zsxkib/wd-image-tagger 🖼️❓🔢✓ → ❓

▶️ 6.5K runs 📅 May 2024 ⚙️ Cog 0.9.7 🔗 GitHub ⚖️ License

About

Image tagger fine-tuned on WaifuDiffusion w/ (SwinV2, SwinV2, ConvNext, and ViT)

Example Output

Output

[object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object][object Object]

Performance Metrics

1.91s Prediction Time

328.19s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/KyBHXfcGfwSFs0ob5gIoW0gPgU8e06B2t2gyGKeDElufpsj0/bunny3.webp",
  "category": "all_tags",
  "model_repo": "models/wd-swinv2-tagger-v3",
  "general_thresh": 0.35,
  "character_thresh": 0.85,
  "general_mcut_enabled": false,
  "character_mcut_enabled": false
}

Input Parameters

image (required) Type: string: Path to the input image file to be analyzed by the WaifuDiffusion tagger model
category Default: all_tags: Category of tags to return in the output
model_repo Default: models/wd-swinv2-tagger-v3: Name of the pre-trained model repository to use for image analysis
general_thresh Type: numberDefault: 0.35Range: 0 - 1: Probability threshold for including general tags in the output (between 0 and 1)
character_thresh Type: numberDefault: 0.85Range: 0 - 1: Probability threshold for including character tags in the output (between 0 and 1)
general_mcut_enabled Type: booleanDefault: false: Whether to use the MCut algorithm to automatically determine the general tags threshold
character_mcut_enabled Type: booleanDefault: false: Whether to use the MCut algorithm to automatically determine the character tags threshold

Output Schema

Output

Type: array

Version Details

Version ID: f9cfa5bef6e8f789662b1d6014a378f5e514a9f4d6b409e0ad84da126a4bdf62
Version Created: May 22, 2024

Run on Replicate →