peter65374 / sam-vit

SAM(Segment Anything) ViT-H image encoder

  • Public
  • 357.9K runs
  • T4
  • GitHub
  • Paper

Input

source_image
*file

input image file handler

Output

https://replicate.delivery/pbxt/twXbheQ2lZw1IKbrMpwcHCfnlyc36Sm7SYEI1b7bqoMIh9uRA/tmpxy0btoy2.npy
Generated in

Run time and cost

This model costs approximately $0.00054 to run on Replicate, or 1851 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 3 seconds.

Readme

SAM(Segment Anything) ViT-H image encoder