koninik/WordStylist

Official PyTorch Implementation of "WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models" - ICDAR 2023

41
/ 100
Emerging

This tool helps researchers and developers in document image processing create new, realistic handwritten word images. You provide existing handwritten text examples and specify the desired text content, and it generates fresh images of those words in various authentic-looking handwriting styles. It's ideal for scientists and engineers working on tasks like text recognition or handwriting analysis.

No commits in the last 6 months.

Use this if you need to generate high-quality synthetic handwritten word images to expand your dataset for training document analysis or text recognition models.

Not ideal if you're looking to convert existing digital text into a specific person's handwriting style or to create long-form handwritten documents.

document-imaging handwriting-analysis text-recognition synthetic-data computer-vision-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

83

Forks

14

Language

Python

License

MIT

Last pushed

Jun 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/koninik/WordStylist"

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