lodestones / tagger-experiment

DINOv3 ViT-H/16+ Booru Tagger

A multi-label image tagger trained on e621 and Danbooru annotations, using a DINOv3 ViT-H/16+ backbone fine-tuned end-to-end with a single linear projection head.

Model Details

Training

Usage

Standalone (no transformers dependency)

from inference_tagger_standalone import Tagger

tagger = Tagger(
    checkpoint_path="tagger_proto.safetensors",
    vocab_path="tagger_vocab_with_categories.json",
    device="cuda",
)

tags = tagger.predict("photo.jpg", topk=40)
# → [("solo", 0.98), ("anthro", 0.95), ...]

# or threshold-based
tags = tagger.predict("https://example.com/image.jpg", threshold=0.35)

CLI

# top-30 tags, pretty output
python inference_tagger_standalone.py \
    --checkpoint tagger_proto.safetensors \
    --vocab tagger_vocab_with_categories.json \
    --images photo.jpg https://example.com/image.jpg \
    --topk 30

# comma-separated string (pipe into diffusion trainer)
python inference_tagger_standalone.py ... --format tags

# JSON
python inference_tagger_standalone.py ... --format json

Web UI

pip install fastapi uvicorn jinja2 aiofiles

python tagger_ui_server.py \
    --checkpoint tagger_proto.safetensors \
    --vocab tagger_vocab_with_categories.json \
    --port 7860
# → open http://localhost:7860

Files

Tag Vocabulary

Tags are sourced from e621 and Danbooru annotations and cover:

• Subject — species, character count, gender ( solo , duo , anthro , 1girl , male , …)
• Body — anatomy, fur/scale/skin markings, body parts
• Action / pose — looking at viewer , sitting , …
• Scene — background, lighting, setting
• Style — digital art , hi res , sketch , watercolor , …
• Rating — explicit content tags are included; filter as needed for your use case

Minimum tag frequency threshold: 50 occurrences across the combined dataset.

Limitations

• Evaluated on booru-style illustrations and furry art; performance on photographic images or other art styles is untested.
• The vocabulary reflects the biases of e621 and Danbooru annotation practices.

License

Apache 2.0