You're looking at a specific version of this model. Jump to the model overview.

afiaka87 /sd-aesthetic-guidance:1af76e80

Input

string
Shift + Return to add a new line

Input prompt

Default: ""

integer
(minimum: 1, maximum: 9)

An aesthetic 'rating' from 1 - 9 (1 is the lowest, 9 is the highest). 9 is mostly art and will tend to do a painting style more often. 6 - 8 tend to work well.

Default: 8

number
(minimum: 0, maximum: 1)

How much of the aesthetic CLIP embed should be subtracted from the unconditional latent. 0.0 will disable aesthetic guidance. Going above 0.2 tends to produce artifacts and highly abstract/simplified visuals.

Default: 0.1

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

file

Inital image to generate variations of. Will be resized to the specified width and height

file

Black and white image to use as mask for inpainting over init_image. Black pixels are inpainted and white pixels are preserved. Experimental feature, tends to work better with prompt strength of 0.5-0.7

number

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

Default: 0.8

integer

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

integer

Random seed. Leave blank to randomize the seed

Output

output
Generated in