IBM/DiffuseKronA

DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models

32
/ 100
Emerging

This project helps artists, designers, and marketers create highly specific and personalized images from text descriptions, even with limited examples. You provide a few images of a subject (like a specific car model, a person, or an art style) and text prompts, and the system generates new, consistent images of that subject in various scenarios or styles. It's for anyone needing to generate unique visual content that maintains fidelity to a particular subject or concept.

132 stars. No commits in the last 6 months.

Use this if you need to fine-tune a powerful image generation model to accurately represent a specific subject or style without requiring a massive dataset or extensive computational resources.

Not ideal if you primarily need to generate generic images without a strong focus on personalizing a diffusion model for a unique subject.

generative-art digital-marketing visual-design content-creation image-personalization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

132

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Sep 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/IBM/DiffuseKronA"

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