affjljoo3581/Inverse-DALL-E-for-Optical-Character-Recognition
Inverse DALL-E for Optical Character Recognition
This project helps anyone working with Korean text in images to accurately extract the characters. It takes an image containing Korean text, regardless of its size or orientation, and outputs the recognized text. This is designed for researchers or practitioners needing to automate text extraction from various visual sources.
No commits in the last 6 months.
Use this if you need to reliably convert Korean text within images of diverse shapes and layouts into machine-readable text.
Not ideal if you are working with languages other than Korean or if your primary need is image generation from text rather than text recognition.
Stars
38
Forks
6
Language
Python
License
—
Category
Last pushed
Oct 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/affjljoo3581/Inverse-DALL-E-for-Optical-Character-Recognition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
filipstrand/mflux
MLX native implementations of state-of-the-art generative image models
potamides/DeTikZify
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.
FoundationVision/Infinity
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
zai-org/CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image...
EleutherAI/DALLE-mtf
Open-AI's DALL-E for large scale training in mesh-tensorflow.