TencentARC/GenCompositor
[ICLR 2026] GenCompositor: Generative Video Compositing with Diffusion Transformer
This project helps video creators and film producers by automating the complex process of video compositing. You provide a background video and a foreground element, and the tool generates a new video where the foreground is seamlessly integrated into the background with customizable motion and attributes. This is ideal for video editors, animators, and content creators looking to efficiently produce high-quality composite videos.
150 stars.
Use this if you need to combine live-action footage or separate video elements into a single cohesive video production, saving significant manual effort and time.
Not ideal if you require frame-by-frame precision control for extremely subtle manipulations, as the generative approach focuses on automation rather than granular manual adjustments.
Stars
150
Forks
6
Language
Python
License
—
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TencentARC/GenCompositor"
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