Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control
Paper • 2405.12970 • Published • 25
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Warlord-K/Adapter", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]FaceAdapter Model Card
Introduction
Face-Adapter is an efficient and effective face editing adapter for pre-trained diffusion models, specifically targeting face reenactment and swapping tasks.
Usage
You can directly download the model in this repository or download in python script:
# Download a specific file
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="FaceAdapter/FaceAdapter", filename="controlnet/config.json", local_dir="./checkpoints")
# Download all files
from huggingface_hub import snapshot_download
snapshot_download(repo_id="FaceAdapter/FaceAdapter", local_dir="./checkpoints")
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support