Model reference · open weights
IP-Adapter-FaceID is an open-weight image model from h94, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
IP-Adapter-FaceID Model Card Project Page | Paper (ArXiv) | Code Introduction 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. Update 2023/12/27: IP-Adapter-FaceID-Plus: face ID embedding (for face ID) + CLIP image embedding (for face structure) Update 2023/12/28: IP-Adapter-FaceID-PlusV2: face ID embedding (for face ID) + controllable CLIP image embedding (for face structure) You can adjust the weight of the face structure to get different generation! Update 2024/01/04: IP-Adapter-FaceID-SDXL: An experimental SDXL version of IP-Adapter-FaceID Update 2024/01/17: IP-Adapter-FaceID-PlusV2-SDXL: An experimental SDXL version of IP-Adapter-FaceID-PlusV2 Update 2024/01/19: IP-Adapter-FaceID-Portrait: same with IP-Adapter-FaceID but for portrait generation (no lora! no controlnet!). Specifically, it accepts multiple facial images to enhance similarity (the default is 5). Usage IP-Adapter-FaceID Firstly, you should use insightface to extract face ID embedding: Then, you can generate images conditioned on the face embeddings: you can also use a normal IP-Adapter and a normal LoRA to load model: IP-Adapter-FaceID-SDXL Firstly, you should use insightface to extract face ID embedding: Then, you can generate images conditioned on the face embeddings: IP-Adapter-FaceID-Plus Firstly, you should use insightface to extract face ID embedding and face image: Then, you can generate images conditioned on the face embeddings: IP-Adapter-FaceID-Portrait Limitations and Bias - The models do not achieve perfect photorealism and ID consistency. - The generalization of the models is limited due to limitations of the training data, base model and face recognition model. Non-commercial use AS InsightFace pretrained models are available for non-commercial research purposes, IP-Adapter-FaceID models are released exclusively for research purposes and is not intended for commercial use.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | h94 |
|---|---|
| Type | Image models |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2023-12-20 |
| Popularity | 194k downloads / month |
| Likes | 1,878 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| IP-Adapter-FaceID | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys ip-adapter-faceid for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ip-adapter-faceid below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"ip-adapter-faceid","prompt":"a red bicycle","size":"1024x1024"}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗