fater-ai / pixel-hacker

  • Public
  • 1 run
Iterate in playground

Run fater-ai/pixel-hacker with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
image
string
Input image for inpainting.
mask
string
Mask image (white pixels indicate regions to inpaint, black pixels are known).
model_version
string (enum)
ft_places2

Options:

ft_places2, ft_celebahq, ft_ffhq, pretrained

PixelHacker model version to use.
image_size
integer
512
Resize short edge of the image to this size for processing. Output matches original size.
mask_dilate_kernel_size
integer
0
Kernel size for mask dilation. 0 means no dilation.
mask_preprocess_type
string (enum)
dilate

Options:

dilate, morphologyEx

Mask preprocessing type.
num_steps
integer
20

Min: 1

Max: 200

Number of denoising steps.
guidance_scale
number
4.5

Min: 1

Max: 20

Classifier-Free Guidance scale. Higher values adhere more to guidance.
strength
number
0.999

Max: 1

Controls how much noise is added to the initial image, affecting how much the image is altered. 1.0 means full noise. (Used to determine inference timesteps).
paste_composite
boolean
True
If true, composites the inpainted region back into the original image context using the mask. Otherwise, returns the full inpainted image.
compensate_color
boolean
True
If true (and paste_composite is true), applies color compensation during compositing.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "title": "Output"
}