RahulSajnani/GeoDiffuser

[WACV 2025, Best Student Paper, Oral] GeoDiffuser: Geometry-Based Image Editing with Diffusion Models

30
/ 100
Emerging

This tool helps graphic designers, marketers, and artists precisely edit objects within existing images. You provide an image and specify geometric changes like moving, rotating in 3D, or removing objects. It then generates a new, photorealistic image with the edits seamlessly integrated, including accurate lighting and shadows, even filling in areas where objects were removed.

No commits in the last 6 months.

Use this if you need to perform specific geometric transformations on objects within images, such as repositioning a product or virtually rotating an item, while maintaining photorealism.

Not ideal if you're looking for text-based image generation from scratch or general artistic style transfer without precise geometric control.

image-editing graphic-design product-visualization digital-art visual-marketing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

22

Forks

2

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RahulSajnani/GeoDiffuser"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.