Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bytedance/stylessp

[CVPR 2025] StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer

https://github.com/bytedance/stylessp

Science Score: 23.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

[CVPR 2025] StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer

Basic Info
  • Host: GitHub
  • Owner: bytedance
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 2.48 MB
Statistics
  • Stars: 10
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

[CVPR 2025] StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer

Arxiv

imgs

Usage

To run the code, please follow these step:

  1. Download
  2. Setup
  3. Run

Download

This project contains contributions from ControlNet and IP-Adapter-Instruct, licensed under the Apache License 2.0. Modifications and additional content added by StyleSSP in 2024. The pre-trained checkpoints from Tile-ControlNet, MistoLine, IP-Adapter-Instruct

```

download adapters

huggingface-cli download --resume-download h94/IP-Adapter --local-dir checkpoints/IP-Adapter

download ControlNets

huggingface-cli download --resume-download TheMistoAI/MistoLine --local-dir checkpoints/MistoLine huggingface-cli download --resume-download xinsir/controlnet-tile-sdxl-1.0 --local-dir checkpoints/controlnet-tile-sdxl-1.0

download models IP-Adapter-Instruct

download the models ckpt ip-adapter-instruct-sdxl.bin from: https://huggingface.co/CiaraRowles/IP-Adapter-Instruct and put it in the folder checkpoints/models ```

Environment Setup

conda env create -f environment.yaml conda activate StyleSSP pip install git+https://github.com/openai/CLIP.git

Run

For running StyleSSP, modify content_image_dir and style_image_dir in src/config.py, then run: python infer_style.py

Evaluation

For a quantitative evaluation, we incorporate a set of randomly selected inputs from MS-COCO and WikiArt in "./data" directory, as InstantStyle-Plus do.

Before executing evalution code, please run infer_style.py to get the results (40 styles, 20 contents -> 800 stylized images), then put the content, style and stylized images in "./dataevl/content", "./dataevl/style", and "./data_evl/tar" directory, respectively.

Then, run: cd evaluation; python eval_artfid.py --sty ../data_evl/style --cnt ../data_evl/content --tar ../data_evl/tar

Citation

If you find our work useful, please consider citing and star: @article{xu2025stylessp, title={StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer}, author={Xu, Ruojun and Xi, Weijie and Wang, Xiaodi and Mao, Yongbo and Cheng, Zach}, journal={arXiv preprint arXiv:2501.11319}, year={2025} }

Owner

  • Name: Bytedance Inc.
  • Login: bytedance
  • Kind: organization
  • Location: Singapore

GitHub Events

Total
  • Issues event: 7
  • Watch event: 38
  • Issue comment event: 12
  • Push event: 1
  • Public event: 1
  • Fork event: 2
Last Year
  • Issues event: 7
  • Watch event: 38
  • Issue comment event: 12
  • Push event: 1
  • Public event: 1
  • Fork event: 2

Dependencies

environment.yaml pypi
  • accelerate ==0.33.0
  • certifi ==2024.7.4
  • cffi ==1.17.0
  • charset-normalizer ==3.3.2
  • contourpy ==1.3.0
  • controlnet-aux ==0.0.9
  • cycler ==0.12.1
  • diffusers ==0.30.0
  • einops ==0.8.0
  • executing ==2.0.1
  • filelock ==3.15.4
  • fonttools ==4.54.0
  • fsspec ==2024.6.1
  • ftfy ==6.2.3
  • hf-transfer ==0.1.8
  • huggingface-hub ==0.24.5
  • idna ==3.7
  • imageio ==2.35.1
  • importlib-metadata ==8.2.0
  • importlib-resources ==6.4.5
  • jinja2 ==3.1.4
  • joblib ==1.4.2
  • jupyter-client ==7.4.9
  • kiwisolver ==1.4.7
  • lazy-loader ==0.4
  • lpips ==0.1.4
  • markupsafe ==2.1.5
  • matplotlib ==3.7.1
  • mpmath ==1.3.0
  • mypy-extensions ==1.0.0
  • networkx ==3.2.1
  • numpy ==1.26.4
  • nvidia-cublas-cu12 ==12.1.3.1
  • nvidia-cuda-cupti-cu12 ==12.1.105
  • nvidia-cuda-nvrtc-cu12 ==12.1.105
  • nvidia-cuda-runtime-cu12 ==12.1.105
  • nvidia-cudnn-cu12 ==9.1.0.70
  • nvidia-cufft-cu12 ==11.0.2.54
  • nvidia-curand-cu12 ==10.3.2.106
  • nvidia-cusolver-cu12 ==11.4.5.107
  • nvidia-cusparse-cu12 ==12.1.0.106
  • nvidia-nccl-cu12 ==2.20.5
  • nvidia-nvjitlink-cu12 ==12.6.20
  • nvidia-nvtx-cu12 ==12.1.105
  • opencv-python ==4.10.0.84
  • opencv-python-headless ==4.10.0.84
  • packaging ==24.1
  • pillow ==10.4.0
  • platformdirs ==4.2.2
  • pygments ==2.18.0
  • pyparsing ==3.1.4
  • pyrallis ==0.3.1
  • regex ==2024.7.24
  • requests ==2.32.3
  • safetensors ==0.4.4
  • scikit-image ==0.24.0
  • scikit-learn ==1.1.1
  • scipy ==1.13.1
  • six ==1.16.0
  • sympy ==1.13.2
  • threadpoolctl ==3.5.0
  • tifffile ==2024.8.28
  • timm ==0.6.7
  • tokenizers ==0.19.1
  • torch ==2.4.0
  • torchaudio ==2.4.0
  • torchvision ==0.19.0
  • transformers ==4.44.0
  • triton ==3.0.0
  • types-python-dateutil ==2.9.0.20240821
  • typing-extensions ==4.12.2
  • typing-inspect ==0.9.0
  • urllib3 ==1.26.14
  • virtualenv ==20.26.3
  • watchdog ==5.0.0
  • xformers ==0.0.27.post2
  • zipp ==3.20.0
requirements.txt pypi
  • accelerate ==0.33.0
  • certifi ==2024.7.4
  • cffi ==1.17.0
  • charset-normalizer ==3.3.2
  • contourpy ==1.3.0
  • controlnet-aux ==0.0.9
  • cycler ==0.12.1
  • diffusers ==0.30.0
  • einops ==0.8.0
  • executing ==2.0.1
  • filelock ==3.15.4
  • fonttools ==4.54.0
  • fsspec ==2024.6.1
  • ftfy ==6.2.3
  • hf-transfer ==0.1.8
  • huggingface-hub ==0.24.5
  • idna ==3.7
  • imageio ==2.35.1
  • importlib-metadata ==8.2.0
  • importlib-resources ==6.4.5
  • jinja2 ==3.1.4
  • joblib ==1.4.2
  • jupyter-client ==7.4.9
  • kiwisolver ==1.4.7
  • lazy-loader ==0.4
  • lpips ==0.1.4
  • markupsafe ==2.1.5
  • matplotlib ==3.7.1
  • mpmath ==1.3.0
  • mypy-extensions ==1.0.0
  • networkx ==3.2.1
  • numpy ==1.26.4
  • nvidia-cublas-cu12 ==12.1.3.1
  • nvidia-cuda-cupti-cu12 ==12.1.105
  • nvidia-cuda-nvrtc-cu12 ==12.1.105
  • nvidia-cuda-runtime-cu12 ==12.1.105
  • nvidia-cudnn-cu12 ==8.9.2.26
  • nvidia-cufft-cu12 ==11.0.2.54
  • nvidia-curand-cu12 ==10.3.2.106
  • nvidia-cusolver-cu12 ==11.4.5.107
  • nvidia-cusparse-cu12 ==12.1.0.106
  • nvidia-nccl-cu12 ==2.20.5
  • nvidia-nvjitlink-cu12 ==12.6.20
  • nvidia-nvtx-cu12 ==12.1.105
  • opencv-python ==4.10.0.84
  • opencv-python-headless ==4.10.0.84
  • packaging ==24.1
  • pillow ==10.4.0
  • platformdirs ==4.2.2
  • pygments ==2.18.0
  • pyparsing ==3.1.4
  • pyrallis ==0.3.1
  • regex ==2024.7.24
  • requests ==2.32.3
  • safetensors ==0.4.4
  • scikit-image ==0.24.0
  • scikit-learn ==1.1.1
  • scipy ==1.13.1
  • six ==1.16.0
  • sympy ==1.13.2
  • threadpoolctl ==3.5.0
  • tifffile ==2024.8.28
  • timm ==0.6.7
  • tokenizers ==0.19.1
  • torch ==2.3.0
  • torchaudio ==2.3.0
  • torchvision ==0.18.0
  • transformers ==4.44.0
  • triton ==2.3.0
  • types-python-dateutil ==2.9.0.20240821
  • typing-extensions ==4.12.2
  • typing-inspect ==0.9.0
  • urllib3 ==1.26.14
  • virtualenv ==20.26.3
  • watchdog ==5.0.0
  • xformers ==0.0.26.post1
  • zipp ==3.20.0