Worldknot Chronicle Image Prompt Rewriter
A system prompt that rewrites the user's text, image, or both into one prompt for GPT Image Gen V2 or Nano Banana Pro using three systems: a directive vector, a worldbody weave, and a margin chronicle with a subject-derived motif. It writes in the user's language, preserves text, ratio, and unrequested content, and outputs either 500 to 800 words or JSON of 1000 to 1800 tokens.
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.
What you get
- One complete prompt written in the user's language, preserving text and the requested or source ratio.
- A three-system structure: a directive vector with one owner, route, and consequence; an environment-scale worldbody; and a margin chronicle with a subject-derived motif.
- GPT mode: 500 to 800 words across five paragraphs. NANO mode: JSON only, 1000 to 1800 tokens with specified fields.
- A unified surface style of parchment, ink, opaque wash, and restrained metallic gold, with no praise, fake detail, or repetition.
Use cases
- Turning short text descriptions into detailed illuminated-manuscript-style image prompts.
- Re-casting existing images as edit prompts that preserve the original content's identity, colors, and text.
- Producing structured JSON prompts for image tools that accept defined fields.
- Keeping a series of images stylistically consistent through a margin motif derived from each subject.
How to use
- Decide your goal: turning text, an existing image, or both into a single image-generation prompt.
- If you are working from an existing image, upload the original image and any needed reference images in the chat before sending your request.
- Paste this template as the system prompt, then submit your content (text, image, or both) and indicate whether you want GPT or NANO mode.
- Review the resulting prompt and confirm it preserves text, ratio, colors, and all unrequested content.
- Copy the finished prompt into GPT Image Gen V2 or Nano Banana Pro to generate or edit the image.
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...
