QuanjianSong/UniVST
[TPAMI 2025] Official Pytorch Code of the Paper "UniVST: A Unified Framework for Training-free Localized Video Style Transfer"
This project helps video creators, marketers, or artists apply specific visual styles from an image onto a video, selectively or across the entire footage. You provide an original video and a style image, and it outputs a new video with the desired artistic style. This tool is for anyone looking to transform the aesthetic of their video content without extensive manual editing.
Use this if you want to apply a unique visual style from a static image to a moving video, especially if you need to stylize only specific objects or regions within the video.
Not ideal if you're looking for simple color grading, basic video filters, or if you don't have programming knowledge, as it requires running Python scripts.
Stars
83
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/QuanjianSong/UniVST"
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