AI Agent Skills

HunyuanVideo: A Systematic Framework For Large Video Generation Model

⚡ TabPFN: Foundation Model for Tabular Data ⚡

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

A library for generative social simulation

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Wan: Open and Advanced Large-Scale Video Generative Models

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Port of OpenAI's Whisper model in C/C++

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

A TTS model capable of generating ultra-realistic dialogue in one pass.

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

OCR model that handles complex tables, forms, handwriting with full layout.

Sui, a next-generation smart contract platform with high throughput, low latency, and an asset-oriented programming model powered by the Move programming language

Fara-7B: An Efficient Agentic Model for Computer Use

A framework to enable a multimodal model to operate a computer.

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and…