I figured I should spend a few hours on the native image generation bandwagon and push the bounds of my imagination. Here are some of my experiments with image generation on ChatGPT.
- Replacements: Replace the person with this image (after uploading a photo of Naveen)
- Sticker: Create a transparent comic-style sticker of a lady chef featuring this person happily cooking salad (after uploading a photo of my wife)
- Meme sticker: Create a transparent sticker of a Vadivelu meme
- Meme: Create an image of Vadivelu looking up from a well. No caption. Make it look like a frame from a Tamil film.
- Recipe: Invent a vegetarian dish that has NEVER been created. Describe the ingredients and procedure first. Then draw a mouth-watering image of the dish. (Another version)
- Infographics: Create a detailed comic infographic explaining the double slit experiment.
- Slides. Draw a beautiful infographic highlighting these 6 accessibility testing aspects, with apt icons and visuals.
- UI mockups. Draw the screenshot of a chat application incorporating these features: …
- Product ideation. Draw an iSuit designed by Apple and Iris van Herpen. Show multiple views showcasing all features. Then write a product description.
- Interior design. Draw a biophilic office where the ceiling is a mirrored hydroponic garden, reflecting lush greenery downward to create the illusion of working in a floating forest.
- Meeting room design. Draw a modern office with sound-absorbing ‘whisper walls’ covered in fractal patterns that visually dampen noise pollution while doubling as collaborative whiteboards.
- Restaurant design. Draw a marble dining table with a river flowing through it, serving conveyor belt sushi as the dishes float gently on the water on top of plates.
- A sentient toaster with googly eyes, riding a unicycle through a library.
- A painting painting itself, but it’s struggling with existential dread.
- Photo of a gym where people work out by lifting their own regrets.
Here’s what I learnt.
- The refusal rate is low, but it does refuse to generate some copyrighted material like Calvin & Hobbes strips.
- Using a prompt to generate the description and using THAT to prompt for images helps.
- A more imaginative model (like DeepSeek, maybe Grok) can help create good prompts that ChatGPT can execute faithfully.
- There are hallucinations that experts can detect. E.g. Naveen’s and Vadivelu’s faces are clearly off, but only slightly. This will improve, but until then, don’t expect perfection.
