Image-to-Image
Diffusers
blind-face-restoration
face-restoration
flux
lora
diffusion
text-guided-image-restoration
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("thetrigger/A2BFR")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]A2BFR: Attribute-Aware Blind Face Restoration
A2BFR 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 A2BFR LoRA checkpoint for inference.
- Code: MediaX-SJTU/A2BFR
- Base model: black-forest-labs/FLUX.1-dev
- Checkpoint:
default.safetensors
- Downloads last month
- 4
Model tree for thetrigger/A2BFR
Base model
black-forest-labs/FLUX.1-dev