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.
Source previews
These example images come from the original source. DROPIDEA has not independently tested these examples; results depend on the model and settings.
Your prompt
Replace the red variables with your information. Copy the full prompt and use it with your preferred agent.
Variable guide
500 to 800 wordsWord-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 value600 to 900 words
1000 to 1800 tokensToken-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 value1200 to 2000 tokens
magenta, cyan, or blueAllowed 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 valueice blue, teal, or indigo
white felt objects under pink lightNegative 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 valuewhite 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
30-Second Script: The Forest Checkpoint
A fully timestamped 12-segment comedy video script following a tiny backpacker stopped at a mushroom-guarded checkp...
Comparing GPT Image 2.5 Sunburst and Flare
A request to generate the same image with Flare and Sunburst and compare results using a complex prompt, with a sam...
Seedance Video Prompt Template With Timecoded Beats
A detailed video prompt-writing template covering recurring character blocks, reference asset bindings for images,...
Organized Shot Planning Before AI Prompt Generation
A preparation methodology covering angles, camera movement, lighting, lens, and actions per part, then handing the...
