nahyeonkaty/textboost

TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder

33
/ 100
Emerging

This tool helps creative professionals, marketers, and designers generate diverse images of a specific subject using just one reference photo. You provide a single image of a subject (like a unique product or character) and text prompts describing different scenarios. It then produces a variety of images featuring that exact subject, tailored to your prompts, without overfitting to the original image.

No commits in the last 6 months.

Use this if you need to create many varied images of a consistent subject from just one example, for things like marketing campaigns, product showcases, or visual storytelling.

Not ideal if you need to generate images of entirely new, unreferenced subjects or if you have many reference images for a subject and want to fine-tune a model more extensively.

generative-art digital-marketing product-showcasing visual-content-creation design-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

57

Forks

4

Language

Python

License

MIT

Last pushed

Jan 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nahyeonkaty/textboost"

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