EzioBy/Ditto
[CVPR 2026] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Ditto helps content creators, marketers, or anyone needing high-quality video edits by transforming existing videos based on text instructions. You input a video file and a prompt like "change the background to a forest," and it outputs a new, edited video. This is for professionals who want to rapidly produce polished video content without complex manual editing.
585 stars.
Use this if you need to quickly and scalably edit videos with specific, complex text instructions and want superior quality and temporal consistency.
Not ideal if you need to make simple edits that can be done with basic video editing software or if your primary focus is on static image manipulation.
Stars
585
Forks
49
Language
Python
License
—
Category
Last pushed
Oct 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/EzioBy/Ditto"
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