Wonderful tutorial, thank you very much. I encounter this error when running it: Error occurred when executing WD14Tagger|pysssss: [ONNXRuntimeError] : 1 : FAIL : Load model from C:\Users\luna\Documents\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WD14-Tagger\models\wd-vit-tagger-v3.onnx failed:D:\a\_work\1\s\onnxruntime\core/graph/model_load_utils.h:56 onnxruntime::model_load_utils::ValidateOpsetForDomain ONNX Runtime only *guarantees* support for models stamped with official released onnx opset versions. Opset 4 is under development and support for this is limited. The operator schemas and or other functionality may change before next ONNX release and in this case ONNX Runtime will not guarantee backward compatibility. Current official support for domain ai.onnx.ml is till opset 3.
Error occurred when executing DWPreprocessor: open file failed because of errno 2 on fopen: No such file or directory, file path: F:\夸克\ComfyUI-aki\ComfyUI-aki-v1.2\.cache\sdwebuilauncher\hfmirror efs\hr16\yolox-onnx\main\yolox_l.torchscript.pt
Error occurred when executing DWPreprocessor: open file failed because of errno 2 on fopen: No such file or directory, file path: F:\夸克\ComfyUI-aki\ComfyUI-aki-v1.2\.cache\sdwebuilauncher\hfmirror efs\hr16\yolox-onnx\main\yolox_l.torchscript.pt
Actually, I have prepared to do the English version, but I haven't been able to find a suitable netbook to store such a large file, and I found it difficult for non-Chinese to download my links of Quark and Baidu ~
非常感谢,已安装。 启动时,出现下列报错,怎么修改? 1)Torch version: 2.0.1+cu118 [comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\ComfyUI_Full\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts [comfyui_controlnet_aux] | INFO -> Using symlinks: False [comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider'] 2)左上角无工作流菜单,如何设置?
The images in this video did not use IPAdapter. I just discovered during my experiments that you can use IPAdapter's style transfer to modify the visual results.
太厉害了!有个问题想请教下,自动存储遮罩、动作这些的工作流是如何运行的,我这边总是报错 Prompt outputs failed validation: Failed to convert an input value to a INT value: quality, false, invalid literal for int() with base 10: 'false' Value not in list: overwrite_mode: 'true' not in ['false', 'prefix_as_filename'] Failed to convert an input value to a INT value: quality, false, invalid literal for int() with base 10: 'false' Failed to convert an input value to a INT value: quality, None, int() argument must be a string, a bytes-like object or a real number, not 'NoneType' Value not in list: overwrite_mode: 'true' not in ['false', 'prefix_as_filename'] Image Save: - Failed to convert an input value to a INT value: quality, false, invalid literal for int() with base 10: 'false' - Value not in list: overwrite_mode: 'true' not in ['false', 'prefix_as_filename']