ali-vilab/VGen
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
This helps creative professionals, marketers, and content creators generate high-quality videos from text descriptions, single images, or specific motion instructions. You provide text, an image, or motion cues, and it outputs a new video. It's designed for anyone needing to quickly produce custom video content for digital media, advertising, or storytelling.
3,152 stars. No commits in the last 6 months.
Use this if you need to create custom video content from simple inputs like text or an image, with control over motion and subject matter.
Not ideal if you're looking for a simple drag-and-drop video editing tool or if you need to generate highly precise, real-world footage without any creative input.
Stars
3,152
Forks
274
Language
Python
License
—
Category
Last pushed
Jan 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ali-vilab/VGen"
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