Convert mobile videos to NeRF-ready colmap files
Dream a seamless sequence of hallucinations.
Fully distilled and accelerated MobileSAM
Separate instruments and/or vocals from any song.
A soon-to-be accelerated endpoint for multi-modal inference.
This model is not yet booted but ready for API calls. Your first API call will boot the model and may take longer, but after that subsequent responses will be fast.
This model runs on T4.