{ "schema": "aiblocks-page/1", "id": "accurate-product-image-ad-maker", "type": "prompt", "name": "Product image ad prompt writer", "summary": "Share your approved ad, product facts and photos. Get an image prompt, photo roles and a checklist for the first image.", "headline": "Product image ad prompt writer", "subhead": "Share your approved ad, product facts and product photos. It fixes the product details, assigns each photo a role and writes a five-part image prompt. With an image tool, it can make the picture. You get the prompt and a six-point check to run on the first image.", "job": { "id": "make-image-ads", "name": "Make image ads" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-19", "inputs": [ { "type": "brief", "required": true, "label": "Brief", "what": "a creative brief: goal, audience, angle, offer, mandatory claims (by ID), formats" }, { "type": "product_photos", "required": false, "label": "Product photos", "what": "photos of the real product, labelled by angle and use" }, { "type": "ad_copy", "required": false, "label": "Ad copy", "what": "headline, primary text, description and CTA within platform limits" }, { "type": "brand_brain", "required": false, "label": "Brand brain", "what": "the brand's facts, voice, products, offers (with effective dates), claims register, personas and look" }, { "type": "lessons_register", "required": false, "label": "Lessons register", "what": "what past creative taught: what worked, what failed and why, with dates" }, { "type": "hooks", "required": false, "label": "Hooks", "what": "opening lines, each with the angle and persona it targets" } ], "outputs": [ { "type": "image_prompt", "required": true, "label": "Image prompt", "what": "a render-ready image prompt plus the reference roles it uses" } ], "you_give": [ "The approved scene, layout and image shape, from your ad brief or the designer's sign-off (rejected versions can stay in the paste)", "Your product facts, ideally the lock lines from your truth sheet, and how the product opens and is held", "Product photos, attached as pictures, each with what it's for (front as sold, out of the pack, in a hand)", "The approved words, with where they sit and which is biggest (optional)", "Which image tool you use, its image limit and length limit (optional)", "Your mistakes list from past image jobs (optional)" ], "you_get": [ "One prompt in five blocks plus a keep line, with its character count", "A subject block that says which hand holds what, which hand tears or pours, and how they move", "A one-line role for every attached photo", "A six-line pass-or-fail check for the first image, with failure notes for your mistakes list", "A list of what was left out or added, and a MISSING line for any fact it needed" ], "use_when": [ "Your designer or client has signed off one ad, and you now need the prompt for GPT Image, Nano Banana or FLUX.", "Your last three AI images had the wrong green, a hand over the name or a pack that opened in the wrong place, and each redo costs money.", "Your brief has grown to a page of notes and rejected versions, and the images keep picking up an idea you dropped.", "A product photo shows the pack one way, your words describe it another, and the tool keeps following the words." ], "skip_when": [ "You have no approved ad yet, only a product and a vague idea. Write the words first with the fact-based ad copy writer, then come back.", "You want six different ad ideas from one product photo. Use the Product photo ad prompt set writer.", "You want a moving clip. Approve a still here first, then use it as the start frame in a video prompt writer.", "You have no photos of the product and no lock lines. It still writes a prompt, but marks the photo match as still to do and shows the product closed, so expect a rough first image." ], "output_sample": { "input": [ "The approved ad scene, layout and image shape", "Your product facts, ideally the lock lines from your truth sheet", "Product photos, each with what it is for", "The approved words (optional)", "Your image tool and its limits (optional)" ], "prerequisites": [ "An AI that can read attached photos", "An image tool to draw the picture, such as Nano Banana or ChatGPT" ], "output": [ { "name": "PROMPT", "contains": "One image prompt in five blocks (use, subject, place, camera and light, words) plus a keep line, with its character count." }, { "name": "IMAGES", "contains": "A one-line role for each photo you attached." }, { "name": "LEFT OUT", "contains": "What was dropped from the brief, and any detail it added that you did not give." }, { "name": "CHECK THE FIRST IMAGE", "contains": "Six pass-or-fail lines to run on the first picture, with a failure note for each miss." }, { "name": "MISSING", "contains": "Any photo, product fact, approved words or price it needed and did not have." }, { "name": "CHECKS MISSED", "contains": "One line for each check it could not run, or none." } ] }, "output_shape": "PROMPT ()\n1 Use and shape: <...>\n2 Subject: \n3 Place: \n4 Camera, light: \n5 Words: \"\", \nKeep: \n\nIMAGES Image 1 = ; Image 2 = ; ...\nLEFT OUT \n Added, not in the brief:
\nCHECK THE FIRST IMAGE (pass or fail)\n[ ] \nFAILURE NOTE Asked: <...>. Got: <...>.\nMISSING \nCHECKS MISSED ", "how_to_use": [ "Start a chat with the prompt. Open it if you added it to your AI, or copy it and paste it in. Claude writes the prompt but can't draw the picture, so plan to paste the prompt into GPT Image (ChatGPT), Nano Banana (Gemini) or FLUX. In ChatGPT or Gemini you can run the whole skill there.", "Paste the approved ad, the exact words and the product facts. Rejected versions can stay in; they'll be dropped.", "Attach your product photos as pictures, not a description, and say what each one is for.", "Say which image tool you use, the image shape and any length limit, such as \"GPT Image, 4:5, 1,000 characters\".", "Read the prompt before you make anything. Check the lock lines match your photos, the words are spelt right, and the hands make sense: which hand holds the pack, which one tears.", "Make one image only, put your photos beside it and run the six checks. Ask for one fix at a time until it passes." ], "checks": [ "Every attached photo has one stated role.", "Your lock lines appear word for word, and the pack hasn't been swapped or simplified.", "Approved words appear once, in quotes, with their place, or the prompt asks for clear space.", "No rejected idea, research note or placeholder made it into the prompt.", "The camera is a real position, and the hands say which one holds what.", "Anything it couldn't know is marked MISSING, and the product is shown closed until you answer." ], "next": [ { "name": "Pre-launch ad checker", "url": "https://useaiblocks.com/skills/pre-launch-ad-checker", "why": "Check it before it goes live" }, { "name": "Visual twist image ad maker", "url": "https://useaiblocks.com/skills/visual-twist-image-ad-maker", "why": "Make image ads" }, { "name": "Image ad batch brief writer", "url": "https://useaiblocks.com/skills/weekly-image-ad-batch-maker", "why": "Make image ads" }, { "name": "Meta ad policy checker", "url": "https://useaiblocks.com/skills/meta-ads-compliance-checker", "why": "Check it before it goes live" }, { "name": "Image enlargement quality checker", "url": "https://useaiblocks.com/skills/image-upscale-checker", "why": "Make image ads" } ], "source": null, "credits": [ { "title": "Gpt-image-1.5 Prompting Guide", "by": "OpenAI Cookbook", "url": "https://developers.openai.com/cookbook/examples/multimodal/image-gen-1.5-prompting_guide", "used": "Labelling each image by number and role; quoting exact text; restating what stays fixed; one change per fix" }, { "title": "Prompting Guide - FLUX.2 [pro] & [max]", "by": "Black Forest Labs", "url": "https://docs.bfl.ai/guides/prompting_guide_flux2", "used": "Most important words first; describing what you want instead of negatives; hex colours tied to one object" }, { "title": "Nano Banana image generation", "by": "Google AI for Developers", "url": "https://ai.google.dev/gemini-api/docs/image-generation", "used": "Describing the scene with camera and light terms; reference image limits; 'keep everything else the same' for edits" }, { "title": "Federal Trade Commission Announces Final Rule Banning Fake Reviews and Testimonials", "by": "US Federal Trade Commission", "url": "https://www.ftc.gov/news-events/news/press-releases/2024/08/federal-trade-commission-announces-final-rule-banning-fake-reviews-testimonials", "used": "Why a generated person never stands in for a real customer" } ], "files": [], "links": { "page": "https://useaiblocks.com/prompts/accurate-product-image-ad-maker", "markdown": "https://useaiblocks.com/prompts/accurate-product-image-ad-maker.md", "json": "https://useaiblocks.com/prompts/accurate-product-image-ad-maker.json", "instructions": "https://useaiblocks.com/skills/accurate-product-image-ad-maker/SKILL.md", "api_item": "https://useaiblocks.com/api/v1/items/accurate-product-image-ad-maker", "api_document": "https://useaiblocks.com/api/v1/documents/prompt/accurate-product-image-ad-maker", "mcp": "https://useaiblocks.com/mcp" } }