
2x2 grid, 16:9, do this for creativity, hope, science, fortitude: class ToyBubbleDiorama: def __init__(self, topic): self.topic = topic self.title = derive_short_title(topic) self.moment = infer_core_moment(topic) self.props = infer_iconic_props(topic, count=3) self.characters = infer_mini_characters(topic) self.base = infer_environment_base(topic) self.palette = infer_playful_palette(topic) def letters(self): return { "form": "chunky rounded 3D bubble letters", "material": "soft toy plastic / clay / rubbery foam", "finish": "matte with gentle gloss highlights", "layout": "large centered title" } def scene(self): return { "props": self.props, "characters": self.characters, "base": self.base, "background": "dark studio backdrop" } def render(self): return """ Render one compact 3D diorama where colorful bubble letters tell the title and the surrounding props explain the topic. """ generate_image(ToyBubbleDiorama(TOPIC))
This image was generated with Nano Banana 2.1 by Google. The prompt on this page is the exact text used to create it.
The example was generated with Nano Banana 2.1 using: 1672:941 · Cartoon · Whimsical · 3D Render. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.