AI Agent Skills

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

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

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

Official code of Motus: A Unified Latent Action World Model

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

A unified framework for easy reinforcement learning in Flow-Matching models

[ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models…

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks