Implementation of Video Diffusion Models
Implementation of Make-A-Video, new SOTA text to video generator
@videojs component for @vuejs
InvokeAI is a leading creative engine for Stable Diffusion models
A safe home for all your data
Multimodal AI Story Teller, built with Stable Diffusion, GPT, etc.
Transcribe any audio to text, translate and edit subtitles 100% locall
Client-side JS platform for artists, designers and students to express
Label Studio is a multi-type data labeling and annotation tool
An interactive process viewer
The most powerful screen recorder & annotation tool for Chrome
Private messenger for Windows, Mac, and Linux
Implementation of Phenaki Video, which uses Mask GIT
Desktop client for Matrix using Qt and C++20
Run code interactively, inspect data, and plot
A real-time collaborative document editor for the web
WhatsApp tool for chatbots with advanced features
A walk along memory lane
Implementation of NÜWA, attention network for text to video synthesis
blingful character graphics/TUI library. definitely not curses
CLIP + FFT/DWT/RGB = text to image/video
Powerful open source team chat application
Small program rich text component, supports rendering and editing html
Multiparty web-meetings using mediasoup and WebRTC
The data structure for multimodal data