Skip to content
ImagesFree

Edible Sushi Diorama Prompt for GPT Image 2.5

An image prompt that turns any subject into a tiny edible sushi diorama on a matte black ceramic plate, rendered as a 2x2 grid in 16:9 featuring 4 days that made humans proud, with premium macro food photography and dark elegant lighting.

OpenAI

Source previews

These example images come from the original source. DROPIDEA has not independently tested these examples; results depend on the model and settings.

Ready to personalize

Your prompt

English

Replace the red variables with your information. Copy the full prompt and use it with your preferred agent.

TXT MD English version
I like this one though not necessarily GPT's output. edible sushi diorama prompt for GPT Image 2.5. 2x2 grid, 16:9, do this for 4 days that made humans proud: -- INPUT: $ SUBJECT CREATE TEMP VIEW subject_analysis AS SELECT INFER_MAIN_SILHOUETTE(:SUBJECT) AS silhouette, INFER_INTERNAL_ZONES(:SUBJECT) AS zones, INFER_TINY_ACTORS(:SUBJECT) AS actors, INFER_SYMBOLIC_PROPS(:SUBJECT) AS props, INFER_MOVEMENT_PATHS(:SUBJECT) AS routes; CREATE TEMP VIEW plate_base AS SELECT BUILD_SERVING_STAGE( plate = 'matte black ceramic plate', ground = 'sushi rice terrain with sesame scatter', lighting = 'premium food photography, dark background, soft overhead highlights' ) AS plate FROM subject_analysis; CREATE TEMP VIEW edible_structure AS SELECT CONVERT_TO_SUSHI_ARCHITECTURE( silhouette, material_map = ARRAY[ 'pressed rice blocks for walls and mass', 'salmon and tuna sashimi for smooth surfaces', 'tamago for roofs, panels, platforms', 'nori strips for beams, supports, outlines, flags', 'cucumber for rails, wheels, columns, arcs', 'roe and sesame for small lights, stones, crowds, particles' ], construction = 'precise knife-cut edible miniature' ) AS sushi_subject FROM subject_analysis; CREATE TEMP VIEW cutaway_world AS SELECT BUILD_EDIBLE_ROOMS( zones, style = 'tiny isometric dollhouse spaces made of food', actors = 'small rice-and-nori figures', props = 'food-based mini props inferred from subject' ) AS rooms, ADD_ROUTE_SYSTEM( routes, material = 'thin cucumber paths, nori rails, sauce lines, sashimi roads' ) AS paths FROM subject_analysis; RENDER plate_base.plate, edible_structure.sushi_subject ON plate_base.plate, cutaway_world.rooms INSIDE edible_structure.sushi_subject, cutaway_world.paths AROUND edible_structure.sushi_subject WITH CAMERA = 'macro food photography, three-quarter view', PALETTE = 'black plate, white rice, salmon orange, tuna red, nori black, cucumber green, roe orange', DETAIL = 'tiny edible craftsmanship, clean plating, playful narrative clarity'; -- OUTPUT RULES: -- 1. $ SUBJECT becomes an edible sushi diorama. -- 2. Keep the subject readable through silhouette and major structural features. -- 3. Convert interior logic into tiny food-built rooms, decks, paths, and platforms. -- 4. Add tiny food characters performing inferred actions. -- 5. Use elegant plating and premium culinary lighting. -- 6. Avoid messy food piles, random ingredients, full-scale realism, and flat cartoon rendering
Preview results

Your prompt

I like this one though not necessarily GPT's output. edible sushi diorama prompt for GPT Image 2.5. 2x2 grid, 16:9, do this for 4 days that made humans proud: -- INPUT: $ SUBJECT CREATE TEMP VIEW subject_analysis AS SELECT INFER_MAIN_SILHOUETTE(:SUBJECT) AS silhouette, INFER_INTERNAL_ZONES(:SUBJECT) AS zones, INFER_TINY_ACTORS(:SUBJECT) AS actors, INFER_SYMBOLIC_PROPS(:SUBJECT) AS props, INFER_MOVEMENT_PATHS(:SUBJECT) AS routes; CREATE TEMP VIEW plate_base AS SELECT BUILD_SERVING_STAGE( plate = 'matte black ceramic plate', ground = 'sushi rice terrain with sesame scatter', lighting = 'premium food photography, dark background, soft overhead highlights' ) AS plate FROM subject_analysis; CREATE TEMP VIEW edible_structure AS SELECT CONVERT_TO_SUSHI_ARCHITECTURE( silhouette, material_map = ARRAY[ 'pressed rice blocks for walls and mass', 'salmon and tuna sashimi for smooth surfaces', 'tamago for roofs, panels, platforms', 'nori strips for beams, supports, outlines, flags', 'cucumber for rails, wheels, columns, arcs', 'roe and sesame for small lights, stones, crowds, particles' ], construction = 'precise knife-cut edible miniature' ) AS sushi_subject FROM subject_analysis; CREATE TEMP VIEW cutaway_world AS SELECT BUILD_EDIBLE_ROOMS( zones, style = 'tiny isometric dollhouse spaces made of food', actors = 'small rice-and-nori figures', props = 'food-based mini props inferred from subject' ) AS rooms, ADD_ROUTE_SYSTEM( routes, material = 'thin cucumber paths, nori rails, sauce lines, sashimi roads' ) AS paths FROM subject_analysis; RENDER plate_base.plate, edible_structure.sushi_subject ON plate_base.plate, cutaway_world.rooms INSIDE edible_structure.sushi_subject, cutaway_world.paths AROUND edible_structure.sushi_subject WITH CAMERA = 'macro food photography, three-quarter view', PALETTE = 'black plate, white rice, salmon orange, tuna red, nori black, cucumber green, roe orange', DETAIL = 'tiny edible craftsmanship, clean plating, playful narrative clarity'; -- OUTPUT RULES: -- 1. $ SUBJECT becomes an edible sushi diorama. -- 2. Keep the subject readable through silhouette and major structural features. -- 3. Convert interior logic into tiny food-built rooms, decks, paths, and platforms. -- 4. Add tiny food characters performing inferred actions. -- 5. Use elegant plating and premium culinary lighting. -- 6. Avoid messy food piles, random ingredients, full-scale realism, and flat cartoon rendering

Variable guide

$ SUBJECT

The day or event to be turned into an edible sushi diorama.

Replace the $ SUBJECT text after the '-- INPUT:' line; it also appears automatically in rule '1.'.

Example value

The day humans first walked on the Moon

matte black ceramic plate

The type of plate the diorama is built on.

In plate_base at plate = 'matte black ceramic plate'; replace only the quoted text.

Example value

dark gray stone plate

premium food photography, dark background, soft overhead highlights

The overall lighting and photography style.

In plate_base at lighting = 'premium food photography, dark background, soft overhead highlights'.

Example value

dramatic side lighting with glossy reflections

black plate, white rice, salmon orange, tuna red, nori black, cucumber green, roe orange

The overall color palette of the image.

In the RENDER clause at PALETTE = 'black plate, white rice, salmon orange, tuna red, nori black, cucumber green, roe orange'.

Example value

white plate, white rice, salmon pink, avocado green

What you get

  • A 2x2 grid of four panels, each a tiny edible sushi diorama of a day that made humans proud.
  • Readable architecture: pressed-rice walls, sashimi surfaces, tamago roofs and platforms, nori beams and outlines.
  • Tiny isometric dollhouse-style interior rooms with rice-and-nori characters performing inferred actions.
  • Route systems of thin cucumber paths, nori rails, sauce lines, and sashimi roads inside and around the structure.
  • A premium macro food-photography look: matte black plate, dark background, soft overhead highlights, clean plating.

Use cases

  • Celebratory social media posts about famous historic days and milestones.
  • Creative marketing content for Japanese restaurants and sushi brands.
  • Eye-catching posters and menu designs with a playful artistic twist.
  • Digital artworks blending miniature architecture with culinary art.

How to use

  • Replace $ SUBJECT with the historic day you want to celebrate, such as the day humans first walked on the Moon.
  • Optionally edit the creative values: plate type, lighting, and color palette, while keeping the SQL structure and technical settings intact.
  • Paste the full template into GPT Image 2.5 and submit it; no reference images are needed since the prompt relies on text description alone.
  • Request a 2x2 grid in 16:9 so a different day appears in each of the four panels.
  • Repeat with other days or modify the subject to generate multiple variations in the same artistic style.

Related prompts