Image variations using Dall-E

In this notebook we will use Dall-E 2 to vary an image. Image variations can be useful for producing multiple example images and studying if algorithms, e.g. for segmentation, are capable to process these images. For convenience reasons, we will use the Darth-D library to process the image.

from darth_d import vary

from skimage.io import imread
import stackview

As example image we use this image.

image = imread("../../data/blobs.tif")
stackview.insight(image)

shape (254, 256) dtype uint8 size 63.5 kB min 8 max 248

output_image = vary(image)

output_image

C:\Users\haase\mambaforge\envs\t310\lib\site-packages\darth_d\_vary.py:36: UserWarning: Using the vary function on scientific images could be seen as scientific misconduct. Handle this function with care.
  warn("Using the vary function on scientific images could be seen as scientific misconduct. Handle this function with care.")

darth-d made image shape (254, 256) dtype uint8 size 63.5 kB min 16 max 254

Exercise

Load the human_mitosis example from scikit-image and vary it.

from skimage.data import human_mitosis
image = human_mitosis()