anotherjesse / controlnet-1.5-canny-template

Template Version for use with Dreambooth API

  • Public
  • 22 runs
  • T4
  • GitHub

Input

file

Optional Image to use for guidance based on canny

file

Optional Image to use for img2img guidance

file

Optional Mask to use for legacy inpainting

string
Shift + Return to add a new line

Input prompt

Default: "photo of cjw person"

string
Shift + Return to add a new line

Specify things to not see in the output

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

integer
(minimum: 1, maximum: 10)

Number of images to output.

Default: 1

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

integer

Low threshold for canny filter

Default: 100

integer

High threshold for canny filter

Default: 200

string

Choose a scheduler.

Default: "DPMSolverMultistep"

boolean

Disable safety check. Use at your own risk!

Default: false

boolean

if using control_image, return processed control as first image

Default: false

integer

Random seed. Leave blank to randomize the seed

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

Model description

Intended use

Ethical considerations

Caveats and recommendations