caiyuanhao1998/Open-OmniVCus
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions (NeurIPS 2025)
This project helps video creators, animators, and marketers customize video content by taking an existing video and a subject you want to feature. It uses various control conditions like subject segmentation, depth, and motion to generate new video content where the subject is integrated seamlessly. The ideal user is someone who needs to quickly adapt video content with specific subjects for creative or promotional purposes.
517 stars.
Use this if you need to generate new video clips that feature specific subjects while maintaining the original video's motion, depth, and other visual characteristics.
Not ideal if you need a simple video editor for basic cuts or color correction, or if you don't require advanced subject-driven video customization.
Stars
517
Forks
39
Language
Python
License
—
Category
Last pushed
Jan 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/caiyuanhao1998/Open-OmniVCus"
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