tejank10/null-text-inversion

Unofficial Implementation of Null-text Inversion (https://arxiv.org/abs/2211.09794)

21
/ 100
Experimental

This tool helps creative professionals and digital artists precisely edit existing images using text descriptions. You provide an image and a text prompt describing it, and the system learns how to represent that image. You can then modify the text prompt to generate a new, edited version of the original image, like changing a regular cake into a chocolate cake.

No commits in the last 6 months.

Use this if you want to subtly or significantly alter an image's content by simply describing the desired changes in text.

Not ideal if you need to generate images from scratch without an initial image input, or if you require pixel-level manual editing control.

digital-art image-editing creative-design text-to-image-editing visual-content-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tejank10/null-text-inversion"

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