Home Projects Ditto
Ditto
Python

Ditto

[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

by EzioBy · GitHub
Stars
Forks
Created
Last commit
Language
diffusion-modelssynthetic-datavideo-editingPython
View on GitHub
In plain words

Create high-quality video editing data to train advanced video editing models.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Ditto — GitHub preview card
📈 Star history
617616
2026-07-202026-08-31
📈 Track Ditto

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Ditto has 616 stars on GitHub. It has been forked 51 times. Ditto is written mainly in Python. It has been in active development since 2025. Its main topics are diffusion-models, synthetic-data, video-editing.

Frequently asked questions

What is Ditto?

[CVPR'26 Highlight] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Is Ditto open source?

Ditto is an open-source project.

Is Ditto free?

Yes. Ditto is free and open source — you can use, modify and self-host it.

What language is Ditto written in?

Ditto is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — Ditto

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=ezioby-ditto)](https://olud.ai/project/ezioby-ditto.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
Awesome-Video-Diffusion
A curated list of recent diffusion models for video generation, editing, and various other appl…
5.7k · awesome
sharesvideo-editingdiffusion-models
mtt-distillation
Official code for our CVPR '22 paper "Dataset Distillation by Matching Training Trajectories"
442 · artificial-intelligence
sharessynthetic-data
RAVE
RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models [C…
314 · diffusion
sharesvideo-editing
bonito
A lightweight library for generating synthetic instruction tuning datasets for your data withou…
830 · domain-adaptation
sharessynthetic-data
DiffuEraser
DiffuEraser is a diffusion model for video inpainting, which performs great content completenes…
673 · stable-diffusion
sharesvideo-editing
Bernini
Bernini is a unified framework for video generation and editing that combines an MLLM-based sem…
1.1k · image-editing
sharesvideo-editing
Open-dLLM
Open diffusion language model for code generation — releasing pretraining, evaluation, inferenc…
649 · diffusion-models
sharesdiffusion-models
be_great
A novel approach for synthesizing tabular data using pretrained large language models
366 · data-generation
sharessynthetic-data
MagicDance
[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions R…
776 · behavior-generation
sharesvideo-editingdiffusion-models
NCFM
Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic F…
414 · computer-vision
sharessynthetic-data

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.