Merge branch 'dev' into allow-no-venv-install

.github/workflows/on_pull_request.yaml

-name: Run Linting/Formatting on Pull Requests
+name: Linter
 
 on:
   - push
@@ -6,7 +6,9 @@ on:
 
 jobs:
   lint-python:
+    name: ruff
     runs-on: ubuntu-latest
+    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
@@ -18,11 +20,13 @@ 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==0.0.265
+        run: pip install ruff==0.0.272
       - name: Run Ruff
         run: ruff .
   lint-js:
+    name: eslint
     runs-on: ubuntu-latest
+    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

.github/workflows/run_tests.yaml

-name: Run basic features tests on CPU with empty SD model
+name: Tests
 
 on:
   - push
@@ -6,7 +6,9 @@ on:
 
 jobs:
   test:
+    name: tests on CPU with empty model
     runs-on: ubuntu-latest
+    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
@@ -39,10 +41,11 @@ jobs:
           --skip-prepare-environment
           --skip-torch-cuda-test
           --test-server
+          --do-not-download-clip
           --no-half
           --disable-opt-split-attention
           --use-cpu all
-          --add-stop-route
+          --api-server-stop
           2>&1 | tee output.txt &
       - name: Run tests
         run: |
@@ -50,7 +53,7 @@ jobs:
           python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
       - name: Kill test server
         if: always()
-        run: curl -vv -XPOST http://127.0.0.1:7860/_stop && sleep 10
+        run: curl -vv -XPOST http://127.0.0.1:7860/sdapi/v1/server-stop && sleep 10
       - name: Show coverage
         run: |
           python -m coverage combine .coverage*

.github/workflows/warns_merge_master.yml

+name: Pull requests can't target master branch
+
+"on":
+  pull_request:
+    types:
+      - opened
+      - synchronize
+      - reopened
+    branches:
+      - master
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Warning marge into master
+        run: |
+          echo -e "::warning::This pull request directly merge into \"master\" branch, normally development happens on \"dev\" branch."
+          exit 1

CHANGELOG.md

+## 1.5.0
+
+### Features:
+ * SD XL support
+ * user metadata system for custom networks
+ * extended Lora metadata editor: set activation text, default weight, view tags, training info
+ * Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)
+ * show github stars for extenstions
+ * img2img batch mode can read extra stuff from png info
+ * img2img batch works with subdirectories
+ * hotkeys to move prompt elements: alt+left/right
+ * restyle time taken/VRAM display
+ * add textual inversion hashes to infotext
+ * optimization: cache git extension repo information
+ * move generate button next to the generated picture for mobile clients
+ * hide cards for networks of incompatible Stable Diffusion version in Lora extra networks interface
+ * skip installing packages with pip if they all are already installed - startup speedup of about 2 seconds
+
+### Minor:
+ * checkbox to check/uncheck all extensions in the Installed tab
+ * add gradio user to infotext and to filename patterns
+ * allow gif for extra network previews
+ * add options to change colors in grid
+ * use natural sort for items in extra networks
+ * Mac: use empty_cache() from torch 2 to clear VRAM
+ * added automatic support for installing the right libraries for Navi3 (AMD)
+ * add option SWIN_torch_compile to accelerate SwinIR upscale
+ * suppress printing TI embedding info at start to console by default
+ * speedup extra networks listing
+ * added `[none]` filename token.
+ * removed thumbs extra networks view mode (use settings tab to change width/height/scale to get thumbs)
+ * add always_discard_next_to_last_sigma option to XYZ plot 
+ 
+### Extensions and API:
+ * api endpoints: /sdapi/v1/server-kill, /sdapi/v1/server-restart, /sdapi/v1/server-stop
+ * allow Script to have custom metaclass
+ * add model exists status check /sdapi/v1/options
+ * rename --add-stop-route to --api-server-stop
+ * add `before_hr` script callback
+ * add callback `after_extra_networks_activate`
+ * disable rich exception output in console for API by default, use WEBUI_RICH_EXCEPTIONS env var to enable
+ * return http 404 when thumb file not found
+ * allow replacing extensions index with environment variable
+ 
+### Bug Fixes:
+ * fix for catch errors when retrieving extension index #11290
+ * fix very slow loading speed of .safetensors files when reading from network drives
+ * API cache cleanup
+ * fix UnicodeEncodeError when writing to file CLIP Interrogator batch mode
+ * fix warning of 'has_mps' deprecated from PyTorch
+ * fix problem with extra network saving images as previews losing generation info
+ * fix throwing exception when trying to resize image with I;16 mode
+ * fix for #11534: canvas zoom and pan extension hijacking shortcut keys
+ * fixed launch script to be runnable from any directory
+ * don't add "Seed Resize: -1x-1" to API image metadata
+ * correctly remove end parenthesis with ctrl+up/down
+ * fixing --subpath on newer gradio version
+ * fix: check fill size none zero when resize  (fixes #11425)
+ * use submit and blur for quick settings textbox
+ * save img2img batch with images.save_image()
+ * prevent running preload.py for disabled extensions
+
+
 ## 1.4.1
 
 ### Bug Fixes:

README.md

@@ -135,8 +135,11 @@ Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-w
 Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
 
 ## Documentation
+
 The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
 
+For the purposes of getting Google and other search engines to crawl the wiki, here's a link to the (not for humans) [crawlable wiki](https://github-wiki-see.page/m/AUTOMATIC1111/stable-diffusion-webui/wiki).
+
 ## Credits
 Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
 
@@ -165,5 +168,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - Security advice - RyotaK
 - UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
 - TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
+- LyCORIS - KohakuBlueleaf
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

extensions-builtin/LDSR/ldsr_model_arch.py

@@ -12,7 +12,7 @@ import safetensors.torch
 
 from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.util import instantiate_from_config, ismap
-from modules import shared, sd_hijack
+from modules import shared, sd_hijack, devices
 
 cached_ldsr_model: torch.nn.Module = None
 
@@ -112,8 +112,7 @@ class LDSR:
 
 
         gc.collect()
-        if torch.cuda.is_available:
-            torch.cuda.empty_cache()
+        devices.torch_gc()
 
         im_og = image
         width_og, height_og = im_og.size
@@ -150,8 +149,7 @@ class LDSR:
 
         del model
         gc.collect()
-        if torch.cuda.is_available:
-            torch.cuda.empty_cache()
+        devices.torch_gc()
 
         return a
 

extensions-builtin/LDSR/scripts/ldsr_model.py

 import os
 
-from basicsr.utils.download_util import load_file_from_url
-
+from modules.modelloader import load_file_from_url
 from modules.upscaler import Upscaler, UpscalerData
 from ldsr_model_arch import LDSR
 from modules import shared, script_callbacks, errors
@@ -43,20 +42,17 @@ class UpscalerLDSR(Upscaler):
         if local_safetensors_path is not None and os.path.exists(local_safetensors_path):
             model = local_safetensors_path
         else:
-            model = local_ckpt_path if local_ckpt_path is not None else load_file_from_url(url=self.model_url, model_dir=self.model_download_path, file_name="model.ckpt", progress=True)
+            model = local_ckpt_path or load_file_from_url(self.model_url, model_dir=self.model_download_path, file_name="model.ckpt")
 
-        yaml = local_yaml_path if local_yaml_path is not None else load_file_from_url(url=self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml", progress=True)
+        yaml = local_yaml_path or load_file_from_url(self.yaml_url, model_dir=self.model_download_path, file_name="project.yaml")
 
-        try:
-            return LDSR(model, yaml)
-        except Exception:
-            errors.report("Error importing LDSR", exc_info=True)
-        return None
+        return LDSR(model, yaml)
 
     def do_upscale(self, img, path):
-        ldsr = self.load_model(path)
-        if ldsr is None:
-            print("NO LDSR!")
+        try:
+            ldsr = self.load_model(path)
+        except Exception:
+            errors.report(f"Failed loading LDSR model {path}", exc_info=True)
             return img
         ddim_steps = shared.opts.ldsr_steps
         return ldsr.super_resolution(img, ddim_steps, self.scale)

extensions-builtin/Lora/extra_networks_lora.py

 from modules import extra_networks, shared
-import lora
+import networks
 
 
 class ExtraNetworkLora(extra_networks.ExtraNetwork):
@@ -9,24 +9,38 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
     def activate(self, p, params_list):
         additional = shared.opts.sd_lora
 
-        if additional != "None" and additional in lora.available_loras and not any(x for x in params_list if x.items[0] == additional):
+        if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
             p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
             params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
 
         names = []
-        multipliers = []
+        te_multipliers = []
+        unet_multipliers = []
+        dyn_dims = []
         for params in params_list:
             assert params.items
 
-            names.append(params.items[0])
-            multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
+            names.append(params.positional[0])
 
-        lora.load_loras(names, multipliers)
+            te_multiplier = float(params.positional[1]) if len(params.positional) > 1 else 1.0
+            te_multiplier = float(params.named.get("te", te_multiplier))
+
+            unet_multiplier = float(params.positional[2]) if len(params.positional) > 2 else te_multiplier
+            unet_multiplier = float(params.named.get("unet", unet_multiplier))
+
+            dyn_dim = int(params.positional[3]) if len(params.positional) > 3 else None
+            dyn_dim = int(params.named["dyn"]) if "dyn" in params.named else dyn_dim
+
+            te_multipliers.append(te_multiplier)
+            unet_multipliers.append(unet_multiplier)
+            dyn_dims.append(dyn_dim)
+
+        networks.load_networks(names, te_multipliers, unet_multipliers, dyn_dims)
 
         if shared.opts.lora_add_hashes_to_infotext:
-            lora_hashes = []
-            for item in lora.loaded_loras:
-                shorthash = item.lora_on_disk.shorthash
+            network_hashes = []
+            for item in networks.loaded_networks:
+                shorthash = item.network_on_disk.shorthash
                 if not shorthash:
                     continue
 
@@ -36,10 +50,10 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
 
                 alias = alias.replace(":", "").replace(",", "")
 
-                lora_hashes.append(f"{alias}: {shorthash}")
+                network_hashes.append(f"{alias}: {shorthash}")
 
-            if lora_hashes:
-                p.extra_generation_params["Lora hashes"] = ", ".join(lora_hashes)
+            if network_hashes:
+                p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
 
     def deactivate(self, p):
         pass

extensions-builtin/Lora/lyco_helpers.py

+import torch
+
+
+def make_weight_cp(t, wa, wb):
+    temp = torch.einsum('i j k l, j r -> i r k l', t, wb)
+    return torch.einsum('i j k l, i r -> r j k l', temp, wa)
+
+
+def rebuild_conventional(up, down, shape, dyn_dim=None):
+    up = up.reshape(up.size(0), -1)
+    down = down.reshape(down.size(0), -1)
+    if dyn_dim is not None:
+        up = up[:, :dyn_dim]
+        down = down[:dyn_dim, :]
+    return (up @ down).reshape(shape)
+
+
+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)

extensions-builtin/Lora/network.py

+import os
+from collections import namedtuple
+import enum
+
+from modules import sd_models, cache, errors, hashes, shared
+
+NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
+
+metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
+
+
+class SdVersion(enum.Enum):
+    Unknown = 1
+    SD1 = 2
+    SD2 = 3
+    SDXL = 4
+
+
+class NetworkOnDisk:
+    def __init__(self, name, filename):
+        self.name = name
+        self.filename = filename
+        self.metadata = {}
+        self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
+
+        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
+
+        if self.is_safetensors:
+            try:
+                self.metadata = cache.cached_data_for_file('safetensors-metadata', "lora/" + self.name, filename, read_metadata)
+            except Exception as e:
+                errors.display(e, f"reading lora {filename}")
+
+        if self.metadata:
+            m = {}
+            for k, v in sorted(self.metadata.items(), key=lambda x: metadata_tags_order.get(x[0], 999)):
+                m[k] = v
+
+            self.metadata = m
+
+        self.alias = self.metadata.get('ss_output_name', self.name)
+
+        self.hash = None
+        self.shorthash = None
+        self.set_hash(
+            self.metadata.get('sshs_model_hash') or
+            hashes.sha256_from_cache(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or
+            ''
+        )
+
+        self.sd_version = self.detect_version()
+
+    def detect_version(self):
+        if str(self.metadata.get('ss_base_model_version', "")).startswith("sdxl_"):
+            return SdVersion.SDXL
+        elif str(self.metadata.get('ss_v2', "")) == "True":
+            return SdVersion.SD2
+        elif len(self.metadata):
+            return SdVersion.SD1
+
+        return SdVersion.Unknown
+
+    def set_hash(self, v):
+        self.hash = v
+        self.shorthash = self.hash[0:12]
+
+        if self.shorthash:
+            import networks
+            networks.available_network_hash_lookup[self.shorthash] = self
+
+    def read_hash(self):
+        if not self.hash:
+            self.set_hash(hashes.sha256(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or '')
+
+    def get_alias(self):
+        import networks
+        if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in networks.forbidden_network_aliases:
+            return self.name
+        else:
+            return self.alias
+
+
+class Network:  # LoraModule
+    def __init__(self, name, network_on_disk: NetworkOnDisk):
+        self.name = name
+        self.network_on_disk = network_on_disk
+        self.te_multiplier = 1.0
+        self.unet_multiplier = 1.0
+        self.dyn_dim = None
+        self.modules = {}
+        self.mtime = None
+
+        self.mentioned_name = None
+        """the text that was used to add the network to prompt - can be either name or an alias"""
+
+
+class ModuleType:
+    def create_module(self, net: Network, weights: NetworkWeights) -> Network | None:
+        return None
+
+
+class NetworkModule:
+    def __init__(self, net: Network, weights: NetworkWeights):
+        self.network = net
+        self.network_key = weights.network_key
+        self.sd_key = weights.sd_key
+        self.sd_module = weights.sd_module
+
+        if hasattr(self.sd_module, 'weight'):
+            self.shape = self.sd_module.weight.shape
+
+        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
+
+    def multiplier(self):
+        if 'transformer' in self.sd_key[:20]:
+            return self.network.te_multiplier
+        else:
+            return self.network.unet_multiplier
+
+    def calc_scale(self):
+        if self.scale is not None:
+            return self.scale
+        if self.dim is not None and self.alpha is not None:
+            return self.alpha / self.dim
+
+        return 1.0
+
+    def finalize_updown(self, updown, orig_weight, output_shape):
+        if self.bias is not None:
+            updown = updown.reshape(self.bias.shape)
+            updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
+            updown = updown.reshape(output_shape)
+
+        if len(output_shape) == 4:
+            updown = updown.reshape(output_shape)
+
+        if orig_weight.size().numel() == updown.size().numel():
+            updown = updown.reshape(orig_weight.shape)
+
+        return updown * self.calc_scale() * self.multiplier()
+
+    def calc_updown(self, target):
+        raise NotImplementedError()
+
+    def forward(self, x, y):
+        raise NotImplementedError()
+

extensions-builtin/Lora/network_full.py

+import network
+
+
+class ModuleTypeFull(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["diff"]):
+            return NetworkModuleFull(net, weights)
+
+        return None
+
+
+class NetworkModuleFull(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.weight = weights.w.get("diff")
+
+    def calc_updown(self, orig_weight):
+        output_shape = self.weight.shape
+        updown = self.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_hada.py

+import lyco_helpers
+import network
+
+
+class ModuleTypeHada(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["hada_w1_a", "hada_w1_b", "hada_w2_a", "hada_w2_b"]):
+            return NetworkModuleHada(net, weights)
+
+        return None
+
+
+class NetworkModuleHada(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        if hasattr(self.sd_module, 'weight'):
+            self.shape = self.sd_module.weight.shape
+
+        self.w1a = weights.w["hada_w1_a"]
+        self.w1b = weights.w["hada_w1_b"]
+        self.dim = self.w1b.shape[0]
+        self.w2a = weights.w["hada_w2_a"]
+        self.w2b = weights.w["hada_w2_b"]
+
+        self.t1 = weights.w.get("hada_t1")
+        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)
+
+        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)
+            updown1 = lyco_helpers.make_weight_cp(t1, w1a, w1b)
+            output_shape += t1.shape[2:]
+        else:
+            if len(w1b.shape) == 4:
+                output_shape += w1b.shape[2:]
+            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)
+            updown2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
+        else:
+            updown2 = lyco_helpers.rebuild_conventional(w2a, w2b, output_shape)
+
+        updown = updown1 * updown2
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_ia3.py

+import network
+
+
+class ModuleTypeIa3(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["weight"]):
+            return NetworkModuleIa3(net, weights)
+
+        return None
+
+
+class NetworkModuleIa3(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.w = weights.w["weight"]
+        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)
+
+        output_shape = [w.size(0), orig_weight.size(1)]
+        if self.on_input:
+            output_shape.reverse()
+        else:
+            w = w.reshape(-1, 1)
+
+        updown = orig_weight * w
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_lokr.py

+import torch
+
+import lyco_helpers
+import network
+
+
+class ModuleTypeLokr(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        has_1 = "lokr_w1" in weights.w or ("lokr_w1_a" in weights.w and "lokr_w1_b" in weights.w)
+        has_2 = "lokr_w2" in weights.w or ("lokr_w2_a" in weights.w and "lokr_w2_b" in weights.w)
+        if has_1 and has_2:
+            return NetworkModuleLokr(net, weights)
+
+        return None
+
+
+def make_kron(orig_shape, w1, w2):
+    if len(w2.shape) == 4:
+        w1 = w1.unsqueeze(2).unsqueeze(2)
+    w2 = w2.contiguous()
+    return torch.kron(w1, w2).reshape(orig_shape)
+
+
+class NetworkModuleLokr(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.w1 = weights.w.get("lokr_w1")
+        self.w1a = weights.w.get("lokr_w1_a")
+        self.w1b = weights.w.get("lokr_w1_b")
+        self.dim = self.w1b.shape[0] if self.w1b is not None else self.dim
+        self.w2 = weights.w.get("lokr_w2")
+        self.w2a = weights.w.get("lokr_w2_a")
+        self.w2b = weights.w.get("lokr_w2_b")
+        self.dim = self.w2b.shape[0] if self.w2b is not None else self.dim
+        self.t2 = weights.w.get("lokr_t2")
+
+    def calc_updown(self, orig_weight):
+        if self.w1 is not None:
+            w1 = self.w1.to(orig_weight.device, dtype=orig_weight.dtype)
+        else:
+            w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+            w1 = w1a @ w1b
+
+        if self.w2 is not None:
+            w2 = self.w2.to(orig_weight.device, dtype=orig_weight.dtype)
+        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)
+            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)
+            w2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
+
+        output_shape = [w1.size(0) * w2.size(0), w1.size(1) * w2.size(1)]
+        if len(orig_weight.shape) == 4:
+            output_shape = orig_weight.shape
+
+        updown = make_kron(output_shape, w1, w2)
+
+        return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/network_lora.py

+import torch
+
+import lyco_helpers
+import network
+from modules import devices
+
+
+class ModuleTypeLora(network.ModuleType):
+    def create_module(self, net: network.Network, weights: network.NetworkWeights):
+        if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
+            return NetworkModuleLora(net, weights)
+
+        return None
+
+
+class NetworkModuleLora(network.NetworkModule):
+    def __init__(self,  net: network.Network, weights: network.NetworkWeights):
+        super().__init__(net, weights)
+
+        self.up_model = self.create_module(weights.w, "lora_up.weight")
+        self.down_model = self.create_module(weights.w, "lora_down.weight")
+        self.mid_model = self.create_module(weights.w, "lora_mid.weight", none_ok=True)
+
+        self.dim = weights.w["lora_down.weight"].shape[0]
+
+    def create_module(self, weights, key, none_ok=False):
+        weight = weights.get(key)
+
+        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_conv = type(self.sd_module) in [torch.nn.Conv2d]
+
+        if is_linear:
+            weight = weight.reshape(weight.shape[0], -1)
+            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
+        elif is_conv and key == "lora_down.weight" or key == "dyn_up":
+            if len(weight.shape) == 2:
+                weight = weight.reshape(weight.shape[0], -1, 1, 1)
+
+            if weight.shape[2] != 1 or weight.shape[3] != 1:
+                module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
+            else:
+                module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
+        elif is_conv and key == "lora_mid.weight":
+            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
+        elif is_conv and key == "lora_up.weight" or key == "dyn_down":
+            module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
+        else:
+            raise AssertionError(f'Lora layer {self.network_key} matched a layer with unsupported type: {type(self.sd_module).__name__}')
+
+        with torch.no_grad():
+            if weight.shape != module.weight.shape:
+                weight = weight.reshape(module.weight.shape)
+            module.weight.copy_(weight)
+
+        module.to(device=devices.cpu, dtype=devices.dtype)
+        module.weight.requires_grad_(False)
+
+        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)
+
+        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)
+            updown = lyco_helpers.rebuild_cp_decomposition(up, down, mid)
+            output_shape += mid.shape[2:]
+        else:
+            if len(down.shape) == 4:
+                output_shape += down.shape[2:]
+            updown = lyco_helpers.rebuild_conventional(up, down, output_shape, self.network.dyn_dim)
+
+        return self.finalize_updown(updown, orig_weight, output_shape)
+
+    def forward(self, x, y):
+        self.up_model.to(device=devices.device)
+        self.down_model.to(device=devices.device)
+
+        return y + self.up_model(self.down_model(x)) * self.multiplier() * self.calc_scale()
+
+

extensions-builtin/Lora/preload.py

@@ -4,3 +4,4 @@ from modules import paths
 
 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'))

extensions-builtin/Lora/scripts/lora_script.py

@@ -4,69 +4,76 @@ import torch
 import gradio as gr
 from fastapi import FastAPI
 
-import lora
+import network
+import networks
+import lora  # noqa:F401
 import extra_networks_lora
 import ui_extra_networks_lora
 from modules import script_callbacks, ui_extra_networks, extra_networks, shared
 
 def unload():
-    torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora
-    torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_lora
-    torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_lora
-    torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_lora
-    torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_lora
-    torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_lora
+    torch.nn.Linear.forward = torch.nn.Linear_forward_before_network
+    torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_network
+    torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_network
+    torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_network
+    torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_network
+    torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_network
 
 
 def before_ui():
     ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
-    extra_networks.register_extra_network(extra_networks_lora.ExtraNetworkLora())
 
+    extra_network = extra_networks_lora.ExtraNetworkLora()
+    extra_networks.register_extra_network(extra_network)
+    extra_networks.register_extra_network_alias(extra_network, "lyco")
 
-if not hasattr(torch.nn, 'Linear_forward_before_lora'):
-    torch.nn.Linear_forward_before_lora = torch.nn.Linear.forward
 
-if not hasattr(torch.nn, 'Linear_load_state_dict_before_lora'):
-    torch.nn.Linear_load_state_dict_before_lora = torch.nn.Linear._load_from_state_dict
+if not hasattr(torch.nn, 'Linear_forward_before_network'):
+    torch.nn.Linear_forward_before_network = torch.nn.Linear.forward
 
-if not hasattr(torch.nn, 'Conv2d_forward_before_lora'):
-    torch.nn.Conv2d_forward_before_lora = torch.nn.Conv2d.forward
+if not hasattr(torch.nn, 'Linear_load_state_dict_before_network'):
+    torch.nn.Linear_load_state_dict_before_network = torch.nn.Linear._load_from_state_dict
 
-if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_lora'):
-    torch.nn.Conv2d_load_state_dict_before_lora = torch.nn.Conv2d._load_from_state_dict
+if not hasattr(torch.nn, 'Conv2d_forward_before_network'):
+    torch.nn.Conv2d_forward_before_network = torch.nn.Conv2d.forward
 
-if not hasattr(torch.nn, 'MultiheadAttention_forward_before_lora'):
-    torch.nn.MultiheadAttention_forward_before_lora = torch.nn.MultiheadAttention.forward
+if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_network'):
+    torch.nn.Conv2d_load_state_dict_before_network = torch.nn.Conv2d._load_from_state_dict
 
-if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_lora'):
-    torch.nn.MultiheadAttention_load_state_dict_before_lora = torch.nn.MultiheadAttention._load_from_state_dict
+if not hasattr(torch.nn, 'MultiheadAttention_forward_before_network'):
+    torch.nn.MultiheadAttention_forward_before_network = torch.nn.MultiheadAttention.forward
 
-torch.nn.Linear.forward = lora.lora_Linear_forward
-torch.nn.Linear._load_from_state_dict = lora.lora_Linear_load_state_dict
-torch.nn.Conv2d.forward = lora.lora_Conv2d_forward
-torch.nn.Conv2d._load_from_state_dict = lora.lora_Conv2d_load_state_dict
-torch.nn.MultiheadAttention.forward = lora.lora_MultiheadAttention_forward
-torch.nn.MultiheadAttention._load_from_state_dict = lora.lora_MultiheadAttention_load_state_dict
+if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_network'):
+    torch.nn.MultiheadAttention_load_state_dict_before_network = torch.nn.MultiheadAttention._load_from_state_dict
 
-script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules)
+torch.nn.Linear.forward = networks.network_Linear_forward
+torch.nn.Linear._load_from_state_dict = networks.network_Linear_load_state_dict
+torch.nn.Conv2d.forward = networks.network_Conv2d_forward
+torch.nn.Conv2d._load_from_state_dict = networks.network_Conv2d_load_state_dict
+torch.nn.MultiheadAttention.forward = networks.network_MultiheadAttention_forward
+torch.nn.MultiheadAttention._load_from_state_dict = networks.network_MultiheadAttention_load_state_dict
+
+script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
 script_callbacks.on_script_unloaded(unload)
 script_callbacks.on_before_ui(before_ui)
-script_callbacks.on_infotext_pasted(lora.infotext_pasted)
+script_callbacks.on_infotext_pasted(networks.infotext_pasted)
 
 
 shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), {
-    "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None", *lora.available_loras]}, refresh=lora.list_available_loras),
+    "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_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"]}),
 }))
 
 
 shared.options_templates.update(shared.options_section(('compatibility', "Compatibility"), {
-    "lora_functional": shared.OptionInfo(False, "Lora: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
+    "lora_functional": shared.OptionInfo(False, "Lora/Networks: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
 }))
 
 
-def create_lora_json(obj: lora.LoraOnDisk):
+def create_lora_json(obj: network.NetworkOnDisk):
     return {
         "name": obj.name,
         "alias": obj.alias,
@@ -75,17 +82,17 @@ def create_lora_json(obj: lora.LoraOnDisk):
     }
 
 
-def api_loras(_: gr.Blocks, app: FastAPI):
+def api_networks(_: gr.Blocks, app: FastAPI):
     @app.get("/sdapi/v1/loras")
     async def get_loras():
-        return [create_lora_json(obj) for obj in lora.available_loras.values()]
+        return [create_lora_json(obj) for obj in networks.available_networks.values()]
 
     @app.post("/sdapi/v1/refresh-loras")
     async def refresh_loras():
-        return lora.list_available_loras()
+        return networks.list_available_networks()
 
 
-script_callbacks.on_app_started(api_loras)
+script_callbacks.on_app_started(api_networks)
 
 re_lora = re.compile("<lora:([^:]+):")
 
@@ -98,19 +105,19 @@ def infotext_pasted(infotext, d):
     hashes = [x.strip().split(':', 1) for x in hashes.split(",")]
     hashes = {x[0].strip().replace(",", ""): x[1].strip() for x in hashes}
 
-    def lora_replacement(m):
+    def network_replacement(m):
         alias = m.group(1)
         shorthash = hashes.get(alias)
         if shorthash is None:
             return m.group(0)
 
-        lora_on_disk = lora.available_lora_hash_lookup.get(shorthash)
-        if lora_on_disk is None:
+        network_on_disk = networks.available_network_hash_lookup.get(shorthash)
+        if network_on_disk is None:
             return m.group(0)
 
-        return f'<lora:{lora_on_disk.get_alias()}:'
+        return f'<lora:{network_on_disk.get_alias()}:'
 
-    d["Prompt"] = re.sub(re_lora, lora_replacement, d["Prompt"])
+    d["Prompt"] = re.sub(re_lora, network_replacement, d["Prompt"])
 
 
 script_callbacks.on_infotext_pasted(infotext_pasted)

extensions-builtin/Lora/ui_edit_user_metadata.py

+import datetime
+import html
+import random
+
+import gradio as gr
+import re
+
+from modules import ui_extra_networks_user_metadata
+
+
+def is_non_comma_tagset(tags):
+    average_tag_length = sum(len(x) for x in tags.keys()) / len(tags)
+
+    return average_tag_length >= 16
+
+
+re_word = re.compile(r"[-_\w']+")
+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)
+
+    if tags and is_non_comma_tagset(tags):
+        new_tags = {}
+
+        for text, text_count in tags.items():
+            for word in re.findall(re_word, text):
+                if len(word) < 3:
+                    continue
+
+                new_tags[word] = new_tags.get(word, 0) + text_count
+
+        tags = new_tags
+
+    ordered_tags = sorted(tags.keys(), key=tags.get, reverse=True)
+
+    return [(tag, tags[tag]) for tag in ordered_tags]
+
+
+class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor):
+    def __init__(self, ui, tabname, page):
+        super().__init__(ui, tabname, page)
+
+        self.select_sd_version = None
+
+        self.taginfo = None
+        self.edit_activation_text = None
+        self.slider_preferred_weight = None
+        self.edit_notes = None
+
+    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, 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["notes"] = notes
+
+        self.write_user_metadata(name, user_metadata)
+
+    def get_metadata_table(self, name):
+        table = super().get_metadata_table(name)
+        item = self.page.items.get(name, {})
+        metadata = item.get("metadata") or {}
+
+        keys = {
+            'ss_sd_model_name': "Model:",
+            'ss_clip_skip': "Clip skip:",
+            'ss_network_module': "Kohya module:",
+        }
+
+        for key, label in keys.items():
+            value = metadata.get(key, None)
+            if value is not None and str(value) != "None":
+                table.append((label, html.escape(value)))
+
+        ss_training_started_at = metadata.get('ss_training_started_at')
+        if ss_training_started_at:
+            table.append(("Date trained:", datetime.datetime.utcfromtimestamp(float(ss_training_started_at)).strftime('%Y-%m-%d %H:%M')))
+
+        ss_bucket_info = metadata.get("ss_bucket_info")
+        if ss_bucket_info and "buckets" in ss_bucket_info:
+            resolutions = {}
+            for _, bucket in ss_bucket_info["buckets"].items():
+                resolution = bucket["resolution"]
+                resolution = f'{resolution[1]}x{resolution[0]}'
+
+                resolutions[resolution] = resolutions.get(resolution, 0) + int(bucket["count"])
+
+            resolutions_list = sorted(resolutions.keys(), key=resolutions.get, reverse=True)
+            resolutions_text = html.escape(", ".join(resolutions_list[0:4]))
+            if len(resolutions) > 4:
+                resolutions_text += ", ..."
+                resolutions_text = f"<span title='{html.escape(', '.join(resolutions_list))}'>{resolutions_text}</span>"
+
+            table.append(('Resolutions:' if len(resolutions_list) > 1 else 'Resolution:', resolutions_text))
+
+        image_count = 0
+        for _, params in metadata.get("ss_dataset_dirs", {}).items():
+            image_count += int(params.get("img_count", 0))
+
+        if image_count:
+            table.append(("Dataset size:", image_count))
+
+        return table
+
+    def put_values_into_components(self, name):
+        user_metadata = self.get_user_metadata(name)
+        values = super().put_values_into_components(name)
+
+        item = self.page.items.get(name, {})
+        metadata = item.get("metadata") or {}
+
+        tags = build_tags(metadata)
+        gradio_tags = [(tag, str(count)) for tag, count in tags[0:24]]
+
+        return [
+            *values[0:5],
+            item.get("sd_version", "Unknown"),
+            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)),
+            gr.update(visible=True if tags else False),
+            gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
+        ]
+
+    def generate_random_prompt(self, name):
+        item = self.page.items.get(name, {})
+        metadata = item.get("metadata") or {}
+        tags = build_tags(metadata)
+
+        return self.generate_random_prompt_from_tags(tags)
+
+    def generate_random_prompt_from_tags(self, tags):
+        max_count = None
+        res = []
+        for tag, count in tags:
+            if not max_count:
+                max_count = count
+
+            v = random.random() * max_count
+            if count > v:
+                res.append(tag)
+
+        return ", ".join(sorted(res))
+
+    def create_extra_default_items_in_left_column(self):
+
+        # this would be a lot better as gr.Radio but I can't make it work
+        self.select_sd_version = gr.Dropdown(['SD1', 'SD2', 'SDXL', 'Unknown'], value='Unknown', label='Stable Diffusion version', interactive=True)
+
+    def create_editor(self):
+        self.create_default_editor_elems()
+
+        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)
+
+        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)
+
+            with gr.Column(scale=1, min_width=120):
+                generate_random_prompt = gr.Button('Generate').style(full_width=True, size="lg")
+
+        self.edit_notes = gr.TextArea(label='Notes', lines=4)
+
+        generate_random_prompt.click(fn=self.generate_random_prompt, inputs=[self.edit_name_input], outputs=[random_prompt], show_progress=False)
+
+        def select_tag(activation_text, evt: gr.SelectData):
+            tag = evt.value[0]
+
+            words = re.split(re_comma, activation_text)
+            if tag in words:
+                words = [x for x in words if x != tag and x.strip()]
+                return ", ".join(words)
+
+            return activation_text + ", " + tag if activation_text else tag
+
+        self.taginfo.select(fn=select_tag, inputs=[self.edit_activation_text], outputs=[self.edit_activation_text], show_progress=False)
+
+        self.create_default_buttons()
+
+        viewed_components = [
+            self.edit_name,
+            self.edit_description,
+            self.html_filedata,
+            self.html_preview,
+            self.edit_notes,
+            self.select_sd_version,
+            self.taginfo,
+            self.edit_activation_text,
+            self.slider_preferred_weight,
+            row_random_prompt,
+            random_prompt,
+        ]
+
+        self.button_edit\
+            .click(fn=self.put_values_into_components, inputs=[self.edit_name_input], outputs=viewed_components)\
+            .then(fn=lambda: gr.update(visible=True), inputs=[], outputs=[self.box])
+
+        edited_components = [
+            self.edit_description,
+            self.select_sd_version,
+            self.edit_activation_text,
+            self.slider_preferred_weight,
+            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

-import json
 import os
-import lora
+
+import network
+import networks
 
 from modules import shared, ui_extra_networks
+from modules.ui_extra_networks import quote_js
+from ui_edit_user_metadata import LoraUserMetadataEditor
 
 
 class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
@@ -10,27 +13,66 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         super().__init__('Lora')
 
     def refresh(self):
-        lora.list_available_loras()
+        networks.list_available_networks()
 
-    def list_items(self):
-        for index, (name, lora_on_disk) in enumerate(lora.available_loras.items()):
-            path, ext = os.path.splitext(lora_on_disk.filename)
+    def create_item(self, name, index=None, enable_filter=True):
+        lora_on_disk = networks.available_networks.get(name)
+
+        path, ext = os.path.splitext(lora_on_disk.filename)
+
+        alias = lora_on_disk.get_alias()
+
+        item = {
+            "name": name,
+            "filename": lora_on_disk.filename,
+            "preview": self.find_preview(path),
+            "description": self.find_description(path),
+            "search_term": self.search_terms_from_path(lora_on_disk.filename),
+            "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)},
+            "sd_version": lora_on_disk.sd_version.name,
+        }
 
-            alias = lora_on_disk.get_alias()
+        self.read_user_metadata(item)
+        activation_text = item["user_metadata"].get("activation text")
+        preferred_weight = item["user_metadata"].get("preferred weight", 0.0)
+        item["prompt"] = quote_js(f"<lora:{alias}:") + " + " + (str(preferred_weight) if preferred_weight else "opts.extra_networks_default_multiplier") + " + " + quote_js(">")
 
-            yield {
-                "name": name,
-                "filename": path,
-                "preview": self.find_preview(path),
-                "description": self.find_description(path),
-                "search_term": self.search_terms_from_path(lora_on_disk.filename),
-                "prompt": json.dumps(f"<lora:{alias}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
-                "local_preview": f"{path}.{shared.opts.samples_format}",
-                "metadata": json.dumps(lora_on_disk.metadata, indent=4) if lora_on_disk.metadata else None,
-                "sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
+        if activation_text:
+            item["prompt"] += " + " + quote_js(" " + activation_text)
+
+        sd_version = item["user_metadata"].get("sd version")
+        if sd_version in network.SdVersion.__members__:
+            item["sd_version"] = sd_version
+            sd_version = network.SdVersion[sd_version]
+        else:
+            sd_version = lora_on_disk.sd_version
+
+        if shared.opts.lora_show_all or not enable_filter:
+            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
+            if model_version.name in shared.opts.lora_hide_unknown_for_versions:
+                return None
+        elif shared.sd_model.is_sdxl and sd_version != network.SdVersion.SDXL:
+            return None
+        elif shared.sd_model.is_sd2 and sd_version != network.SdVersion.SD2:
+            return None
+        elif shared.sd_model.is_sd1 and sd_version != network.SdVersion.SD1:
+            return None
+
+        return item
+
+    def list_items(self):
+        for index, name in enumerate(networks.available_networks):
+            item = self.create_item(name, index)
 
-            }
+            if item is not None:
+                yield item
 
     def allowed_directories_for_previews(self):
-        return [shared.cmd_opts.lora_dir]
+        return [shared.cmd_opts.lora_dir, shared.cmd_opts.lyco_dir_backcompat]
 
+    def create_user_metadata_editor(self, ui, tabname):
+        return LoraUserMetadataEditor(ui, tabname, self)

extensions-builtin/ScuNET/scripts/scunet_model.py

-import os.path
 import sys
 
 import PIL.Image
@@ -6,12 +5,11 @@ import numpy as np
 import torch
 from tqdm import tqdm
 
-from basicsr.utils.download_util import load_file_from_url
-
 import modules.upscaler
 from modules import devices, modelloader, script_callbacks, errors
-from scunet_model_arch import SCUNet as net
+from scunet_model_arch import SCUNet
 
+from modules.modelloader import load_file_from_url
 from modules.shared import opts
 
 
@@ -28,7 +26,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         scalers = []
         add_model2 = True
         for file in model_paths:
-            if "http" in file:
+            if file.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
@@ -87,11 +85,12 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
 
     def do_upscale(self, img: PIL.Image.Image, selected_file):
 
-        torch.cuda.empty_cache()
+        devices.torch_gc()
 
-        model = self.load_model(selected_file)
-        if model is None:
-            print(f"ScuNET: Unable to load model from {selected_file}", file=sys.stderr)
+        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')
@@ -111,7 +110,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         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
-        torch.cuda.empty_cache()
+        devices.torch_gc()
 
         output = np_output.transpose((1, 2, 0))  # CHW to HWC
         output = output[:, :, ::-1]  # BGR to RGB
@@ -119,15 +118,12 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
 
     def load_model(self, path: str):
         device = devices.get_device_for('scunet')
-        if "http" in path:
-            filename = load_file_from_url(url=self.model_url, model_dir=self.model_download_path, file_name="%s.pth" % self.name, progress=True)
+        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")
         else:
             filename = path
-        if not os.path.exists(os.path.join(self.model_path, filename)) or filename is None:
-            print(f"ScuNET: Unable to load model from {filename}", file=sys.stderr)
-            return None
-
-        model = net(in_nc=3, config=[4, 4, 4, 4, 4, 4, 4], dim=64)
+        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():

extensions-builtin/SwinIR/scripts/swinir_model.py

-import os
+import sys
+import platform
 
 import numpy as np
 import torch
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
 from modules import modelloader, devices, script_callbacks, shared
 from modules.shared import opts, state
-from swinir_model_arch import SwinIR as net
-from swinir_model_arch_v2 import Swin2SR as net2
+from swinir_model_arch import SwinIR
+from swinir_model_arch_v2 import Swin2SR
 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')
 
 
 class UpscalerSwinIR(Upscaler):
     def __init__(self, dirname):
+        self._cached_model = None           # keep the model when SWIN_torch_compile is on to prevent re-compile every runs
+        self._cached_model_config = None    # to clear '_cached_model' when changing model (v1/v2) or settings
         self.name = "SwinIR"
-        self.model_url = "https://github.com/JingyunLiang/SwinIR/releases/download/v0.0" \
-                         "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \
-                         "-L_x4_GAN.pth "
+        self.model_url = SWINIR_MODEL_URL
         self.model_name = "SwinIR 4x"
         self.user_path = dirname
         super().__init__()
         scalers = []
         model_files = self.find_models(ext_filter=[".pt", ".pth"])
         for model in model_files:
-            if "http" in model:
+            if model.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(model)
@@ -37,42 +38,54 @@ class UpscalerSwinIR(Upscaler):
         self.scalers = scalers
 
     def do_upscale(self, img, model_file):
-        model = self.load_model(model_file)
-        if model is None:
-            return img
-        model = model.to(device_swinir, dtype=devices.dtype)
+        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)
+
+        if use_compile and 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)
-        try:
-            torch.cuda.empty_cache()
-        except Exception:
-            pass
+        devices.torch_gc()
         return img
 
     def load_model(self, path, scale=4):
-        if "http" in path:
-            dl_name = "%s%s" % (self.model_name.replace(" ", "_"), ".pth")
-            filename = load_file_from_url(url=path, model_dir=self.model_download_path, file_name=dl_name, progress=True)
+        if path.startswith("http"):
+            filename = modelloader.load_file_from_url(
+                url=path,
+                model_dir=self.model_download_path,
+                file_name=f"{self.model_name.replace(' ', '_')}.pth",
+            )
         else:
             filename = path
-        if filename is None or not os.path.exists(filename):
-            return None
         if filename.endswith(".v2.pth"):
-            model = net2(
-            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",
+            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 = net(
+            model = SwinIR(
                 upscale=scale,
                 in_chans=3,
                 img_size=64,
@@ -172,6 +185,8 @@ 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"))
 
 
 script_callbacks.on_ui_settings(on_ui_settings)

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

@@ -200,7 +200,8 @@ onUiLoaded(async() => {
         canvas_hotkey_move: "KeyF",
         canvas_hotkey_overlap: "KeyO",
         canvas_disabled_functions: [],
-        canvas_show_tooltip: true
+        canvas_show_tooltip: true,
+        canvas_blur_prompt: false
     };
 
     const functionMap = {
@@ -608,6 +609,19 @@ onUiLoaded(async() => {
 
         // Handle keydown events
         function handleKeyDown(event) {
+            // Disable key locks to make pasting from the buffer work correctly
+            if ((event.ctrlKey && event.code === 'KeyV') || (event.ctrlKey && event.code === 'KeyC') || event.code === "F5") {
+                return;
+            }
+
+            // before activating shortcut, ensure user is not actively typing in an input field
+            if (!hotkeysConfig.canvas_blur_prompt) {
+                if (event.target.nodeName === 'TEXTAREA' || event.target.nodeName === 'INPUT') {
+                    return;
+                }
+            }
+
+
             const hotkeyActions = {
                 [hotkeysConfig.canvas_hotkey_reset]: resetZoom,
                 [hotkeysConfig.canvas_hotkey_overlap]: toggleOverlap,
@@ -686,6 +700,20 @@ onUiLoaded(async() => {
 
         // Handle the move event for pan functionality. Updates the panX and panY variables and applies the new transform to the target element.
         function handleMoveKeyDown(e) {
+
+            // Disable key locks to make pasting from the buffer work correctly
+            if ((e.ctrlKey && e.code === 'KeyV') || (e.ctrlKey && event.code === 'KeyC') || e.code === "F5") {
+                return;
+            }
+
+            // before activating shortcut, ensure user is not actively typing in an input field
+            if (!hotkeysConfig.canvas_blur_prompt) {
+                if (e.target.nodeName === 'TEXTAREA' || e.target.nodeName === 'INPUT') {
+                    return;
+                }
+            }
+
+
             if (e.code === hotkeysConfig.canvas_hotkey_move) {
                 if (!e.ctrlKey && !e.metaKey && isKeyDownHandlerAttached) {
                     e.preventDefault();

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

@@ -9,5 +9,6 @@ shared.options_templates.update(shared.options_section(('canvas_hotkey', "Canvas
     "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_show_tooltip": shared.OptionInfo(True, "Enable tooltip on the canvas"),
+    "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"]}),
 }))

extensions-builtin/mobile/javascript/mobile.js

+var isSetupForMobile = false;
+
+function isMobile() {
+    for (var tab of ["txt2img", "img2img"]) {
+        var imageTab = gradioApp().getElementById(tab + '_results');
+        if (imageTab && imageTab.offsetParent && imageTab.offsetLeft == 0) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+function reportWindowSize() {
+    var currentlyMobile = isMobile();
+    if (currentlyMobile == isSetupForMobile) return;
+    isSetupForMobile = currentlyMobile;
+
+    for (var tab of ["txt2img", "img2img"]) {
+        var button = gradioApp().getElementById(tab + '_generate_box');
+        var target = gradioApp().getElementById(currentlyMobile ? tab + '_results' : tab + '_actions_column');
+        target.insertBefore(button, target.firstElementChild);
+    }
+}
+
+window.addEventListener("resize", reportWindowSize);

html/extra-networks-card.html

-<div class='card' style={style} onclick={card_clicked} {sort_keys}>
+<div class='card' style={style} onclick={card_clicked} data-name="{name}" {sort_keys}>
 	{background_image}
-	{metadata_button}
+	<div class="button-row">
+		{metadata_button}
+		{edit_button}
+	</div>
 	<div class='actions'>
 		<div class='additional'>
-			<ul>
-				<a href="#" title="replace preview image with currently selected in gallery" onclick={save_card_preview}>replace preview</a>
-			</ul>
 			<span style="display:none" class='search_term{search_only}'>{search_term}</span>
 		</div>
 		<span class='name'>{name}</span>

html/image-update.svg

-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
-  <filter id='shadow' color-interpolation-filters="sRGB">
-    <feDropShadow flood-color="black" dx="0" dy="0" flood-opacity="0.9" stdDeviation="0.5"/>
-    <feDropShadow flood-color="black" dx="0" dy="0" flood-opacity="0.9" stdDeviation="0.5"/>
-  </filter>
-  <path style="filter:url(#shadow);" fill="#FFFFFF" d="M13.18 19C13.35 19.72 13.64 20.39 14.03 21H5C3.9 21 3 20.11 3 19V5C3 3.9 3.9 3 5 3H19C20.11 3 21 3.9 21 5V11.18C20.5 11.07 20 11 19.5 11C19.33 11 19.17 11 19 11.03V5H5V19H13.18M11.21 15.83L9.25 13.47L6.5 17H13.03C13.14 15.54 13.73 14.22 14.64 13.19L13.96 12.29L11.21 15.83M19 13.5V12L16.75 14.25L19 16.5V15C20.38 15 21.5 16.12 21.5 17.5C21.5 17.9 21.41 18.28 21.24 18.62L22.33 19.71C22.75 19.08 23 18.32 23 17.5C23 15.29 21.21 13.5 19 13.5M19 20C17.62 20 16.5 18.88 16.5 17.5C16.5 17.1 16.59 16.72 16.76 16.38L15.67 15.29C15.25 15.92 15 16.68 15 17.5C15 19.71 16.79 21.5 19 21.5V23L21.25 20.75L19 18.5V20Z" />
-</svg>

javascript/badScaleChecker.js

+(function() {
+    var ignore = localStorage.getItem("bad-scale-ignore-it") == "ignore-it";
+
+    function getScale() {
+        var ratio = 0,
+            screen = window.screen,
+            ua = navigator.userAgent.toLowerCase();
+
+        if (window.devicePixelRatio !== undefined) {
+            ratio = window.devicePixelRatio;
+        } else if (~ua.indexOf('msie')) {
+            if (screen.deviceXDPI && screen.logicalXDPI) {
+                ratio = screen.deviceXDPI / screen.logicalXDPI;
+            }
+        } else if (window.outerWidth !== undefined && window.innerWidth !== undefined) {
+            ratio = window.outerWidth / window.innerWidth;
+        }
+
+        return ratio == 0 ? 0 : Math.round(ratio * 100);
+    }
+
+    var showing = false;
+
+    var div = document.createElement("div");
+    div.style.position = "fixed";
+    div.style.top = "0px";
+    div.style.left = "0px";
+    div.style.width = "100vw";
+    div.style.backgroundColor = "firebrick";
+    div.style.textAlign = "center";
+    div.style.zIndex = 99;
+
+    var b = document.createElement("b");
+    b.innerHTML = 'Bad Scale: ??% ';
+
+    div.appendChild(b);
+
+    var note1 = document.createElement("p");
+    note1.innerHTML = "Change your browser or your computer settings!";
+    note1.title = 'Just make sure "computer-scale" * "browser-scale" = 100% ,\n' +
+        "you can keep your computer-scale and only change this page's scale,\n" +
+        "for example: your computer-scale is 125%, just use [\"CTRL\"+\"-\"] to make your browser-scale of this page to 80%.";
+    div.appendChild(note1);
+
+    var note2 = document.createElement("p");
+    note2.innerHTML = " Otherwise, it will cause this page to not function properly!";
+    note2.title = "When you click \"Copy image to: [inpaint sketch]\" in some img2img's tab,\n" +
+        "if scale<100% the canvas will be invisible,\n" +
+        "else if scale>100% this page will take large amount of memory and CPU performance.";
+    div.appendChild(note2);
+
+    var btn = document.createElement("button");
+    btn.innerHTML = "Click here to ignore";
+
+    div.appendChild(btn);
+
+    function tryShowTopBar(scale) {
+        if (showing) return;
+
+        b.innerHTML = 'Bad Scale: ' + scale + '% ';
+
+        var updateScaleTimer = setInterval(function() {
+            var newScale = getScale();
+            b.innerHTML = 'Bad Scale: ' + newScale + '% ';
+            if (newScale == 100) {
+                var p = div.parentNode;
+                if (p != null) p.removeChild(div);
+                showing = false;
+                clearInterval(updateScaleTimer);
+                check();
+            }
+        }, 999);
+
+        btn.onclick = function() {
+            clearInterval(updateScaleTimer);
+            var p = div.parentNode;
+            if (p != null) p.removeChild(div);
+            ignore = true;
+            showing = false;
+            localStorage.setItem("bad-scale-ignore-it", "ignore-it");
+        };
+
+        document.body.appendChild(div);
+    }
+
+    function check() {
+        if (!ignore) {
+            var timer = setInterval(function() {
+                var scale = getScale();
+                if (scale != 100 && !ignore) {
+                    tryShowTopBar(scale);
+                    clearInterval(timer);
+                }
+                if (ignore) {
+                    clearInterval(timer);
+                }
+            }, 999);
+        }
+    }
+
+    if (document.readyState != "complete") {
+        document.onreadystatechange = function() {
+            if (document.readyState != "complete") check();
+        };
+    } else {
+        check();
+    }
+})();

javascript/edit-attention.js

@@ -100,11 +100,12 @@ function keyupEditAttention(event) {
     if (String(weight).length == 1) weight += ".0";
 
     if (closeCharacter == ')' && weight == 1) {
-        text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + 5);
+        var endParenPos = text.substring(selectionEnd).indexOf(')');
+        text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + endParenPos + 1);
         selectionStart--;
         selectionEnd--;
     } else {
-        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + 1 + end - 1);
+        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + end);
     }
 
     target.focus();

javascript/edit-order.js

+/* alt+left/right moves text in prompt */
+
+function keyupEditOrder(event) {
+    if (!opts.keyedit_move) return;
+
+    let target = event.originalTarget || event.composedPath()[0];
+    if (!target.matches("*:is([id*='_toprow'] [id*='_prompt'], .prompt) textarea")) return;
+    if (!event.altKey) return;
+
+    let isLeft = event.key == "ArrowLeft";
+    let isRight = event.key == "ArrowRight";
+    if (!isLeft && !isRight) return;
+    event.preventDefault();
+
+    let selectionStart = target.selectionStart;
+    let selectionEnd = target.selectionEnd;
+    let text = target.value;
+    let items = text.split(",");
+    let indexStart = (text.slice(0, selectionStart).match(/,/g) || []).length;
+    let indexEnd = (text.slice(0, selectionEnd).match(/,/g) || []).length;
+    let range = indexEnd - indexStart + 1;
+
+    if (isLeft && indexStart > 0) {
+        items.splice(indexStart - 1, 0, ...items.splice(indexStart, range));
+        target.value = items.join();
+        target.selectionStart = items.slice(0, indexStart - 1).join().length + (indexStart == 1 ? 0 : 1);
+        target.selectionEnd = items.slice(0, indexEnd).join().length;
+    } else if (isRight && indexEnd < items.length - 1) {
+        items.splice(indexStart + 1, 0, ...items.splice(indexStart, range));
+        target.value = items.join();
+        target.selectionStart = items.slice(0, indexStart + 1).join().length + 1;
+        target.selectionEnd = items.slice(0, indexEnd + 2).join().length;
+    }
+
+    event.preventDefault();
+    updateInput(target);
+}
+
+addEventListener('keydown', (event) => {
+    keyupEditOrder(event);
+});

javascript/extensions.js

@@ -72,3 +72,21 @@ function config_state_confirm_restore(_, config_state_name, config_restore_type)
     }
     return [confirmed, config_state_name, config_restore_type];
 }
+
+function toggle_all_extensions(event) {
+    gradioApp().querySelectorAll('#extensions .extension_toggle').forEach(function(checkbox_el) {
+        checkbox_el.checked = event.target.checked;
+    });
+}
+
+function toggle_extension() {
+    let all_extensions_toggled = true;
+    for (const checkbox_el of gradioApp().querySelectorAll('#extensions .extension_toggle')) {
+        if (!checkbox_el.checked) {
+            all_extensions_toggled = false;
+            break;
+        }
+    }
+
+    gradioApp().querySelector('#extensions .all_extensions_toggle').checked = all_extensions_toggled;
+}

javascript/extraNetworks.js

@@ -113,7 +113,7 @@ function setupExtraNetworks() {
 
 onUiLoaded(setupExtraNetworks);
 
-var re_extranet = /<([^:]+:[^:]+):[\d.]+>/;
+var re_extranet = /<([^:]+:[^:]+):[\d.]+>(.*)/;
 var re_extranet_g = /\s+<([^:]+:[^:]+):[\d.]+>/g;
 
 function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
@@ -121,15 +121,22 @@ function tryToRemoveExtraNetworkFromPrompt(textarea, text) {
     var replaced = false;
     var newTextareaText;
     if (m) {
+        var extraTextAfterNet = m[2];
         var partToSearch = m[1];
-        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found) {
+        var foundAtPosition = -1;
+        newTextareaText = textarea.value.replaceAll(re_extranet_g, function(found, net, pos) {
             m = found.match(re_extranet);
             if (m[1] == partToSearch) {
                 replaced = true;
+                foundAtPosition = pos;
                 return "";
             }
             return found;
         });
+
+        if (foundAtPosition >= 0 && newTextareaText.substr(foundAtPosition, extraTextAfterNet.length) == extraTextAfterNet) {
+            newTextareaText = newTextareaText.substr(0, foundAtPosition) + newTextareaText.substr(foundAtPosition + extraTextAfterNet.length);
+        }
     } else {
         newTextareaText = textarea.value.replaceAll(new RegExp(text, "g"), function(found) {
             if (found == text) {
@@ -182,19 +189,20 @@ function extraNetworksSearchButton(tabs_id, event) {
 
 var globalPopup = null;
 var globalPopupInner = null;
+function closePopup() {
+    if (!globalPopup) return;
+
+    globalPopup.style.display = "none";
+}
 function popup(contents) {
     if (!globalPopup) {
         globalPopup = document.createElement('div');
-        globalPopup.onclick = function() {
-            globalPopup.style.display = "none";
-        };
+        globalPopup.onclick = closePopup;
         globalPopup.classList.add('global-popup');
 
         var close = document.createElement('div');
         close.classList.add('global-popup-close');
-        close.onclick = function() {
-            globalPopup.style.display = "none";
-        };
+        close.onclick = closePopup;
         close.title = "Close";
         globalPopup.appendChild(close);
 
@@ -205,7 +213,7 @@ function popup(contents) {
         globalPopupInner.classList.add('global-popup-inner');
         globalPopup.appendChild(globalPopupInner);
 
-        gradioApp().appendChild(globalPopup);
+        gradioApp().querySelector('.main').appendChild(globalPopup);
     }
 
     globalPopupInner.innerHTML = '';
@@ -263,3 +271,43 @@ function extraNetworksRequestMetadata(event, extraPage, cardName) {
 
     event.stopPropagation();
 }
+
+var extraPageUserMetadataEditors = {};
+
+function extraNetworksEditUserMetadata(event, tabname, extraPage, cardName) {
+    var id = tabname + '_' + extraPage + '_edit_user_metadata';
+
+    var editor = extraPageUserMetadataEditors[id];
+    if (!editor) {
+        editor = {};
+        editor.page = gradioApp().getElementById(id);
+        editor.nameTextarea = gradioApp().querySelector("#" + id + "_name" + ' textarea');
+        editor.button = gradioApp().querySelector("#" + id + "_button");
+        extraPageUserMetadataEditors[id] = editor;
+    }
+
+    editor.nameTextarea.value = cardName;
+    updateInput(editor.nameTextarea);
+
+    editor.button.click();
+
+    popup(editor.page);
+
+    event.stopPropagation();
+}
+
+function extraNetworksRefreshSingleCard(page, tabname, name) {
+    requestGet("./sd_extra_networks/get-single-card", {page: page, tabname: tabname, name: name}, function(data) {
+        if (data && data.html) {
+            var card = gradioApp().querySelector('.card[data-name=' + JSON.stringify(name) + ']'); // likely using the wrong stringify function
+
+            var newDiv = document.createElement('DIV');
+            newDiv.innerHTML = data.html;
+            var newCard = newDiv.firstElementChild;
+
+            newCard.style = '';
+            card.parentElement.insertBefore(newCard, card);
+            card.parentElement.removeChild(card);
+        }
+    });
+}

javascript/hints.js

@@ -84,8 +84,6 @@ var titles = {
     "Checkpoint name": "Loads weights from checkpoint before making images. You can either use hash or a part of filename (as seen in settings) for checkpoint name. Recommended to use with Y axis for less switching.",
     "Inpainting conditioning mask strength": "Only applies to inpainting models. Determines how strongly to mask off the original image for inpainting and img2img. 1.0 means fully masked, which is the default behaviour. 0.0 means a fully unmasked conditioning. Lower values will help preserve the overall composition of the image, but will struggle with large changes.",
 
-    "vram": "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.\nTorch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.\nSys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%).",
-
     "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.",
 
     "Filename word regex": "This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.",
@@ -110,7 +108,6 @@ var titles = {
     "Upscale by": "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.",
     "Resize width to": "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.",
     "Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.",
-    "Multiplier for extra networks": "When adding extra network such as Hypernetwork or Lora to prompt, use this multiplier for it.",
     "Discard weights with matching name": "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.",
     "Extra networks tab order": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order listed.",
     "Negative Guidance minimum sigma": "Skip negative prompt for steps where image is already mostly denoised; the higher this value, the more skips there will be; provides increased performance in exchange for minor quality reduction."

launch.py

@@ -18,6 +18,7 @@ run_pip = launch_utils.run_pip
 check_run_python = launch_utils.check_run_python
 git_clone = launch_utils.git_clone
 git_pull_recursive = launch_utils.git_pull_recursive
+list_extensions = launch_utils.list_extensions
 run_extension_installer = launch_utils.run_extension_installer
 prepare_environment = launch_utils.prepare_environment
 configure_for_tests = launch_utils.configure_for_tests

modules/api/models.py

 import inspect
+
 from pydantic import BaseModel, Field, create_model
 from typing import Any, Optional
 from typing_extensions import Literal
@@ -207,11 +208,12 @@ class PreprocessResponse(BaseModel):
 fields = {}
 for key, metadata in opts.data_labels.items():
     value = opts.data.get(key)
-    optType = opts.typemap.get(type(metadata.default), type(value))
+    optType = opts.typemap.get(type(metadata.default), type(metadata.default))
 
-    if (metadata is not None):
-        fields.update({key: (Optional[optType], Field(
-            default=metadata.default ,description=metadata.label))})
+    if metadata.default is None:
+        pass
+    elif metadata is not None:
+        fields.update({key: (Optional[optType], Field(default=metadata.default, description=metadata.label))})
     else:
         fields.update({key: (Optional[optType], Field())})
 
@@ -274,10 +276,6 @@ class PromptStyleItem(BaseModel):
     prompt: Optional[str] = Field(title="Prompt")
     negative_prompt: Optional[str] = Field(title="Negative Prompt")
 
-class ArtistItem(BaseModel):
-    name: str = Field(title="Name")
-    score: float = Field(title="Score")
-    category: str = Field(title="Category")
 
 class EmbeddingItem(BaseModel):
     step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available")

modules/cache.py

+import json
+import os.path
+import threading
+import time
+
+from modules.paths import data_path, script_path
+
+cache_filename = os.path.join(data_path, "cache.json")
+cache_data = None
+cache_lock = threading.Lock()
+
+dump_cache_after = None
+dump_cache_thread = None
+
+
+def dump_cache():
+    """
+    Marks cache for writing to disk. 5 seconds after no one else flags the cache for writing, it is written.
+    """
+
+    global dump_cache_after
+    global dump_cache_thread
+
+    def thread_func():
+        global dump_cache_after
+        global dump_cache_thread
+
+        while dump_cache_after is not None and time.time() < dump_cache_after:
+            time.sleep(1)
+
+        with cache_lock:
+            with open(cache_filename, "w", encoding="utf8") as file:
+                json.dump(cache_data, file, indent=4)
+
+            dump_cache_after = None
+            dump_cache_thread = None
+
+    with cache_lock:
+        dump_cache_after = time.time() + 5
+        if dump_cache_thread is None:
+            dump_cache_thread = threading.Thread(name='cache-writer', target=thread_func)
+            dump_cache_thread.start()
+
+
+def cache(subsection):
+    """
+    Retrieves or initializes a cache for a specific subsection.
+
+    Parameters:
+        subsection (str): The subsection identifier for the cache.
+
+    Returns:
+        dict: The cache data for the specified subsection.
+    """
+
+    global cache_data
+
+    if cache_data is None:
+        with cache_lock:
+            if cache_data is None:
+                if not os.path.isfile(cache_filename):
+                    cache_data = {}
+                else:
+                    try:
+                        with open(cache_filename, "r", encoding="utf8") as file:
+                            cache_data = json.load(file)
+                    except Exception:
+                        os.replace(cache_filename, os.path.join(script_path, "tmp", "cache.json"))
+                        print('[ERROR] issue occurred while trying to read cache.json, move current cache to tmp/cache.json and create new cache')
+                        cache_data = {}
+
+    s = cache_data.get(subsection, {})
+    cache_data[subsection] = s
+
+    return s
+
+
+def cached_data_for_file(subsection, title, filename, func):
+    """
+    Retrieves or generates data for a specific file, using a caching mechanism.
+
+    Parameters:
+        subsection (str): The subsection of the cache to use.
+        title (str): The title of the data entry in the subsection of the cache.
+        filename (str): The path to the file to be checked for modifications.
+        func (callable): A function that generates the data if it is not available in the cache.
+
+    Returns:
+        dict or None: The cached or generated data, or None if data generation fails.
+
+    The `cached_data_for_file` function implements a caching mechanism for data stored in files.
+    It checks if the data associated with the given `title` is present in the cache and compares the
+    modification time of the file with the cached modification time. If the file has been modified,
+    the cache is considered invalid and the data is regenerated using the provided `func`.
+    Otherwise, the cached data is returned.
+
+    If the data generation fails, None is returned to indicate the failure. Otherwise, the generated
+    or cached data is returned as a dictionary.
+    """
+
+    existing_cache = cache(subsection)
+    ondisk_mtime = os.path.getmtime(filename)
+
+    entry = existing_cache.get(title)
+    if entry:
+        cached_mtime = entry.get("mtime", 0)
+        if ondisk_mtime > cached_mtime:
+            entry = None
+
+    if not entry or 'value' not in entry:
+        value = func()
+        if value is None:
+            return None
+
+        entry = {'mtime': ondisk_mtime, 'value': value}
+        existing_cache[title] = entry
+
+        dump_cache()
+
+    return entry['value']

modules/call_queue.py

+from functools import wraps
 import html
 import threading
 import time
@@ -18,6 +19,7 @@ def wrap_queued_call(func):
 
 
 def wrap_gradio_gpu_call(func, extra_outputs=None):
+    @wraps(func)
     def f(*args, **kwargs):
 
         # if the first argument is a string that says "task(...)", it is treated as a job id
@@ -28,7 +30,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
             id_task = None
 
         with queue_lock:
-            shared.state.begin()
+            shared.state.begin(job=id_task)
             progress.start_task(id_task)
 
             try:
@@ -45,6 +47,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
 
 
 def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
+    @wraps(func)
     def f(*args, extra_outputs_array=extra_outputs, **kwargs):
         run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats
         if run_memmon:
@@ -82,9 +85,9 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
         elapsed = time.perf_counter() - t
         elapsed_m = int(elapsed // 60)
         elapsed_s = elapsed % 60
-        elapsed_text = f"{elapsed_s:.2f}s"
+        elapsed_text = f"{elapsed_s:.1f} sec."
         if elapsed_m > 0:
-            elapsed_text = f"{elapsed_m}m "+elapsed_text
+            elapsed_text = f"{elapsed_m} min. "+elapsed_text
 
         if run_memmon:
             mem_stats = {k: -(v//-(1024*1024)) for k, v in shared.mem_mon.stop().items()}
@@ -92,14 +95,22 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
             reserved_peak = mem_stats['reserved_peak']
             sys_peak = mem_stats['system_peak']
             sys_total = mem_stats['total']
-            sys_pct = round(sys_peak/max(sys_total, 1) * 100, 2)
+            sys_pct = sys_peak/max(sys_total, 1) * 100
 
-            vram_html = f"<p class='vram'>Torch active/reserved: {active_peak}/{reserved_peak} MiB, <wbr>Sys VRAM: {sys_peak}/{sys_total} MiB ({sys_pct}%)</p>"
+            toltip_a = "Active: peak amount of video memory used during generation (excluding cached data)"
+            toltip_r = "Reserved: total amout of video memory allocated by the Torch library "
+            toltip_sys = "System: peak amout of video memory allocated by all running programs, out of total capacity"
+
+            text_a = f"<abbr title='{toltip_a}'>A</abbr>: <span class='measurement'>{active_peak/1024:.2f} GB</span>"
+            text_r = f"<abbr title='{toltip_r}'>R</abbr>: <span class='measurement'>{reserved_peak/1024:.2f} GB</span>"
+            text_sys = f"<abbr title='{toltip_sys}'>Sys</abbr>: <span class='measurement'>{sys_peak/1024:.1f}/{sys_total/1024:g} GB</span> ({sys_pct:.1f}%)"
+
+            vram_html = f"<p class='vram'>{text_a}, <wbr>{text_r}, <wbr>{text_sys}</p>"
         else:
             vram_html = ''
 
         # last item is always HTML
-        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"
+        res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr><span class='measurement'>{elapsed_text}</span></p>{vram_html}</div>"
 
         return tuple(res)
 

modules/cmd_args.py

@@ -15,6 +15,7 @@ parser.add_argument("--update-check", action='store_true', help="launch.py argum
 parser.add_argument("--test-server", action='store_true', help="launch.py argument: configure server for testing")
 parser.add_argument("--skip-prepare-environment", action='store_true', help="launch.py argument: skip all environment preparation")
 parser.add_argument("--skip-install", action='store_true', help="launch.py argument: skip installation of packages")
+parser.add_argument("--do-not-download-clip", action='store_true', help="do not download CLIP model even if it's not included in the checkpoint")
 parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
 parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
 parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
@@ -107,3 +108,5 @@ parser.add_argument("--no-hashing", action='store_true', help="disable sha256 ha
 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)
 parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
 parser.add_argument('--add-stop-route', action='store_true', help='add /_stop route to stop server')
+parser.add_argument('--api-server-stop', action='store_true', help='enable server stop/restart/kill via api')
+parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')

modules/codeformer_model.py

@@ -15,7 +15,6 @@ model_dir = "Codeformer"
 model_path = os.path.join(models_path, model_dir)
 model_url = 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth'
 
-have_codeformer = False
 codeformer = None
 
 
@@ -100,7 +99,7 @@ def setup_model(dirname):
                             output = self.net(cropped_face_t, w=w if w is not None else shared.opts.code_former_weight, adain=True)[0]
                             restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
                         del output
-                        torch.cuda.empty_cache()
+                        devices.torch_gc()
                     except Exception:
                         errors.report('Failed inference for CodeFormer', exc_info=True)
                         restored_face = tensor2img(cropped_face_t, rgb2bgr=True, min_max=(-1, 1))
@@ -123,9 +122,6 @@ def setup_model(dirname):
 
                 return restored_img
 
-        global have_codeformer
-        have_codeformer = True
-
         global codeformer
         codeformer = FaceRestorerCodeFormer(dirname)
         shared.face_restorers.append(codeformer)

modules/devices.py

@@ -15,13 +15,6 @@ def has_mps() -> bool:
     else:
         return mac_specific.has_mps
 
-def extract_device_id(args, name):
-    for x in range(len(args)):
-        if name in args[x]:
-            return args[x + 1]
-
-    return None
-
 
 def get_cuda_device_string():
     from modules import shared
@@ -56,11 +49,15 @@ def get_device_for(task):
 
 
 def torch_gc():
+
     if torch.cuda.is_available():
         with torch.cuda.device(get_cuda_device_string()):
             torch.cuda.empty_cache()
             torch.cuda.ipc_collect()
 
+    if has_mps():
+        mac_specific.torch_mps_gc()
+
 
 def enable_tf32():
     if torch.cuda.is_available():

modules/esrgan_model.py

-import os
+import sys
 
 import numpy as np
 import torch
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 
 import modules.esrgan_model_arch as arch
 from modules import modelloader, images, devices
-from modules.upscaler import Upscaler, UpscalerData
 from modules.shared import opts
-
+from modules.upscaler import Upscaler, UpscalerData
 
 
 def mod2normal(state_dict):
@@ -134,7 +132,7 @@ class UpscalerESRGAN(Upscaler):
             scaler_data = UpscalerData(self.model_name, self.model_url, self, 4)
             scalers.append(scaler_data)
         for file in model_paths:
-            if "http" in file:
+            if file.startswith("http"):
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
@@ -143,26 +141,25 @@ class UpscalerESRGAN(Upscaler):
             self.scalers.append(scaler_data)
 
     def do_upscale(self, img, selected_model):
-        model = self.load_model(selected_model)
-        if model is None:
+        try:
+            model = self.load_model(selected_model)
+        except Exception as e:
+            print(f"Unable to load ESRGAN model {selected_model}: {e}", file=sys.stderr)
             return img
         model.to(devices.device_esrgan)
         img = esrgan_upscale(model, img)
         return img
 
     def load_model(self, path: str):
-        if "http" in path:
-            filename = load_file_from_url(
+        if path.startswith("http"):
+            # TODO: this doesn't use `path` at all?
+            filename = modelloader.load_file_from_url(
                 url=self.model_url,
                 model_dir=self.model_download_path,
                 file_name=f"{self.model_name}.pth",
-                progress=True,
             )
         else:
             filename = path
-        if not os.path.exists(filename) or filename is None:
-            print(f"Unable to load {self.model_path} from {filename}")
-            return None
 
         state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
 

modules/extensions.py

 import os
 import threading
 
-from modules import shared, errors
+from modules import shared, errors, cache
 from modules.gitpython_hack import Repo
 from modules.paths_internal import extensions_dir, extensions_builtin_dir, script_path  # noqa: F401
 
@@ -21,6 +21,7 @@ def active():
 
 class Extension:
     lock = threading.Lock()
+    cached_fields = ['remote', 'commit_date', 'branch', 'commit_hash', 'version']
 
     def __init__(self, name, path, enabled=True, is_builtin=False):
         self.name = name
@@ -36,15 +37,29 @@ class Extension:
         self.remote = None
         self.have_info_from_repo = False
 
+    def to_dict(self):
+        return {x: getattr(self, x) for x in self.cached_fields}
+
+    def from_dict(self, d):
+        for field in self.cached_fields:
+            setattr(self, field, d[field])
+
     def read_info_from_repo(self):
         if self.is_builtin or self.have_info_from_repo:
             return
 
-        with self.lock:
-            if self.have_info_from_repo:
-                return
+        def read_from_repo():
+            with self.lock:
+                if self.have_info_from_repo:
+                    return
+
+                self.do_read_info_from_repo()
+
+                return self.to_dict()
 
-            self.do_read_info_from_repo()
+        d = cache.cached_data_for_file('extensions-git', self.name, os.path.join(self.path, ".git"), read_from_repo)
+        self.from_dict(d)
+        self.status = 'unknown'
 
     def do_read_info_from_repo(self):
         repo = None
@@ -58,7 +73,6 @@ class Extension:
             self.remote = None
         else:
             try:
-                self.status = 'unknown'
                 self.remote = next(repo.remote().urls, None)
                 commit = repo.head.commit
                 self.commit_date = commit.committed_date

modules/extra_networks.py

@@ -4,16 +4,22 @@ from collections import defaultdict
 from modules import errors
 
 extra_network_registry = {}
+extra_network_aliases = {}
 
 
 def initialize():
     extra_network_registry.clear()
+    extra_network_aliases.clear()
 
 
 def register_extra_network(extra_network):
     extra_network_registry[extra_network.name] = extra_network
 
 
+def register_extra_network_alias(extra_network, alias):
+    extra_network_aliases[alias] = extra_network
+
+
 def register_default_extra_networks():
     from modules.extra_networks_hypernet import ExtraNetworkHypernet
     register_extra_network(ExtraNetworkHypernet())
@@ -82,20 +88,26 @@ def activate(p, extra_network_data):
     """call activate for extra networks in extra_network_data in specified order, then call
     activate for all remaining registered networks with an empty argument list"""
 
+    activated = []
+
     for extra_network_name, extra_network_args in extra_network_data.items():
         extra_network = extra_network_registry.get(extra_network_name, None)
+
+        if extra_network is None:
+            extra_network = extra_network_aliases.get(extra_network_name, None)
+
         if extra_network is None:
             print(f"Skipping unknown extra network: {extra_network_name}")
             continue
 
         try:
             extra_network.activate(p, extra_network_args)
+            activated.append(extra_network)
         except Exception as e:
             errors.display(e, f"activating extra network {extra_network_name} with arguments {extra_network_args}")
 
     for extra_network_name, extra_network in extra_network_registry.items():
-        args = extra_network_data.get(extra_network_name, None)
-        if args is not None:
+        if extra_network in activated:
             continue
 
         try:
@@ -103,6 +115,9 @@ def activate(p, extra_network_data):
         except Exception as e:
             errors.display(e, f"activating extra network {extra_network_name}")
 
+    if p.scripts is not None:
+        p.scripts.after_extra_networks_activate(p, batch_number=p.iteration, prompts=p.prompts, seeds=p.seeds, subseeds=p.subseeds, extra_network_data=extra_network_data)
+
 
 def deactivate(p, extra_network_data):
     """call deactivate for extra networks in extra_network_data in specified order, then call

modules/extras.py

@@ -73,8 +73,7 @@ def to_half(tensor, enable):
 
 
 def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata):
-    shared.state.begin()
-    shared.state.job = 'model-merge'
+    shared.state.begin(job="model-merge")
 
     def fail(message):
         shared.state.textinfo = message

modules/generation_parameters_copypaste.py

@@ -174,31 +174,6 @@ def send_image_and_dimensions(x):
     return img, w, h
 
 
-
-def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
-    """Determines the config parameter name to use for the hypernet based on the parameters in the infotext.
-
-    Example: an infotext provides "Hypernet: ke-ta" and "Hypernet hash: 1234abcd". For the "Hypernet" config
-    parameter this means there should be an entry that looks like "ke-ta-10000(1234abcd)" to set it to.
-
-    If the infotext has no hash, then a hypernet with the same name will be selected instead.
-    """
-    hypernet_name = hypernet_name.lower()
-    if hypernet_hash is not None:
-        # Try to match the hash in the name
-        for hypernet_key in shared.hypernetworks.keys():
-            result = re_hypernet_hash.search(hypernet_key)
-            if result is not None and result[1] == hypernet_hash:
-                return hypernet_key
-    else:
-        # Fall back to a hypernet with the same name
-        for hypernet_key in shared.hypernetworks.keys():
-            if hypernet_key.lower().startswith(hypernet_name):
-                return hypernet_key
-
-    return None
-
-
 def restore_old_hires_fix_params(res):
     """for infotexts that specify old First pass size parameter, convert it into
     width, height, and hr scale"""
@@ -332,10 +307,6 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     return res
 
 
-settings_map = {}
-
-
-
 infotext_to_setting_name_mapping = [
     ('Clip skip', 'CLIP_stop_at_last_layers', ),
     ('Conditional mask weight', 'inpainting_mask_weight'),

modules/gfpgan_model.py

@@ -25,7 +25,7 @@ def gfpgann():
         return None
 
     models = modelloader.load_models(model_path, model_url, user_path, ext_filter="GFPGAN")
-    if len(models) == 1 and "http" in models[0]:
+    if len(models) == 1 and models[0].startswith("http"):
         model_file = models[0]
     elif len(models) != 0:
         latest_file = max(models, key=os.path.getctime)

modules/hashes.py

 import hashlib
-import json
 import os.path
 
-import filelock
-
 from modules import shared
-from modules.paths import data_path
-
-
-cache_filename = os.path.join(data_path, "cache.json")
-cache_data = None
-
-
-def dump_cache():
-    with filelock.FileLock(f"{cache_filename}.lock"):
-        with open(cache_filename, "w", encoding="utf8") as file:
-            json.dump(cache_data, file, indent=4)
-
-
-def cache(subsection):
-    global cache_data
-
-    if cache_data is None:
-        with filelock.FileLock(f"{cache_filename}.lock"):
-            if not os.path.isfile(cache_filename):
-                cache_data = {}
-            else:
-                with open(cache_filename, "r", encoding="utf8") as file:
-                    cache_data = json.load(file)
-
-    s = cache_data.get(subsection, {})
-    cache_data[subsection] = s
+import modules.cache
 
-    return s
+dump_cache = modules.cache.dump_cache
+cache = modules.cache.cache
 
 
 def calculate_sha256(filename):

modules/hypernetworks/hypernetwork.py

@@ -3,6 +3,7 @@ import glob
 import html
 import os
 import inspect
+from contextlib import closing
 
 import modules.textual_inversion.dataset
 import torch
@@ -353,17 +354,6 @@ def load_hypernetworks(names, multipliers=None):
         shared.loaded_hypernetworks.append(hypernetwork)
 
 
-def find_closest_hypernetwork_name(search: str):
-    if not search:
-        return None
-    search = search.lower()
-    applicable = [name for name in shared.hypernetworks if search in name.lower()]
-    if not applicable:
-        return None
-    applicable = sorted(applicable, key=lambda name: len(name))
-    return applicable[0]
-
-
 def apply_single_hypernetwork(hypernetwork, context_k, context_v, layer=None):
     hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context_k.shape[2], None)
 
@@ -388,7 +378,7 @@ def apply_hypernetworks(hypernetworks, context, layer=None):
     return context_k, context_v
 
 
-def attention_CrossAttention_forward(self, x, context=None, mask=None):
+def attention_CrossAttention_forward(self, x, context=None, mask=None, **kwargs):
     h = self.heads
 
     q = self.to_q(x)
@@ -446,18 +436,6 @@ def statistics(data):
     return total_information, recent_information
 
 
-def report_statistics(loss_info:dict):
-    keys = sorted(loss_info.keys(), key=lambda x: sum(loss_info[x]) / len(loss_info[x]))
-    for key in keys:
-        try:
-            print("Loss statistics for file " + key)
-            info, recent = statistics(list(loss_info[key]))
-            print(info)
-            print(recent)
-        except Exception as e:
-            print(e)
-
-
 def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, dropout_structure=None):
     # Remove illegal characters from name.
     name = "".join( x for x in name if (x.isalnum() or x in "._- "))
@@ -734,8 +712,9 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi
 
                     preview_text = p.prompt
 
-                    processed = processing.process_images(p)
-                    image = processed.images[0] if len(processed.images) > 0 else None
+                    with closing(p):
+                        processed = processing.process_images(p)
+                        image = processed.images[0] if len(processed.images) > 0 else None
 
                     if unload:
                         shared.sd_model.cond_stage_model.to(devices.cpu)
@@ -770,7 +749,6 @@ Last saved image: {html.escape(last_saved_image)}<br/>
         pbar.leave = False
         pbar.close()
         hypernetwork.eval()
-        #report_statistics(loss_dict)
         sd_hijack_checkpoint.remove()
 
 

modules/images.py

+from __future__ import annotations
+
 import datetime
 
 import pytz
@@ -10,7 +12,7 @@ import re
 import numpy as np
 import piexif
 import piexif.helper
-from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
+from PIL import Image, ImageFont, ImageDraw, ImageColor, PngImagePlugin
 import string
 import json
 import hashlib
@@ -139,6 +141,11 @@ class GridAnnotation:
 
 
 def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
+
+    color_active = ImageColor.getcolor(opts.grid_text_active_color, 'RGB')
+    color_inactive = ImageColor.getcolor(opts.grid_text_inactive_color, 'RGB')
+    color_background = ImageColor.getcolor(opts.grid_background_color, 'RGB')
+
     def wrap(drawing, text, font, line_length):
         lines = ['']
         for word in text.split():
@@ -168,9 +175,6 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
 
     fnt = get_font(fontsize)
 
-    color_active = (0, 0, 0)
-    color_inactive = (153, 153, 153)
-
     pad_left = 0 if sum([sum([len(line.text) for line in lines]) for lines in ver_texts]) == 0 else width * 3 // 4
 
     cols = im.width // width
@@ -179,7 +183,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
     assert cols == len(hor_texts), f'bad number of horizontal texts: {len(hor_texts)}; must be {cols}'
     assert rows == len(ver_texts), f'bad number of vertical texts: {len(ver_texts)}; must be {rows}'
 
-    calc_img = Image.new("RGB", (1, 1), "white")
+    calc_img = Image.new("RGB", (1, 1), color_background)
     calc_d = ImageDraw.Draw(calc_img)
 
     for texts, allowed_width in zip(hor_texts + ver_texts, [width] * len(hor_texts) + [pad_left] * len(ver_texts)):
@@ -200,7 +204,7 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
 
     pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
 
-    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), "white")
+    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), color_background)
 
     for row in range(rows):
         for col in range(cols):
@@ -302,12 +306,14 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
 
         if ratio < src_ratio:
             fill_height = height // 2 - src_h // 2
-            res.paste(resized.resize((width, fill_height), box=(0, 0, width, 0)), box=(0, 0))
-            res.paste(resized.resize((width, fill_height), box=(0, resized.height, width, resized.height)), box=(0, fill_height + src_h))
+            if fill_height > 0:
+                res.paste(resized.resize((width, fill_height), box=(0, 0, width, 0)), box=(0, 0))
+                res.paste(resized.resize((width, fill_height), box=(0, resized.height, width, resized.height)), box=(0, fill_height + src_h))
         elif ratio > src_ratio:
             fill_width = width // 2 - src_w // 2
-            res.paste(resized.resize((fill_width, height), box=(0, 0, 0, height)), box=(0, 0))
-            res.paste(resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)), box=(fill_width + src_w, 0))
+            if fill_width > 0:
+                res.paste(resized.resize((fill_width, height), box=(0, 0, 0, height)), box=(0, 0))
+                res.paste(resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)), box=(fill_width + src_w, 0))
 
     return res
 
@@ -372,8 +378,9 @@ class FilenameGenerator:
         'hasprompt': lambda self, *args: self.hasprompt(*args),  # accepts formats:[hasprompt<prompt1|default><prompt2>..]
         'clip_skip': lambda self: opts.data["CLIP_stop_at_last_layers"],
         'denoising': lambda self: self.p.denoising_strength if self.p and self.p.denoising_strength else NOTHING_AND_SKIP_PREVIOUS_TEXT,
+        'user': lambda self: self.p.user,
         'vae_filename': lambda self: self.get_vae_filename(),
-
+        'none': lambda self: '', # Overrides the default so you can get just the sequence number
     }
     default_time_format = '%Y%m%d%H%M%S'
 
@@ -497,13 +504,23 @@ def get_next_sequence_number(path, basename):
     return result + 1
 
 
-def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_pnginfo=None):
+def save_image_with_geninfo(image, geninfo, filename, extension=None, existing_pnginfo=None, pnginfo_section_name='parameters'):
+    """
+    Saves image to filename, including geninfo as text information for generation info.
+    For PNG images, geninfo is added to existing pnginfo dictionary using the pnginfo_section_name argument as key.
+    For JPG images, there's no dictionary and geninfo just replaces the EXIF description.
+    """
+
     if extension is None:
         extension = os.path.splitext(filename)[1]
 
     image_format = Image.registered_extensions()[extension]
 
     if extension.lower() == '.png':
+        existing_pnginfo = existing_pnginfo or {}
+        if opts.enable_pnginfo:
+            existing_pnginfo[pnginfo_section_name] = geninfo
+
         if opts.enable_pnginfo:
             pnginfo_data = PngImagePlugin.PngInfo()
             for k, v in (existing_pnginfo or {}).items():
@@ -585,13 +602,13 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         else:
             file_decoration = opts.samples_filename_pattern or "[seed]-[prompt_spaces]"
 
+        file_decoration = namegen.apply(file_decoration) + suffix
+
         add_number = opts.save_images_add_number or file_decoration == ''
 
         if file_decoration != "" and add_number:
             file_decoration = f"-{file_decoration}"
 
-        file_decoration = namegen.apply(file_decoration) + suffix
-
         if add_number:
             basecount = get_next_sequence_number(path, basename)
             fullfn = None
@@ -622,7 +639,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         """
         temp_file_path = f"{filename_without_extension}.tmp"
 
-        save_image_with_geninfo(image_to_save, info, temp_file_path, extension, params.pnginfo)
+        save_image_with_geninfo(image_to_save, info, temp_file_path, extension, existing_pnginfo=params.pnginfo, pnginfo_section_name=pnginfo_section_name)
 
         os.replace(temp_file_path, filename_without_extension + extension)
 
@@ -639,12 +656,18 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     oversize = image.width > opts.target_side_length or image.height > opts.target_side_length
     if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > opts.img_downscale_threshold * 1024 * 1024):
         ratio = image.width / image.height
-
+        resize_to = None
         if oversize and ratio > 1:
-            image = image.resize((round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)), LANCZOS)
+            resize_to = round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)
         elif oversize:
-            image = image.resize((round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)), LANCZOS)
+            resize_to = round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)
 
+        if resize_to is not None:
+            try:
+                # Resizing image with LANCZOS could throw an exception if e.g. image mode is I;16
+                image = image.resize(resize_to, LANCZOS)
+            except Exception:
+                image = image.resize(resize_to)
         try:
             _atomically_save_image(image, fullfn_without_extension, ".jpg")
         except Exception as e:
@@ -662,8 +685,15 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     return fullfn, txt_fullfn
 
 
-def read_info_from_image(image):
-    items = image.info or {}
+IGNORED_INFO_KEYS = {
+    'jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
+    'loop', 'background', 'timestamp', 'duration', 'progressive', 'progression',
+    'icc_profile', 'chromaticity', 'photoshop',
+}
+
+
+def read_info_from_image(image: Image.Image) -> tuple[str | None, dict]:
+    items = (image.info or {}).copy()
 
     geninfo = items.pop('parameters', None)
 
@@ -679,9 +709,7 @@ def read_info_from_image(image):
             items['exif comment'] = exif_comment
             geninfo = exif_comment
 
-    for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
-                    'loop', 'background', 'timestamp', 'duration', 'progressive', 'progression',
-                    'icc_profile', 'chromaticity']:
+    for field in IGNORED_INFO_KEYS:
         items.pop(field, None)
 
     if items.get("Software", None) == "NovelAI":

modules/img2img.py

 import os
+from contextlib import closing
 from pathlib import Path
 
 import numpy as np
 from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops, UnidentifiedImageError
+import gradio as gr
 
-from modules import sd_samplers
-from modules.generation_parameters_copypaste import create_override_settings_dict
+from modules import sd_samplers, images as imgutil
+from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
+from modules.images import save_image
 import modules.shared as shared
 import modules.processing as processing
 from modules.ui import plaintext_to_html
 import modules.scripts
 
 
-def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0):
+def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
     processing.fix_seed(p)
 
-    images = shared.listfiles(input_dir)
+    images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp")))
 
     is_inpaint_batch = False
     if inpaint_mask_dir:
@@ -36,6 +39,14 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
 
     state.job_count = len(images) * p.n_iter
 
+    # extract "default" params to use in case getting png info fails
+    prompt = p.prompt
+    negative_prompt = p.negative_prompt
+    seed = p.seed
+    cfg_scale = p.cfg_scale
+    sampler_name = p.sampler_name
+    steps = p.steps
+
     for i, image in enumerate(images):
         state.job = f"{i+1} out of {len(images)}"
         if state.skipped:
@@ -79,25 +90,45 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
             mask_image = Image.open(mask_image_path)
             p.image_mask = mask_image
 
+        if use_png_info:
+            try:
+                info_img = img
+                if png_info_dir:
+                    info_img_path = os.path.join(png_info_dir, os.path.basename(image))
+                    info_img = Image.open(info_img_path)
+                geninfo, _ = imgutil.read_info_from_image(info_img)
+                parsed_parameters = parse_generation_parameters(geninfo)
+                parsed_parameters = {k: v for k, v in parsed_parameters.items() if k in (png_info_props or {})}
+            except Exception:
+                parsed_parameters = {}
+
+            p.prompt = prompt + (" " + parsed_parameters["Prompt"] if "Prompt" in parsed_parameters else "")
+            p.negative_prompt = negative_prompt + (" " + parsed_parameters["Negative prompt"] if "Negative prompt" in parsed_parameters else "")
+            p.seed = int(parsed_parameters.get("Seed", seed))
+            p.cfg_scale = float(parsed_parameters.get("CFG scale", cfg_scale))
+            p.sampler_name = parsed_parameters.get("Sampler", sampler_name)
+            p.steps = int(parsed_parameters.get("Steps", steps))
+
         proc = modules.scripts.scripts_img2img.run(p, *args)
         if proc is None:
             proc = process_images(p)
 
         for n, processed_image in enumerate(proc.images):
-            filename = image_path.name
+            filename = image_path.stem
+            infotext = proc.infotext(p, n)
+            relpath = os.path.dirname(os.path.relpath(image, input_dir))
 
             if n > 0:
-                left, right = os.path.splitext(filename)
-                filename = f"{left}-{n}{right}"
+                filename += f"-{n}"
 
             if not save_normally:
-                os.makedirs(output_dir, exist_ok=True)
+                os.makedirs(os.path.join(output_dir, relpath), exist_ok=True)
                 if processed_image.mode == 'RGBA':
                     processed_image = processed_image.convert("RGB")
-                processed_image.save(os.path.join(output_dir, filename))
+                save_image(processed_image, os.path.join(output_dir, relpath), None, extension=opts.samples_format, info=infotext, forced_filename=filename, save_to_dirs=False)
 
 
-def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args):
+def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
     override_settings = create_override_settings_dict(override_settings_texts)
 
     is_batch = mode == 5
@@ -180,24 +211,25 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     p.scripts = modules.scripts.scripts_img2img
     p.script_args = args
 
+    p.user = request.username
+
     if shared.cmd_opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
     if mask:
         p.extra_generation_params["Mask blur"] = mask_blur
 
-    if is_batch:
-        assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
+    with closing(p):
+        if is_batch:
+            assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
 
-        process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by)
-
-        processed = Processed(p, [], p.seed, "")
-    else:
-        processed = modules.scripts.scripts_img2img.run(p, *args)
-        if processed is None:
-            processed = process_images(p)
+            process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
 
-    p.close()
+            processed = Processed(p, [], p.seed, "")
+        else:
+            processed = modules.scripts.scripts_img2img.run(p, *args)
+            if processed is None:
+                processed = process_images(p)
 
     shared.total_tqdm.clear()
 
@@ -208,4 +240,4 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     if opts.do_not_show_images:
         processed.images = []
 
-    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)
+    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments, classname="comments")

modules/interrogate.py

@@ -184,8 +184,7 @@ class InterrogateModels:
 
     def interrogate(self, pil_image):
         res = ""
-        shared.state.begin()
-        shared.state.job = 'interrogate'
+        shared.state.begin(job="interrogate")
         try:
             if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
                 lowvram.send_everything_to_cpu()

modules/launch_utils.py

 # this scripts installs necessary requirements and launches main program in webui.py
+import re
 import subprocess
 import os
 import sys
@@ -9,6 +10,9 @@ from functools import lru_cache
 
 from modules import cmd_args, errors
 from modules.paths_internal import script_path, extensions_dir
+from modules import timer
+
+timer.startup_timer.record("start")
 
 args, _ = cmd_args.parser.parse_known_args()
 
@@ -69,10 +73,12 @@ def git_tag():
         return subprocess.check_output([git, "describe", "--tags"], shell=False, encoding='utf8').strip()
     except Exception:
         try:
-            from pathlib import Path
-            changelog_md = Path(__file__).parent.parent / "CHANGELOG.md"
-            with changelog_md.open(encoding="utf-8") as file:
-                return next((line.strip() for line in file if line.strip()), "<none>")
+
+            changelog_md = os.path.join(os.path.dirname(os.path.dirname(__file__)), "CHANGELOG.md")
+            with open(changelog_md, "r", encoding="utf-8") as file:
+                line = next((line.strip() for line in file if line.strip()), "<none>")
+                line = line.replace("## ", "")
+                return line
         except Exception:
             return "<none>"
 
@@ -142,15 +148,15 @@ def git_clone(url, dir, name, commithash=None):
         if commithash is None:
             return
 
-        current_hash = run(f'"{git}" -C "{dir}" rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}").strip()
+        current_hash = run(f'"{git}" -C "{dir}" rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}", live=False).strip()
         if current_hash == commithash:
             return
 
         run(f'"{git}" -C "{dir}" fetch', f"Fetching updates for {name}...", f"Couldn't fetch {name}")
-        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}")
+        run(f'"{git}" -C "{dir}" checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
         return
 
-    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}")
+    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}", live=True)
 
     if commithash is not None:
         run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
@@ -224,6 +230,44 @@ def run_extensions_installers(settings_file):
         run_extension_installer(os.path.join(extensions_dir, dirname_extension))
 
 
+re_requirement = re.compile(r"\s*([-_a-zA-Z0-9]+)\s*(?:==\s*([-+_.a-zA-Z0-9]+))?\s*")
+
+
+def requrements_met(requirements_file):
+    """
+    Does a simple parse of a requirements.txt file to determine if all rerqirements in it
+    are already installed. Returns True if so, False if not installed or parsing fails.
+    """
+
+    import importlib.metadata
+    import packaging.version
+
+    with open(requirements_file, "r", encoding="utf8") as file:
+        for line in file:
+            if line.strip() == "":
+                continue
+
+            m = re.match(re_requirement, line)
+            if m is None:
+                return False
+
+            package = m.group(1).strip()
+            version_required = (m.group(2) or "").strip()
+
+            if version_required == "":
+                continue
+
+            try:
+                version_installed = importlib.metadata.version(package)
+            except Exception:
+                return False
+
+            if packaging.version.parse(version_required) != packaging.version.parse(version_installed):
+                return False
+
+    return True
+
+
 def prepare_environment():
     torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu118")
     torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url {torch_index_url}")
@@ -235,11 +279,13 @@ def prepare_environment():
     openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip")
 
     stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
+    stable_diffusion_xl_repo = os.environ.get('STABLE_DIFFUSION_XL_REPO', "https://github.com/Stability-AI/generative-models.git")
     k_diffusion_repo = os.environ.get('K_DIFFUSION_REPO', 'https://github.com/crowsonkb/k-diffusion.git')
     codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
     blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
 
     stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
+    stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "5c10deee76adad0032b412294130090932317a87")
     k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "c9fe758757e022f05ca5a53fa8fac28889e4f1cf")
     codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
     blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
@@ -297,6 +343,7 @@ def prepare_environment():
     os.makedirs(os.path.join(script_path, dir_repos), exist_ok=True)
 
     git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
+    git_clone(stable_diffusion_xl_repo, repo_dir('generative-models'), "Stable Diffusion XL", stable_diffusion_xl_commit_hash)
     git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
     git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
     git_clone(blip_repo, repo_dir('BLIP'), "BLIP", blip_commit_hash)
@@ -306,7 +353,9 @@ def prepare_environment():
 
     if not os.path.isfile(requirements_file):
         requirements_file = os.path.join(script_path, requirements_file)
-    run_pip(f"install -r \"{requirements_file}\"", "requirements")
+
+    if not requrements_met(requirements_file):
+        run_pip(f"install -r \"{requirements_file}\"", "requirements")
 
     run_extensions_installers(settings_file=args.ui_settings_file)
 
@@ -321,6 +370,7 @@ def prepare_environment():
         exit(0)
 
 
+
 def configure_for_tests():
     if "--api" not in sys.argv:
         sys.argv.append("--api")

modules/lowvram.py

@@ -53,19 +53,46 @@ def setup_for_low_vram(sd_model, use_medvram):
         send_me_to_gpu(first_stage_model, None)
         return first_stage_model_decode(z)
 
-    # for SD1, cond_stage_model is CLIP and its NN is in the tranformer frield, but for SD2, it's open clip, and it's in model field
-    if hasattr(sd_model.cond_stage_model, 'model'):
-        sd_model.cond_stage_model.transformer = sd_model.cond_stage_model.model
-
-    # remove several big modules: cond, first_stage, depth/embedder (if applicable), and unet from the model and then
-    # send the model to GPU. Then put modules back. the modules will be in CPU.
-    stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, getattr(sd_model, 'depth_model', None), getattr(sd_model, 'embedder', None), sd_model.model
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = None, None, None, None, None
+    to_remain_in_cpu = [
+        (sd_model, 'first_stage_model'),
+        (sd_model, 'depth_model'),
+        (sd_model, 'embedder'),
+        (sd_model, 'model'),
+        (sd_model, 'embedder'),
+    ]
+
+    is_sdxl = hasattr(sd_model, 'conditioner')
+    is_sd2 = not is_sdxl and hasattr(sd_model.cond_stage_model, 'model')
+
+    if is_sdxl:
+        to_remain_in_cpu.append((sd_model, 'conditioner'))
+    elif is_sd2:
+        to_remain_in_cpu.append((sd_model.cond_stage_model, 'model'))
+    else:
+        to_remain_in_cpu.append((sd_model.cond_stage_model, 'transformer'))
+
+    # remove several big modules: cond, first_stage, depth/embedder (if applicable), and unet from the model
+    stored = []
+    for obj, field in to_remain_in_cpu:
+        module = getattr(obj, field, None)
+        stored.append(module)
+        setattr(obj, field, None)
+
+    # send the model to GPU.
     sd_model.to(devices.device)
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = stored
+
+    # put modules back. the modules will be in CPU.
+    for (obj, field), module in zip(to_remain_in_cpu, stored):
+        setattr(obj, field, module)
 
     # register hooks for those the first three models
-    sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
+    if is_sdxl:
+        sd_model.conditioner.register_forward_pre_hook(send_me_to_gpu)
+    elif is_sd2:
+        sd_model.cond_stage_model.model.register_forward_pre_hook(send_me_to_gpu)
+    else:
+        sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
+
     sd_model.first_stage_model.register_forward_pre_hook(send_me_to_gpu)
     sd_model.first_stage_model.encode = first_stage_model_encode_wrap
     sd_model.first_stage_model.decode = first_stage_model_decode_wrap
@@ -73,11 +100,9 @@ def setup_for_low_vram(sd_model, use_medvram):
         sd_model.depth_model.register_forward_pre_hook(send_me_to_gpu)
     if sd_model.embedder:
         sd_model.embedder.register_forward_pre_hook(send_me_to_gpu)
-    parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
 
-    if hasattr(sd_model.cond_stage_model, 'model'):
-        sd_model.cond_stage_model.model = sd_model.cond_stage_model.transformer
-        del sd_model.cond_stage_model.transformer
+    if hasattr(sd_model, 'cond_stage_model'):
+        parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
 
     if use_medvram:
         sd_model.model.register_forward_pre_hook(send_me_to_gpu)

modules/mac_specific.py

+import logging
+
 import torch
 import platform
 from modules.sd_hijack_utils import CondFunc
 from packaging import version
 
+log = logging.getLogger(__name__)
+
 
-# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
-# check `getattr` and try it for compatibility
+# before torch version 1.13, has_mps is only available in nightly pytorch and macOS 12.3+,
+# use check `getattr` and try it for compatibility.
+# in torch version 1.13, backends.mps.is_available() and backends.mps.is_built() are introduced in to check mps availabilty,
+# since torch 2.0.1+ nightly build, getattr(torch, 'has_mps', False) was deprecated, see https://github.com/pytorch/pytorch/pull/103279
 def check_for_mps() -> bool:
-    if not getattr(torch, 'has_mps', False):
-        return False
+    if version.parse(torch.__version__) <= version.parse("2.0.1"):
+        if not getattr(torch, 'has_mps', False):
+            return False
+        try:
+            torch.zeros(1).to(torch.device("mps"))
+            return True
+        except Exception:
+            return False
+    else:
+        return torch.backends.mps.is_available() and torch.backends.mps.is_built()
+
+
+has_mps = check_for_mps()
+
+
+def torch_mps_gc() -> None:
     try:
-        torch.zeros(1).to(torch.device("mps"))
-        return True
+        from modules.shared import state
+        if state.current_latent is not None:
+            log.debug("`current_latent` is set, skipping MPS garbage collection")
+            return
+        from torch.mps import empty_cache
+        empty_cache()
     except Exception:
-        return False
-has_mps = check_for_mps()
+        log.warning("MPS garbage collection failed", exc_info=True)
 
 
 # MPS workaround for https://github.com/pytorch/pytorch/issues/89784

modules/modelloader.py

+from __future__ import annotations
+
 import os
 import shutil
 import importlib
@@ -8,6 +10,29 @@ from modules.upscaler import Upscaler, UpscalerLanczos, UpscalerNearest, Upscale
 from modules.paths import script_path, models_path
 
 
+def load_file_from_url(
+    url: str,
+    *,
+    model_dir: str,
+    progress: bool = True,
+    file_name: str | None = None,
+) -> str:
+    """Download a file from `url` into `model_dir`, using the file present if possible.
+
+    Returns the path to the downloaded file.
+    """
+    os.makedirs(model_dir, exist_ok=True)
+    if not file_name:
+        parts = urlparse(url)
+        file_name = os.path.basename(parts.path)
+    cached_file = os.path.abspath(os.path.join(model_dir, file_name))
+    if not os.path.exists(cached_file):
+        print(f'Downloading: "{url}" to {cached_file}\n')
+        from torch.hub import download_url_to_file
+        download_url_to_file(url, cached_file, progress=progress)
+    return cached_file
+
+
 def load_models(model_path: str, model_url: str = None, command_path: str = None, ext_filter=None, download_name=None, ext_blacklist=None) -> list:
     """
     A one-and done loader to try finding the desired models in specified directories.
@@ -46,9 +71,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
 
         if model_url is not None and len(output) == 0:
             if download_name is not None:
-                from basicsr.utils.download_util import load_file_from_url
-                dl = load_file_from_url(model_url, places[0], True, download_name)
-                output.append(dl)
+                output.append(load_file_from_url(model_url, model_dir=places[0], file_name=download_name))
             else:
                 output.append(model_url)
 
@@ -59,7 +82,7 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
 
 
 def friendly_name(file: str):
-    if "http" in file:
+    if file.startswith("http"):
         file = urlparse(file).path
 
     file = os.path.basename(file)

modules/paths.py

@@ -5,6 +5,21 @@ from modules.paths_internal import models_path, script_path, data_path, extensio
 import modules.safe  # noqa: F401
 
 
+def mute_sdxl_imports():
+    """create fake modules that SDXL wants to import but doesn't actually use for our purposes"""
+
+    class Dummy:
+        pass
+
+    module = Dummy()
+    module.LPIPS = None
+    sys.modules['taming.modules.losses.lpips'] = module
+
+    module = Dummy()
+    module.StableDataModuleFromConfig = None
+    sys.modules['sgm.data'] = module
+
+
 # data_path = cmd_opts_pre.data
 sys.path.insert(0, script_path)
 
@@ -18,8 +33,11 @@ for possible_sd_path in possible_sd_paths:
 
 assert sd_path is not None, f"Couldn't find Stable Diffusion in any of: {possible_sd_paths}"
 
+mute_sdxl_imports()
+
 path_dirs = [
     (sd_path, 'ldm', 'Stable Diffusion', []),
+    (os.path.join(sd_path, '../generative-models'), 'sgm', 'Stable Diffusion XL', ["sgm"]),
     (os.path.join(sd_path, '../CodeFormer'), 'inference_codeformer.py', 'CodeFormer', []),
     (os.path.join(sd_path, '../BLIP'), 'models/blip.py', 'BLIP', []),
     (os.path.join(sd_path, '../k-diffusion'), 'k_diffusion/sampling.py', 'k_diffusion', ["atstart"]),
@@ -35,20 +53,13 @@ for d, must_exist, what, options in path_dirs:
         d = os.path.abspath(d)
         if "atstart" in options:
             sys.path.insert(0, d)
+        elif "sgm" in options:
+            # Stable Diffusion XL repo has scripts dir with __init__.py in it which ruins every extension's scripts dir, so we
+            # import sgm and remove it from sys.path so that when a script imports scripts.something, it doesbn't use sgm's scripts dir.
+
+            sys.path.insert(0, d)
+            import sgm  # noqa: F401
+            sys.path.pop(0)
         else:
             sys.path.append(d)
         paths[what] = d
-
-
-class Prioritize:
-    def __init__(self, name):
-        self.name = name
-        self.path = None
-
-    def __enter__(self):
-        self.path = sys.path.copy()
-        sys.path = [paths[self.name]] + sys.path
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        sys.path = self.path
-        self.path = None

modules/postprocessing.py

@@ -9,8 +9,7 @@ from modules.shared import opts
 def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True):
     devices.torch_gc()
 
-    shared.state.begin()
-    shared.state.job = 'extras'
+    shared.state.begin(job="extras")
 
     image_data = []
     image_names = []
@@ -54,7 +53,9 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
     for image, name in zip(image_data, image_names):
         shared.state.textinfo = name
 
-        existing_pnginfo = image.info or {}
+        parameters, existing_pnginfo = images.read_info_from_image(image)
+        if parameters:
+            existing_pnginfo["parameters"] = parameters
 
         pp = scripts_postprocessing.PostprocessedImage(image.convert("RGB"))
 

modules/prompt_parser.py

+from __future__ import annotations
+
 import re
 from collections import namedtuple
 from typing import List
@@ -109,7 +111,25 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
 ScheduledPromptConditioning = namedtuple("ScheduledPromptConditioning", ["end_at_step", "cond"])
 
 
-def get_learned_conditioning(model, prompts, steps):
+class SdConditioning(list):
+    """
+    A list with prompts for stable diffusion's conditioner model.
+    Can also specify width and height of created image - SDXL needs it.
+    """
+    def __init__(self, prompts, is_negative_prompt=False, width=None, height=None, copy_from=None):
+        super().__init__()
+        self.extend(prompts)
+
+        if copy_from is None:
+            copy_from = prompts
+
+        self.is_negative_prompt = is_negative_prompt or getattr(copy_from, 'is_negative_prompt', False)
+        self.width = width or getattr(copy_from, 'width', None)
+        self.height = height or getattr(copy_from, 'height', None)
+
+
+
+def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps):
     """converts a list of prompts into a list of prompt schedules - each schedule is a list of ScheduledPromptConditioning, specifying the comdition (cond),
     and the sampling step at which this condition is to be replaced by the next one.
 
@@ -139,12 +159,17 @@ def get_learned_conditioning(model, prompts, steps):
             res.append(cached)
             continue
 
-        texts = [x[1] for x in prompt_schedule]
+        texts = SdConditioning([x[1] for x in prompt_schedule], copy_from=prompts)
         conds = model.get_learned_conditioning(texts)
 
         cond_schedule = []
         for i, (end_at_step, _) in enumerate(prompt_schedule):
-            cond_schedule.append(ScheduledPromptConditioning(end_at_step, conds[i]))
+            if isinstance(conds, dict):
+                cond = {k: v[i] for k, v in conds.items()}
+            else:
+                cond = conds[i]
+
+            cond_schedule.append(ScheduledPromptConditioning(end_at_step, cond))
 
         cache[prompt] = cond_schedule
         res.append(cond_schedule)
@@ -155,11 +180,13 @@ def get_learned_conditioning(model, prompts, steps):
 re_AND = re.compile(r"\bAND\b")
 re_weight = re.compile(r"^(.*?)(?:\s*:\s*([-+]?(?:\d+\.?|\d*\.\d+)))?\s*$")
 
-def get_multicond_prompt_list(prompts):
+
+def get_multicond_prompt_list(prompts: SdConditioning | list[str]):
     res_indexes = []
 
-    prompt_flat_list = []
     prompt_indexes = {}
+    prompt_flat_list = SdConditioning(prompts)
+    prompt_flat_list.clear()
 
     for prompt in prompts:
         subprompts = re_AND.split(prompt)
@@ -196,6 +223,7 @@ class MulticondLearnedConditioning:
         self.shape: tuple = shape  # the shape field is needed to send this object to DDIM/PLMS
         self.batch: List[List[ComposableScheduledPromptConditioning]] = batch
 
+
 def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearnedConditioning:
     """same as get_learned_conditioning, but returns a list of ScheduledPromptConditioning along with the weight objects for each prompt.
     For each prompt, the list is obtained by splitting the prompt using the AND separator.
@@ -214,20 +242,57 @@ def get_multicond_learned_conditioning(model, prompts, steps) -> MulticondLearne
     return MulticondLearnedConditioning(shape=(len(prompts),), batch=res)
 
 
+class DictWithShape(dict):
+    def __init__(self, x, shape):
+        super().__init__()
+        self.update(x)
+
+    @property
+    def shape(self):
+        return self["crossattn"].shape
+
+
 def reconstruct_cond_batch(c: List[List[ScheduledPromptConditioning]], current_step):
     param = c[0][0].cond
-    res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype)
+    is_dict = isinstance(param, dict)
+
+    if is_dict:
+        dict_cond = param
+        res = {k: torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype) for k, param in dict_cond.items()}
+        res = DictWithShape(res, (len(c),) + dict_cond['crossattn'].shape)
+    else:
+        res = torch.zeros((len(c),) + param.shape, device=param.device, dtype=param.dtype)
+
     for i, cond_schedule in enumerate(c):
         target_index = 0
         for current, entry in enumerate(cond_schedule):
             if current_step <= entry.end_at_step:
                 target_index = current
                 break
-        res[i] = cond_schedule[target_index].cond
+
+        if is_dict:
+            for k, param in cond_schedule[target_index].cond.items():
+                res[k][i] = param
+        else:
+            res[i] = cond_schedule[target_index].cond
 
     return res
 
 
+def stack_conds(tensors):
+    # if prompts have wildly different lengths above the limit we'll get tensors of different shapes
+    # and won't be able to torch.stack them. So this fixes that.
+    token_count = max([x.shape[0] for x in tensors])
+    for i in range(len(tensors)):
+        if tensors[i].shape[0] != token_count:
+            last_vector = tensors[i][-1:]
+            last_vector_repeated = last_vector.repeat([token_count - tensors[i].shape[0], 1])
+            tensors[i] = torch.vstack([tensors[i], last_vector_repeated])
+
+    return torch.stack(tensors)
+
+
+
 def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step):
     param = c.batch[0][0].schedules[0].cond
 
@@ -249,16 +314,14 @@ def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step):
 
         conds_list.append(conds_for_batch)
 
-    # if prompts have wildly different lengths above the limit we'll get tensors fo different shapes
-    # and won't be able to torch.stack them. So this fixes that.
-    token_count = max([x.shape[0] for x in tensors])
-    for i in range(len(tensors)):
-        if tensors[i].shape[0] != token_count:
-            last_vector = tensors[i][-1:]
-            last_vector_repeated = last_vector.repeat([token_count - tensors[i].shape[0], 1])
-            tensors[i] = torch.vstack([tensors[i], last_vector_repeated])
+    if isinstance(tensors[0], dict):
+        keys = list(tensors[0].keys())
+        stacked = {k: stack_conds([x[k] for x in tensors]) for k in keys}
+        stacked = DictWithShape(stacked, stacked['crossattn'].shape)
+    else:
+        stacked = stack_conds(tensors).to(device=param.device, dtype=param.dtype)
 
-    return conds_list, torch.stack(tensors).to(device=param.device, dtype=param.dtype)
+    return conds_list, stacked
 
 
 re_attention = re.compile(r"""

modules/realesrgan_model.py

@@ -2,7 +2,6 @@ import os
 
 import numpy as np
 from PIL import Image
-from basicsr.utils.download_util import load_file_from_url
 from realesrgan import RealESRGANer
 
 from modules.upscaler import Upscaler, UpscalerData
@@ -43,9 +42,10 @@ class UpscalerRealESRGAN(Upscaler):
         if not self.enable:
             return img
 
-        info = self.load_model(path)
-        if not os.path.exists(info.local_data_path):
-            print(f"Unable to load RealESRGAN model: {info.name}")
+        try:
+            info = self.load_model(path)
+        except Exception:
+            errors.report(f"Unable to load RealESRGAN model {path}", exc_info=True)
             return img
 
         upsampler = RealESRGANer(
@@ -63,20 +63,17 @@ class UpscalerRealESRGAN(Upscaler):
         return image
 
     def load_model(self, path):
-        try:
-            info = next(iter([scaler for scaler in self.scalers if scaler.data_path == path]), None)
-
-            if info is None:
-                print(f"Unable to find model info: {path}")
-                return None
-
-            if info.local_data_path.startswith("http"):
-                info.local_data_path = load_file_from_url(url=info.data_path, model_dir=self.model_download_path, progress=True)
-
-            return info
-        except Exception:
-            errors.report("Error making Real-ESRGAN models list", exc_info=True)
-        return None
+        for scaler in self.scalers:
+            if scaler.data_path == path:
+                if scaler.local_data_path.startswith("http"):
+                    scaler.local_data_path = modelloader.load_file_from_url(
+                        scaler.data_path,
+                        model_dir=self.model_download_path,
+                    )
+                if not os.path.exists(scaler.local_data_path):
+                    raise FileNotFoundError(f"RealESRGAN data missing: {scaler.local_data_path}")
+                return scaler
+        raise ValueError(f"Unable to find model info: {path}")
 
     def load_models(self, _):
         return get_realesrgan_models(self)

modules/script_loading.py

@@ -12,11 +12,12 @@ def load_module(path):
     return module
 
 
-def preload_extensions(extensions_dir, parser):
+def preload_extensions(extensions_dir, parser, extension_list=None):
     if not os.path.isdir(extensions_dir):
         return
 
-    for dirname in sorted(os.listdir(extensions_dir)):
+    extensions = extension_list if extension_list is not None else os.listdir(extensions_dir)
+    for dirname in sorted(extensions):
         preload_script = os.path.join(extensions_dir, dirname, "preload.py")
         if not os.path.isfile(preload_script):
             continue

modules/scripts.py

 import os
 import re
 import sys
+import inspect
 from collections import namedtuple
 
 import gradio as gr
@@ -116,6 +117,21 @@ class Script:
 
         pass
 
+    def after_extra_networks_activate(self, p, *args, **kwargs):
+        """
+        Calledafter extra networks activation, before conds calculation
+        allow modification of the network after extra networks activation been applied
+        won't be call if p.disable_extra_networks
+
+        **kwargs will have those items:
+          - batch_number - index of current batch, from 0 to number of batches-1
+          - prompts - list of prompts for current batch; you can change contents of this list but changing the number of entries will likely break things
+          - seeds - list of seeds for current batch
+          - subseeds - list of subseeds for current batch
+          - extra_network_data - list of ExtraNetworkParams for current stage
+        """
+        pass
+
     def process_batch(self, p, *args, **kwargs):
         """
         Same as process(), but called for every batch.
@@ -186,6 +202,11 @@ class Script:
 
         return f'script_{tabname}{title}_{item_id}'
 
+    def before_hr(self, p, *args):
+        """
+        This function is called before hires fix start.
+        """
+        pass
 
 current_basedir = paths.script_path
 
@@ -249,7 +270,7 @@ def load_scripts():
 
     def register_scripts_from_module(module):
         for script_class in module.__dict__.values():
-            if type(script_class) != type:
+            if not inspect.isclass(script_class):
                 continue
 
             if issubclass(script_class, Script):
@@ -483,6 +504,14 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running before_process_batch: {script.filename}", exc_info=True)
 
+    def after_extra_networks_activate(self, p, **kwargs):
+        for script in self.alwayson_scripts:
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.after_extra_networks_activate(p, *script_args, **kwargs)
+            except Exception:
+                errors.report(f"Error running after_extra_networks_activate: {script.filename}", exc_info=True)
+
     def process_batch(self, p, **kwargs):
         for script in self.alwayson_scripts:
             try:
@@ -548,6 +577,15 @@ class ScriptRunner:
                     self.scripts[si].args_to = args_to
 
 
+    def before_hr(self, p):
+        for script in self.alwayson_scripts:
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.before_hr(p, *script_args)
+            except Exception:
+                errors.report(f"Error running before_hr: {script.filename}", exc_info=True)
+
+
 scripts_txt2img: ScriptRunner = None
 scripts_img2img: ScriptRunner = None
 scripts_postproc: scripts_postprocessing.ScriptPostprocessingRunner = None

modules/sd_hijack.py

@@ -15,6 +15,11 @@ import ldm.models.diffusion.ddim
 import ldm.models.diffusion.plms
 import ldm.modules.encoders.modules
 
+import sgm.modules.attention
+import sgm.modules.diffusionmodules.model
+import sgm.modules.diffusionmodules.openaimodel
+import sgm.modules.encoders.modules
+
 attention_CrossAttention_forward = ldm.modules.attention.CrossAttention.forward
 diffusionmodules_model_nonlinearity = ldm.modules.diffusionmodules.model.nonlinearity
 diffusionmodules_model_AttnBlock_forward = ldm.modules.diffusionmodules.model.AttnBlock.forward
@@ -56,6 +61,9 @@ def apply_optimizations(option=None):
     ldm.modules.diffusionmodules.model.nonlinearity = silu
     ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
 
+    sgm.modules.diffusionmodules.model.nonlinearity = silu
+    sgm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
+
     if current_optimizer is not None:
         current_optimizer.undo()
         current_optimizer = None
@@ -89,6 +97,10 @@ def undo_optimizations():
     ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
     ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
 
+    sgm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity
+    sgm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
+    sgm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
+
 
 def fix_checkpoint():
     """checkpoints are now added and removed in embedding/hypernet code, since torch doesn't want
@@ -147,7 +159,6 @@ def undo_weighted_forward(sd_model):
 
 class StableDiffusionModelHijack:
     fixes = None
-    comments = []
     layers = None
     circular_enabled = False
     clip = None
@@ -156,6 +167,9 @@ class StableDiffusionModelHijack:
     embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase()
 
     def __init__(self):
+        self.extra_generation_params = {}
+        self.comments = []
+
         self.embedding_db.add_embedding_dir(cmd_opts.embeddings_dir)
 
     def apply_optimizations(self, option=None):
@@ -166,6 +180,32 @@ class StableDiffusionModelHijack:
             undo_optimizations()
 
     def hijack(self, m):
+        conditioner = getattr(m, 'conditioner', None)
+        if conditioner:
+            text_cond_models = []
+
+            for i in range(len(conditioner.embedders)):
+                embedder = conditioner.embedders[i]
+                typename = type(embedder).__name__
+                if typename == 'FrozenOpenCLIPEmbedder':
+                    embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self)
+                    conditioner.embedders[i] = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(embedder, self)
+                    text_cond_models.append(conditioner.embedders[i])
+                if typename == 'FrozenCLIPEmbedder':
+                    model_embeddings = embedder.transformer.text_model.embeddings
+                    model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self)
+                    conditioner.embedders[i] = sd_hijack_clip.FrozenCLIPEmbedderForSDXLWithCustomWords(embedder, self)
+                    text_cond_models.append(conditioner.embedders[i])
+                if typename == 'FrozenOpenCLIPEmbedder2':
+                    embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self)
+                    conditioner.embedders[i] = sd_hijack_open_clip.FrozenOpenCLIPEmbedder2WithCustomWords(embedder, self)
+                    text_cond_models.append(conditioner.embedders[i])
+
+            if len(text_cond_models) == 1:
+                m.cond_stage_model = text_cond_models[0]
+            else:
+                m.cond_stage_model = conditioner
+
         if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
             model_embeddings = m.cond_stage_model.roberta.embeddings
             model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
@@ -236,6 +276,7 @@ class StableDiffusionModelHijack:
 
     def clear_comments(self):
         self.comments = []
+        self.extra_generation_params = {}
 
     def get_prompt_lengths(self, text):
         if self.clip is None:

modules/sd_hijack_open_clip.py

@@ -32,6 +32,40 @@ class FrozenOpenCLIPEmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWit
     def encode_embedding_init_text(self, init_text, nvpt):
         ids = tokenizer.encode(init_text)
         ids = torch.asarray([ids], device=devices.device, dtype=torch.int)
-        embedded = self.wrapped.model.token_embedding.wrapped(ids).squeeze(0)
+        embedded = self.wrapped.model.token_embedding.wrapped(ids.to(self.wrapped.model.token_embedding.wrapped.weight.device)).squeeze(0)
+
+        return embedded
+
+
+class FrozenOpenCLIPEmbedder2WithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWordsBase):
+    def __init__(self, wrapped, hijack):
+        super().__init__(wrapped, hijack)
+
+        self.comma_token = [v for k, v in tokenizer.encoder.items() if k == ',</w>'][0]
+        self.id_start = tokenizer.encoder["<start_of_text>"]
+        self.id_end = tokenizer.encoder["<end_of_text>"]
+        self.id_pad = 0
+
+    def tokenize(self, texts):
+        assert not opts.use_old_emphasis_implementation, 'Old emphasis implementation not supported for Open Clip'
+
+        tokenized = [tokenizer.encode(text) for text in texts]
+
+        return tokenized
+
+    def encode_with_transformers(self, tokens):
+        d = self.wrapped.encode_with_transformer(tokens)
+        z = d[self.wrapped.layer]
+
+        pooled = d.get("pooled")
+        if pooled is not None:
+            z.pooled = pooled
+
+        return z
+
+    def encode_embedding_init_text(self, init_text, nvpt):
+        ids = tokenizer.encode(init_text)
+        ids = torch.asarray([ids], device=devices.device, dtype=torch.int)
+        embedded = self.wrapped.model.token_embedding.wrapped(ids.to(self.wrapped.model.token_embedding.wrapped.weight.device)).squeeze(0)
 
         return embedded

modules/sd_hijack_unet.py

@@ -39,7 +39,10 @@ def apply_model(orig_func, self, x_noisy, t, cond, **kwargs):
 
     if isinstance(cond, dict):
         for y in cond.keys():
-            cond[y] = [x.to(devices.dtype_unet) if isinstance(x, torch.Tensor) else x for x in cond[y]]
+            if isinstance(cond[y], list):
+                cond[y] = [x.to(devices.dtype_unet) if isinstance(x, torch.Tensor) else x for x in cond[y]]
+            else:
+                cond[y] = cond[y].to(devices.dtype_unet) if isinstance(cond[y], torch.Tensor) else cond[y]
 
     with devices.autocast():
         return orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs).float()
@@ -77,3 +80,6 @@ first_stage_sub = lambda orig_func, self, x, **kwargs: orig_func(self, x.to(devi
 CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.decode_first_stage', first_stage_sub, first_stage_cond)
 CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.encode_first_stage', first_stage_sub, first_stage_cond)
 CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.get_first_stage_encoding', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).float(), first_stage_cond)
+
+CondFunc('sgm.modules.diffusionmodules.wrappers.OpenAIWrapper.forward', apply_model, unet_needs_upcast)
+CondFunc('sgm.modules.diffusionmodules.openaimodel.timestep_embedding', lambda orig_func, timesteps, *args, **kwargs: orig_func(timesteps, *args, **kwargs).to(torch.float32 if timesteps.dtype == torch.int64 else devices.dtype_unet), unet_needs_upcast)

modules/sd_samplers.py

@@ -28,6 +28,9 @@ def create_sampler(name, model):
 
     assert config is not None, f'bad sampler name: {name}'
 
+    if model.is_sdxl and config.options.get("no_sdxl", False):
+        raise Exception(f"Sampler {config.name} is not supported for SDXL")
+
     sampler = config.constructor(model)
     sampler.config = config
 

modules/textual_inversion/preprocess.py

@@ -7,7 +7,7 @@ from modules import paths, shared, images, deepbooru
 from modules.textual_inversion import autocrop
 
 
-def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
+def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.15, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
     try:
         if process_caption:
             shared.interrogator.load()