Running 267 267 Qwen2.5 Omni 7B Demo ๐ Generate text and speech responses from text, images, or audio input
Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 โข 3 items โข Updated 28 days ago โข 90
TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting Paper โข 2503.17032 โข Published Mar 21 โข 26