Skip to content

    FaceAdapter/Face-Adapter

    Repository files navigation

    Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control

    arXiv GitHub

    Introduction

    Face-Adapter is an efficient and effective face editing adapter for pre-trained diffusion models, specifically targeting face reenactment and swapping tasks.

    Release

    • [2024/5/25] ?? We release the gradio demo.
    • [2024/5/24] ?? We release the code and models.

    Installation

    # Torch >= 2.0 recommended for acceleration without xformers
    pip install accelerate diffusers==0.26.0 insightface onnxruntime
    
    

    Download Models

    You can download models of FaceAdapter directly from here or download using python script:

    # Download all files 
    from huggingface_hub import snapshot_download
    snapshot_download(repo_id="FaceAdapter/FaceAdapter", local_dir="./checkpoints")
    
    # If you want to download one specific file
    from huggingface_hub import hf_hub_download
    hf_hub_download(repo_id="FaceAdapter/FaceAdapter", filename="controlnet/config.json", local_dir="./checkpoints")

    To run the demo, you should also download the pre-trained SD models below:

    ? Quick Inference

    SD_1.5

    python infer.py 

    You can adjust the cropping size with the --crop_ratio (default:0.81)parameter. But be careful not to set the crop range too large, as this can decrease the quality of the generated images due to the limit of the training data size.

    ?? FaceAdapter can be seamlessly plugged into community models:

    python infer.py --base_model "frankjoshua/toonyou_beta6"

    Disclaimer

    This project strives to positively impact the domain of AI-driven image generation. Users are granted the freedom to create images using this tool, but they are expected to comply with local laws and utilize it in a responsible manner. The developers do not assume any responsibility for potential misuse by users.

    Citation

    If you find Face-Adapter useful for your research and applications, please cite using this BibTeX:

    @article{han2024face,
      title={Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control},
      author={Han, Yue and Zhu, Junwei and He, Keke and Chen, Xu and Ge, Yanhao and Li, Wei and Li, Xiangtai and Zhang, Jiangning and Wang, Chengjie and Liu, Yong},
      journal={arXiv preprint arXiv:2405.12970},
      year={2024}
    }

    About

    No description, website, or topics provided.

    Resources

    Stars

    Watchers

    Forks

    Releases

    No releases published

    Packages

    No packages published

    Contributors 2

    •  
    •  

    Languages

    主站蜘蛛池模板: 狠狠做深爱婷婷综合一区 | 中文字幕一区精品| 国产人妖视频一区二区| 亚洲午夜精品第一区二区8050| 日本一区二区三区不卡视频 | 3d动漫精品啪啪一区二区中| 国产日韩AV免费无码一区二区三区| 亚洲宅男精品一区在线观看| 中文字幕人妻第一区| 无码人妻精品一区二区三区9厂 | 一区二区亚洲精品精华液| 果冻传媒董小宛一区二区| 国产内射在线激情一区| 国产香蕉一区二区三区在线视频| 亚洲高清美女一区二区三区 | 亚洲福利视频一区二区| 国产熟女一区二区三区五月婷| 日本一道一区二区免费看| 亚洲区精品久久一区二区三区| 亚洲AV综合色区无码一区| 亚洲福利视频一区| 欧美日韩一区二区成人午夜电影| 亚洲综合在线成人一区| av无码免费一区二区三区| 国产乱人伦精品一区二区在线观看| 人妻aⅴ无码一区二区三区| 国产一区二区好的精华液| 国产成人午夜精品一区二区三区| 亚洲中文字幕乱码一区| 国模无码一区二区三区| 在线不卡一区二区三区日韩| 秋霞电影网一区二区三区| 中文字幕一区二区区免| 一区二区三区无码视频免费福利| 久久久99精品一区二区| 久草新视频一区二区三区| 好爽毛片一区二区三区四无码三飞| 国产一区二区三区乱码在线观看| 免费一区二区视频| 国产激情无码一区二区app| 无码人妻精品一区二区三区东京热|