deepseek-ai/Janus-Pro-7B
mit1. Introduction Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitat...
Qwen/Qwen2.5-Omni-7B
otherQwen2.5-Omni Overview Introduction Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, i...
openbmb/MiniCPM-o-2_6
A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone GitHub( | Online Demo( | Technical Blog( | Join Us( News ...
HiDream-ai/HiDream-E1-Full
mit!HiDream-E1 Demo(demo.jpg) HiDream-E1 is an image editing model built on HiDream-I1( For more features and to experience the full capabiliti...
gemma-4-E4B-it
apache-2.0Official any-to-any model by google.
gemma-4-12B-it
apache-2.0Official any-to-any model by google.
gemma-4-E2B-it
apache-2.0Official any-to-any model by google.
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4
otherOfficial any-to-any model by nvidia.
gemma-4-12B-it-qat-w4a16-ct
apache-2.0Official any-to-any model by google.
Qwen3-Omni-30B-A3B-Instruct
otherOfficial any-to-any model by Qwen.