运行节点出错：OpenCV(4.10.0) /io/opencv/modules/imgproc/src/color.cpp:196: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'

[fishxiaou]

配置好了依赖，在运行工作流的时候，走到LatentSyncNode节点报错
我的系统是：Ubuntu 22.04
是环境配置出错？还是代码有问题？
谢谢解答

ComfyUI Error Report

Error Details

• Node ID: 54
• Node Type: LatentSyncNode
• Exception Type: cv2.error
• Exception Message: OpenCV(4.10.0) /io/opencv/modules/imgproc/src/color.cpp:196: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'

Stack Trace

  File "/data/ComfyUI/execution.py", line 327, in execute
    output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/data/ComfyUI/execution.py", line 202, in get_output_data
    return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/data/ComfyUI/execution.py", line 174, in _map_node_over_list
    process_inputs(input_dict, i)

  File "/data/ComfyUI/execution.py", line 163, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/data/ComfyUI/custom_nodes/ComfyUI-LatentSyncWrapper/nodes.py", line 584, in inference
    inference_module.main(config, args)

  File "/data/ComfyUI/custom_nodes/ComfyUI-LatentSyncWrapper/scripts/inference.py", line 133, in main
    pipeline(

  File "/data/ComfyUI/venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^

  File "/data/ComfyUI/custom_nodes/ComfyUI-LatentSyncWrapper/latentsync/pipelines/lipsync_pipeline.py", line 314, in __call__
    mask_image = load_fixed_mask(height, mask_image_path)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/data/ComfyUI/custom_nodes/ComfyUI-LatentSyncWrapper/latentsync/utils/image_processor.py", line 33, in load_fixed_mask
    mask_image = cv2.cvtColor(mask_image, cv2.COLOR_BGR2RGB)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

cv2.error: OpenCV(4.10.0) /io/opencv/modules/imgproc/src/color.cpp:196: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'

[chunyu-li]

可能是因为 comfy UI 的代码有改动导致的，你试试这个仓库的代码

[zouzhekang]

mask图片的问题，你可以看看./latentsync/utils/image_processor.py的第26行的函数：

def load_fixed_mask(resolution: int, mask_image_path="latentsync/utils/mask.png") -> torch.Tensor:
    mask_image = cv2.imread(mask_image_path)
    mask_image = cv2.cvtColor(mask_image, cv2.COLOR_BGR2RGB)
    mask_image = cv2.resize(mask_image, (resolution, resolution), interpolation=cv2.INTER_LANCZOS4) / 255.0
    mask_image = rearrange(torch.from_numpy(mask_image), "h w c -> c h w")
    return mask_image

打印一下mask_image发现mask_image没读到，说明图片或者opencv其中一个不得行。

我的解决方法是改为pillow读取图片：

def load_fixed_mask(resolution: int, mask_image_path="latentsync/utils/mask.png") -> torch.Tensor:
    pil_image = Image.open(mask_image_path).convert("RGB")
    mask_image = np.array(pil_image, dtype=np.uint8)
    # mask_image = cv2.imread(mask_image_path)
    # mask_image = cv2.cvtColor(mask_image, cv2.COLOR_BGR2RGB)
    mask_image = cv2.resize(mask_image, (resolution, resolution), interpolation=cv2.INTER_LANCZOS4) / 255.0
    mask_image = rearrange(torch.from_numpy(mask_image), "h w c -> c h w")
    return mask_image

解决！
字节的作者大大，快点来夸夸我吧！！！