🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

A generative speech model for daily dialogue.

🔊 Text-Prompted Generative Audio Model

Instant voice cloning by MIT and MyShell. Audio foundation model.

Easily train a good VC model with voice data <= 10 mins!

SOTA Open Source TTS

SoftVC VITS Singing Voice Conversion

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

A fast, local neural text to speech system

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

https://hf.co/hexgrad/Kokoro-82M

Inference and training library for high-quality TTS models.

Stable Diffusion web UI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Focus on prompting and generating

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Official inference repo for FLUX.1 models

Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.

Platform built on top of Stable Diffusion WebUI to optimize resource management, speed up inference, and support experimental features like Flux and GGUF models.

The community repository for the Draw Things app.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Train transformer language models with reinforcement learning.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.