wfanyue/DPG-T2I-Personalization

[ECCV 2024] Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning

21
/ 100
Experimental

This project helps graphic designers, marketers, and content creators generate highly specific and personalized images from text descriptions. You provide a few images of a unique item or style, along with a text prompt, and it outputs new images featuring that specific item or style in various scenarios. It's ideal for anyone who needs to quickly create diverse visual content centered around a consistent, personalized subject.

No commits in the last 6 months.

Use this if you need to generate many unique images of a specific object, person, or style that you've 'taught' the system, using only text prompts.

Not ideal if you just need generic image generation and don't require the creation of highly personalized subjects or styles.

graphic-design content-creation marketing-materials digital-art branding
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

51

Forks

1

Language

Python

License

Last pushed

Jun 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/wfanyue/DPG-T2I-Personalization"

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