|
|
--- |
|
|
license: apache-2.0 |
|
|
pipeline_tag: image-classification |
|
|
tags: |
|
|
- multi-label |
|
|
- anime |
|
|
- danbooru |
|
|
- safetensors |
|
|
--- |
|
|
|
|
|
ℹ️ This is a **safetensors + tag JSON version** of the original model [pixai-labs/pixai-tagger-v0.9](https://huggingface.co/pixai-labs/pixai-tagger-v0.9). |
|
|
🔄 Converted by [1038lab](https://huggingface.co/1038lab). |
|
|
📦 No changes were made to model weights or logic — only converted `.pth` → `.safetensors` and bundled with `tags_v0.9_13k.json` for convenience. |
|
|
🧠 Full credits and model training go to PixAI Labs. |
|
|
|
|
|
--- |
|
|
|
|
|
<p> |
|
|
<img src="https://huggingface.co/pixai-labs/pixai-tagger-v0.9/resolve/main/banner_09_cropped.jpg" style="height:240px;" /> |
|
|
<a href="https://huggingface.co/pixai-labs/pixai-tagger-v0.9"><strong>Original Model</strong></a> · |
|
|
<a href="#quickstart"><strong>Quickstart</strong></a> · |
|
|
<a href="#training-notes"><strong>Training Notes</strong></a> · |
|
|
<a href="#credits"><strong>Credits</strong></a> |
|
|
</p> |
|
|
|
|
|
--- |
|
|
|
|
|
# PixAI Tagger v0.9 |
|
|
|
|
|
A practical anime **multi-label tagger**. Not trying to win benchmarks; trying to be useful. |
|
|
**High recall**, updated **character coverage**, trained on a fresh Danbooru snapshot (2025-01). |
|
|
We’ll keep shipping: **v1.0** (with updated tags) is next. |
|
|
|
|
|
> TL;DR |
|
|
> |
|
|
> - ~**13.5k** Danbooru-style tags (**general**, **character**, **copyright**) |
|
|
> - Headline: strong **character** performance; recall-leaning defaults |
|
|
> - Built for search, dataset curation, caption assistance, and text-to-image conditioning |
|
|
|
|
|
--- |
|
|
|
|
|
## What it is (in one breath) |
|
|
|
|
|
`pixai-tagger-v0.9` is a multi-label image classifier for anime images. It predicts Danbooru-style tags and aims to **find more of the right stuff** (recall) so you can filter later. We continued training the **classification head** of EVA02 (from WD v3) on a newer dataset, and used **embedding-space MixUp** to help calibration. |
|
|
|
|
|
- **Last trained:** 2025-04 |
|
|
- **Data snapshot:** Danbooru IDs 1–8,600,750 (2025-01) |
|
|
- **Finetuned from:** `SmilingWolf/wd-eva02-large-tagger-v3` (encoder frozen) |
|
|
- **License (weights):** Apache 2.0 *(Note: Danbooru content has its own licenses.)* |
|
|
|
|
|
--- |
|
|
|
|
|
## Why you might care |
|
|
|
|
|
- **Newer data.** Catches more recent IPs/characters. |
|
|
- **Recall-first defaults.** Good for search and curation; dial thresholds for precision. |
|
|
- **Character focus.** We spent time here; it shows up in evals. |
|
|
- **Simple to run.** Works as an endpoint or locally; small set of knobs. |
|
|
|
|
|
--- |
|
|
|
|
|
## Quickstart |
|
|
|
|
|
**Recommended defaults (balanced):** |
|
|
|
|
|
- `top_k = 128` |
|
|
- `threshold_general = 0.30` |
|
|
- `threshold_character = 0.75` |
|
|
|
|
|
**Coverage preset (recall-heavier):** `threshold_general = 0.10` (expect more false positives) |
|
|
|
|
|
### 1) Inference Endpoint |
|
|
|
|
|
Deploy as an HF Inference Endpoint and test with the following command: |
|
|
|
|
|
```bash |
|
|
# Replace with your own endpoint URL |
|
|
curl "https://YOUR_ENDPOINT_URL.huggingface.cloud" \ |
|
|
-X POST \ |
|
|
-H "Accept: application/json" \ |
|
|
-H "Content-Type: application/json" \ |
|
|
-d '{ |
|
|
"inputs": {"url": "https://your.cdn/image.jpg"}, |
|
|
"parameters": { |
|
|
"top_k": 128, |
|
|
"threshold_general": 0.10, |
|
|
"threshold_character": 0.75 |
|
|
} |
|
|
}' |
|
|
|
