PKU-YuanGroup/MagicTime

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

54
/ 100
Established

Leverages a diffusion-based architecture with temporal modeling to synthesize long-duration time-lapse sequences from text prompts, integrating with diffusers and Hugging Face ecosystem. Introduces the ChronoMagic dataset and benchmark for evaluating metamorphic video transformations, addressing limitations in capturing realistic temporal progression and physical state changes across extended timeframes.

1,344 stars. Actively maintained with 4 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 19 / 25

How are scores calculated?

Stars

1,344

Forks

122

Language

Python

License

Apache-2.0

Category

video-editing-diffusion

Last pushed

Mar 08, 2026

Commits (30d)

4

GitHub
Video Editing Diffusion · 135 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PKU-YuanGroup/MagicTime"

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

Related models

hao-ai-lab/FastVideo

A unified inference and post-training framework for accelerated video generation.

85

thu-ml/TurboDiffusion

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

73

PKU-YuanGroup/Helios

Helios: Real Real-Time Long Video Generation Model

62

ModelTC/LightX2V

Light Image Video Generation Inference Framework

61

Lightricks/LTX-Video

Official repository for LTX-Video

56

Explore Diffusion Models

All categories Trending Diffusion directory Insights