Stars
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
A framework for building realtime voice AI agents 🤖🎙️📹
A TTS model capable of generating ultra-realistic dialogue in one pass.
Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
MARS5 speech model (TTS) from CAMB.AI
Open-Sora: Democratizing Efficient Video Production for All
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
TensorRT Extension for Stable Diffusion Web UI
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
OSS AI Companion Chatbot - Build your own AI companion in Python using ChatGPT.
An extensive prompt to make a friendly persona from a chatbot-like model like ChatGPT
Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
⚡️ Python client for the ChatGPT API with, conversation tracking, proxy support and more.
Your API ⇒ Paid MCP. Instantly.
App that leverages GPT-3 to facilitate new language listening and speaking practice.
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.