ZiyiZhang27/MVC-ZigAL

[CVPR 2026] Code for the paper "Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning"

22
/ 100
Experimental

This project helps 3D artists, game developers, or designers create multiple views of a 3D scene from a simple text description. You provide a text prompt (e.g., "a frog wearing a sweater") and it generates several consistent images of that object from different angles. This tool is for professionals who need high-quality, consistent multi-view images quickly for their projects.

Use this if you need to rapidly generate realistic and consistent sets of images of an object or scene from various viewpoints, based solely on a text description.

Not ideal if you need to generate single, standalone images or if you require precise control over individual camera angles and object poses rather than just a general multiview output.

3D-asset-creation game-design virtual-photography text-to-image-generation content-creation
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

Last pushed

Feb 25, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZiyiZhang27/MVC-ZigAL"

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