IP-Adapter-FaceID
An experimental version of IP-Adapter-FaceID: we use face ID embedding from a face recognition model instead of CLIP image embedding, additionally, we use LoRA to improve ID consistency. IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts.
Params
—
Context
—
Downloads 30d
274 K
Likes
1,917
Download history
daily snapshots · 106 days
▲ 79 K in the last 30 days (40.8%)
278 K200 K
Oct 12Oct 22Nov 1Nov 10
278 K179 K
Aug 13Sep 12Oct 12Nov 10
278 K179 K
Jul 28Sep 1Oct 6Nov 10
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 | fp16 | 0.9 GB | 1.5 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- First seen on the Hub
- 2023-12-20
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-to-image model