rossjillian/controlnet

Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise

Seed

Input image

Scale for classifier-free guidance

Steps

Prompt for the model

Choose a scheduler.

Controlnet structure to condition on

Number of images to output (higher values may OOM)

[canny only] Line detection low threshold

[canny only] Line detection high threshold

Negative prompt

Resolution of output image (will be scaled to this as its smaller dimension)

whether to return the reference image along with the output