581
Scaling test-time compute
📈
Implement test-time compute scaling for math problems
Multimodal Image-to-Video
Remove background from images
Generate 3D models and videos from images
Generate a 3D mesh model from an image
Generate images by blending foreground with custom backgrounds
Erase any object from an image with just a prompt
Generate spatial audio from images (and optionally text)
text-to-3D & image-to-3D
Media understanding
Transfers textures from a reference image to a masked region in a source image
Transcribe voice to text
Generate a cartoon video from two images