Merge branch 'dev' into finer-settings-freezing-control

.github/workflows/on_pull_request.yaml

@@ -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==0.0.272
+        run: pip install ruff==0.1.6
       - name: Run Ruff
         run: ruff .
   lint-js:

.github/workflows/run_tests.yaml

@@ -20,6 +20,12 @@ jobs:
           cache-dependency-path: |
             **/requirements*txt
             launch.py
+      - name: Cache models
+        id: cache-models
+        uses: actions/cache@v3
+        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()

.gitignore

@@ -37,3 +37,4 @@ notification.mp3
 /node_modules
 /package-lock.json
 /.coverage*
+/test/test_outputs

README.md

@@ -91,6 +91,7 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
 - Now with a license!
 - Reorder elements in the UI from settings screen
+- [Segmind Stable Diffusion](https://huggingface.co/segmind/SSD-1B) support
 
 ## Installation and Running
 Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:
@@ -120,7 +121,9 @@ 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
+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
 ```
@@ -146,7 +149,7 @@ 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/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
+- Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
 - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
 - GFPGAN - https://github.com/TencentARC/GFPGAN.git
 - CodeFormer - https://github.com/sczhou/CodeFormer
@@ -173,5 +176,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
 - LyCORIS - KohakuBlueleaf
 - Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
+- Hypertile - tfernd - https://github.com/tfernd/HyperTile
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

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: True
+        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

extensions-builtin/Lora/lyco_helpers.py

@@ -19,3 +19,50 @@ def rebuild_cp_decomposition(up, down, mid):
     up = up.reshape(up.size(0), -1)
     down = down.reshape(down.size(0), -1)
     return torch.einsum('n m k l, i n, m j -> i j k l', mid, up, down)
+
+
+# copied from https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/lokr.py
+def factorization(dimension: int, factor:int=-1) -> tuple[int, int]:
+    '''
+    return a tuple of two value of input dimension decomposed by the number closest to factor
+    second value is higher or equal than first value.
+
+    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.
+
+    examples)
+    factor
+        -1               2                4               8               16               ...
+    127 -> 1, 127   127 -> 1, 127    127 -> 1, 127   127 -> 1, 127   127 -> 1, 127
+    128 -> 8, 16    128 -> 2, 64     128 -> 4, 32    128 -> 8, 16    128 -> 8, 16
+    250 -> 10, 25   250 -> 2, 125    250 -> 2, 125   250 -> 5, 50    250 -> 10, 25
+    360 -> 8, 45    360 -> 2, 180    360 -> 4, 90    360 -> 8, 45    360 -> 12, 30
+    512 -> 16, 32   512 -> 2, 256    512 -> 4, 128   512 -> 8, 64    512 -> 16, 32
+    1024 -> 32, 32  1024 -> 2, 512   1024 -> 4, 256  1024 -> 8, 128  1024 -> 16, 64
+    '''
+
+    if factor > 0 and (dimension % factor) == 0:
+        m = factor
+        n = dimension // factor
+        if m > n:
+            n, m = m, n
+        return m, n
+    if factor < 0:
+        factor = dimension
+    m, n = 1, dimension
+    length = m + n
+    while m<n:
+        new_m = m + 1
+        while dimension%new_m != 0:
+            new_m += 1
+        new_n = dimension // new_m
+        if new_m + new_n > length or new_m>factor:
+            break
+        else:
+            m, n = new_m, new_n
+    if m > n:
+        n, m = m, n
+    return m, n
+

extensions-builtin/Lora/network.py

@@ -137,7 +137,7 @@ class NetworkModule:
     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:

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

@@ -61,13 +61,13 @@ 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
+
+
+class ModuleTypeOFT(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["oft_blocks"]) or all(x in weights.w for x in ["oft_diag"]):
+            return NetworkModuleOFT(net, weights)
+
+        return None
+
+# Supports both kohya-ss' implementation of COFT  https://github.com/kohya-ss/sd-scripts/blob/main/networks/oft.py
+# and KohakuBlueleaf's implementation of OFT/COFT https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/diag_oft.py
+class NetworkModuleOFT(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+
+        super().__init__(net, weights)
+
+        self.lin_module = None
+        self.org_module: list[torch.Module] = [self.sd_module]
+
+        self.scale = 1.0
+
+        # kohya-ss
+        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.dim = self.oft_blocks.shape[0] # lora dim
+        # LyCORIS
+        elif "oft_diag" in weights.w.keys():
+            self.is_kohya = False
+            self.oft_blocks = weights.w["oft_diag"]
+            # self.alpha is unused
+            self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
+
+        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear]
+        is_conv = type(self.sd_module) in [torch.nn.Conv2d]
+        is_other_linear = type(self.sd_module) in [torch.nn.MultiheadAttention] # unsupported
+
+        if is_linear:
+            self.out_dim = self.sd_module.out_features
+        elif is_conv:
+            self.out_dim = self.sd_module.out_channels
+        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:
+            self.constraint = None
+            self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
+
+    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 = 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
+        output_shape = orig_weight.shape
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/networks.py

+import gradio as gr
 import logging
 import os
 import re
@@ -11,6 +12,7 @@ import network_ia3
 import network_lokr
 import network_full
 import network_norm
+import network_oft
 
 import torch
 from typing import Union
@@ -28,6 +30,7 @@ module_types = [
     network_full.ModuleTypeFull(),
     network_norm.ModuleTypeNorm(),
     network_glora.ModuleTypeGLora(),
+    network_oft.ModuleTypeOFT(),
 ]
 
 
@@ -157,7 +160,8 @@ def load_network(name, network_on_disk):
     bundle_embeddings = {}
 
     for key_network, weight in sd.items():
-        key_network_without_network_parts, network_part = key_network.split(".", 1)
+        key_network_without_network_parts, _, network_part = key_network.partition(".")
+
         if key_network_without_network_parts == "bundle_emb":
             emb_name, vec_name = network_part.split(".", 1)
             emb_dict = bundle_embeddings.get(emb_name, {})
@@ -189,6 +193,17 @@ def load_network(name, network_on_disk):
                 key = key_network_without_network_parts.replace("lora_te1_text_model", "transformer_text_model")
                 sd_module = shared.sd_model.network_layer_mapping.get(key, None)
 
+        # kohya_ss OFT module
+        elif sd_module is None and "oft_unet" in key_network_without_network_parts:
+            key = key_network_without_network_parts.replace("oft_unet", "diffusion_model")
+            sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+        # KohakuBlueLeaf OFT module
+        if sd_module is None and "oft_diag" in key:
+            key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
+            key = key_network_without_network_parts.replace("lora_te1_text_model", "0_transformer_text_model")
+            sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
         if sd_module is None:
             keys_failed_to_match[key_network] = key
             continue
@@ -300,7 +315,12 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
                 emb_db.skipped_embeddings[name] = embedding
 
     if failed_to_load_networks:
-        sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
+        lora_not_found_message = f'Lora not found: {", ".join(failed_to_load_networks)}'
+        sd_hijack.model_hijack.comments.append(lora_not_found_message)
+        if shared.opts.lora_not_found_warning_console:
+            print(f'\n{lora_not_found_message}\n')
+        if shared.opts.lora_not_found_gradio_warning:
+            gr.Warning(lora_not_found_message)
 
     purge_networks_from_memory()
 
@@ -375,18 +395,26 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
             if module is not None and hasattr(self, 'weight'):
                 try:
                     with torch.no_grad():
-                        updown, ex_bias = module.calc_updown(self.weight)
+                        if getattr(self, 'fp16_weight', None) is None:
+                            weight = self.weight
+                            bias = self.bias
+                        else:
+                            weight = self.fp16_weight.clone().to(self.weight.device)
+                            bias = getattr(self, 'fp16_bias', None)
+                            if bias is not None:
+                                bias = bias.clone().to(self.bias.device)
+                        updown, ex_bias = module.calc_updown(weight)
 
-                        if len(self.weight.shape) == 4 and self.weight.shape[1] == 9:
+                        if len(weight.shape) == 4 and weight.shape[1] == 9:
                             # inpainting model. zero pad updown to make channel[1]  4 to 9
                             updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
 
-                        self.weight += updown
+                        self.weight.copy_((weight.to(dtype=updown.dtype) + updown).to(dtype=self.weight.dtype))
                         if ex_bias is not None and hasattr(self, 'bias'):
                             if self.bias is None:
-                                self.bias = torch.nn.Parameter(ex_bias)
+                                self.bias = torch.nn.Parameter(ex_bias).to(self.weight.dtype)
                             else:
-                                self.bias += ex_bias
+                                self.bias.copy_((bias + ex_bias).to(dtype=self.bias.dtype))
                 except RuntimeError as e:
                     logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
                     extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1

extensions-builtin/Lora/scripts/lora_script.py

@@ -39,6 +39,8 @@ shared.options_templates.update(shared.options_section(('extra_networks', "Extra
     "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

@@ -54,12 +54,13 @@ 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 +128,7 @@ 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),
         ]
@@ -162,7 +164,7 @@ 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 +200,7 @@ 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 +214,9 @@ 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

@@ -17,6 +17,8 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
 
     def create_item(self, name, index=None, enable_filter=True):
         lora_on_disk = networks.available_networks.get(name)
+        if lora_on_disk is None:
+            return
 
         path, ext = os.path.splitext(lora_on_disk.filename)
 
@@ -43,6 +45,11 @@ 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
@@ -66,9 +73,10 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         return item
 
     def list_items(self):
-        for index, name in enumerate(networks.available_networks):
+        # instantiate a list to protect against concurrent modification
+        names = list(networks.available_networks)
+        for index, name in enumerate(names):
             item = self.create_item(name, index)
-
             if item is not None:
                 yield item
 

extensions-builtin/ScuNET/scripts/scunet_model.py

@@ -3,14 +3,11 @@ 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.upscaler_utils import tiled_upscale_2
 
 
 class UpscalerScuNET(modules.upscaler.Upscaler):
@@ -42,47 +39,6 @@ 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()
@@ -106,7 +62,16 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
             _img[:, :, :h, :w] = torch_img # pad image
             torch_img = _img
 
-        torch_output = self.tiled_inference(torch_img, model).squeeze(0)
+        with torch.no_grad():
+            torch_output = tiled_upscale_2(
+                torch_img,
+                model,
+                tile_size=opts.SCUNET_tile,
+                tile_overlap=opts.SCUNET_tile_overlap,
+                scale=1,
+                device=devices.get_device_for('scunet'),
+                desc="ScuNET tiles",
+            ).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
@@ -120,17 +85,10 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         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():

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.shared import opts
 from modules.upscaler import Upscaler, UpscalerData
+from modules.upscaler_utils import tiled_upscale_2
 
 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 +35,29 @@ 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"
+    def do_upscale(self, img: Image.Image, model_file: str) -> Image.Image:
         current_config = (model_file, opts.SWIN_tile)
 
-        if use_compile and self._cached_model_config == current_config:
+        device = self._get_device()
+
+        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 = upscale(
+            img,
+            model,
+            tile=opts.SWIN_tile,
+            tile_overlap=opts.SWIN_tile_overlap,
+            device=device,
+        )
         devices.torch_gc()
         return img
 
@@ -69,69 +70,55 @@ 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
+        model_descriptor = modelloader.load_spandrel_model(
+            filename,
+            device=self._get_device(),
+            dtype=devices.dtype,
+            expected_architecture="SwinIR",
+        )
+        if getattr(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 upscale(
-        img,
-        model,
-        tile=None,
-        tile_overlap=None,
-        window_size=8,
-        scale=4,
+    img,
+    model,
+    *,
+    tile: int,
+    tile_overlap: int,
+    window_size=8,
+    scale=4,
+    device,
 ):
-    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)
+    img = img.unsqueeze(0).to(device, 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 = tiled_upscale_2(
+            img,
+            model,
+            tile_size=tile,
+            tile_overlap=tile_overlap,
+            scale=scale,
+            device=device,
+            desc="SwinIR tiles",
+        )
         output = output[..., : h_old * scale, : w_old * scale]
         output = output.data.squeeze().float().cpu().clamp_(0, 1).numpy()
         if output.ndim == 3:
@@ -142,51 +129,12 @@ def upscale(
         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
-
-
 def on_ui_settings():
     import gradio as gr
 
     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/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
 from modules.ui_components import FormColumn
 
 
@@ -23,11 +23,12 @@ class ExtraOptionsSection(scripts.Script):
         self.setting_names = []
         self.infotext_fields = []
         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.infotext_to_setting_name_mapping}
 
         with gr.Blocks() as interface:
-            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
+            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):
 
                 row_count = math.ceil(len(extra_options) / shared.opts.extra_options_cols)
 
@@ -64,11 +65,14 @@ class ExtraOptionsSection(scripts.Script):
                 p.override_settings[name] = value
 
 
-shared.options_templates.update(shared.options_section(('ui', "User interface"), {
-    "extra_options_txt2img": shared.OptionInfo([], "Options in main UI - txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
-    "extra_options_img2img": shared.OptionInfo([], "Options in main UI - img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
-    "extra_options_cols": shared.OptionInfo(1, "Options in main UI - number of columns", gr.Number, {"precision": 0}).needs_reload_ui(),
-    "extra_options_accordion": shared.OptionInfo(False, "Options in main UI - place into an accordion").needs_reload_ui()
+shared.options_templates.update(shared.options_section(('settings_in_ui', "Settings in UI", "ui"), {
+    "settings_in_ui": shared.OptionHTML("""
+This page allows you to add some settings to the main interface of txt2img and img2img tabs.
+"""),
+    "extra_options_txt2img": shared.OptionInfo([], "Settings for txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
+    "extra_options_img2img": shared.OptionInfo([], "Settings for img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
+    "extra_options_cols": shared.OptionInfo(1, "Number of columns for added settings", gr.Slider, {"step": 1, "minimum": 1, "maximum": 20}).info("displayed amount will depend on the actual browser window width").needs_reload_ui(),
+    "extra_options_accordion": shared.OptionInfo(False, "Place added settings into an accordion").needs_reload_ui()
 }))
 
 

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):
+    name = "Hypertile"
+
+    def title(self):
+        return self.name
+
+    def show(self, is_img2img):
+        return scripts.AlwaysVisible
+
+    def process(self, p, *args):
+        hypertile.set_hypertile_seed(p.all_seeds[0])
+
+        configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
+
+        self.add_infotext(p)
+
+    def before_hr(self, p, *args):
+
+        enable = shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet
+
+        # exclusive hypertile seed for the second pass
+        if enable:
+            hypertile.set_hypertile_seed(p.all_seeds[0])
+
+        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=enable)
+
+        if enable and not shared.opts.hypertile_enable_unet:
+            p.extra_generation_params["Hypertile U-Net second pass"] = True
+
+            self.add_infotext(p, add_unet_params=True)
+
+    def add_infotext(self, p, add_unet_params=False):
+        def option(name):
+            value = getattr(shared.opts, name)
+            default_value = shared.opts.get_default(name)
+            return None if value == default_value else value
+
+        if shared.opts.hypertile_enable_unet:
+            p.extra_generation_params["Hypertile U-Net"] = True
+
+        if shared.opts.hypertile_enable_unet or add_unet_params:
+            p.extra_generation_params["Hypertile U-Net max depth"] = option('hypertile_max_depth_unet')
+            p.extra_generation_params["Hypertile U-Net max tile size"] = option('hypertile_max_tile_unet')
+            p.extra_generation_params["Hypertile U-Net swap size"] = option('hypertile_swap_size_unet')
+
+        if shared.opts.hypertile_enable_vae:
+            p.extra_generation_params["Hypertile VAE"] = True
+            p.extra_generation_params["Hypertile VAE max depth"] = option('hypertile_max_depth_vae')
+            p.extra_generation_params["Hypertile VAE max tile size"] = option('hypertile_max_tile_vae')
+            p.extra_generation_params["Hypertile VAE swap size"] = option('hypertile_swap_size_vae')
+
+
+def configure_hypertile(width, height, enable_unet=True):
+    hypertile.hypertile_hook_model(
+        shared.sd_model.first_stage_model,
+        width,
+        height,
+        swap_size=shared.opts.hypertile_swap_size_vae,
+        max_depth=shared.opts.hypertile_max_depth_vae,
+        tile_size_max=shared.opts.hypertile_max_tile_vae,
+        enable=shared.opts.hypertile_enable_vae,
+    )
+
+    hypertile.hypertile_hook_model(
+        shared.sd_model.model,
+        width,
+        height,
+        swap_size=shared.opts.hypertile_swap_size_unet,
+        max_depth=shared.opts.hypertile_max_depth_unet,
+        tile_size_max=shared.opts.hypertile_max_tile_unet,
+        enable=enable_unet,
+        is_sdxl=shared.sd_model.is_sdxl
+    )
+
+
+def on_ui_settings():
+    import gradio as gr
+
+    options = {
+        "hypertile_explanation": shared.OptionHTML("""
+    <a href='https://github.com/tfernd/HyperTile'>Hypertile</a> optimizes the self-attention layer within U-Net and VAE models,
+    resulting in a reduction in computation time ranging from 1 to 4 times. The larger the generated image is, the greater the
+    benefit.
+    """),
+
+        "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net", infotext="Hypertile U-Net").info("enables hypertile for all modes, including hires fix second pass; noticeable change in details of the generated picture"),
+        "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass", infotext="Hypertile U-Net second pass").info("enables hypertile just for hires fix second pass - regardless of whether the above setting is enabled"),
+        "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"),
+        "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile VAE swap size"),
+    }
+
+    for name, opt in options.items():
+        opt.section = ('hypertile', "Hypertile")
+        shared.opts.add_option(name, opt)
+
+
+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)

extensions-builtin/mobile/javascript/mobile.js

@@ -12,6 +12,8 @@ function isMobile() {
 }
 
 function reportWindowSize() {
+    if (gradioApp().querySelector('.toprow-compact-tools')) return; // not applicable for compact prompt layout
+
     var currentlyMobile = isMobile();
     if (currentlyMobile == isSetupForMobile) return;
     isSetupForMobile = currentlyMobile;

javascript/edit-attention.js

@@ -28,7 +28,7 @@ function keyupEditAttention(event) {
         if (afterParen == -1) return false;
 
         let afterOpeningParen = after.indexOf(OPEN);
-        if (afterOpeningParen != -1 && afterOpeningParen < beforeParen) return false;
+        if (afterOpeningParen != -1 && afterOpeningParen < afterParen) return false;
 
         // Set the selection to the text between the parenthesis
         const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);

javascript/extraNetworks.js

@@ -26,8 +26,9 @@ function setupExtraNetworksForTab(tabname) {
     var refresh = gradioApp().getElementById(tabname + '_extra_refresh');
     var showDirsDiv = gradioApp().getElementById(tabname + '_extra_show_dirs');
     var showDirs = gradioApp().querySelector('#' + tabname + '_extra_show_dirs input');
+    var promptContainer = gradioApp().querySelector('.prompt-container-compact#' + tabname + '_prompt_container');
+    var negativePrompt = gradioApp().querySelector('#' + tabname + '_neg_prompt');
 
-    sort.dataset.sortkey = 'sortDefault';
     tabs.appendChild(searchDiv);
     tabs.appendChild(sort);
     tabs.appendChild(sortOrder);
@@ -49,20 +50,23 @@ function setupExtraNetworksForTab(tabname) {
 
             elem.style.display = visible ? "" : "none";
         });
+
+        applySort();
     };
 
     var applySort = function() {
+        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
+
         var reverse = sortOrder.classList.contains("sortReverse");
-        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim();
-        sortKey = sortKey ? "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1) : "";
-        var sortKeyStore = sortKey ? sortKey + (reverse ? "Reverse" : "") : "";
-        if (!sortKey || sortKeyStore == sort.dataset.sortkey) {
+        var sortKey = sort.querySelector("input").value.toLowerCase().replace("sort", "").replaceAll(" ", "_").replace(/_+$/, "").trim() || "name";
+        sortKey = "sort" + sortKey.charAt(0).toUpperCase() + sortKey.slice(1);
+        var sortKeyStore = sortKey + "-" + (reverse ? "Descending" : "Ascending") + "-" + cards.length;
+
+        if (sortKeyStore == sort.dataset.sortkey) {
             return;
         }
-
         sort.dataset.sortkey = sortKeyStore;
 
-        var cards = gradioApp().querySelectorAll('#' + tabname + '_extra_tabs div.card');
         cards.forEach(function(card) {
             card.originalParentElement = card.parentElement;
         });
@@ -88,15 +92,13 @@ function setupExtraNetworksForTab(tabname) {
     };
 
     search.addEventListener("input", applyFilter);
-    applyFilter();
-    ["change", "blur", "click"].forEach(function(evt) {
-        sort.querySelector("input").addEventListener(evt, applySort);
-    });
     sortOrder.addEventListener("click", function() {
         sortOrder.classList.toggle("sortReverse");
         applySort();
     });
+    applyFilter();
 
+    extraNetworksApplySort[tabname] = applySort;
     extraNetworksApplyFilter[tabname] = applyFilter;
 
     var showDirsUpdate = function() {
@@ -109,11 +111,51 @@ function setupExtraNetworksForTab(tabname) {
     showDirsUpdate();
 }
 
+function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt) {
+    if (!gradioApp().querySelector('.toprow-compact-tools')) return; // only applicable for compact prompt layout
+
+    var promptContainer = gradioApp().getElementById(tabname + '_prompt_container');
+    var prompt = gradioApp().getElementById(tabname + '_prompt_row');
+    var negPrompt = gradioApp().getElementById(tabname + '_neg_prompt_row');
+    var elem = id ? gradioApp().getElementById(id) : null;
+
+    if (showNegativePrompt && elem) {
+        elem.insertBefore(negPrompt, elem.firstChild);
+    } else {
+        promptContainer.insertBefore(negPrompt, promptContainer.firstChild);
+    }
+
+    if (showPrompt && elem) {
+        elem.insertBefore(prompt, elem.firstChild);
+    } else {
+        promptContainer.insertBefore(prompt, promptContainer.firstChild);
+    }
+
+    if (elem) {
+        elem.classList.toggle('extra-page-prompts-active', showNegativePrompt || showPrompt);
+    }
+}
+
+
+function extraNetworksUrelatedTabSelected(tabname) { // called from python when user selects an unrelated tab (generate)
+    extraNetworksMovePromptToTab(tabname, '', false, false);
+}
+
+function extraNetworksTabSelected(tabname, id, showPrompt, showNegativePrompt) { // called from python when user selects an extra networks tab
+    extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePrompt);
+
+}
+
 function applyExtraNetworkFilter(tabname) {
     setTimeout(extraNetworksApplyFilter[tabname], 1);
 }
 
+function applyExtraNetworkSort(tabname) {
+    setTimeout(extraNetworksApplySort[tabname], 1);
+}
+
 var extraNetworksApplyFilter = {};
+var extraNetworksApplySort = {};
 var activePromptTextarea = {};
 
 function setupExtraNetworks() {
@@ -143,8 +185,10 @@ onUiLoaded(setupExtraNetworks);
 var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
 var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
 
-function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
-    var m = text.match(re_extranet);
+var re_extranet_neg = /\(([^:^>]+:[\d.]+)\)/;
+var re_extranet_g_neg = /\(([^:^>]+:[\d.]+)\)/g;
+function tryToRemoveExtraNetworkFromPrompt(textarea, text, isNeg) {
+    var m = text.match(isNeg ? re_extranet_neg : re_extranet);
     var replaced = false;
     var newTextareaText;
     if (m) {
@@ -152,8 +196,8 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
         var extraTextAfterNet = m[2];
         var partToSearch = m[1];
         var foundAtPosition = -1;
-        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found, net, pos) {
-            m = found.match(re_extranet);
+        newTextareaText = textarea.value.replaceAll(isNeg ? re_extranet_g_neg : re_extranet_g, function(found, net, pos) {
+            m = found.match(isNeg ? re_extranet_neg : re_extranet);
             if (m[1] == partToSearch) {
                 replaced = true;
                 foundAtPosition = pos;
@@ -163,7 +207,7 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
         });
 
         if (foundAtPosition >= 0) {
-            if (newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
+            if (extraTextAfterNet && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
                 newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
             }
             if (newTextareaText.substr(foundAtPosition - extraTextBeforeNet.length, extraTextBeforeNet.length) == extraTextBeforeNet) {
@@ -188,14 +232,23 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
     return false;
 }
 
-function cardClicked(tabname, textToAdd, allowNegativePrompt) {
-    var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
+function updatePromptArea(text, textArea, isNeg) {
 
-    if (!tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)) {
-        textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd;
+    if (!tryToRemoveExtraNetworkFromPrompt(textArea, text, isNeg)) {
+        textArea.value = textArea.value + opts.extra_networks_add_text_separator + text;
     }
 
-    updateInput(textarea);
+    updateInput(textArea);
+}
+
+function cardClicked(tabname, textToAdd, textToAddNegative, allowNegativePrompt) {
+    if (textToAddNegative.length > 0) {
+        updatePromptArea(textToAdd, gradioApp().querySelector("#" + tabname + "_prompt > label > textarea"));
+        updatePromptArea(textToAddNegative, gradioApp().querySelector("#" + tabname + "_neg_prompt > label > textarea"), true);
+    } else {
+        var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea");
+        updatePromptArea(textToAdd, textarea);
+    }
 }
 
 function saveCardPreview(event, tabname, filename) {
@@ -350,3 +403,9 @@ function extraNetworksRefreshSingleCard(page, tabname, name) {
         }
     });
 }
+
+window.addEventListener("keydown", function(event) {
+    if (event.key == "Escape") {
+        closePopup();
+    }
+});

javascript/imageviewer.js

@@ -34,7 +34,7 @@ function updateOnBackgroundChange() {
     if (modalImage && modalImage.offsetParent) {
         let currentButton = selected_gallery_button();
         let preview = gradioApp().querySelectorAll('.livePreview > img');
-        if (preview.length > 0) {
+        if (opts.js_live_preview_in_modal_lightbox && preview.length > 0) {
             // show preview image if available
             modalImage.src = preview[preview.length - 1].src;
         } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {

javascript/inputAccordion.js

-var observerAccordionOpen = new MutationObserver(function(mutations) {
-    mutations.forEach(function(mutationRecord) {
-        var elem = mutationRecord.target;
-        var open = elem.classList.contains('open');
+function inputAccordionChecked(id, checked) {
+    var accordion = gradioApp().getElementById(id);
+    accordion.visibleCheckbox.checked = checked;
+    accordion.onVisibleCheckboxChange();
+}
 
-        var accordion = elem.parentNode;
-        accordion.classList.toggle('input-accordion-open', open);
+function setupAccordion(accordion) {
+    var labelWrap = accordion.querySelector('.label-wrap');
+    var gradioCheckbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input");
+    var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
+    var span = labelWrap.querySelector('span');
+    var linked = true;
 
-        var checkbox = gradioApp().querySelector('#' + accordion.id + "-checkbox input");
-        checkbox.checked = open;
-        updateInput(checkbox);
+    var isOpen = function() {
+        return labelWrap.classList.contains('open');
+    };
 
-        var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
-        if (extra) {
-            extra.style.display = open ? "" : "none";
-        }
+    var observerAccordionOpen = new MutationObserver(function(mutations) {
+        mutations.forEach(function(mutationRecord) {
+            accordion.classList.toggle('input-accordion-open', isOpen());
+
+            if (linked) {
+                accordion.visibleCheckbox.checked = isOpen();
+                accordion.onVisibleCheckboxChange();
+            }
+        });
     });
-});
+    observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']});
 
-function inputAccordionChecked(id, checked) {
-    var label = gradioApp().querySelector('#' + id + " .label-wrap");
-    if (label.classList.contains('open') != checked) {
-        label.click();
+    if (extra) {
+        labelWrap.insertBefore(extra, labelWrap.lastElementChild);
     }
+
+    accordion.onChecked = function(checked) {
+        if (isOpen() != checked) {
+            labelWrap.click();
+        }
+    };
+
+    var visibleCheckbox = document.createElement('INPUT');
+    visibleCheckbox.type = 'checkbox';
+    visibleCheckbox.checked = isOpen();
+    visibleCheckbox.id = accordion.id + "-visible-checkbox";
+    visibleCheckbox.className = gradioCheckbox.className + " input-accordion-checkbox";
+    span.insertBefore(visibleCheckbox, span.firstChild);
+
+    accordion.visibleCheckbox = visibleCheckbox;
+    accordion.onVisibleCheckboxChange = function() {
+        if (linked && isOpen() != visibleCheckbox.checked) {
+            labelWrap.click();
+        }
+
+        gradioCheckbox.checked = visibleCheckbox.checked;
+        updateInput(gradioCheckbox);
+    };
+
+    visibleCheckbox.addEventListener('click', function(event) {
+        linked = false;
+        event.stopPropagation();
+    });
+    visibleCheckbox.addEventListener('input', accordion.onVisibleCheckboxChange);
 }
 
 onUiLoaded(function() {
     for (var accordion of gradioApp().querySelectorAll('.input-accordion')) {
-        var labelWrap = accordion.querySelector('.label-wrap');
-        observerAccordionOpen.observe(labelWrap, {attributes: true, attributeFilter: ['class']});
-
-        var extra = gradioApp().querySelector('#' + accordion.id + "-extra");
-        if (extra) {
-            labelWrap.insertBefore(extra, labelWrap.lastElementChild);
-        }
+        setupAccordion(accordion);
     }
 });

javascript/notification.js

@@ -26,7 +26,11 @@ onAfterUiUpdate(function() {
     lastHeadImg = headImg;
 
     // play notification sound if available
-    gradioApp().querySelector('#audio_notification audio')?.play();
+    const notificationAudio = gradioApp().querySelector('#audio_notification audio');
+    if (notificationAudio) {
+        notificationAudio.volume = opts.notification_volume / 100.0 || 1.0;
+        notificationAudio.play();
+    }
 
     if (document.hasFocus()) return;
 

javascript/settings.js

@@ -44,3 +44,28 @@ onUiLoaded(function() {
 
     buttonShowAllPages.addEventListener("click", settingsShowAllTabs);
 });
+
+
+onOptionsChanged(function() {
+    if (gradioApp().querySelector('#settings .settings-category')) return;
+
+    var sectionMap = {};
+    gradioApp().querySelectorAll('#settings > div > button').forEach(function(x) {
+        sectionMap[x.textContent.trim()] = x;
+    });
+
+    opts._categories.forEach(function(x) {
+        var section = x[0];
+        var category = x[1];
+
+        var span = document.createElement('SPAN');
+        span.textContent = category;
+        span.className = 'settings-category';
+
+        var sectionElem = sectionMap[section];
+        if (!sectionElem) return;
+
+        sectionElem.parentElement.insertBefore(span, sectionElem);
+    });
+});
+

javascript/ui.js

@@ -170,6 +170,23 @@ function submit_img2img() {
     return res;
 }
 
+function submit_extras() {
+    showSubmitButtons('extras', false);
+
+    var id = randomId();
+
+    requestProgress(id, gradioApp().getElementById('extras_gallery_container'), gradioApp().getElementById('extras_gallery'), function() {
+        showSubmitButtons('extras', true);
+    });
+
+    var res = create_submit_args(arguments);
+
+    res[0] = id;
+
+    console.log(res);
+    return res;
+}
+
 function restoreProgressTxt2img() {
     showRestoreProgressButton("txt2img", false);
     var id = localGet("txt2img_task_id");
@@ -198,9 +215,33 @@ function restoreProgressImg2img() {
 }
 
 
+/**
+ * Configure the width and height elements on `tabname` to accept
+ * pasting of resolutions in the form of "width x height".
+ */
+function setupResolutionPasting(tabname) {
+    var width = gradioApp().querySelector(`#${tabname}_width input[type=number]`);
+    var height = gradioApp().querySelector(`#${tabname}_height input[type=number]`);
+    for (const el of [width, height]) {
+        el.addEventListener('paste', function(event) {
+            var pasteData = event.clipboardData.getData('text/plain');
+            var parsed = pasteData.match(/^\s*(\d+)\D+(\d+)\s*$/);
+            if (parsed) {
+                width.value = parsed[1];
+                height.value = parsed[2];
+                updateInput(width);
+                updateInput(height);
+                event.preventDefault();
+            }
+        });
+    }
+}
+
 onUiLoaded(function() {
     showRestoreProgressButton('txt2img', localGet("txt2img_task_id"));
     showRestoreProgressButton('img2img', localGet("img2img_task_id"));
+    setupResolutionPasting('txt2img');
+    setupResolutionPasting('img2img');
 });
 
 

modules/api/models.py

@@ -107,6 +107,8 @@ StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
         {"key": "send_images", "type": bool, "default": True},
         {"key": "save_images", "type": bool, "default": False},
         {"key": "alwayson_scripts", "type": dict, "default": {}},
+        {"key": "force_task_id", "type": str, "default": None},
+        {"key": "infotext", "type": str, "default": None},
     ]
 ).generate_model()
 
@@ -124,6 +126,8 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
         {"key": "send_images", "type": bool, "default": True},
         {"key": "save_images", "type": bool, "default": False},
         {"key": "alwayson_scripts", "type": dict, "default": {}},
+        {"key": "force_task_id", "type": str, "default": None},
+        {"key": "infotext", "type": str, "default": None},
     ]
 ).generate_model()
 
@@ -202,9 +206,6 @@ class TrainResponse(BaseModel):
 class CreateResponse(BaseModel):
     info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.")
 
-class PreprocessResponse(BaseModel):
-    info: str = Field(title="Preprocess info", description="Response string from preprocessing task.")
-
 fields = {}
 for key, metadata in opts.data_labels.items():
     value = opts.data.get(key)

modules/cache.py

@@ -32,7 +32,7 @@ def dump_cache():
         with cache_lock:
             cache_filename_tmp = cache_filename + "-"
             with open(cache_filename_tmp, "w", encoding="utf8") as file:
-                json.dump(cache_data, file, indent=4)
+                json.dump(cache_data, file, indent=4, ensure_ascii=False)
 
             os.replace(cache_filename_tmp, cache_filename)
 

modules/call_queue.py

@@ -78,6 +78,7 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
 
         shared.state.skipped = False
         shared.state.interrupted = False
+        shared.state.stopping_generation = False
         shared.state.job_count = 0
 
         if not add_stats:

modules/cmd_args.py

@@ -70,6 +70,7 @@ parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="pre
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
 parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
 parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--use-ipex", action="store_true", help="use Intel XPU as torch device")
 parser.add_argument("--disable-model-loading-ram-optimization", action='store_true', help="disable an optimization that reduces RAM use when loading a model")
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
@@ -109,7 +110,7 @@ parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, req
 parser.add_argument("--disable-tls-verify", action="store_false", help="When passed, enables the use of self-signed certificates.", default=None)
 parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
 parser.add_argument("--gradio-queue", action='store_true', help="does not do anything", default=True)
-parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the defaul in earlier versions")
+parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the default in earlier versions")
 parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
 parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
 parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)

modules/import_hook.py

@@ -3,3 +3,14 @@ import sys
 # this will break any attempt to import xformers which will prevent stability diffusion repo from trying to use it
 if "--xformers" not in "".join(sys.argv):
     sys.modules["xformers"] = None
+
+# Hack to fix a changed import in torchvision 0.17+, which otherwise breaks
+# basicsr; see https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13985
+try:
+    import torchvision.transforms.functional_tensor  # noqa: F401
+except ImportError:
+    try:
+        import torchvision.transforms.functional as functional
+        sys.modules["torchvision.transforms.functional_tensor"] = functional
+    except ImportError:
+        pass  # shrug...