naver-ai/StyleKeeper
Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance"
Enables training-free style transfer in text-to-image diffusion models by swapping key-value pairs in late self-attention layers while preserving original queries, preventing content leakage from reference images. Supports ControlNet integration for spatial control and real image style extraction with color calibration. Built on diffusers and transformers, with PyTorch 1.13.1+ and includes HuggingFace Spaces demos for interactive style-guided generation.
477 stars.
Stars
477
Forks
33
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/naver-ai/StyleKeeper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jolibrain/joliGEN
Generative AI Image and Video Toolset with GANs and Diffusion for Real-World Applications
ali-vilab/AnyDoor
Official implementations for paper: Anydoor: zero-shot object-level image customization
zhangmozhe/Deep-Exemplar-based-Video-Colorization
The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
un1tz3r0/finetunepixelartdiffusion
Fine tune a pixelart diffusion model with isometric dataset.
ironjr/semantic-draw
Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content...