Artistic Style Transfer

Neural Style Transfer from famous classic paintings and custom visual effects

Request parameters

Parameter’s name Parameter’s type Description
out_filters string Optional. Comma separated list of model outputs to return.
image image Input image
style string Style
curl -X POST \
    -H 'Authorization: Bearer YOUR_USER_TOKEN' \
    -H 'Content-Type: multipart/form-data' \
    -F "out_filters=output" \
    -F "image=image_value" \
    -F "style=style_value" \
curl -X POST \
    -H 'Authorization: Bearer YOUR_USER_TOKEN' \
    -H 'Content-Type: application/json' \
    -d '
        "image": "base64_encoded_image_contents",
        "style": "style_value"
import kclient
from kclient.utils import client, request

cl = client.with_bearer_token("YOUR_USER_TOKEN")
serving_api = kclient.api.serving_api.ServingApi(cl)

data = request.make(data={
    "style": "[pencil[] mosaic[] picasso[] robert[] candy[] scream[] composition[] shipwreck[] rain[] mosaic1[] escher[] udnie[] wave[] woman[] la_muse[] seated[] strip[] feathers[] starry[] stars2[] frida[]]",
}, files={
    "image": "/path/to/image_file",
resp = serving_api.serving_proxy(data, "kuberlab-demo", "mstyles-1-0-21")

Response format

  "output": "base64_encoded_image"