3D HAMSTER β 3D Trajectory Prediction
Predict metric 3D robot trajectories from RGB-D + language
Open-source autoregressive model with binary visual tokens.
Generate animated 3D meshes from video
Extract text and layout from images or PDF documents
Multilingual Pocket TTS voice cloning in the browser (CPU)
Super-resolution for Sentinel-2 satellite imagery
Camera-Controlled Generative Rendering from A Single Vide
Clone a Git repo into a Hugging Face Space
Convert images to 3D models and depth maps
Convert any static image into a 3D Gaussian Splat scene
Turn boring math into engaging animation videos