Zhen-Dong/Magic-Me
Codes for ID-Specific Video Customized Diffusion
This project helps you create personalized videos using photos of your friends, family, or pets. You provide a few images of a person or pet, and it generates custom video clips featuring them based on your text descriptions. This is ideal for individuals, content creators, or small businesses wanting to create unique, personalized video content.
462 stars. No commits in the last 6 months.
Use this if you want to generate new videos or edit existing ones to feature a specific person or pet from just a few reference images.
Not ideal if you need a general text-to-video tool that generates diverse scenes without focusing on a specific identity.
Stars
462
Forks
37
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Zhen-Dong/Magic-Me"
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