A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

Official PyTorch implementation of "Paralinguistics-Aware Speech-Empowered LLMs for Natural Conversation" (NeurIPS 2024)

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

A minimal and universal controller for FLUX.1.

Implementation for the paper "ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems".

Let your Claude able to think

Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.

A Survey of Spoken Dialogue Models (60 pages)

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

Make websites accessible for AI agents

The web version of the NextTalk project

Interface for OuteTTS models.

InstantIR: Blind Image Restoration with Instant Generative Reference 🔥

Official repository of In-Context LoRA for Diffusion Transformers

Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Text-To-Speech for NotebookLM

Inference script for Oasis 500M

O1 Replication Journey: A Strategic Progress Report – Part I

[NeurIPS 2024🔥] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

A general fine-tuning kit geared toward diffusion models.

一个超轻量级、可以在移动端实时运行的数字人模型

A Hub for the State-of-the-art Language and Multimodal Agents

A 6-million Audio-Caption Paired Dataset Built with a LLMs and ALMs-based Automatic Pipeline

Converts text to speech in realtime

This toolbox aims to unify audio generation model evaluation for easier comparison.