Cantina, Inc.

AI & ML interests

text2image, image2image, text2video, image2video, text-to-speech, speech-to-text, large language models

Recent Activity

saurabhcantina  submitted a paper 25 days ago

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

saurabhcantina  authored a paper 26 days ago

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

EndlessSora  authored a paper over 1 year ago

InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

View all activity

Papers

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

View all Papers

Team members 27