face-parsing
Semantic segmentation model fine-tuned from nvidia/mit-b5 with CelebAMask-HQ for face parsing. For additional options, see the Transformers Segformer docs.
Params
85 M
Context
—
Downloads 30d
183 K
Likes
231
Download history
daily snapshots · 9 days203 K183 K
Oct 16Oct 19Oct 22Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 0.3 GB | 0.9 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- SegformerForSemanticSegmentation
- Parameters
- 85 M
- Tensor type
- F32
- First seen on the Hub
- 2022-07-06
- Training datasets
- celebamaskhq
- Added to our catalog
- 2026-10-16
Compare with any image-segmentation model