naver-ai/StyleKeeper

Official Pytorch implementation of "StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance"

46
/ 100
Emerging

This tool helps graphic designers, digital artists, and marketers transform ordinary images into visually striking ones by applying a consistent artistic style from a reference image or text prompt. You provide a source image or text description and a visual style reference, and it generates new images that maintain the original content while faithfully adopting the desired style, preventing unintended blending. This is ideal for creatives looking to quickly produce stylized visual content.

477 stars.

Use this if you need to generate a diverse range of images that consistently adhere to a specific visual style or artistic theme without labor-intensive manual editing or costly fine-tuning of existing generative models.

Not ideal if your primary goal is to generate completely novel images from scratch without a strong emphasis on transferring a predefined style from a reference, or if you require precise control over content elements that go beyond basic image structure.

digital-art graphic-design content-creation visual-marketing image-stylization
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

477

Forks

33

Language

Python

License

Apache-2.0

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.