Fast and memory-efficient exact attention - Windows wheels

Awesome Search - this is all about the (e-commerce, but not only) search and its awesomeness

Fast and memory-efficient exact attention

LlamaIndex is a data framework for your LLM applications

A modular graph-based Retrieval-Augmented Generation (RAG) system

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

Official implementation of "Describing Differences in Image Sets with Natural Language" (CVPR 2024 Oral)

Code and dataset for photorealistic Codec Avatars driven from audio

MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

Language-Agnostic SEntence Representations

Official implementation of the paper "The Stable Signature Rooting Watermarks in Latent Diffusion Models"

FAIR Sequence Modeling Toolkit 2

Foundational Models for State-of-the-Art Speech and Text Translation

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

Hey is a decentralized and permissionless social media app built with Lens Protocol 🌿

[ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"

Official PyTorch implementation of DiffTF (Accepted by ICLR2024)

Lumina-T2X is a unified framework for Text to Any Modality Generation

a research paper for generative cartoon interpolation

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs