akisakurai / stable-karlo

Stable Diffusion Meets Karlo: a combination of the Karlo CLIP image embedding prior, and Stable Diffusion v2.1-768.

  • Public
  • 996 runs
  • T4
  • GitHub
Iterate in playground

Input

string
Shift + Return to add a new line

Input prompt

Default: "A portrait of a panda holding a vial in a laboratory is trending on ArtStation. It was rendered in Blender and has an intriguing, cinematic quality with vivid colors, neon lights, and a blue flame. It evokes the feeling of a movie trailer."

string
Shift + Return to add a new line

Specify things to not see in the output

Default: "amateur, mediocre, grainy, blur"

integer

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

Default: 768

integer

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

Default: 768

integer
(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

integer
(minimum: 1, maximum: 500)

Number of prior denoising steps

Default: 25

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

number
(minimum: 1, maximum: 20)

Scale for prior classifier-free guidance

Default: 4

integer

The amount of noise to add to the image embeddings

Default: 0

string

Choose a scheduler.

Default: "K_EULER_ANCESTRAL"

integer

Random seed. Leave blank to randomize the seed

Output

output
Generated in

This output was created using a different version of the model, akisakurai/stable-karlo:bba407e2.

Run time and cost

This model costs approximately $0.0045 to run on Replicate, or 222 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 T4 GPU hardware. Predictions typically complete within 20 seconds. The predict time for this model varies significantly based on the inputs.