Merge branch 'master' into asset-management

Author: Kosinkadink

.github/workflows/test-execution.yml

@@ -0,0 +1,30 @@
+name: Execution Tests
+
+on:
+  push:
+    branches: [ main, master ]
+  pull_request:
+    branches: [ main, master ]
+
+jobs:
+  test:
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+    runs-on: ${{ matrix.os }}
+    continue-on-error: true
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python      
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.12'
+    - name: Install requirements
+      run: |
+        python -m pip install --upgrade pip
+        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        pip install -r requirements.txt
+        pip install -r tests-unit/requirements.txt
+    - name: Run Execution Tests
+      run: |
+        python -m pytest tests/execution -v --skip-timing-checks

README.md

@@ -65,18 +65,18 @@ See what ComfyUI can do with the [example workflows](https://comfyanonymous.gith
    - [Flux](https://comfyanonymous.github.io/ComfyUI_examples/flux/)
    - [Lumina Image 2.0](https://comfyanonymous.github.io/ComfyUI_examples/lumina2/)
    - [HiDream](https://comfyanonymous.github.io/ComfyUI_examples/hidream/)
-   - [Cosmos Predict2](https://comfyanonymous.github.io/ComfyUI_examples/cosmos_predict2/)
    - [Qwen Image](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/)
+   - [Hunyuan Image 2.1](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_image/)
 - Image Editing Models
    - [Omnigen 2](https://comfyanonymous.github.io/ComfyUI_examples/omnigen/)
    - [Flux Kontext](https://comfyanonymous.github.io/ComfyUI_examples/flux/#flux-kontext-image-editing-model)
    - [HiDream E1.1](https://comfyanonymous.github.io/ComfyUI_examples/hidream/#hidream-e11)
+   - [Qwen Image Edit](https://comfyanonymous.github.io/ComfyUI_examples/qwen_image/#edit-model)
 - Video Models
    - [Stable Video Diffusion](https://comfyanonymous.github.io/ComfyUI_examples/video/)
    - [Mochi](https://comfyanonymous.github.io/ComfyUI_examples/mochi/)
    - [LTX-Video](https://comfyanonymous.github.io/ComfyUI_examples/ltxv/)
    - [Hunyuan Video](https://comfyanonymous.github.io/ComfyUI_examples/hunyuan_video/)
-   - [Nvidia Cosmos](https://comfyanonymous.github.io/ComfyUI_examples/cosmos/) and [Cosmos Predict2](https://comfyanonymous.github.io/ComfyUI_examples/cosmos_predict2/)
    - [Wan 2.1](https://comfyanonymous.github.io/ComfyUI_examples/wan/)
    - [Wan 2.2](https://comfyanonymous.github.io/ComfyUI_examples/wan22/)
 - Audio Models
@@ -191,7 +191,7 @@ comfy install
 
 ## Manual Install (Windows, Linux)
 
-python 3.13 is supported but using 3.12 is recommended because some custom nodes and their dependencies might not support it yet.
+Python 3.13 is very well supported. If you have trouble with some custom node dependencies you can try 3.12
 
 Git clone this repo.
 

app/user_manager.py

@@ -363,10 +363,17 @@ async def post_userdata(request):
             if not overwrite and os.path.exists(path):
                 return web.Response(status=409, text="File already exists")
 
-            body = await request.read()
+            try:
+                body = await request.read()
 
-            with open(path, "wb") as f:
-                f.write(body)
+                with open(path, "wb") as f:
+                    f.write(body)
+            except OSError as e:
+                logging.warning(f"Error saving file '{path}': {e}")
+                return web.Response(
+                    status=400,
+                    reason="Invalid filename. Please avoid special characters like :\\/*?\"<>|"
+                )
 
             user_path = self.get_request_user_filepath(request, None)
             if full_info:

comfy/audio_encoders/audio_encoders.py

@@ -0,0 +1,91 @@
+from .wav2vec2 import Wav2Vec2Model
+from .whisper import WhisperLargeV3
+import comfy.model_management
+import comfy.ops
+import comfy.utils
+import logging
+import torchaudio
+
+
+class AudioEncoderModel():
+    def __init__(self, config):
+        self.load_device = comfy.model_management.text_encoder_device()
+        offload_device = comfy.model_management.text_encoder_offload_device()
+        self.dtype = comfy.model_management.text_encoder_dtype(self.load_device)
+        model_type = config.pop("model_type")
+        model_config = dict(config)
+        model_config.update({
+            "dtype": self.dtype,
+            "device": offload_device,
+            "operations": comfy.ops.manual_cast
+        })
+
+        if model_type == "wav2vec2":
+            self.model = Wav2Vec2Model(**model_config)
+        elif model_type == "whisper3":
+            self.model = WhisperLargeV3(**model_config)
+        self.model.eval()
+        self.patcher = comfy.model_patcher.ModelPatcher(self.model, load_device=self.load_device, offload_device=offload_device)
+        self.model_sample_rate = 16000
+
+    def load_sd(self, sd):
+        return self.model.load_state_dict(sd, strict=False)
+
+    def get_sd(self):
+        return self.model.state_dict()
+
+    def encode_audio(self, audio, sample_rate):
+        comfy.model_management.load_model_gpu(self.patcher)
+        audio = torchaudio.functional.resample(audio, sample_rate, self.model_sample_rate)
+        out, all_layers = self.model(audio.to(self.load_device))
+        outputs = {}
+        outputs["encoded_audio"] = out
+        outputs["encoded_audio_all_layers"] = all_layers
+        outputs["audio_samples"] = audio.shape[2]
+        return outputs
+
+
+def load_audio_encoder_from_sd(sd, prefix=""):
+    sd = comfy.utils.state_dict_prefix_replace(sd, {"wav2vec2.": ""})
+    if "encoder.layer_norm.bias" in sd: #wav2vec2
+        embed_dim = sd["encoder.layer_norm.bias"].shape[0]
+        if embed_dim == 1024:# large
+            config = {
+                "model_type": "wav2vec2",
+                "embed_dim": 1024,
+                "num_heads": 16,
+                "num_layers": 24,
+                "conv_norm": True,
+                "conv_bias": True,
+                "do_normalize": True,
+                "do_stable_layer_norm": True
+                }
+        elif embed_dim == 768: # base
+            config = {
+                "model_type": "wav2vec2",
+                "embed_dim": 768,
+                "num_heads": 12,
+                "num_layers": 12,
+                "conv_norm": False,
+                "conv_bias": False,
+                "do_normalize": False, # chinese-wav2vec2-base has this False
+                "do_stable_layer_norm": False
+            }
+        else:
+            raise RuntimeError("ERROR: audio encoder file is invalid or unsupported embed_dim: {}".format(embed_dim))
+    elif "model.encoder.embed_positions.weight" in sd:
+        sd = comfy.utils.state_dict_prefix_replace(sd, {"model.": ""})
+        config = {
+            "model_type": "whisper3",
+        }
+    else:
+        raise RuntimeError("ERROR: audio encoder not supported.")
+
+    audio_encoder = AudioEncoderModel(config)
+    m, u = audio_encoder.load_sd(sd)
+    if len(m) > 0:
+        logging.warning("missing audio encoder: {}".format(m))
+    if len(u) > 0:
+        logging.warning("unexpected audio encoder: {}".format(u))
+
+    return audio_encoder