ChenyangQiQi/FateZero
[ICCV 2023 Oral] "FateZero: Fusing Attentions for Zero-shot Text-based Video Editing"
This project helps video editors, marketers, and content creators quickly change elements or styles within existing videos using simple text descriptions. You provide a video and a text prompt (e.g., "silver jeep ➜ Porsche car" or "+ Van Gogh style"), and the system outputs a new, edited video that maintains consistent motion and structure. It's designed for anyone who needs to modify video content without complex manual editing or extensive training.
1,160 stars. No commits in the last 6 months.
Use this if you need to rapidly alter objects, attributes, or the artistic style of a video with text commands, without requiring per-frame editing or masks.
Not ideal if you need precise frame-by-frame control, intricate masking for highly specific edits, or are working with extremely low-resolution or poor-quality source videos.
Stars
1,160
Forks
110
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ChenyangQiQi/FateZero"
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