nkolkin13 / neuralneighborstyletransfer

Transfer the texture/style of one image onto another

  • Public
  • 7.7K runs
  • T4
  • GitHub
  • Paper
  • License
Iterate in playground

Input

*file
Preview
content

Content image.

*file
Preview
style

Style image.

boolean

Whether use color correction in the output.

Default: true

boolean

Whether output high resolution image (1024 instead if 512).

Default: false

number
(minimum: 0, maximum: 1)

alpha=1.0 corresponds to maximum content preservation, alpha=0.0 is maximum stylization.

Default: 0.75

boolean

Whether use experimental content loss.

Default: false

Output

output
Generated in

This output was created using a different version of the model, nkolkin13/neuralneighborstyletransfer:63688d76.

Run time and cost

This model costs approximately $0.063 to run on Replicate, or 15 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 5 minutes. The predict time for this model varies significantly based on the inputs.

Readme

NNST

Repo for the algorithm NNST-Opt, described in the preprint “Neural Neighbor Style Transfer”, please feel free to email any questions to kolkin@adobe.com

Example Output

Example Output

Produce an output without color correction: Example Output w/o Colorization