stevenlsw/physgen
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)
This project helps graphic designers, animators, and visual effects artists create realistic video animations of objects moving under physical forces. You provide a single image of objects, define their physical properties, and the tool generates a video where those objects interact naturally. It's designed for anyone needing to visualize or animate rigid-body physics in a compelling, visually rich way without complex 3D modeling.
340 stars. No commits in the last 6 months.
Use this if you need to quickly generate dynamic videos from static images, showing objects interacting realistically as if moved by forces like gravity or impacts.
Not ideal if you need to animate highly deformable objects, fluids, or characters, as it focuses specifically on rigid-body physics.
Stars
340
Forks
13
Language
Python
License
—
Category
Last pushed
Oct 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/stevenlsw/physgen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators