The process for this AI image generation uses the Midjouney AI feature of taking an image + text prompt to generate an image. An initial simple reference illustration and a simple prompt “charcoal illustration portrait of a young woman staring into the camera.” First I created a reference image by making a simple digital sketch of a woman (on a Samsung Tablet s6). Then I uploaded the image to a Discord channel for MidJourney. Combining the Image and prompt, I got back a set of four Images that followed the image prompt well. The eyes and brows matched, the nose shading is a nice touch, and I like how the hair flows, all seem to follow the reference image well.
<reference image> charcoal illustration portrait of a young woman staring into the camera.
Prompt Details: <reference image> (URL to the image) Charcoal (medium) Illustration (style of art) portrait (headshot framing) of a young (affects the age of subject) woman (affects both sex and maturity – not a child) staring into the camera (controls focus of subject relative to the camera)
The result image has black bands on either side of the image which is a result of the original simple reference illustration having a different aspect ratio from the image result. could have been avoided by making sure your uploaded image and your desired output image has the same image aspect ratio. This is where setting an Aspect ratio can help. The use of this feature adds a –ar 2:3. (two units in wide by three units in height). By taking the reference image and the text prompt and –ar 2:3, the image result simply removed the side black bands and heightened the Image composition a little.