koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten Text Generation" - ECCV 2024
This project helps generate new handwritten text in a specific style, even if you only have a few examples of that handwriting. You provide a small set of images showing a particular handwriting, and it creates new text that matches that unique style. This is useful for researchers in handwriting recognition, digital archiving, or anyone needing to generate custom handwritten text for various applications.
No commits in the last 6 months.
Use this if you need to create realistic, stylized handwritten text from scratch, especially for research in handwriting recognition or digital document creation, with minimal examples of the target style.
Not ideal if you need to convert printed text to handwritten form without needing to replicate a specific existing handwriting style.
Stars
94
Forks
21
Language
Python
License
MIT
Category
Last pushed
Oct 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/koninik/DiffusionPen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation
bytedance/LatentUnfold
Implementation of paper: Flux Already Knows – Activating Subject-Driven Image Generation without Training