RehgLab/RAVE
RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models [CVPR 2024]
RAVE helps video creators quickly transform existing video footage by changing elements like visual style, backgrounds, or object attributes. You provide an original video and a text description of your desired changes, and it outputs a new, edited video with consistent motion and visual quality. This tool is for video editors, content creators, or anyone needing to repurpose or stylize videos.
314 stars. No commits in the last 6 months.
Use this if you need to perform text-guided edits on videos of any length, quickly changing styles, backgrounds, or objects while preserving original motion, without needing to train a new model.
Not ideal if you require frame-by-frame precision editing or detailed manual control over specific visual elements that go beyond text prompts.
Stars
314
Forks
20
Language
Python
License
MIT
Category
Last pushed
Feb 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RehgLab/RAVE"
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