
class CreatorToyBoxDiorama: def __init__(self, CREATOR): s = infer(CREATOR) # figure, box, escapees, artifacts, present self.s = s def render(self): return collectible_render( figure=vinyl_figure(self.s.figure, at=self.s.station, pose=WORKING), # B₁ box=retail_box(title=self.s.title, art=depicts(self.s.figure)), # B₂ escapees=[ burst_from(e, origin=self. s. box. art, into=SPACE, dynamic=True) for e in self.s.escapees ], # B₃ artifacts=suspended(self.s.artifacts, ground_contact=NONE), # B₄ studio=neutral_bg(soft_light=True, title_legible=True) ) # B₅ def verify(self, img): assert figure_at_craft(img) and toy_material(img.figure), "B₁: realistic/idle" assert box_present(img) and design_equal(img. box. art.figure, img.figure), "B₂: mismatch" assert len(img.escapees) >= 2 and all(origin_on(e, img .box. art) and body_outside(e, img. box) for e in img.escapees), "B₃: static on box" assert all(no_ground_contact(a) for a in img.artifacts), "B₄: resting props" assert neutral_bg(img) and legible(img . box.title) and collectible_quality(img), "B₅" CreatorToyBoxDiorama(CREATOR).render()
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: 1199:675 · Digital Art · Product Photography · 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.