grey-hound432/fast-bg-removal

Fast background removal for images. Designed for product photos, ecommerce, and bulk workflows.

Public
1 run
License
GitHub
Playground API Examples README Versions

Examples

View more

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Fast Background Removal

This model removes backgrounds from images quickly and reliably using the open-source rembg library.

Use cases

  • Product photos for ecommerce
  • Thumbnails and marketing images
  • Bulk image processing
  • Content pipelines

Features

  • Fast execution
  • Simple interface
  • Transparent PNG output
  • Commercial-safe (MIT licensed)

How it works

The model uses a pre-trained segmentation network to separate foreground objects from the background and outputs a clean RGBA image.

Input

  • image: An image file (PNG, JPG, etc.)

Output

  • A PNG image with the background removed

License

This model is built using the open-source rembg project, which is licensed under the MIT License and allows commercial use.

Notes

  • Best results on clear subjects with good contrast
  • No training or data collection is performed
  • Fast background removal: grey-hound432/fast-bg-removal
  • MIT image upscaler: grey-hound432/fast-image-upscaler-mit
  • Image format converter: grey-hound432/image-format-converter-mit

Here is an example:

import replicate

output = replicate.run( “grey-hound432/fast-bg-removal”, input={“image”: open(“image.png”, “rb”)} )

Model created