lucataco / sdxl-controlnet

SDXL ControlNet - Canny

  • Public
  • 2.2M runs
  • L40S
  • GitHub
  • License

Input

image
file

Input image for img2img or inpaint mode

string
Shift + Return to add a new line

Input prompt

Default: "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"

string
Shift + Return to add a new line

Input Negative Prompt

Default: "low quality, bad quality, sketches"

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

number
(minimum: 0, maximum: 1)

controlnet conditioning scale for generalization

Default: 0.5

integer

Random seed. Set to 0 to randomize the seed

Default: 0

Output

output
Generated in

Run time and cost

This model costs approximately $0.0094 to run on Replicate, or 106 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 10 seconds.

Readme

About

Implementation of diffusers/controlnet-canny-sdxl-1.0

Changelog

10/3/23 - Now handles large input images, resizes to SDXL ratios, keeping the original aspect ratio

Support

Give me a follow if you like my work! @lucataco93