In addition to interacting with OpenAI’s ChatGPT, I’ve interacted with their image generator, DALL·E 2.
In my composition courses, I like to teach students how to apply the same critical thinking skills we practice on traditional texts (such as articles, short stories, novels, music lyrics, and so forth) to their interpretations of visual tests (such as ads, paintings, and performances, and so forth), as well as hybrid works (like visual novels or comics).
In a consumerist society so deeply entrenched in marketing and propaganda, hybrid and visual texts bombard us with suggestions on how to think and behave; so approaching them with a critical eye (whether it’s looking for fallacious reasoning or literary meaning) is essential to our everyday life.
That said, I thought it would be fun to do the reverse: input the meaning I want the image to evoke, and then see what DALL·E 2 generates.
The Great 21st Century Flood
Prompt: A medieval painting that explores the existential dread of climate change
There’ll Be Robots
Prompt: The heroic journey from a 21st century perspective, digital art
Prompt: Literary symbol for rebirth, watercolor painting
Make Politics Cute
Prompt: Kawaii aesthetic propaganda, comic book style
Dove Dove Dep
Prompt: Don’t give up hope, oil painting
Do the visual texts successfully communicate the prompt? What do you think?