HyeonHo99/Video-Motion-Customization
VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models (CVPR 2024)
This project helps video creators, marketers, and artists transform existing video clips by applying new visual elements while preserving the original motion. You provide an input video and a text description, and it generates a new video where the described objects move exactly like those in your input. This is ideal for quickly generating diverse visual content with consistent motion.
198 stars. No commits in the last 6 months.
Use this if you need to create multiple video variations with different subjects but the same dynamic movement, or apply a specific artistic style to an existing video's motion.
Not ideal if you need to generate entirely new motions from scratch or perform detailed, frame-by-frame video editing.
Stars
198
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HyeonHo99/Video-Motion-Customization"
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