adobe-research/custom-diffusion

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

51
/ 100
Established

Enables efficient multi-concept customization by fine-tuning only cross-attention key/value projections, reducing per-concept storage to 75MB while completing training in ~6 minutes on 2 A100 GPUs. Supports composing multiple learned concepts (objects, styles) through joint training or optimization-based weight merging. Integrated into Hugging Face Diffusers library with support for Stable Diffusion v1.4 and SDXL models.

1,971 stars.

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.