duxiaodan/Fast_text2StyleGAN

Official repo of Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

29
/ 100
Experimental

This project helps graphic designers, content creators, or marketers quickly generate realistic human face images using simple text descriptions. You input natural language descriptions like "a person with blue eyes and a slight smile," and it outputs diverse, high-quality face images. This is for professionals who need to rapidly prototype or produce custom face imagery without manually editing existing photos or learning complex 3D modeling.

No commits in the last 6 months.

Use this if you need to generate specific, diverse, and high-quality human face images from text descriptions quickly and without extensive manual effort.

Not ideal if you need to generate images of objects other than human faces or require extreme pixel-level control over the output.

graphic-design content-creation digital-art media-production visual-marketing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

65

Forks

2

Language

Python

License

MIT

Category

gan-based-t2i

Last pushed

Dec 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/duxiaodan/Fast_text2StyleGAN"

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