下载model.onnx并使用模型名称命名,例如wd-v1-4-convnext-tagger-v2.onnx 下载selected_tags.csv并使用模型名称命名,例如wd-v1-4-convnext-tagger-v2.csv 总结一下 像WD14这样安装上稍微复杂一点的节点,一个节点往往需要下载节点文件(git),安装依赖包(python),下载模型(huggingface)三个主要步骤。我们需要的...
wd14-convnextv2.v1 wd14-swinv2-v1 wd-v1-4-moat-tagger.v2 mld-caformer.dec-5-97527 mld-tresnetd.6-30000 API Docs API documentation can be accessed fromhttp://localhost:8002/docswhen the server is running. This documentation is automatically generated by FastAPI and provides an interact...
'wd14-convnextv2-v2': WaifuDiffusionInterrogator( 'wd14-convnext-v2', repo_id='SmilingWolf/wd-v1-4-convnextv2-tagger-v2', ), 'wd14-vit-v2-git': WaifuDiffusionInterrogator( 'wd14-vit-v2-git', repo_id='SmilingWolf/wd-v1-4-vit-tagger-v2'0...
'wd14-swinv2-v2', repo_id='SmilingWolf/wd-v1-4-swinv2-tagger-v2', revision='v2.0' ), 'wd14-vit-v2-git': WaifuDiffusionInterrogator( 'wd14-vit-v2-git', repo_id='SmilingWolf/wd-v1-4-vit-tagger-v2' ), 'wd14-convnext-v2-git': WaifuDiffusionInterrogator( ...
ConvNext was used to extract features because SwinV2 is a bit of a pain cuz it is twice as slow and more memory intensive — [this message](https://discord.com/channels/930499730843250783/930499731451428926/1066830289382408285) from the [東方Project AI discord server](https://discord.com/in...
wd-v1-4-convnext-tagger-v2.csv Requirements onnxruntime (recommended, interrogation is still fast on CPU, included in requirements.txt) or onnxruntime-gpu (allows use of GPU, many people have issues with this, if you try I can't provide support for this) Changelog 2023-05-14 - ...
The newest model (as of writing) is MOAT and the most popular is ConvNextV2. threshold: The score for the tag to be considered valid character_threshold: The score for the character tag to be considered valid exclude_tags A comma separated list of tags that should not be included in ...
-wd14-convnextv2.v1 -wd14-swinv2-v1 -wd-v1-4-moat-tagger.v2 -mld-caformer.dec-5-97527 -mld-tresnetd.6-30000 ##API Docs API documentation can be accessed from[http://localhost:8002/docs](http://localhost:8002/docs)when the server is running. This documentation is automatically ...
convnextv2-tagger-v2", "wd-v1-4-convnext-tagger-v2": "{HF_ENDPOINT}/SmilingWolf/wd-v1-4-convnext-tagger-v2", "wd-v1-4-convnext-tagger": "{HF_ENDPOINT}/SmilingWolf/wd-v1-4-convnext-tagger", "wd-v1-4-vit-tagger-v2": "{HF_ENDPOINT}/SmilingWolf/wd-v1-4-vit-tagger-v2"...
"model": "wd-v1-4-convnext-tagger-v2", "threshold": 0.35, "character_threshold": 0.85, "exclude_tags": "" } defaults.update(config.get("settings", {})) models_dir = get_ext_dir("models", mkdir=True) all_models = ("wd-v1-4-convnext-tagger-v2", "wd-v1-4-convnext-tagger...