Generate 3D CAD models from images
Real-time video captioning powered by FastVLM
Demo space for Mistral latest speech models
Add objects to images using text prompts
Official Space for SpatialTrackerV2
LightGlue demo
Dimple: Discrete Diffusion Multimodal Large Language Model
Interact with an AI agent to perform web tasks
A Step Towards Music Generation Foundation Model
Create 3D models from videos or images
Fill in image areas using prompts and masks
High-fidelity 3D Geometry Generation from single view image
Generate any application with DeepSeek
Large Animatable Human Model
VGGT (CVPR 2025)