| license: apache-2.0 | |
| base_model: black-forest-labs/FLUX.1-dev | |
| tags: | |
| - image-to-image | |
| - blind-face-restoration | |
| - face-restoration | |
| - flux | |
| - lora | |
| - diffusion | |
| - text-guided-image-restoration | |
| library_name: diffusers | |
| pipeline_tag: image-to-image | |
| # A<sup>2</sup>BFR: Attribute-Aware Blind Face Restoration | |
| A<sup>2</sup>BFR is an attribute-aware blind face restoration model built on **FLUX.1-dev**. It restores low-quality face images while allowing text prompts to guide facial attributes such as smiling, eyeglasses, hairstyle, and other semantic changes. | |
| This repository hosts the released A<sup>2</sup>BFR **LoRA checkpoint** for inference. | |
| - Code: [MediaX-SJTU/A2BFR](https://github.com/MediaX-SJTU/A2BFR) | |
| - Base model: [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) | |
| - Checkpoint: `default.safetensors` | |