A gradio web UI for running Large Language Models like LLaMA
OCRmyPDF adds an OCR text layer to scanned PDF files
World's most comprehensive, powerful, process-based PDF editor
A pure Javascript Multilingual OCR
World's most comprehensive, powerful, process-based PDF editor
Open source personal AI Assistant for Linux, Windows and Mac
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis
Implementation of Make-A-Video, new SOTA text to video generator
Multimodal AI Story Teller, built with Stable Diffusion, GPT, etc.
Label Studio is a multi-type data labeling and annotation tool
A community-supported supercharged version of paperless
Stable Diffusion built-in to Blender
Node.js module for rendering pdf pages to images, svgs and HTML files
Integrate with the latest language models, image generation and speech
A web application that allows users to interact with OpenAI's models
Venom is the most complete javascript library for Whatsapp
OpenMMLab Text Detection, Recognition and Understanding Toolbox
InvokeAI is a leading creative engine for Stable Diffusion models
Implementation of Video Diffusion Models
A walk along memory lane
State-of-the-art diffusion models for image and audio generation
Algorithms for outlier, adversarial and drift detection
Basaran, an open-source alternative to the OpenAI text completion API
Open source libraries and APIs to build custom preprocessing pipelines
Your Second Brain supercharged by Generative AI