NeuralTextualInversion/NeTI

Official Implementation for "A Neural Space-Time Representation for Text-to-Image Personalization" (SIGGRAPH Asia 2023)

38
/ 100
Emerging

This project helps graphic designers and digital artists create personalized images from text descriptions. You provide a few example images of a unique object, style, or concept, and the tool learns how to represent it. Then, you can generate new images where your personalized concept appears in various scenes and styles, controlled by text prompts. This is ideal for creatives who want to incorporate specific, custom elements into their text-to-image workflows.

181 stars. No commits in the last 6 months.

Use this if you need to generate images of a specific, unique object or style—like your pet, a custom logo, or a distinctive artistic brushstroke—using only text descriptions.

Not ideal if you're looking for a general-purpose text-to-image generator and don't require the ability to personalize specific visual concepts.

digital-art graphic-design image-generation creative-content visual-branding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

181

Forks

15

Language

Python

License

MIT

Last pushed

Sep 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NeuralTextualInversion/NeTI"

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