Generate premium product ad images from WhatsApp with Gemini

Get Job Alerts
One email when a teaching platform opens hiring or a new AI training project drops. No weekly filler.

E-commerce sellers need scroll-stopping product images but can't afford a photographer for every SKU. This AI automation lets you offer a productised image upgrade service where clients send a raw photo via WhatsApp and get a polished marketing visual back in under a minute.

What This Automation Does

Accepts a product photo and caption sent by a client over WhatsApp, then passes both through an AI pipeline without any manual handling
Gemini AI rewrites the client's basic caption into a detailed, professional image-generation prompt that actually produces high-quality output
Nano Banana AI uses that enhanced prompt to generate a premium marketing image while keeping the original product visually intact
Delivers the finished, social-media-ready visual back to the client inside the same WhatsApp conversation within 60 seconds

Tools Used

WhatsApp
Google Gemini
n8n

Where to Get Hired for This Skill

On Contra, top freelancers across this stack have earned 80 combined verified reviews from real client projects.

Source: Contra freelancer search · refreshed 30 May 2026

Start Earning as a Freelancer on Contra

Contra is a commission-free professional network for independents. Browse live AI automation work and keep what you earn.

Join Contra Free →

How To Build It

Connect WhatsApp as the intake channel

Wire up a WhatsApp Business account as the entry point so that any inbound message containing a photo and a text caption automatically triggers the pipeline without polling or manual checks.

Extract the image file from the message

Pull the raw image binary out of the incoming WhatsApp payload and convert it into a file format the downstream AI services can consume, handling both JPEG and PNG inputs cleanly.

Enhance the caption with Gemini AI

Send the client's plain-text caption to Gemini with a system prompt that instructs it to rewrite the input as a structured, professional image-generation prompt, specifying lighting style, background, composition, and mood that suit product advertising.

Generate the marketing image with Nano Banana AI

Pass the enhanced prompt and the original product image to the Nano Banana AI endpoint via an authenticated HTTP request, instructing it to produce a new marketing visual that preserves the product's exact appearance while placing it in a premium advertising context.

Return the finished image over WhatsApp

Convert the generated image back into a sendable file, merge it with the client's originating conversation thread, and deliver it as a WhatsApp reply so the client receives their polished ad-ready visual in the same chat where they submitted the photo.

Pitfalls

Nano Banana AI imposes per-minute and monthly request limits that will silently queue or drop jobs during burst usage, so you need to build retry logic and client-facing status messages rather than assuming every request completes first time.
WhatsApp Business API tokens expire and Meta's webhook verification resets during platform updates, meaning the intake trigger can go silent without any obvious error, leaving clients waiting indefinitely for images that never generate.
Gemini's prompt enhancement output is non-deterministic, so the same client caption can produce noticeably different image styles across sessions. Without a stable system prompt with pinned instructions, you'll field quality complaints that are hard to reproduce or diagnose.

FAQ

Can I build this without coding?

Almost entirely, yes. The core pipeline uses visual workflow logic and pre-built API connectors. The one area requiring a small amount of custom code is handling the image binary conversion between WhatsApp and the AI image service, which is a short, copy-paste-friendly script rather than full development work.

How long does it take?

Expect two to four hours to get a working version live, assuming you already have WhatsApp Business API access. API approvals for WhatsApp are the longest variable, sometimes taking several days, so factor that into client timelines.

What can I charge?

Pricing is yours to set based on your market and positioning. Most freelancers offering productised AI creative services package this as a per-image or monthly retainer model rather than an hourly rate, since the automation means your time per image is minimal once the workflow is running.

Which tool is required vs optional?

WhatsApp is the required delivery channel since the entire user experience depends on it. Gemini is central to prompt quality and should be treated as required. Nano Banana AI could theoretically be swapped for another image-generation API with a compatible endpoint, but that would require rebuilding the HTTP request and output handling steps.

This is original DigiNo analysis. The underlying automation pattern is a community workflow template – view the original on n8n.