lixirui142/VidToMe
Official Pytorch Implementation for "VidToMe: Video Token Merging for Zero-Shot Video Editing" (CVPR 2024)
This tool helps video creators and editors transform existing video footage into new styles or scenes while maintaining smooth, consistent motion. You provide an original video, and the tool outputs an edited version with changes like style transfer or object modification, ensuring that movements look natural and not jumpy. It's designed for anyone who needs to quickly re-imagine or alter video content without complex manual frame-by-frame adjustments.
230 stars. No commits in the last 6 months.
Use this if you need to edit or stylize a video and want to ensure that the edited footage maintains realistic, consistent motion across all frames.
Not ideal if you're looking for a tool to generate entirely new video content from scratch, as it focuses on transforming existing videos.
Stars
230
Forks
13
Language
Python
License
MIT
Category
Last pushed
Jan 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lixirui142/VidToMe"
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