下载model.onnx和selected_tags.csv这两个文件。保存到custom_nodes\ComfyUI-WD14-Tagger\models路径下,并建议改名为wd-v1-4-convnextv2-tagger-v2.csv,wd-v1-4-convnextv2-tagger-v2.onnx。 如果你选用其它模型也是相同的道理。 4.使用 在comfyui界面上测试WD14节点,可以直接加载图片交给模型处理。节点可...
models_dir = folder_paths.get_folder_paths("wd14_tagger")[0] else: models_dir = get_ext_dir("models", mkdir=True) all_models = ("wd-v1-4-moat-tagger-v2", "wd-v1-4-convnext-tagger-v2", "wd-v1-4-convnext-tagger", "wd-v1-4-convnextv2-tagger-v2", "wd-v1-4-vit-...
Models are automatically downloaded at runtime if missing. ![image](https://github.com/pythongosssss/ComfyUI-WD14-Tagger/assets/125205205/cc09ae71-1a38-44da-afec-90f470a4b47d) Supports tagging and outputting multiple batched inputs.
All models created bySmilingWolf Installation git clone https://github.com/pythongosssss/ComfyUI-WD14-Taggerinto thecustom_nodesfolder e.g.custom_nodes\ComfyUI-WD14-Tagger Open a Command Prompt/Terminal/etc Change to thecustom_nodes\ComfyUI-WD14-Taggerfolder you just created ...
models_dir=folder_paths.get_folder_paths("wd14_tagger")[0] ifnotos.path.exists(models_dir): os.makedirs(models_dir) else: models_dir=get_ext_dir("models",mkdir=True) known_models=list(config["models"].keys()) log("Available ORT providers: "+", ".join(ort.get_available_providers(...
All models created by SmilingWolf Installation git clone https://github.com/pythongosssss/ComfyUI-WD14-Tagger into the custom_nodes folder e.g. custom_nodes\ComfyUI-WD14-Tagger Open a Command Prompt/Terminal/etc Change to the custom_nodes\ComfyUI-WD14-Tagger folder you just created e....
Models are automatically downloaded at runtime if missing.Supports tagging and outputting multiple batched inputs. model: The interrogation model to use. You can try them out here WaifuDiffusion v1.4 Tags. The newest model (as of writing) is MOAT and the most popular is ConvNextV2. ...
["CUDAExecutionProvider", "CPUExecutionProvider"], "HF_ENDPOINT": "https://huggingface.co" }, "models": { "wd-vit-tagger-v3": "{HF_ENDPOINT}/SmilingWolf/wd-vit-tagger-v3", "wd-swinv2-tagger-v3": "{HF_ENDPOINT}/SmilingWolf/wd-swinv2-tagger-v3", "wd-convnext-tagger-v3": "{HF...
"models": { "wd-eva02-large-tagger-v3": "{HF_ENDPOINT}/SmilingWolf/wd-eva02-large-tagger-v3", "wd-vit-tagger-v3": "{HF_ENDPOINT}/SmilingWolf/wd-vit-tagger-v3", "wd-swinv2-tagger-v3": "{HF_ENDPOINT}/SmilingWolf/wd-swinv2-tagger-v3", "wd-convnext-tagger-v3": "{HF_ENDPOINT...
path.join(models_dir,f"{model}.csv"), update_callback, session=session) try: await download_to_file( f"{url}model.onnx", os.path.join(models_dir,f"{model}.onnx"), update_callback, session=session) await download_to_file( f"{url}selected_tags.csv", os.path.join(models_dir,f"...