NLP Cloud serves high performance pre-trained or custom models for NER
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
Multimodal AI Story Teller, built with Stable Diffusion, GPT, etc.
Stable Diffusion built-in to Blender
InvokeAI is a leading creative engine for Stable Diffusion models
⚡ Building applications with LLMs through composability ⚡
A ChatGPT web client that supports multiple users, and databases
All-in-one image generation AI
Implementation of Video Diffusion Models
Audio generation using diffusion models
Implementation of MusicLM music generation model in Pytorch
A walk along memory lane
Generate photo-realistic textures based on source images
CLIP + FFT/DWT/RGB = text to image/video
Multilingual sentence & image embeddings with BERT
Ongoing research training transformer models at scale
Implementation of NÜWA, attention network for text to video synthesis
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis
Reverse engineered ChatGPT API
Implementation of AudioLM audio generation model in Pytorch
An open source implementation of OpenAI's ChatGPT Code interpreter
Low-code app builder for RAG and multi-agent AI applications
State-of-the-art diffusion models for image and audio generation
CPT: A Pre-Trained Unbalanced Transformer
Implementation of Make-A-Video, new SOTA text to video generator