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. The people count in the finished image comes from your attached references, not from any separate count.
New here? Hit ✦ Surprise Me first for a fresh combination — see what the tool can do, then tweak any choice. Or pick one of 19 scenes (block party, booth session, DJ set, mural, record shop, …) and open the ingredient groups — focus, subject, setting, wardrobe, jewelry, vehicle, era, treatment, palette, microdetail — 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. Conflicting picks are never auto-removed: if you check two things that fight, the prompt carries both and your image AI works it out.
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.
Three groups, nineteen scenes — the stage, the street, and the style. Each scene brings its own focus list and curated ingredients.
Outdoor block party — a whole neighborhood in the street, speakers stacked, everybody dancing. Recording booth session — one voice, one mic, the red light on. Producer listening room — the beat gets built one pad at a time. DJ turntables set — two decks, a mixer, and a room moving as one. Live show / concert — stage lights, crowd hands, the hook landing live. Rooftop performance — skyline behind, cipher in front. Dance rehearsal — eight counts at a time until it locks. Behind-the-scenes video shoot — the camera sees the take; the crew sees everything else. Album-cover shoot — one frame that has to carry the whole record.
Graffiti mural in progress — original letters going up, no real tags, all hand. Sneaker customization bench — one pair, rebuilt by hand, paint still tacky. Record shop — crates, covers, and the find of the day. Barber studio — the chair, the clippers, the conversation. Flyer-poster workshop — paste, print, and paper the block. Photography set — lights, backdrop, and a subject who knows the lens.
Jewelry workshop reveal — the piece comes out of the bench and catches every light. Street fashion editorial — the fit is the statement; the street is the runway. Lowrider / classic coupe scene — chrome, paint, and a slow roll past the whole block. Animal performer (fantastical) — a grown animal performer, played straight, in a world that makes sense.
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, correct tooth placement and jewelry fit. 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, jewelry, and detail choices, follow the scene so you never get impossible combos (like a jewelry bench offering tour-bus vehicles).
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.
No. Jewelry is a choice, not a default. Pick an intensity — restrained, statement, or extravagant — choose specific pieces like custom grillz or a bespoke pendant, or check No jewelry and the prompt says so plainly. The culture here is bigger than any one accessory.
No. Every mural, design, and composition is original — fictional lettering shapes, no real tags, no real brand logos, no imitations of any known creator's distinctive imagery. If you want words in the art, type them yourself in the exact lettering field.
They're adult-coded anthropomorphic performers or photoreal pets in tasteful, safe wardrobe, played straight inside a coherent scene. The prompt demands anatomically coherent paws, limbs, and fur, and never sexualizes animal characters.
Pick one era — early foundational, golden-era, 1990s, 2000s, contemporary, or futuristic original — and the prompt keeps wardrobe, equipment, graphics, vehicles, and camera treatment plausible for that era instead of smearing decades together. Leave it blank and the prompt says nothing about era.
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.