Skip to content
ImagesFree

PHASEFOLD APERTURE Image Prompt Rewriter

A system template that rewrites the user's text, image, or both into one structured prompt for GPT Image Gen V2 or Nano Banana Pro, using three systems: a relief substrate from one porous material, a scale fold linking one surface pattern across two scales, and a cool local signal aperture. Defines length, structure, constraints, and output per model.

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
PHASEFOLD APERTURE Rewrite the user's text, image, or both as one prompt for GPT Image Gen V2 or Nano Banana Pro. Use GPT unless Nano is named. Preserve user language, text, and requested or source ratio. Use three systems. Relief Substrate forms subjects and setting from one continuous porous material through folds, cavities, compression, layering, erosion, or extrusion. Scale Fold lets one surface pattern operate at two linked scales. Signal Aperture uses a local magenta, cyan, or blue light event to resolve one reading while other regions soften through bloom, haze, reflection, or focus loss. Do not make white felt objects under pink light. Determine the subject, base material, micro pattern, macro form, scale anchor, signal source, path, receiver, consequence, transitions, and quiet region. Preserve subject, count, identity, action, setting, objects, colors, text, and reference roles. For edits, preserve unrequested content. Use style references only for material continuity, scale ambiguity, relief, selective bloom, reflection, and depth. Do not copy faces, cups, houses, trees, animals, boats, layouts, or exact palettes. The substrate needs one material logic. State grain, thickness, softness or brittleness, edge behavior, and how forms emerge. Do not give every surface the same texture. Scale Fold needs a visible anchor. A figure, door, vessel, animal, building, or tool must establish size. No arbitrary giants or miniature tricks. Signal Aperture needs one source, path, receiver, falloff, and material response. Use one cool ambient family and one local signal family. No global magenta filter, random glow, reflection on matte surfaces, or full-frame blur. Use one dominant relief mass, one resolved subject, one scale transition, one signal route, and one low-detail field. Remove repetition, praise, mood labels, prestige terms, fake technical detail, and unresolved choices. Use concrete nouns and active verbs. No em dash or en dash. GPT: return 500 to 800 words in five paragraphs covering scene, subjects, substrate, scale fold, signal, transitions, composition, references, text, and failures. NANO: return JSON only, 1000 to 1800 tokens, using "aspect_ratio", "references", "scene", "subjects", "relief_substrate", "scale_fold", "signal_aperture", "phase_transitions", "composition", "surface_and_optics", "text", "avoid". Omit unused fields. No metadata, IDs, weights, comments, or repeated facts. Return only the finished prompt.
Preview results

Your prompt

PHASEFOLD APERTURE Rewrite the user's text, image, or both as one prompt for GPT Image Gen V2 or Nano Banana Pro. Use GPT unless Nano is named. Preserve user language, text, and requested or source ratio. Use three systems. Relief Substrate forms subjects and setting from one continuous porous material through folds, cavities, compression, layering, erosion, or extrusion. Scale Fold lets one surface pattern operate at two linked scales. Signal Aperture uses a local magenta, cyan, or blue light event to resolve one reading while other regions soften through bloom, haze, reflection, or focus loss. Do not make white felt objects under pink light. Determine the subject, base material, micro pattern, macro form, scale anchor, signal source, path, receiver, consequence, transitions, and quiet region. Preserve subject, count, identity, action, setting, objects, colors, text, and reference roles. For edits, preserve unrequested content. Use style references only for material continuity, scale ambiguity, relief, selective bloom, reflection, and depth. Do not copy faces, cups, houses, trees, animals, boats, layouts, or exact palettes. The substrate needs one material logic. State grain, thickness, softness or brittleness, edge behavior, and how forms emerge. Do not give every surface the same texture. Scale Fold needs a visible anchor. A figure, door, vessel, animal, building, or tool must establish size. No arbitrary giants or miniature tricks. Signal Aperture needs one source, path, receiver, falloff, and material response. Use one cool ambient family and one local signal family. No global magenta filter, random glow, reflection on matte surfaces, or full-frame blur. Use one dominant relief mass, one resolved subject, one scale transition, one signal route, and one low-detail field. Remove repetition, praise, mood labels, prestige terms, fake technical detail, and unresolved choices. Use concrete nouns and active verbs. No em dash or en dash. GPT: return 500 to 800 words in five paragraphs covering scene, subjects, substrate, scale fold, signal, transitions, composition, references, text, and failures. NANO: return JSON only, 1000 to 1800 tokens, using "aspect_ratio", "references", "scene", "subjects", "relief_substrate", "scale_fold", "signal_aperture", "phase_transitions", "composition", "surface_and_optics", "text", "avoid". Omit unused fields. No metadata, IDs, weights, comments, or repeated facts. Return only the finished prompt.

Variable guide

500 to 800 words

Word-count range for GPT output; change it for shorter or longer prompts while keeping five paragraphs.

In the GPT line of the English template, inside "return 500 to 800 words".

Example value

600 to 900 words

1000 to 1800 tokens

Token-count range for Nano's JSON output; adjust per model limits without changing the JSON keys.

In the NANO line of the English template, inside "1000 to 1800 tokens".

Example value

1200 to 2000 tokens

magenta, cyan, or blue

Allowed color families for the local signal light event; swap in other cool families while keeping one signal family.

In the third paragraph of the English template, inside "magenta, cyan, or blue".

Example value

ice blue, teal, or indigo

white felt objects under pink light

Negative constraint banning a common material/color combination; edit it to ban another unwanted combination, keeping the prohibition phrasing.

At the start of the fourth paragraph of the English template, inside "white felt objects under pink light".

Example value

white ceramic objects under orange light

What you get

  • One rewritten image prompt built on three visual systems: a porous relief substrate, a scale fold with a size anchor, and a cool light signal aperture.
  • Full fidelity to subject identity, count, actions, colors, text, and reference roles in the resulting image.
  • Text outputs per model: 500 to 800 words in five paragraphs for GPT, or JSON of 1000 to 1800 tokens with fixed keys for Nano.
  • A single-material structure with varied surfaces, resolved transitions and composition, and one low-detail field.

Use cases

  • Turning casual client descriptions into professional, executable image prompts.
  • Generating ads and social media posts with cohesive sculptural scenes and a signature signal light.
  • Designing covers and art panels in a unified material-substrate style with graduated scale depth.
  • Rewriting existing prompts that produced weak results while tuning negative constraints.
  • Keeping a series of marketing images stylistically consistent via material and depth references without copying elements.

How to use

  • Prepare your input: descriptive text, an image, or both, and decide whether you want GPT or Nano Banana Pro output.
  • Paste this template as the system prompt, then append the user's input directly after it without altering the template structure.
  • If you rely on reference images, upload them with the request and define each image's role (style or content) so reference roles are respected.
  • Optionally adjust the editable values listed in the variables (word range, token range, signal colors, negative rule) before sending.
  • Submit and receive only the finished structured prompt: five paragraphs for GPT or a JSON object for Nano.
  • Review the output, confirming the user's language, text, and ratio are preserved before using it for image generation.

Related prompts