Converting a smart cell to a one-file elixir script

I am trying to change a livebook smart cell to a one-file Elixir script, mostly for educational reasons. I successfully Mix.install dependencies, load the model (“Salesforce/blip-image-captioning-base”), create a featurizer, a tokenizer, run the configure step and create a serving.

serving =
  Bumblebee.Vision.image_to_text(model_info, featurizer, tokenizer, generation_config,
    compile: [batch_size: 1],
    defn_options: [compiler: EXLA]
  )

And then I load an image like so:

image = 
  "/tmp/22911352.jpg"
  |> File.read!()
  |> Nx.from_binary(:u8)
  |> ....

I cannot figure out what the last step in the image processing pipeline should be. The original smart cell does the following:

    image =
      image.file_ref
      |> Kino.Input.file_path()
      |> File.read!()
      |> Nx.from_binary(:u8)
      |> Nx.reshape({image.height, image.width, 3})

The height and width are 3468, 4624 but when I hard-code the values and do

      ..
      |> Nx.reshape({3468, 4624, 3})

I get the following error:

  cannot reshape, current shape {4190582} is not compatible with new shape {3468, 4624, 3}

The very last step needs to be

  Nx.Serving.run(serving, image)

This is my first look at livebook - I don’t yet understand where image in the smart cell comes from.