Merge branch 'comfyanonymous:master' into bugfix/extra_data

.github/workflows/test-build.yml

@@ -20,9 +20,9 @@ jobs:
       matrix:
         python-version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies

.github/workflows/windows_release_dependencies.yml

@@ -0,0 +1,67 @@
+name: "Windows Release dependencies"
+
+on:
+  workflow_dispatch:
+    inputs:
+      xformers:
+        description: 'xformers version'
+        required: false
+        type: string
+        default: ""
+      cu:
+        description: 'cuda version'
+        required: true
+        type: string
+        default: "121"
+
+      python_minor:
+        description: 'python minor version'
+        required: true
+        type: string
+        default: "11"
+
+      python_patch:
+        description: 'python patch version'
+        required: true
+        type: string
+        default: "6"
+#  push:
+#    branches:
+#      - master
+
+jobs:
+  build_dependencies:
+    runs-on: windows-latest
+    steps:
+        - uses: actions/checkout@v3
+        - uses: actions/setup-python@v4
+          with:
+            python-version: 3.${{ inputs.python_minor }}.${{ inputs.python_patch }}
+
+        - shell: bash
+          run: |
+            echo "@echo off
+            ..\python_embeded\python.exe .\update.py ..\ComfyUI\\
+            echo -
+            echo This will try to update pytorch and all python dependencies, if you get an error wait for pytorch/xformers to fix their stuff
+            echo You should not be running this anyways unless you really have to
+            echo -
+            echo If you just want to update normally, close this and run update_comfyui.bat instead.
+            echo -
+            pause
+            ..\python_embeded\python.exe -s -m pip install --upgrade torch torchvision torchaudio ${{ inputs.xformers }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r ../ComfyUI/requirements.txt pygit2
+            pause" > update_comfyui_and_python_dependencies.bat
+
+            python -m pip wheel --no-cache-dir torch torchvision torchaudio ${{ inputs.xformers }} --extra-index-url https://download.pytorch.org/whl/cu${{ inputs.cu }} -r requirements.txt pygit2 -w ./temp_wheel_dir
+            python -m pip install --no-cache-dir ./temp_wheel_dir/*
+            echo installed basic
+            ls -lah temp_wheel_dir
+            mv temp_wheel_dir cu${{ inputs.cu }}_python_deps
+            tar cf cu${{ inputs.cu }}_python_deps.tar cu${{ inputs.cu }}_python_deps
+
+        - uses: actions/cache/save@v3
+          with:
+            path: |
+              cu${{ inputs.cu }}_python_deps.tar
+              update_comfyui_and_python_dependencies.bat
+            key: ${{ runner.os }}-build-cu${{ inputs.cu }}-${{ inputs.python_minor }}

.github/workflows/windows_release_nightly_pytorch.yml

@@ -20,12 +20,12 @@ jobs:
             persist-credentials: false
         - uses: actions/setup-python@v4
           with:
-            python-version: '3.11.3'
+            python-version: '3.11.6'
         - shell: bash
           run: |
             cd ..
             cp -r ComfyUI ComfyUI_copy
-            curl https://www.python.org/ftp/python/3.11.3/python-3.11.3-embed-amd64.zip -o python_embeded.zip
+            curl https://www.python.org/ftp/python/3.11.6/python-3.11.6-embed-amd64.zip -o python_embeded.zip
             unzip python_embeded.zip -d python_embeded
             cd python_embeded
             echo 'import site' >> ./python311._pth

.github/workflows/windows_release_package.yml

@@ -0,0 +1,100 @@
+name: "Windows Release packaging"
+
+on:
+  workflow_dispatch:
+    inputs:
+      cu:
+        description: 'cuda version'
+        required: true
+        type: string
+        default: "121"
+
+      python_minor:
+        description: 'python minor version'
+        required: true
+        type: string
+        default: "11"
+
+      python_patch:
+        description: 'python patch version'
+        required: true
+        type: string
+        default: "6"
+#  push:
+#    branches:
+#      - master
+
+jobs:
+  package_comfyui:
+    permissions:
+        contents: "write"
+        packages: "write"
+        pull-requests: "read"
+    runs-on: windows-latest
+    steps:
+        - uses: actions/cache/restore@v3
+          id: cache
+          with:
+            path: |
+              cu${{ inputs.cu }}_python_deps.tar
+              update_comfyui_and_python_dependencies.bat
+            key: ${{ runner.os }}-build-cu${{ inputs.cu }}-${{ inputs.python_minor }}
+        - shell: bash
+          run: |
+            mv cu${{ inputs.cu }}_python_deps.tar ../
+            mv update_comfyui_and_python_dependencies.bat ../
+            cd ..
+            tar xf cu${{ inputs.cu }}_python_deps.tar
+            pwd
+            ls
+
+        - uses: actions/checkout@v3
+          with:
+            fetch-depth: 0
+            persist-credentials: false
+        - shell: bash
+          run: |
+            cd ..
+            cp -r ComfyUI ComfyUI_copy
+            curl https://www.python.org/ftp/python/3.${{ inputs.python_minor }}.${{ inputs.python_patch }}/python-3.${{ inputs.python_minor }}.${{ inputs.python_patch }}-embed-amd64.zip -o python_embeded.zip
+            unzip python_embeded.zip -d python_embeded
+            cd python_embeded
+            echo 'import site' >> ./python3${{ inputs.python_minor }}._pth
+            curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
+            ./python.exe get-pip.py
+            ./python.exe -s -m pip install ../cu${{ inputs.cu }}_python_deps/*
+            sed -i '1i../ComfyUI' ./python3${{ inputs.python_minor }}._pth
+            cd ..
+
+            git clone https://github.com/comfyanonymous/taesd
+            cp taesd/*.pth ./ComfyUI_copy/models/vae_approx/
+
+            mkdir ComfyUI_windows_portable
+            mv python_embeded ComfyUI_windows_portable
+            mv ComfyUI_copy ComfyUI_windows_portable/ComfyUI
+
+            cd ComfyUI_windows_portable
+
+            mkdir update
+            cp -r ComfyUI/.ci/update_windows/* ./update/
+            cp -r ComfyUI/.ci/windows_base_files/* ./
+            cp ../update_comfyui_and_python_dependencies.bat ./update/
+
+            cd ..
+
+            "C:\Program Files\7-Zip\7z.exe" a -t7z -m0=lzma -mx=8 -mfb=64 -md=32m -ms=on -mf=BCJ2 ComfyUI_windows_portable.7z ComfyUI_windows_portable
+            mv ComfyUI_windows_portable.7z ComfyUI/new_ComfyUI_windows_portable_nvidia_cu${{ inputs.cu }}_or_cpu.7z
+
+            cd ComfyUI_windows_portable
+            python_embeded/python.exe -s ComfyUI/main.py --quick-test-for-ci --cpu
+
+            ls
+
+        - name: Upload binaries to release
+          uses: svenstaro/upload-release-action@v2
+          with:
+                repo_token: ${{ secrets.GITHUB_TOKEN }}
+                file: new_ComfyUI_windows_portable_nvidia_cu${{ inputs.cu }}_or_cpu.7z
+                tag: "latest"
+                overwrite: true
+

README.md

@@ -1,6 +1,6 @@
 ComfyUI
 =======
-A powerful and modular stable diffusion GUI and backend.
+The most powerful and modular stable diffusion GUI and backend.
 -----------
 ![ComfyUI Screenshot](comfyui_screenshot.png)
 
@@ -69,7 +69,7 @@ Ctrl can also be replaced with Cmd instead for macOS users
 
 There is a portable standalone build for Windows that should work for running on Nvidia GPUs or for running on your CPU only on the [releases page](https://github.com/comfyanonymous/ComfyUI/releases).
 
-### [Direct link to download](https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_cu118_or_cpu.7z)
+### [Direct link to download](https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_cu121_or_cpu.7z)
 
 Simply download, extract with [7-Zip](https://7-zip.org) and run. Make sure you put your Stable Diffusion checkpoints/models (the huge ckpt/safetensors files) in: ComfyUI\models\checkpoints
 
@@ -92,16 +92,16 @@ Put your VAE in: models/vae
 ### AMD GPUs (Linux only)
 AMD users can install rocm and pytorch with pip if you don't have it already installed, this is the command to install the stable version:
 
-```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.4.2```
+```pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.6```
 
-This is the command to install the nightly with ROCm 5.6 that supports the 7000 series and might have some performance improvements:
-```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm5.6```
+This is the command to install the nightly with ROCm 5.7 that might have some performance improvements:
+```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/rocm5.7```
 
 ### NVIDIA
 
-Nvidia users should install torch and xformers using this command:
+Nvidia users should install pytorch using this command:
 
-```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu118 xformers```
+```pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121```
 
 #### Troubleshooting
 

comfy/controlnet.py

@@ -354,7 +354,7 @@ def load_controlnet(ckpt_path, model=None):
 
     if controlnet_config is None:
         use_fp16 = comfy.model_management.should_use_fp16()
-        controlnet_config = comfy.model_detection.model_config_from_unet(controlnet_data, prefix, use_fp16).unet_config
+        controlnet_config = comfy.model_detection.model_config_from_unet(controlnet_data, prefix, use_fp16, True).unet_config
     controlnet_config.pop("out_channels")
     controlnet_config["hint_channels"] = controlnet_data["{}input_hint_block.0.weight".format(prefix)].shape[1]
     control_model = comfy.cldm.cldm.ControlNet(**controlnet_config)

comfy/extra_samplers/uni_pc.py

@@ -688,7 +688,7 @@ def multistep_uni_pc_bh_update(self, x, model_prev_list, t_prev_list, t, order,
                 x_t = x_t_ - expand_dims(alpha_t * B_h, dims) * (corr_res + rhos_c[-1] * D1_t)
         else:
             x_t_ = (
-                expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dimss) * x
+                expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
                 - expand_dims(sigma_t * h_phi_1, dims) * model_prev_0
             )
             if x_t is None:

comfy/ldm/models/diffusion/ddim.py

@@ -59,7 +59,7 @@ def make_schedule_timesteps(self, ddim_timesteps, ddim_eta=0., verbose=True):
     @torch.no_grad()
     def sample_custom(self,
                       ddim_timesteps,
-                      conditioning,
+                      conditioning=None,
                       callback=None,
                       img_callback=None,
                       quantize_x0=False,

comfy/ldm/modules/attention.py

@@ -538,6 +538,8 @@ def _forward(self, x, context=None, transformer_options={}):
         if "block" in transformer_options:
             block = transformer_options["block"]
             extra_options["block"] = block
+        if "cond_or_uncond" in transformer_options:
+            extra_options["cond_or_uncond"] = transformer_options["cond_or_uncond"]
         if "patches" in transformer_options:
             transformer_patches = transformer_options["patches"]
         else:

comfy/ldm/modules/diffusionmodules/openaimodel.py

@@ -608,6 +608,7 @@ def forward(self, x, timesteps=None, context=None, y=None, control=None, transfo
         """
         transformer_options["original_shape"] = list(x.shape)
         transformer_options["current_index"] = 0
+        transformer_patches = transformer_options.get("patches", {})
 
         assert (y is not None) == (
             self.num_classes is not None
@@ -644,6 +645,11 @@ def forward(self, x, timesteps=None, context=None, y=None, control=None, transfo
                 if ctrl is not None:
                     hsp += ctrl
 
+            if "output_block_patch" in transformer_patches:
+                patch = transformer_patches["output_block_patch"]
+                for p in patch:
+                    h, hsp = p(h, hsp, transformer_options)
+
             h = th.cat([h, hsp], dim=1)
             del hsp
             if len(hs) > 0:

comfy/model_detection.py

@@ -1,5 +1,5 @@
-
-from . import supported_models
+import comfy.supported_models
+import comfy.supported_models_base
 
 def count_blocks(state_dict_keys, prefix_string):
     count = 0
@@ -109,17 +109,20 @@ def detect_unet_config(state_dict, key_prefix, use_fp16):
     return unet_config
 
 def model_config_from_unet_config(unet_config):
-    for model_config in supported_models.models:
+    for model_config in comfy.supported_models.models:
         if model_config.matches(unet_config):
             return model_config(unet_config)
 
     print("no match", unet_config)
     return None
 
-def model_config_from_unet(state_dict, unet_key_prefix, use_fp16):
+def model_config_from_unet(state_dict, unet_key_prefix, use_fp16, use_base_if_no_match=False):
     unet_config = detect_unet_config(state_dict, unet_key_prefix, use_fp16)
-    return model_config_from_unet_config(unet_config)
-
+    model_config = model_config_from_unet_config(unet_config)
+    if model_config is None and use_base_if_no_match:
+        return comfy.supported_models_base.BASE(unet_config)
+    else:
+        return model_config
 
 def unet_config_from_diffusers_unet(state_dict, use_fp16):
     match = {}

comfy/model_management.py

@@ -488,6 +488,8 @@ def cast_to_device(tensor, device, dtype, copy=False):
     elif tensor.dtype == torch.bfloat16:
         if hasattr(device, 'type') and device.type.startswith("cuda"):
             device_supports_cast = True
+        elif is_intel_xpu():
+            device_supports_cast = True
 
     if device_supports_cast:
         if copy:

comfy/model_patcher.py

@@ -88,6 +88,9 @@ def set_model_attn1_output_patch(self, patch):
     def set_model_attn2_output_patch(self, patch):
         self.set_model_patch(patch, "attn2_output_patch")
 
+    def set_model_output_block_patch(self, patch):
+        self.set_model_patch(patch, "output_block_patch")
+
     def model_patches_to(self, device):
         to = self.model_options["transformer_options"]
         if "patches" in to:

comfy/sample.py

@@ -70,28 +70,44 @@ def cleanup_additional_models(models):
         if hasattr(m, 'cleanup'):
             m.cleanup()
 
-def sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False, noise_mask=None, sigmas=None, callback=None, disable_pbar=False, seed=None):
-    device = comfy.model_management.get_torch_device()
+def prepare_sampling(model, noise_shape, positive, negative, noise_mask):
+    device = model.load_device
 
     if noise_mask is not None:
-        noise_mask = prepare_mask(noise_mask, noise.shape, device)
+        noise_mask = prepare_mask(noise_mask, noise_shape, device)
 
     real_model = None
     models, inference_memory = get_additional_models(positive, negative, model.model_dtype())
-    comfy.model_management.load_models_gpu([model] + models, comfy.model_management.batch_area_memory(noise.shape[0] * noise.shape[2] * noise.shape[3]) + inference_memory)
+    comfy.model_management.load_models_gpu([model] + models, comfy.model_management.batch_area_memory(noise_shape[0] * noise_shape[2] * noise_shape[3]) + inference_memory)
     real_model = model.model
 
-    noise = noise.to(device)
-    latent_image = latent_image.to(device)
+    positive_copy = broadcast_cond(positive, noise_shape[0], device)
+    negative_copy = broadcast_cond(negative, noise_shape[0], device)
+    return real_model, positive_copy, negative_copy, noise_mask, models
+
 
-    positive_copy = broadcast_cond(positive, noise.shape[0], device)
-    negative_copy = broadcast_cond(negative, noise.shape[0], device)
+def sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False, noise_mask=None, sigmas=None, callback=None, disable_pbar=False, seed=None):
+    real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask)
 
+    noise = noise.to(model.load_device)
+    latent_image = latent_image.to(model.load_device)
 
-    sampler = comfy.samplers.KSampler(real_model, steps=steps, device=device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)
+    sampler = comfy.samplers.KSampler(real_model, steps=steps, device=model.load_device, sampler=sampler_name, scheduler=scheduler, denoise=denoise, model_options=model.model_options)
 
     samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
     samples = samples.cpu()
 
     cleanup_additional_models(models)
     return samples
+
+def sample_custom(model, noise, cfg, sampler, sigmas, positive, negative, latent_image, noise_mask=None, callback=None, disable_pbar=False, seed=None):
+    real_model, positive_copy, negative_copy, noise_mask, models = prepare_sampling(model, noise.shape, positive, negative, noise_mask)
+    noise = noise.to(model.load_device)
+    latent_image = latent_image.to(model.load_device)
+    sigmas = sigmas.to(model.load_device)
+
+    samples = comfy.samplers.sample(real_model, noise, positive_copy, negative_copy, cfg, model.load_device, sampler, sigmas, model_options=model.model_options, latent_image=latent_image, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
+    samples = samples.cpu()
+    cleanup_additional_models(models)
+    return samples
+