batouresearch / sdxl-outpainting-lora

An improved outpainting model that supports LoRA urls. This model uses PatchMatch to improve the mask quality.

  • Public
  • 67K runs
  • L40S
  • GitHub

Input

image
string
Shift + Return to add a new line

Input prompt

Default: "An astronaut riding a rainbow unicorn"

integer
(minimum: 0, maximum: 512)

How many pixels the mask should grow in the left direction

Default: 0

integer
(minimum: 0, maximum: 512)

How many pixels the mask should grow in the right direction

Default: 0

integer
(minimum: 0, maximum: 512)

How many pixels the mask should grow in the down direction

Default: 0

integer
(minimum: 0, maximum: 512)

How many pixels the mask should grow in the up direction

Default: 0

file

Input image to inpaint

number
(minimum: 0, maximum: 1)

The bigger this number is, the more ControlNet interferes

Default: 0.15

string
Shift + Return to add a new line

Replicate LoRA weights to use. Leave blank to use the default weights.

number
(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.8

string
Shift + Return to add a new line

Input Negative Prompt

Default: ""

integer
(minimum: 1, maximum: 4)

Number of images to output

Default: 1

string

scheduler

Default: "K_EULER"

number
(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

integer

Random seed. Leave blank to randomize the seed

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

Output

output
Generated in

Run time and cost

This model costs approximately $0.12 to run on Replicate, or 8 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 126 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.