Reconstruct 3D Gaussians from unposes images.
Scalable and Versatile 3D Generation from images
Text Behind Image using birefnet-lite for background removal
3D/4D Scenes from a Single Image w/ Controllable Video Diff
Realtime implementation of Whisper large turbo
Import a portrait, click to move the head!
4k Image from text in 5 second
Generates a sound effect that matches video shot