contrebande-labs/charred

CHARacter-awaRE Diffusion: Multilingual Character-Aware Encoders for Font-Aware Diffusers That Can Actually Spell

27
/ 100
Experimental

Tired of AI image generators that can't spell words correctly or struggle with specific fonts? This project helps you create text-to-image models that generate accurate text within images, respecting exact spelling and diverse typographic styles. It takes your text prompts and desired font details, producing images where the text is perfectly rendered. This is ideal for graphic designers, content creators, and marketers who need high-quality visual content with precise text.

No commits in the last 6 months.

Use this if you need to generate images where the text, typography, and spelling are consistently accurate and match specific design requirements.

Not ideal if your primary goal is generating images without any specific text content or if you don't need fine-grained control over typography.

graphic-design content-creation digital-marketing typography brand-assets
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

14

Forks

3

Language

Python

License

Last pushed

May 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/contrebande-labs/charred"

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