mddunlap924/StableDiffusion2-Image-to-Text

Stable Diffusion with Text-to-Image and Image-to-Text

29
/ 100
Experimental

This project helps prompt engineers and AI artists by reverse-engineering the text prompt used to create an AI-generated image. You feed it an image, and it outputs the original text prompt or its numerical representation. This is valuable for understanding how specific prompts lead to certain visual outcomes or for reproducing images without knowing the initial prompt.

No commits in the last 6 months.

Use this if you have AI-generated images and want to discover or predict the original text prompts that were used to create them.

Not ideal if you're looking to generate images from text prompts; this project focuses on the opposite process.

AI art prompt engineering image analysis creative AI generative art
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

38

Forks

6

Language

Jupyter Notebook

License

Last pushed

Jun 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mddunlap924/StableDiffusion2-Image-to-Text"

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