metadata
license: apache-2.0
language:
- en
library_name: diffusers
Model Card for Arc2Face
Introduction
Arc2Face is an ID-conditioned face model, that can generate diverse, ID-consistent photos of a person given only its ArcFace ID-embedding. It is trained on a restored version of the WebFace42M face recognition database, and is further fine-tuned on FFHQ and CelebA-HQ.
Model Details
It consists of 2 components:
- encoder, a finetuned CLIP ViT-L/14 model
- arc2face, a finetuned UNet model
both of which are fine-tuned from runwayml/stable-diffusion-v1-5. The encoder is tailored for projecting ID-embeddings to the CLIP latent space. Arc2Face adapts the pre-trained backbone to the task of ID-to-face generation, conditioned solely on ID vectors.
Usage
The models can be downloaded directly from this repository or using python:
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="FoivosPar/Arc2Face", filename="arc2face/config.json", local_dir="./models/arc2face")
hf_hub_download(repo_id="FoivosPar/Arc2Face", filename="arc2face/diffusion_pytorch_model.safetensors", local_dir="./models/arc2face")
hf_hub_download(repo_id="FoivosPar/Arc2Face", filename="encoder/config.json", local_dir="./models/encoder")
hf_hub_download(repo_id="FoivosPar/Arc2Face", filename="encoder/pytorch_model.bin", local_dir="./models/encoder")
Please check our GitHub repository for complete inference instruction.
Limitations and Bias
- Only one person per image can be generated.
- Poses are constrained to the frontal hemisphere, similar to FFHQ images.
- The model may reflect the biases of the training data or the ID encoder.
Citation
BibTeX: