Downloads · 30 days
0
tagger-experiment-onnx
silveroxides/tagger-experiment-onnx
tagger-experiment-onnx is a image classification model from silveroxides. Use it when you need a label for an image. The card lists the license as apache-2.0.
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.
Access
Public
Updated Apr 17, 2026
Repo size
15 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data12 GB · 80%
At a glance
- Task
- Image Classification
- License
- apache-2.0
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 17, 2026
- SHA
- 385229cb
Model card
From the Hugging Face model README
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
| Property | Value |
|---|---|
| Backbone | facebook/dinov3-vith16plus-pretrain-lvd1689m |
| Architecture | ViT-H/16+ · 32 layers · hidden dim 1280 · 20 heads · SwiGLU MLP · RoPE · 4 register tokens |
| Head | Linear((1 + 4) × 1280 → 74 625) — CLS + 4 register tokens concatenated |
| Vocabulary | 74 625 tags (min frequency ≥ 50 across training set) |
| Input resolution | Any multiple of 16 px — trained at 512 px, generalises to higher resolutions |
| Input normalisation | ImageNet mean/std [0.485, 0.456, 0.406] / [0.229, 0.224, 0.225] |
| Output | Raw logits — apply sigmoid for per-tag probabilities |
| Parameters | ~632 M (backbone) + ~480 M (head) |
Training
| Hyperparameter | Value |
|---|---|
| Training data | e621 + Danbooru (parquet) |
| Batch size | 32 |
| Learning rate | 1e-6 |
| Warmup steps | 50 |
| Loss | BCEWithLogitsLoss with per-tag pos_weight = (neg/pos)^(1/T), cap 100 |
| Optimiser | AdamW (β₁=0.9, β₂=0.999, wd=0.01) |
| Precision | bfloat16 (backbone) / float32 (projection + loss) |
| Hardware | 2× GPU, ThreadPoolExecutor + NCCL all-reduce |
Usage
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
| File | Description |
|---|---|
*.safetensors | Model weights (bfloat16) |
tagger_vocab_with_categories.json | {"idx2tag": [...]} — 74 625 tag strings ordered by training frequency |
inference_tagger_standalone.py | Self-contained inference script (no transformers dep) |
tagger_ui_server.py | FastAPI + Jinja2 web UI server |
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
- Task
- Image Classification
- License
- apache-2.0
- Created
- Apr 16, 2026
- Updated
- Apr 17, 2026