farhad-dalirani/Multi-Mode-DreamBooth

This repository provides a minimal yet flexible implementation of DreamBooth for subject-driven text-to-image generation. It supports multiple fine-tuning modes (UNet-only, UNet + full text encoder, and UNet + Textual Inversion), making it easy to experiment with different personalization strategies across rigid objects, animals, and human faces.

15
/ 100
Experimental
No Package No Dependents
Maintenance 6 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

MIT

Last pushed

Dec 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/farhad-dalirani/Multi-Mode-DreamBooth"

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