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, or Custom to leave it open), tap an artistic style pill (Photorealistic, Cinematic, Vintage, …), and leave High Resolution on unless you want a lighter touch.
Flip on Use Reference Image(s) if you'll attach photos in your image AI — the tool never sees or uploads them; it just adds wording telling the AI to use your attachments. Add Strict Feature Lock to ask the AI to preserve recognizable identity and keep anatomy credible.
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 15 scenes (disco club, drive-in, Bicentennial summer, the record store, …) and open the ingredient groups — focus, subject, setting, wardrobe, mood, treatment, palette, signature detail — to check whatever fits. 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. You can check more than one option in a group — each adds its own direction to the prompt.
Type poster or sign wording 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 creative title on top. Paste into your image AI (and attach any reference photos there). The title is yours for browsing and sharing — it's never printed on the image.
Four groups, fifteen scenes — earth-tone suburbia on one side, mirror-ball Saturday night on the other. Each scene brings its own focus list and curated ingredients.
Disco club — a light-up floor, a mirror ball the size of a planet and Saturday night as a competitive sport. Roller disco — satin, wheels and a mirror ball. Arena rock — denim, feathered hair, double-neck guitars and ten thousand lighters held honestly. Soul & variety TV — a dance line, a curtain of gold and television when it still dressed up.
Wood-paneled family room — the TV is furniture, the carpet is shag and the whole family fits on one couch. Harvest-gold dinner party — avocado appliances, fondue steam and adults in turtlenecks solving the world. Custom van & the cruise — airbrushed sunsets, shag-lined interiors and Friday night measured in laps of the strip. Drive-in, the late years — big Detroit iron, a speaker on the window and a double feature under real stars.
Bicentennial summer — July 1976, every hydrant, mailbox and main street in America painted red, white and blue. Trucker & CB radio — handles, convoys and the whole country talking to itself at 55 miles an hour. Empty-pool skateboarding — drained pools, vertical walls and kids inventing a sport out of a drought. The record store — gatefold art, listening posts and a Saturday budget of exactly one album.
Movie poster — painted grit: crime, disaster, deep water and one ship in space that changed everything. Album cover art — twelve inches of canvas, airbrushed worlds and funk illustrated at full blast. Magazine & TV Guide covers — cover lines from the checkout rack: teen idols, TV detectives and the news that week.
The prompt carries your ratio choice — 16:9 is the default, and switching to Square, Portrait, or Custom updates the wording (Custom leaves the ratio open for the image AI to decide). 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 photos you attach over there. Nothing leaves your browser except the prompt text itself.
Identity and anatomy — recognizable faces, defining markings, credible hands and proportions. It does not freeze the pose, outfit, expression, or camera angle; those stay free unless you specifically ask for them.
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 scene carries its own curated banks — the focus list, and often the subject, wardrobe, and detail choices, follow the scene so you never get impossible combos (like a disco club offering long-haul trucker wardrobes).
Never. It re-rolls scene, focus, and the ingredient 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.