int = -1):
-    """
-    Returns a function that applies the given value to the given value_name in opts.data.
-    """
-    def validate(value_name:str, value:str):
-        value = int(value)
-        # validate value
-        if not min_range == -1:
-            assert value >= min_range, f"Value {value} for {value_name} must be greater than or equal to {min_range}"
-        if not max_range == -1:
-            assert value <= max_range, f"Value {value} for {value_name} must be less than or equal to {max_range}"
-    def apply_int(p, x, xs):
-        validate(value_name, x)
-        opts.data[value_name] = int(x)
-    return apply_int
-
-def bool_applier(value_name:str):
-    """
-    Returns a function that applies the given value to the given value_name in opts.data.
-    """
-    def validate(value_name:str, value:str):
-        assert value.lower() in ["true", "false"], f"Value {value} for {value_name} must be either true or false"
-    def apply_bool(p, x, xs):
-        validate(value_name, x)
-        value_boolean = x.lower() == "true"
-        opts.data[value_name] = value_boolean
-    return apply_bool
-
-def add_axis_options():
-    extra_axis_options = [
-        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, bool_applier("hypertile_enable_unet"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, bool_applier("hypertile_enable_unet_secondpass"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, int_applier("hypertile_max_depth_unet", 0, 3), choices=lambda: [str(x) for x in range(4)]),
-        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, int_applier("hypertile_max_tile_unet", 0, 512)),
-        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, int_applier("hypertile_swap_size_unet", 0, 64)),
-        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, bool_applier("hypertile_enable_vae"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, int_applier("hypertile_max_depth_vae", 0, 3), choices=lambda: [str(x) for x in range(4)]),
-        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, int_applier("hypertile_max_tile_vae", 0, 512)),
-        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, int_applier("hypertile_swap_size_vae", 0, 64)),
-    ]
-    set_a = {opt.label for opt in xyz_grid.axis_options}
-    set_b = {opt.label for opt in extra_axis_options}
-    if set_a.intersection(set_b):
-        return
-
-    xyz_grid.axis_options.extend(extra_axis_options)

scripts/processing_autosized_crop.py → extensions-builtin/postprocessing-for-training/scripts/postprocessing_autosized_crop.py

@@ -28,7 +28,7 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr
 
 class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing):
     name = "Auto-sized crop"
-    order = 4000
+    order = 4020
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Auto-sized crop") as enable:

scripts/postprocessing_caption.py → extensions-builtin/postprocessing-for-training/scripts/postprocessing_caption.py

@@ -4,7 +4,7 @@ import gradio as gr
 
 class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
     name = "Caption"
-    order = 4000
+    order = 4040
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Caption") as enable:
@@ -25,6 +25,6 @@ class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
             captions.append(deepbooru.model.tag(pp.image))
 
         if "BLIP" in option:
-            captions.append(shared.interrogator.generate_caption(pp.image))
+            captions.append(shared.interrogator.interrogate(pp.image.convert("RGB")))
 
         pp.caption = ", ".join([x for x in captions if x])

scripts/postprocessing_create_flipped_copies.py → extensions-builtin/postprocessing-for-training/scripts/postprocessing_create_flipped_copies.py

@@ -6,7 +6,7 @@ import gradio as gr
 
 class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing):
     name = "Create flipped copies"
-    order = 4000
+    order = 4030
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Create flipped copies") as enable:

scripts/postprocessing_focal_crop.py → extensions-builtin/postprocessing-for-training/scripts/postprocessing_focal_crop.py

@@ -7,7 +7,7 @@ from modules.textual_inversion import autocrop
 
 class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing):
     name = "Auto focal point crop"
-    order = 4000
+    order = 4010
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Auto focal point crop") as enable:

scripts/postprocessing_split_oversized.py → extensions-builtin/postprocessing-for-training/scripts/postprocessing_split_oversized.py

@@ -61,7 +61,7 @@ class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostproces
             ratio = (pp.image.height * width) / (pp.image.width * height)
             inverse_xy = True
 
-        if ratio >= 1.0 and ratio > split_threshold:
+        if ratio >= 1.0 or ratio > split_threshold:
             return
 
         result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio)

html/extra-networks-card.html

-<div class='card' style={style} onclick={card_clicked} data-name="{name}" {sort_keys}>
+<div class="card" style="{style}" onclick="{card_clicked}" data-name="{name}" {sort_keys}>
 	{background_image}
-	<div class="button-row">
-		{metadata_button}
-		{edit_button}
-	</div>
-	<div class='actions'>
-		<div class='additional'>
-			<span style="display:none" class='search_term{search_only}'>{search_term}</span>
-		</div>
-		<span class='name'>{name}</span>
-		<span class='description'>{description}</span>
+	<div class="button-row">{copy_path_button}{metadata_button}{edit_button}</div>
+	<div class="actions">
+		<div class="additional">{search_terms}</div>
+		<span class="name">{name}</span>
+		<span class="description">{description}</span>
 	</div>
 </div>

html/extra-networks-copy-path-button.html

+<div class="copy-path-button card-button"
+    title="Copy path to clipboard"
+    onclick="extraNetworksCopyCardPath(event)"
+    data-clipboard-text="{filename}">
+</div>
\ No newline at end of file

html/extra-networks-edit-item-button.html

+<div class="edit-button card-button"
+    title="Edit metadata"
+    onclick="extraNetworksEditUserMetadata(event, '{tabname}', '{extra_networks_tabname}')">
+</div>
\ No newline at end of file

html/extra-networks-metadata-button.html

+<div class="metadata-button card-button"
+    title="Show internal metadata"
+    onclick="extraNetworksRequestMetadata(event, '{extra_networks_tabname}')">
+</div>
\ No newline at end of file

html/extra-networks-pane-dirs.html

+    <div class="extra-network-pane-content-dirs">
+        <div id='{tabname}_{extra_networks_tabname}_dirs' class='extra-network-dirs'>
+            {dirs_html}
+        </div>
+        <div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards'>
+            {items_html}
+        </div>
+    </div>

html/extra-networks-pane-tree.html

+    <div class="extra-network-pane-content-tree resize-handle-row">
+        <div id='{tabname}_{extra_networks_tabname}_tree' class='extra-network-tree' style='flex-basis: {extra_networks_tree_view_default_width}px'>
+            {tree_html}
+        </div>
+        <div id='{tabname}_{extra_networks_tabname}_cards' class='extra-network-cards' style='flex-grow: 1;'>
+            {items_html}
+        </div>
+    </div>
\ No newline at end of file

html/extra-networks-pane.html

+<div id='{tabname}_{extra_networks_tabname}_pane' class='extra-network-pane {tree_view_div_default_display_class}'>
+    <div class="extra-network-control" id="{tabname}_{extra_networks_tabname}_controls" style="display:none" >
+        <div class="extra-network-control--search">
+            <input
+                id="{tabname}_{extra_networks_tabname}_extra_search"
+                class="extra-network-control--search-text"
+                type="search"
+                placeholder="Search"
+            >
+        </div>
+
+        <small>Sort: </small>
+        <div 
+            id="{tabname}_{extra_networks_tabname}_extra_sort_path"
+            class="extra-network-control--sort{sort_path_active}"
+            data-sortkey="default"
+            title="Sort by path"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_name"
+            class="extra-network-control--sort{sort_name_active}"
+            data-sortkey="name"
+            title="Sort by name"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_date_created"
+            class="extra-network-control--sort{sort_date_created_active}"
+            data-sortkey="date_created"
+            title="Sort by date created"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_date_modified"
+            class="extra-network-control--sort{sort_date_modified_active}"
+            data-sortkey="date_modified"
+            title="Sort by date modified"
+            onclick="extraNetworksControlSortOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-icon"></i>
+        </div>
+
+        <small> </small>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_sort_dir"
+            class="extra-network-control--sort-dir"
+            data-sortdir="{data_sortdir}"
+            title="Sort ascending"
+            onclick="extraNetworksControlSortDirOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--sort-dir-icon"></i>
+        </div>
+
+
+        <small> </small>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_tree_view"
+            class="extra-network-control--tree-view {tree_view_btn_extra_class}"
+            title="Enable Tree View"
+            onclick="extraNetworksControlTreeViewOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--tree-view-icon"></i>
+        </div>
+        <div
+            id="{tabname}_{extra_networks_tabname}_extra_refresh"
+            class="extra-network-control--refresh"
+            title="Refresh page"
+            onclick="extraNetworksControlRefreshOnClick(event, '{tabname}', '{extra_networks_tabname}');"
+        >
+            <i class="extra-network-control--icon extra-network-control--refresh-icon"></i>
+        </div>
+    </div>
+    {pane_content}
+</div>

html/extra-networks-tree-button.html

+<span data-filterable-item-text hidden>{search_terms}</span>
+<div class="tree-list-content {subclass}"
+    type="button"
+    onclick="extraNetworksTreeOnClick(event, '{tabname}', '{extra_networks_tabname}');{onclick_extra}"
+    data-path="{data_path}"
+    data-hash="{data_hash}"
+>
+    <span class='tree-list-item-action tree-list-item-action--leading'>
+        {action_list_item_action_leading}
+    </span>
+    <span class="tree-list-item-visual tree-list-item-visual--leading">
+        {action_list_item_visual_leading}
+    </span>
+    <span class="tree-list-item-label tree-list-item-label--truncate">
+        {action_list_item_label}
+    </span>
+    <span class="tree-list-item-visual tree-list-item-visual--trailing">
+        {action_list_item_visual_trailing}
+    </span>
+    <span class="tree-list-item-action tree-list-item-action--trailing">
+        {action_list_item_action_trailing}
+    </span>
+</div>
\ No newline at end of file

javascript/aspectRatioOverlay.js

@@ -50,17 +50,17 @@ function dimensionChange(e, is_width, is_height) {
         var scaledx = targetElement.naturalWidth * viewportscale;
         var scaledy = targetElement.naturalHeight * viewportscale;
 
-        var cleintRectTop = (viewportOffset.top + window.scrollY);
-        var cleintRectLeft = (viewportOffset.left + window.scrollX);
-        var cleintRectCentreY = cleintRectTop + (targetElement.clientHeight / 2);
-        var cleintRectCentreX = cleintRectLeft + (targetElement.clientWidth / 2);
+        var clientRectTop = (viewportOffset.top + window.scrollY);
+        var clientRectLeft = (viewportOffset.left + window.scrollX);
+        var clientRectCentreY = clientRectTop + (targetElement.clientHeight / 2);
+        var clientRectCentreX = clientRectLeft + (targetElement.clientWidth / 2);
 
         var arscale = Math.min(scaledx / currentWidth, scaledy / currentHeight);
         var arscaledx = currentWidth * arscale;
         var arscaledy = currentHeight * arscale;
 
-        var arRectTop = cleintRectCentreY - (arscaledy / 2);
-        var arRectLeft = cleintRectCentreX - (arscaledx / 2);
+        var arRectTop = clientRectCentreY - (arscaledy / 2);
+        var arRectLeft = clientRectCentreX - (arscaledx / 2);
         var arRectWidth = arscaledx;
         var arRectHeight = arscaledy;
 

javascript/contextMenus.js

@@ -8,9 +8,6 @@ var contextMenuInit = function() {
     };
 
     function showContextMenu(event, element, menuEntries) {
-        let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
-        let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop;
-
         let oldMenu = gradioApp().querySelector('#context-menu');
         if (oldMenu) {
             oldMenu.remove();
@@ -23,10 +20,8 @@ var contextMenuInit = function() {
         contextMenu.style.background = baseStyle.background;
         contextMenu.style.color = baseStyle.color;
         contextMenu.style.fontFamily = baseStyle.fontFamily;
-        contextMenu.style.top = posy + 'px';
-        contextMenu.style.left = posx + 'px';
-
-
+        contextMenu.style.top = event.pageY + 'px';
+        contextMenu.style.left = event.pageX + 'px';
 
         const contextMenuList = document.createElement('ul');
         contextMenuList.className = 'context-menu-items';
@@ -43,21 +38,6 @@ var contextMenuInit = function() {
         });
 
         gradioApp().appendChild(contextMenu);
-
-        let menuWidth = contextMenu.offsetWidth + 4;
-        let menuHeight = contextMenu.offsetHeight + 4;
-
-        let windowWidth = window.innerWidth;
-        let windowHeight = window.innerHeight;
-
-        if ((windowWidth - posx) < menuWidth) {
-            contextMenu.style.left = windowWidth - menuWidth + "px";
-        }
-
-        if ((windowHeight - posy) < menuHeight) {
-            contextMenu.style.top = windowHeight - menuHeight + "px";
-        }
-
     }
 
     function appendContextMenuOption(targetElementSelector, entryName, entryFunction) {
@@ -107,16 +87,23 @@ var contextMenuInit = function() {
                 oldMenu.remove();
             }
         });
-        gradioApp().addEventListener("contextmenu", function(e) {
-            let oldMenu = gradioApp().querySelector('#context-menu');
-            if (oldMenu) {
-                oldMenu.remove();
-            }
-            menuSpecs.forEach(function(v, k) {
-                if (e.composedPath()[0].matches(k)) {
-                    showContextMenu(e, e.composedPath()[0], v);
-                    e.preventDefault();
+        ['contextmenu', 'touchstart'].forEach((eventType) => {
+            gradioApp().addEventListener(eventType, function(e) {
+                let ev = e;
+                if (eventType.startsWith('touch')) {
+                    if (e.touches.length !== 2) return;
+                    ev = e.touches[0];
+                }
+                let oldMenu = gradioApp().querySelector('#context-menu');
+                if (oldMenu) {
+                    oldMenu.remove();
                 }
+                menuSpecs.forEach(function(v, k) {
+                    if (e.composedPath()[0].matches(k)) {
+                        showContextMenu(ev, e.composedPath()[0], v);
+                        e.preventDefault();
+                    }
+                });
             });
         });
         eventListenerApplied = true;

javascript/dragdrop.js

@@ -56,6 +56,15 @@ function eventHasFiles(e) {
     return false;
 }
 
+function isURL(url) {
+    try {
+        const _ = new URL(url);
+        return true;
+    } catch {
+        return false;
+    }
+}
+
 function dragDropTargetIsPrompt(target) {
     if (target?.placeholder && target?.placeholder.indexOf("Prompt") >= 0) return true;
     if (target?.parentNode?.parentNode?.className?.indexOf("prompt") > 0) return true;
@@ -74,22 +83,39 @@ window.document.addEventListener('dragover', e => {
     e.dataTransfer.dropEffect = 'copy';
 });
 
-window.document.addEventListener('drop', e => {
+window.document.addEventListener('drop', async e => {
     const target = e.composedPath()[0];
-    if (!eventHasFiles(e)) return;
+    const url = e.dataTransfer.getData('text/uri-list') || e.dataTransfer.getData('text/plain');
+    if (!eventHasFiles(e) && !isURL(url)) return;
 
     if (dragDropTargetIsPrompt(target)) {
         e.stopPropagation();
         e.preventDefault();
 
-        let prompt_target = get_tab_index('tabs') == 1 ? "img2img_prompt_image" : "txt2img_prompt_image";
+        const isImg2img = get_tab_index('tabs') == 1;
+        let prompt_image_target = isImg2img ? "img2img_prompt_image" : "txt2img_prompt_image";
 
-        const imgParent = gradioApp().getElementById(prompt_target);
+        const imgParent = gradioApp().getElementById(prompt_image_target);
         const files = e.dataTransfer.files;
         const fileInput = imgParent.querySelector('input[type="file"]');
-        if (fileInput) {
+        if (eventHasFiles(e) && fileInput) {
             fileInput.files = files;
             fileInput.dispatchEvent(new Event('change'));
+        } else if (url) {
+            try {
+                const request = await fetch(url);
+                if (!request.ok) {
+                    console.error('Error fetching URL:', url, request.status);
+                    return;
+                }
+                const data = new DataTransfer();
+                data.items.add(new File([await request.blob()], 'image.png'));
+                fileInput.files = data.files;
+                fileInput.dispatchEvent(new Event('change'));
+            } catch (error) {
+                console.error('Error fetching URL:', url, error);
+                return;
+            }
         }
     }
 

javascript/edit-attention.js

@@ -64,6 +64,14 @@ function keyupEditAttention(event) {
             selectionEnd++;
         }
 
+        // deselect surrounding whitespace
+        while (text[selectionStart] == " " && selectionStart < selectionEnd) {
+            selectionStart++;
+        }
+        while (text[selectionEnd - 1] == " " && selectionEnd > selectionStart) {
+            selectionEnd--;
+        }
+
         target.setSelectionRange(selectionStart, selectionEnd);
         return true;
     }

javascript/extensions.js

@@ -2,8 +2,11 @@
 function extensions_apply(_disabled_list, _update_list, disable_all) {
     var disable = [];
     var update = [];
-
-    gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x) {
+    const extensions_input = gradioApp().querySelectorAll('#extensions input[type="checkbox"]');
+    if (extensions_input.length == 0) {
+        throw Error("Extensions page not yet loaded.");
+    }
+    extensions_input.forEach(function(x) {
         if (x.name.startsWith("enable_") && !x.checked) {
             disable.push(x.name.substring(7));
         }

javascript/progressbar.js

@@ -45,8 +45,15 @@ function formatTime(secs) {
     }
 }
 
+
+var originalAppTitle = undefined;
+
+onUiLoaded(function() {
+    originalAppTitle = document.title;
+});
+
 function setTitle(progress) {
-    var title = 'Stable Diffusion';
+    var title = originalAppTitle;
 
     if (opts.show_progress_in_title && progress) {
         title = '[' + progress.trim() + '] ' + title;
@@ -69,6 +76,26 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     var dateStart = new Date();
     var wasEverActive = false;
     var parentProgressbar = progressbarContainer.parentNode;
+    var wakeLock = null;
+
+    var requestWakeLock = async function() {
+        if (!opts.prevent_screen_sleep_during_generation || wakeLock) return;
+        try {
+            wakeLock = await navigator.wakeLock.request('screen');
+        } catch (err) {
+            console.error('Wake Lock is not supported.');
+        }
+    };
+
+    var releaseWakeLock = async function() {
+        if (!opts.prevent_screen_sleep_during_generation || !wakeLock) return;
+        try {
+            await wakeLock.release();
+            wakeLock = null;
+        } catch (err) {
+            console.error('Wake Lock release failed', err);
+        }
+    };
 
     var divProgress = document.createElement('div');
     divProgress.className = 'progressDiv';
@@ -82,6 +109,7 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     var livePreview = null;
 
     var removeProgressBar = function() {
+        releaseWakeLock();
         if (!divProgress) return;
 
         setTitle("");
@@ -93,6 +121,7 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     };
 
     var funProgress = function(id_task) {
+        requestWakeLock();
         request("./internal/progress", {id_task: id_task, live_preview: false}, function(res) {
             if (res.completed) {
                 removeProgressBar();