wolverinn / simple-background

Replace background with stable diffusion

  • Public
  • 4.4K runs
  • L40S
  • GitHub
Iterate in playground

Input

image
*file

Image to replace background

string
Shift + Return to add a new line

prompt en

Default: "RAW photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"

string
Shift + Return to add a new line

negative prompt

Default: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"

integer

seed

Default: -1

Output

output
Generated in

Run time and cost

This model costs approximately $0.11 to run on Replicate, or 9 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 L40S GPU hardware. Predictions typically complete within 118 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Replace background with stable diffusion realisticVisionV51 checkpoint. Keeps the original image size.

First removes background, then generate new background with Stable Diffusion and ControlNet, and finally replaces background.

If you have any problems or feature requests, contact me through GitHub.