adobe-research/custom-diffusion

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

51
/ 100
Established

This tool helps designers, marketers, and artists create unique images by teaching an AI model about new objects, styles, or concepts from just a few example pictures. You provide 4-20 images of something new, like a specific product or an artistic style, and then you can generate new images incorporating that concept using text prompts. It's designed for anyone who needs to quickly generate custom visual content featuring specific items or aesthetics.

1,971 stars.

Use this if you need to generate images of specific, new concepts (like your unique product or a custom art style) that aren't typically found in standard text-to-image AI models.

Not ideal if you primarily need to generate generic images or don't have a specific concept (object, style) in mind that requires custom training.

generative-art product-visualization digital-marketing content-creation graphic-design
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,971

Forks

142

Language

Python

License

Last pushed

Dec 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/adobe-research/custom-diffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.