A toy bubble diorama prompt for Nano Banana 2.1 and GPT 2.5. Produces kind of similar visuals.
2x2 grid, 16:9, do this for : 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": "" } 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))2x2 grid, square 1:1. Four compact 3D toy dioramas, one each for CREATIVITY, HOPE, SCIENCE and FORTITUDE. In each panel the short title is built from chunky rounded 3D bubble letters in soft toy plastic, clay and rubbery foam, matte with gentle gloss highlights, large and centered; around the letters, three iconic props and tiny cute mini characters act out the core moment of the topic on a small environment base (paint tubes and brushes; a sprouting seedling and a lantern; a microscope and bubbling flasks; a small climber on a rocky ledge). Playful palette per panel, dark studio backdrop, soft studio lighting, tactile toy diorama render.
cinel 为生成示例图做了以上替换。
