Same prompt, generated with each model separately — click one to see how it holds up.
Why this works
The centered, commercial product-style framing makes the banana kiosk read immediately as the hero, while “sharp focus on the kiosk and tiny figures” preserves the miniature narrative at the center. “A peeled banana forms the roof” and “giant bananas fill the background” create the scale joke, and “shallow depth of field” separates that focal area from the surrounding forms. The warm golden-amber palette, “subtle orange accents,” and “caramel-brown wooden base details” replace a sharper citrus look with a richer orange-brown harmony; “soft highlights and gentle shadows” keeps the photorealistic scene bright without flattening the textures.
FAQ
→How do I make the tiny people more prominent than the kiosk itself?
Replace “sharp focus on the kiosk and tiny figures” with “sharp focus on the tiny people at the counter, with the kiosk slightly softer,” and change “commercial product-style framing” to “close three-quarter framing at miniature eye level.” Keep “shallow depth of field,” but specify “the nearest figures in crisp focus.”
→How do I make this banana market feel more cozy and less brightly commercial?
Replace “bright” in the style and mood language with “cozy, intimate, storybook,” and change “realistic studio lighting with soft highlights and gentle shadows” to “warm low-key lighting with amber side-light and deeper soft shadows.” Shift “warmer golden-amber palette with subtle orange accents” toward “muted honey, terracotta, and dark caramel tones.”
→How do I build a series of related miniature market scenes from this prompt?
Keep “photorealistic miniature diorama,” “commercial product-style photography,” and “shallow depth of field” unchanged as the series style anchors. Swap “whimsical banana stand market kiosk” for variants such as “miniature citrus juice kiosk,” “tiny pineapple fruit stall,” or “storybook mango market,” then replace “giant bananas fill the background” with the matching oversized fruit and change the palette phrase to two or three colors associated with that fruit.
Learn the technique behind this
- Why can't AI spell, and how do I get readable text in an image? — Older diffusion models had no character-level representation of text, so they produced letterform-shaped texture instead of words.
- How should a prompt be structured, and does word order matter? — A prompt that behaves predictably names one subject first, then what it is doing, then where, then the light, then the lens or medium, then the style.
- Why does the model ignore parts of my prompt? — Ignored instructions are almost always conflicts, counts, or spatial relationships — three things current models handle badly — rather than the model failing to read you.
Related prompts
Blueberries Bursting Into Vanilla Cream
Chocolate Filled Cookie Splitting Midair With Dark Drip
Partially Peeled Banana on Blue
Banana slices in cool milk splash background
