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 by its use (Square for Etsy and Instagram posts, Classic for marketplace listings, Wide for a Shopify hero, Portrait for Instagram posts and Pinterest, Tall for stories and phones, or Custom to leave it open), tap an artistic style pill (Photorealistic, Studio Clean, Editorial, Luxury, …), and leave High Resolution on unless you want a lighter touch. Add text stays off unless you want words in the image — AI lettering garbles easily.
Product Makeover is for a real product: the prompt tells your image AI to use the photo you attach there — the tool never sees or uploads it — and locks in that product's shape, materials, colors, packaging, logos, and label text, changing only the background, lighting, composition, and scene. Product Inventor needs no photo: describe a product concept, or leave it open and the image AI invents one that suits the scene. Inventor outputs are labeled as concepts, never real manufacturable products.
New here? Hit ✦ Surprise Me first for a fresh combination — see what the tool can do, then tweak any choice. Or pick one of 10 scenes (premium hero, clean catalog, lifestyle, macro, luxury, outdoor, flat lay, workshop, seasonal, gift) and open the ingredient groups — focus, setting, props & staging, treatment, palette, microdetail — to check whatever fits. Your custom text, target AI, and mode are never overwritten. In Inventor mode a concept box appears; in Makeover mode it hides, because the photo already decides the product.
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.
Turn on Add text first, then type the exact wording — spelling, caps, everything. The prompt will demand that exact text and forbid the AI from inventing other headlines. Keep it short: AI lettering garbles easily, so check spelling in the result. Leave it off for a clean, text-free shot.
Copy Prompt grabs the model-ready text. Paste into your image AI (and attach your product's photo there if you're in Makeover mode).
Three groups, ten scenes — studio, lifestyle, and seasonal. Each scene brings its own focus list and curated ingredients.
Premium hero shot — the product, front and center. Clean catalog / white background — nothing in the way. Macro detail — close enough to see the craft. Luxury / editorial — magazine pages, velvet ropes, soft shadows. Flat lay — top down, everything in its place.
Lifestyle staging — the product living its best life, in a real room. Outdoor / on location — fresh air, real light, real ground. Workshop / maker story — hands, tools, and the work behind the thing.
Seasonal / holiday — dressed for the season, ready for the gift guide. Gift & unboxing — wrapped, ribboned, and ready to be opened.
The prompt carries your ratio choice — Square is the default, and switching to Classic, Wide, Portrait, Tall, 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. This tool writes prompts for still images only.
No. The Makeover mode only inserts wording instructing the receiving AI to use the photo you attach over there. Nothing leaves your browser except the prompt text itself.
The product itself — shape, dimensions, proportions, materials, colors and colorways, markings, packaging, logos, label text, and component count. It does not freeze the background, lighting, composition, scene, or styling; those change by design, because that is the whole point of a makeover. Image models can garble small label text, so check it in the result.
No — the prompt says so plainly. In Makeover mode every staging element must stay clear of logos, labels, and defining details. Nothing may hide what makes your product recognizable.
Yes — that's Inventor mode. Describe a product concept, or leave it open and the image AI invents one that suits the scene. Everything Inventor makes is labeled a concept, not a real manufacturable product.
Because AI lettering garbles easily. Text stays opt-in: turn on Add text only when you want words in the image, keep the wording short, and check spelling in the result.
No. The engine forbids invented product claims, prices, certifications, badges, review quotes, and endorsements. It also never promises a monetary shoot value or guaranteed fidelity — the prompt aims for quality, and you judge the result.
They can be: leave text off, skip logos you don't own, and keep the staging clean. Stock sites set their own acceptance rules, so check theirs before uploading.
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 setting, props, treatment, and detail choices, follow the scene so you never get impossible combos (like a beach scene offering a throne-room setting).
Never. It re-rolls scene, focus, and the ingredient checkboxes, but your exact lettering, additional directions, target AI, aspect ratio, style, and product mode 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? Turn on Add text and use the exact text 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.