fofr / latent-consistency-model

Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet

  • Public
  • 1.3M runs
  • A100 (80GB)
  • GitHub
  • License

Input

string
Shift + Return to add a new line

For multiple prompts, enter each on a new line.

Default: "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"

integer

Width of output image. Lower if out of memory

Default: 768

integer

Height of output image. Lower if out of memory

Default: 768

string

Decide how to resize images – use width/height, resize based on input image or control image

Default: "width/height"

file
Preview
image

Input image for img2img

number
(minimum: 0, maximum: 1)

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

Default: 0.8

integer
(minimum: 1, maximum: 50)

Number of images per prompt

Default: 1

integer
(minimum: 1, maximum: 50)

Number of denoising steps. Recommend 1 to 8 steps.

Default: 8

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 8

integer
(minimum: 1)

Default: 50

integer

Random seed. Leave blank to randomize the seed

file

Image for controlnet conditioning

number
(minimum: 0.1, maximum: 4)

Controlnet conditioning scale

Default: 2

number
(minimum: 0, maximum: 1)

Controlnet start

Default: 0

number
(minimum: 0, maximum: 1)

Controlnet end

Default: 1

number
(minimum: 1, maximum: 255)

Canny low threshold

Default: 100

number
(minimum: 1, maximum: 255)

Canny high threshold

Default: 200

boolean

Option to archive the output images

Default: false

boolean

This model’s safety checker can’t be disabled when running on the website. Learn more about platform safety on Replicate.

Disable safety checker for generated images. This feature is only available through the API

Default: false

Output

output
Generated in

This example was created by a different version, fofr/latent-consistency-model:fd0f0275.

Run time and cost

This model costs approximately $0.0014 to run on Replicate, or 714 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 A100 (80GB) GPU hardware. Predictions typically complete within 1 seconds.

Readme

This model doesn't have a readme.