pittisl/PhyT2V

official code repo of CVPR 2025 paper PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

26
/ 100
Experimental

This project helps video creators, animators, and content producers generate more realistic videos from text descriptions. You provide a text prompt describing the desired video, and the system uses AI to refine it, producing a video that adheres better to real-world physics and common sense. It's designed for anyone needing to create visually coherent video content from text.

No commits in the last 6 months.

Use this if you need to generate videos from text prompts and want the resulting animation to obey real-world physical laws and common sense, especially for unusual or complex scenarios.

Not ideal if you primarily need stylized, abstract, or non-physical animations, or if you prefer direct control over every aspect of video generation without AI-driven prompt refinement.

video-generation animation content-creation virtual-production visual-effects
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

64

Forks

4

Language

Python

License

Last pushed

Jul 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pittisl/PhyT2V"

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