Ant Ling· 11 JunMing-Omni: A Unified Multimodal Model for Perception and Generation
Open-source model matches GPT-4o in modality support
Open-weight release
Ant Ling released Ming-lite-omni, a unified multimodal model with 2.8 billion activated parameters that processes images, text, audio, and video and supports speech and image generation.
The model is built on the Ling MoE architecture with modality-specific routers and integrates an audio decoder and Ming-Lite-Uni for generation.
The authors state it is the first open-source model to match GPT-4o in modality support, and all code and model weights are released.
