hyeonsangjeon/AIsketcher

Text-to-image generation using Huggingface stable diffusion ControlNet conditioning and AWS Translate's prompt translation function

22
/ 100
Experimental

This tool helps creative professionals like graphic designers or marketers quickly generate new images from an existing photo and a text description. You provide an original image and a descriptive phrase (even in non-English languages), and it produces a brand-new image that maintains the key outlines of your original but reimagines the content based on your text. This is ideal for anyone needing to rapidly prototype visual ideas or create variations of an existing image.

No commits in the last 6 months. Available on PyPI.

Use this if you need to transform an existing image into a new one using a text prompt, especially if your prompt is in a language other than English.

Not ideal if you're looking for a simple text-to-image generator without needing to base it on an existing image's structure, or if you prefer not to use AWS Translate for prompt translation.

graphic-design visual-prototyping content-creation digital-art marketing-materials
No License Stale 6m
Maintenance 0 / 25
Adoption 5 / 25
Maturity 17 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

Last pushed

Aug 25, 2023

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hyeonsangjeon/AIsketcher"

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