tobran/DF-GAN

[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis

51
/ 100
Established

DF-GAN helps you generate realistic images from simple text descriptions. You provide a short phrase or sentence, and the system creates a corresponding image. This is useful for content creators, designers, or anyone needing visual assets quickly without manual design.

322 stars. No commits in the last 6 months.

Use this if you need to rapidly create diverse images based on textual prompts, for example, generating visuals for marketing campaigns or concept art.

Not ideal if you require extremely high-resolution, photorealistic images with intricate details and precise control over every visual element, or if you prefer a system with significantly faster inference that can run on a CPU (consider GALIP instead).

image-generation content-creation visual-design digital-art marketing-asset-generation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

322

Forks

68

Language

Python

License

Category

gan-based-t2i

Last pushed

Sep 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tobran/DF-GAN"

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