In-browser unified multimodal understanding and generation.
Text-to-3D and Image-to-3D Generation
Next-generation reasoning model that runs locally in-browser
View and filter AI model releases in 2024
Generate detailed images from a prompt and an image
Gaze detection using Moondream
Real-time in-browser speech recognition
Gradio demo for FlowEdit: Inversion-Free Text-Based Editing.