Instructions to use Alissonerdx/BFS-Best-Face-Swap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Alissonerdx/BFS-Best-Face-Swap with Diffusers:
pip install -U diffusers transformers accelerate
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.2-klein-9B,black-forest-labs/FLUX.2-klein-4B,black-forest-labs/FLUX.2-klein-base-4B,black-forest-labs/FLUX.2-klein-base-9B,black-forest-labs/FLUX.2-klein-9b-fp8,black-forest-labs/FLUX.2-klein-4b-fp8,Qwen/Qwen-Image-Edit-2511", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Alissonerdx/BFS-Best-Face-Swap") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
face swap v head swap
i have been trying out your head swap and face swap loras in a qwen based workflow. using bfs_head_v5_2511_merged_version_rank_16_fp16 works really good, but im trying to do this without swapping the entire head (wanting to keep original hair). i tried masking, that reduced quality. i tried adjusting strength and denoise, i can make it work so it preserves the hair, but it reduces the quality. i have tried using bfs_face_v1_qwen_image_edit_2509 as well so its just a face swap rather than an entire head swap, but i cant seem to get as good of a result as using the full head swap lora. is this me doing something wrong, or is there just a difference in capabilities between the head swap lora and face swap lora?
got same issue. maybe just the lora question