knightyxp/VideoGrain
[ICLR 2025] VideoGrain: This repo is the official implementation of "VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing"
This project offers a zero-shot solution for editing objects within videos, allowing for precise modifications without needing to train a model. You provide a video and specific masks highlighting the areas you want to change, and the system outputs an edited video. It's designed for video editors, content creators, or anyone needing detailed control over video content.
160 stars. No commits in the last 6 months.
Use this if you need to modify specific objects or regions in a video, from broad changes to detailed alterations, without the overhead of fine-tuning or training a new model.
Not ideal if you need to generate entirely new video content from scratch or perform major structural changes that go beyond modifying existing elements.
Stars
160
Forks
9
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/knightyxp/VideoGrain"
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