Home Projects custom-diffusion
custom-diffusion
Python

custom-diffusion

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

by adobe-research · GitHub
Stars
Forks
Created
Last commit
Language
computer-visioncustomizationdiffusion-modelsPython
View on GitHub
In plain words

Customize image generation models with a few example images of new concepts.

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 →
custom-diffusion — GitHub preview card
📈 Star history
1 9771 976
2026-07-202026-08-31
📈 Track custom-diffusion

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

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

custom-diffusion has 2k stars on GitHub. It has been forked 142 times. custom-diffusion is written mainly in Python. It has been in active development since 2022. Its main topics are computer-vision, customization, diffusion-models, few-shot.

Compare with the paid tools it replaces
A free alternative to DALL·E
Frequently asked questions

What is custom-diffusion?

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Is custom-diffusion open source?

custom-diffusion is an open-source project.

Is custom-diffusion free?

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

What language is custom-diffusion written in?

custom-diffusion is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — custom-diffusion

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

[![olud.ai](https://olud.ai/badge.php?tool=adobe-research-custom-diffusion)](https://olud.ai/project/adobe-research-custom-diffusion.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

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