yrcong/flatten
Pytorch Implementation of FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing (ICLR 2024)
This project helps video editors and content creators modify existing videos using text descriptions, ensuring the edited output remains visually coherent and stable across all frames. You provide a source video and a text prompt describing the desired changes, and it generates a new, edited video where the modifications are seamlessly applied without flickering or inconsistencies. This is ideal for anyone looking to quickly adapt video content based on textual ideas.
213 stars. No commits in the last 6 months.
Use this if you need to edit the visual appearance of a video based on text prompts and require strong visual consistency in the output.
Not ideal if you need to generate entirely new videos from scratch or perform complex, frame-by-frame manual video effects.
Stars
213
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
May 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yrcong/flatten"
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