Merge branch 'AUTOMATIC1111:dev' into dev

.github/workflows/run_tests.yaml

@@ -20,6 +20,12 @@ jobs:
           cache-dependency-path: |
             **/requirements*txt
             launch.py
+      - name: Cache models
+        id: cache-models
+        uses: actions/cache@v3
+        with:
+          path: models
+          key: "2023-12-30"
       - name: Install test dependencies
         run: pip install wait-for-it -r requirements-test.txt
         env:
@@ -33,6 +39,8 @@ jobs:
           TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
           WEBUI_LAUNCH_LIVE_OUTPUT: "1"
           PYTHONUNBUFFERED: "1"
+      - name: Print installed packages
+        run: pip freeze
       - name: Start test server
         run: >
           python -m coverage run
@@ -49,7 +57,7 @@ jobs:
           2>&1 | tee output.txt &
       - name: Run tests
         run: |
-          wait-for-it --service 127.0.0.1:7860 -t 600
+          wait-for-it --service 127.0.0.1:7860 -t 20
           python -m pytest -vv --junitxml=test/results.xml --cov . --cov-report=xml --verify-base-url test
       - name: Kill test server
         if: always()

.gitignore

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

README.md

@@ -1,5 +1,5 @@
 # Stable Diffusion web UI
-A browser interface based on Gradio library for Stable Diffusion.
+A web interface for Stable Diffusion, implemented using Gradio library.
 
 ![](screenshot.png)
 
@@ -151,11 +151,12 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 
 - Stable Diffusion - https://github.com/Stability-AI/stablediffusion, https://github.com/CompVis/taming-transformers
 - k-diffusion - https://github.com/crowsonkb/k-diffusion.git
-- GFPGAN - https://github.com/TencentARC/GFPGAN.git
-- CodeFormer - https://github.com/sczhou/CodeFormer
-- ESRGAN - https://github.com/xinntao/ESRGAN
-- SwinIR - https://github.com/JingyunLiang/SwinIR
-- Swin2SR - https://github.com/mv-lab/swin2sr
+- Spandrel - https://github.com/chaiNNer-org/spandrel implementing
+  - GFPGAN - https://github.com/TencentARC/GFPGAN.git
+  - CodeFormer - https://github.com/sczhou/CodeFormer
+  - ESRGAN - https://github.com/xinntao/ESRGAN
+  - SwinIR - https://github.com/JingyunLiang/SwinIR
+  - Swin2SR - https://github.com/mv-lab/swin2sr
 - LDSR - https://github.com/Hafiidz/latent-diffusion
 - MiDaS - https://github.com/isl-org/MiDaS
 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion

configs/sd_xl_inpaint.yaml

@@ -0,0 +1,98 @@
+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: True
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          attn_type: vanilla-xformers
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult: [1, 2, 4, 4]
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity

extensions-builtin/Lora/network.py

@@ -3,6 +3,9 @@
 from collections import namedtuple
 import enum
 
+import torch.nn as nn
+import torch.nn.functional as F
+
 from modules import sd_models, cache, errors, hashes, shared
 
 NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
@@ -115,6 +118,29 @@ def __init__(self, net: Network, weights: NetworkWeights):
         if hasattr(self.sd_module, 'weight'):
             self.shape = self.sd_module.weight.shape
 
+        self.ops = None
+        self.extra_kwargs = {}
+        if isinstance(self.sd_module, nn.Conv2d):
+            self.ops = F.conv2d
+            self.extra_kwargs = {
+                'stride': self.sd_module.stride,
+                'padding': self.sd_module.padding
+            }
+        elif isinstance(self.sd_module, nn.Linear):
+            self.ops = F.linear
+        elif isinstance(self.sd_module, nn.LayerNorm):
+            self.ops = F.layer_norm
+            self.extra_kwargs = {
+                'normalized_shape': self.sd_module.normalized_shape,
+                'eps': self.sd_module.eps
+            }
+        elif isinstance(self.sd_module, nn.GroupNorm):
+            self.ops = F.group_norm
+            self.extra_kwargs = {
+                'num_groups': self.sd_module.num_groups,
+                'eps': self.sd_module.eps
+            }
+
         self.dim = None
         self.bias = weights.w.get("bias")
         self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
@@ -155,5 +181,10 @@ def calc_updown(self, target):
         raise NotImplementedError()
 
     def forward(self, x, y):
-        raise NotImplementedError()
+        """A general forward implementation for all modules"""
+        if self.ops is None:
+            raise NotImplementedError()
+        else:
+            updown, ex_bias = self.calc_updown(self.sd_module.weight)
+            return y + self.ops(x, weight=updown, bias=ex_bias, **self.extra_kwargs)
 

extensions-builtin/Lora/network_oft.py

@@ -56,7 +56,7 @@ def __init__(self,  net: network.Network, weights: network.NetworkWeights):
             self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
 
     def calc_updown(self, orig_weight):
-        oft_blocks = self.oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
+        oft_blocks = self.oft_blocks.to(orig_weight.device)
         eye = torch.eye(self.block_size, device=self.oft_blocks.device)
 
         if self.is_kohya:
@@ -66,7 +66,7 @@ def calc_updown(self, orig_weight):
             block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
             oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse())
 
-        R = oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
+        R = oft_blocks.to(orig_weight.device)
 
         # This errors out for MultiheadAttention, might need to be handled up-stream
         merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
@@ -77,6 +77,6 @@ def calc_updown(self, orig_weight):
         )
         merged_weight = rearrange(merged_weight, 'k m ... -> (k m) ...')
 
-        updown = merged_weight.to(orig_weight.device, dtype=orig_weight.dtype) - orig_weight
+        updown = merged_weight.to(orig_weight.device) - orig_weight.to(merged_weight.dtype)
         output_shape = orig_weight.shape
         return self.finalize_updown(updown, orig_weight, output_shape)

extensions-builtin/Lora/networks.py

@@ -1,3 +1,4 @@
+import gradio as gr
 import logging
 import os
 import re
@@ -314,7 +315,12 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
                 emb_db.skipped_embeddings[name] = embedding
 
     if failed_to_load_networks:
-        sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
+        lora_not_found_message = f'Lora not found: {", ".join(failed_to_load_networks)}'
+        sd_hijack.model_hijack.comments.append(lora_not_found_message)
+        if shared.opts.lora_not_found_warning_console:
+            print(f'\n{lora_not_found_message}\n')
+        if shared.opts.lora_not_found_gradio_warning:
+            gr.Warning(lora_not_found_message)
 
     purge_networks_from_memory()
 
@@ -452,23 +458,23 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
         self.network_current_names = wanted_names
 
 
-def network_forward(module, input, original_forward):
+def network_forward(org_module, input, original_forward):
     """
     Old way of applying Lora by executing operations during layer's forward.
     Stacking many loras this way results in big performance degradation.
     """
 
     if len(loaded_networks) == 0:
-        return original_forward(module, input)
+        return original_forward(org_module, input)
 
     input = devices.cond_cast_unet(input)
 
-    network_restore_weights_from_backup(module)
-    network_reset_cached_weight(module)
+    network_restore_weights_from_backup(org_module)
+    network_reset_cached_weight(org_module)
 
-    y = original_forward(module, input)
+    y = original_forward(org_module, input)
 
-    network_layer_name = getattr(module, 'network_layer_name', None)
+    network_layer_name = getattr(org_module, 'network_layer_name', None)
     for lora in loaded_networks:
         module = lora.modules.get(network_layer_name, None)
         if module is None:

extensions-builtin/Lora/scripts/lora_script.py

@@ -39,6 +39,8 @@ def before_ui():
     "lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
     "lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
     "lora_in_memory_limit": shared.OptionInfo(0, "Number of Lora networks to keep cached in memory", gr.Number, {"precision": 0}),
+    "lora_not_found_warning_console": shared.OptionInfo(False, "Lora not found warning in console"),
+    "lora_not_found_gradio_warning": shared.OptionInfo(False, "Lora not found warning popup in webui"),
 }))
 
 

extensions-builtin/Lora/ui_edit_user_metadata.py

@@ -54,12 +54,13 @@ def __init__(self, ui, tabname, page):
         self.slider_preferred_weight = None
         self.edit_notes = None
 
-    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, notes):
+    def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, negative_text, notes):
         user_metadata = self.get_user_metadata(name)
         user_metadata["description"] = desc
         user_metadata["sd version"] = sd_version
         user_metadata["activation text"] = activation_text
         user_metadata["preferred weight"] = preferred_weight
+        user_metadata["negative text"] = negative_text
         user_metadata["notes"] = notes
 
         self.write_user_metadata(name, user_metadata)
@@ -127,6 +128,7 @@ def put_values_into_components(self, name):
             gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
             user_metadata.get('activation text', ''),
             float(user_metadata.get('preferred weight', 0.0)),
+            user_metadata.get('negative text', ''),
             gr.update(visible=True if tags else False),
             gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
         ]
@@ -162,7 +164,7 @@ def create_editor(self):
         self.taginfo = gr.HighlightedText(label="Training dataset tags")
         self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
         self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
-
+        self.edit_negative_text = gr.Text(label='Negative prompt', info="Will be added to negative prompts")
         with gr.Row() as row_random_prompt:
             with gr.Column(scale=8):
                 random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
@@ -198,6 +200,7 @@ def select_tag(activation_text, evt: gr.SelectData):
             self.taginfo,
             self.edit_activation_text,
             self.slider_preferred_weight,
+            self.edit_negative_text,
             row_random_prompt,
             random_prompt,
         ]
@@ -211,7 +214,9 @@ def select_tag(activation_text, evt: gr.SelectData):
             self.select_sd_version,
             self.edit_activation_text,
             self.slider_preferred_weight,
+            self.edit_negative_text,
             self.edit_notes,
         ]
 
+
         self.setup_save_handler(self.button_save, self.save_lora_user_metadata, edited_components)

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -45,6 +45,11 @@ def create_item(self, name, index=None, enable_filter=True):
         if activation_text:
             item["prompt"] += " + " + quote_js(" " + activation_text)
 
+        negative_prompt = item["user_metadata"].get("negative text")
+        item["negative_prompt"] = quote_js("")
+        if negative_prompt:
+            item["negative_prompt"] = quote_js('(' + negative_prompt + ':1)')
+
         sd_version = item["user_metadata"].get("sd version")
         if sd_version in network.SdVersion.__members__:
             item["sd_version"] = sd_version