Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

The module extracts text from image using the tesseract-OCR engine. Generally, text present in the images are blur or are of uneven sizes. The image is pre-processed for better comprehension by OCR. This module first makes bounding box for text in images and then normalizes it to 300 dpi, suitable for OCR engine to read.

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

L-Verse: Bidirectional Generation Between Image and Text

Codebase for fine-tuning / evaluating nougat-based image2latex generation models

To extract details from Indian National Identification Cards such as PAN (completed) & Aadhar, Passport, Driving License (WIP) in a structured format

OCR with Google's AI technology (Cloud Vision API)

Everything is very simple: you either download a picture file or specify its link when running a python script, and output you get a text file, and you can immediately view on the command line how it will look the result of your conversion.

Telegram bot to convert image to text using python

DangoOCR: screenshot OCR recognize 文字识别，支持多种语言，识别后翻译，播放声音

Easiest way to use AI models without coding (Web UI & API support)

Inverse DALL-E for Optical Character Recognition

A little Python application to auto tag your photos with the power of machine learning.

Latent Normalizing Flows for Many-to-Many Cross Domain Mappings (ICLR 2020)

A simple image to text converter with GUI!

I2T2I: Text-to-Image Synthesis with textual data augmentation

Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models. ECCV 2024

Convert images or videos to ASCII in the terminal