lucataco / sdxl-inpainting

SDXL Inpainting by the HF Diffusers team

  • Public
  • 2.4M runs
  • L40S
  • GitHub
  • Paper
  • License

Input

*file
Preview
image

Input image

*file
Preview
mask

Mask image - make sure it's the same size as the input image

string
Shift + Return to add a new line

Input prompt

Default: "modern bed with beige sheet and pillows"

string
Shift + Return to add a new line

Input Negative Prompt

Default: "monochrome, lowres, bad anatomy, worst quality, low quality"

string

scheduler

Default: "K_EULER"

number
(minimum: 0, maximum: 10)

Guidance scale

Default: 8

integer
(minimum: 1, maximum: 80)

Number of denoising steps

Default: 20

number
(minimum: 0.01, maximum: 1)

1.0 corresponds to full destruction of information in image

Default: 0.7

integer

Random seed. Leave blank to randomize the seed

integer
(minimum: 1, maximum: 4)

Number of images to output. Higher number of outputs may OOM.

Default: 1

Output

output
Generated in

Run time and cost

This model costs approximately $0.0025 to run on Replicate, or 400 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 3 seconds.