Quickstart guide & FAQ
Seven steps from blank page to model-ready prompt. Takes about two minutes once you've done it once.
The dropdown at the top of panel 1 sets the wording style of your prompt — ChatGPT, Meta AI, Nano Banana, Gemini, Midjourney (experimental), or Generic. It never changes your creative choices, only how the prompt talks to the model.
Choose an aspect ratio (1:1, 16:9, 9:16), tap an artistic style pill (Museum Catalog, Cinematic, Photorealistic, …), and leave High Resolution on unless you want a lighter touch.
Flip on Use reference images if you'll attach images in your image AI — the tool never sees or uploads them; it just adds wording telling the AI to use your attachments. Your reference photo also decides the headcount: the prompt tells the AI to match its number of people exactly. Add Strict Feature Lock to ask the AI to preserve recognizable materials and construction details.
New here? Hit ✦ Surprise Me first for a fresh combinatorial pick — see what the tool can do, then tweak any choice. Or pick one of 14 gallery wings (Hall of Vanished Empires, Sunken Kingdoms Gallery, the Invention Annex, …) and the purpose, artifact, civilization, discovery, presentation, atmosphere, palette, and signature detail refine themselves around it. Your custom text, target AI, and toggles are never overwritten.
An untouched ingredient adds nothing to the prompt. If you want the image AI to decide something, check Random — let the AI decide explicitly. Blank and Random are different choices.
Type the placard inscription exactly as it should appear — spelling, caps, everything. The prompt will demand that exact text and forbid the AI from inventing other headlines.
Copy Prompt grabs the model-ready text; Copy Title + Prompt adds the exhibit name on top. Paste into your image AI (and attach any reference images there). The title is yours for browsing and sharing — it's never printed on the image.
A fictional museum. Every exhibit invents five things: the artifact, the civilization that made it, its original purpose, how it was discovered, and how it is presented. The engine weaves them into one coherent story — the magic is in the relationships between the elements, not just random combinations.
Pick an artifact type and the engine names it ("The Rain Compass"); pick a civilization and the engine writes the artifact into that culture's logic; pick a purpose and it becomes the reason the object exists. Discovery tells where it was found, presentation tells how the museum shows it. Leave any of them blank to skip it, or choose Random — let the AI decide to let the image AI invent that element.
The prompt always carries your ratio choice — 16:9 is the default, and switching to Square or Portrait updates the wording. But the ratio is a request in the prompt text, not a command: your image AI's own size setting has the final word, and some models ignore prompt-text ratios entirely. For a guaranteed ratio, also set the size/aspect control inside your image AI to match.
No. It's a prompt generator — it writes copyable plain text you paste into your own image AI (ChatGPT, Midjourney, Gemini, whatever you use). No images are uploaded, processed, or generated here.
No. The reference toggle only inserts wording instructing the receiving AI to use images you attach over there. Nothing leaves your browser except the prompt text itself.
Identity and construction — recognizable materials, markings, and defining construction details. It does not freeze the camera angle, lighting, or presentation; those stay free unless you specifically ask for them.
Yes — type the inscription in the placard field exactly as it should appear, and the prompt will demand that exact text in elegant museum typography beside the artifact. Keep it short; image AIs spell short phrases best.
Blank means the ingredient is skipped entirely. Random is a deliberate instruction telling the image AI to choose that ingredient itself. Use blank to keep prompts short, Random to invite serendipity.
Each wing carries its own curated banks — the purpose list, and often the artifact, civilization, and detail choices, follow the wing so every combination stays coherent (a sunken-kingdom wing won't offer you a polar research commune's inventions).
Never. It re-rolls the wing, purpose, and the creative checkboxes, but your exact lettering, additional directions, target AI, aspect ratio, style, and toggles are preserved.
Browsing, organizing, and sharing. It's generated from your selections but is not an instruction to put that text on the image. Want words on the image? Use the exact lettering field.
Midjourney interprets structured prompts, reference details, lettering, and aspect-ratio directions differently from the chat-style image AIs. The wording is a starting point — expect to adjust parameters inside Midjourney.
Yes, but expect more scrolling. Best experienced on desktop or tablet.
Freely. Your prompts are yours — inspect them, edit them, post them, no credit needed.
The tool's fine — your image AI is repeating itself. When you generate several images in the same chat, the model starts copying its own earlier work. Open a fresh chat window, or try the prompt in a different image AI, and you'll get fresh results.
Your image AI stopped reading. After several images in the same chat, the model can latch onto a picture it made earlier and keep re-rendering that scene — even when your new prompt describes something completely different. Open a fresh chat, paste the same prompt, and you'll get the image you actually asked for.