State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

DSPy: The framework for programming—not prompting—foundation models

Making the community's best AI chat models available to everyone.

Model components of the Llama Stack APIs

A web app made to let mobile users run ComfyUI workflows.

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

Soundstorm is a cutting-edge AI-powered audio manipulation application designed to provide a rich yet simplified experience for sound designers, algorithmic composers, and experimental audio enthus…

Implementation of SoundStorm built upon SpeechTokenizer.

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

We write your reusable computer vision tools. 💜

LOTUS: The semantic query engine - process data with LMs as easily as writing pandas code

A language model programming library.

Things you can do with the token embeddings of an LLM

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

👤🔍 | BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation | In PyTorch >> ONNX

Diffusers wrapper to run Kwai-Kolors model

Brand new TTS solution

A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.

Text-to-Music Generation with Rectified Flow Transformers

An open-source RAG-based tool for chatting with your documents.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Deploy your agentic worfklows to production

VideoSys: An easy and efficient system for video generation

Input a YouTube video link or upload a video file and get a video with subtitles.