omerbt/TokenFlow
Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)
This tool helps video editors and content creators modify existing videos while maintaining visual consistency across frames. You provide an original video and a text prompt describing the desired changes, and it outputs a new video with those edits applied. It's ideal for anyone looking to transform video content without retraining complex AI models.
1,707 stars. No commits in the last 6 months.
Use this if you need to perform text-guided edits on an existing video, like changing textures or adding effects, while preserving the original motion and layout.
Not ideal if you need to generate entirely new video content from scratch or perform major structural changes that alter the video's underlying motion.
Stars
1,707
Forks
143
Language
Python
License
MIT
Category
Last pushed
Feb 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/omerbt/TokenFlow"
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