AI Agent Skills

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Image-to-image translation with conditional adversarial nets

A unified inference and post-training framework for accelerated video generation.

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference appl…

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inf…

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.