TilemahosAravanis/Only-Style
[ICCVW 2025] Official implementation of "Only-Style: Stylistic Consistency in Image Generation without Content Leakage".
This tool helps artists, designers, and marketers generate images that maintain a consistent visual style without accidentally carrying over specific details from a reference image. You provide a description of a reference subject, a target subject, and the desired style. The tool outputs a new image of your target subject, rendered in the chosen style, along with a 'leakage heatmap' to show areas where unwanted details might have been copied, and a final, cleaned-up image where such 'leakage' is removed. This is for anyone who needs to create stylistically similar images of different subjects, like concept artists or brand managers.
No commits in the last 6 months.
Use this if you need to apply a specific artistic or visual style to different subjects in your image generation, ensuring that the style is consistent without inadvertently copying content or features from your style reference.
Not ideal if you need to use a real image as your stylistic reference, work with multiple subjects in a single image, or require evaluation metrics; this version currently supports only text-based style descriptions and single subjects.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Jun 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TilemahosAravanis/Only-Style"
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
zhangmozhe/Deep-Exemplar-based-Video-Colorization
The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
naver-ai/StyleKeeper
Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual...
un1tz3r0/finetunepixelartdiffusion
Fine tune a pixelart diffusion model with isometric dataset.
lixiaowen-xw/DiffuEraser
DiffuEraser is a diffusion model for video inpainting, which performs great content completeness...