A custom framework for easy use of LLMs, VLMs, etc. supporting various modes and settings via web-ui

Printext is a lightweight, application that extracts text from images.

This project showcases a comprehensive solution for converting images to text using OCR (Optical Character Recognition) and fine-tuning the extracted content. Leveraging powerful tools like AWS, Docker, OpenAI, and CI/CD pipelines, this system ensures high accuracy and efficiency.

This is a program that programmatically reads text in Minecraft. It can be used to "scrape" sign text, chat messages, tooltips and more.

🌻 Blip Server - img2txt Infrastructure - Generate short descriptions from images |从图像推理描述文本

Using AI to write caption for an image (with HuggingFace, Transformer.js or Azure Cognitive Vision API)

Turn image to audio story(Upload image and let AI tells a story about it ).

SmartMeat is a smart BBQ controllable from your phone

Simple image captioning model图生文

This is a repo providing same stable diffusion experiments, regarding textual inversion task and captioning task

caption generator using lavis and argostranslate

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

My solution to the Image Captioning Final Project of the Coursera "Introduction to Deep Learning" course with trained model deployed as telegram bot.

A tool to print images to terminal

Welcome to 📜 Optical_character_recognition using Python 👋

For transforming normal videos to ASCII style

Projects Collections