jyoung105 / instant-style-control

Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team, with ControlNet

  • Public
  • 545 runs
  • L40S
  • GitHub
  • Paper

Input

file
Preview
style_image

Input reference image for style

file
Preview
control_image

Input reference image for original composition

string
Shift + Return to add a new line

Input prompt

string
Shift + Return to add a new line

Input negative prompt

integer
(minimum: 1, maximum: 4)

Number of output images

Default: 1

integer
(minimum: 1, maximum: 50)

Number of denoising steps

Default: 8

number
(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 1

integer

Random seed. Leave blank to randomize the seed

number
(minimum: 0, maximum: 2)

Conditioning scale for ip-adapter

Default: 0.9

number
(minimum: 0, maximum: 2)

Conditioning scale for controlnet

Default: 1.1

string

Mode to reference the image: original, style with or without layout

Default: "style-only"

string

Mode to reference the image: high flexibility but low fidelity or low flexibility but high fidelity

Default: "original"

boolean

Choose whether you extract only style part of prompt or not

Default: false

string
Shift + Return to add a new line

Input negative prompt

number
(minimum: 0, maximum: 1)

Conditioning scale for content you want to exclude

Default: 0.5

Output

output
Generated in

This output was created using a different version of the model, jyoung105/instant-style-control:bf470ed0.

Run time and cost

This model costs approximately $0.012 to run on Replicate, or 83 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 13 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.