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

cjwbw /stable-diffusion-v2:c7fb9275

Input

string
Shift + Return to add a new line

Input prompt

Default: "a photo of an astronaut riding a horse on mars"

string
Shift + Return to add a new line

The prompt NOT to guide the image generation. Ignored when not using guidance

integer

Width of output image. Currently for sd-v2 only allowing 512 and 768 currently.

Default: 768

integer

Height of output image. Currently for sd-v2 only allowing 512 and 768.

Default: 768

number

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

Default: 0.8

integer
(minimum: 1, maximum: 3)

Number of images to output. Currenly allowing 1-3, otherwise would OOM.

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

string

Choose a scheduler. Seems only DDIM and K_EULER work for sd-v2 now.

Default: "K_EULER"

integer

Random seed. Leave blank to randomize the seed

Output

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