anotherjesse / sdxl-recur

explore img2img zooming sdxl

  • Public
  • 1.1K runs
  • L40S
  • GitHub

Input

image
string
Shift + Return to add a new line

Input prompt

Default: "An astronaut riding a rainbow unicorn"

string
Shift + Return to add a new line

Input Negative Prompt

Default: ""

file

instead of starting with txt2img generating the first frame, you can send your own (optional)

integer

Width of output image (ignored if image is provided)

Default: 1024

integer

Height of output image (ignored if image is provided)

Default: 1024

integer
(minimum: 1, maximum: 500)

Number of denoising steps per image

Default: 10

integer
(minimum: 1, maximum: 500)

Number of frames

Default: 20

number
(minimum: 1, maximum: 4)

Zoom factor

Default: 1.05

number
(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

number
(minimum: 0, maximum: 1)

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

Default: 0.8

string

scheduler

Default: "K_EULER"

integer

Random seed. Leave blank to randomize the seed

Output

output
Generated in

This example was created by a different version, anotherjesse/sdxl-recur:9cee5f97.

Run time and cost

This model costs approximately $0.046 to run on Replicate, or 21 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 L40S GPU hardware. Predictions typically complete within 48 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.