Listing Image Generator App with Claude Code and Nano Banana Pro for Amazon Sellers
- Seller task
- Build an internal app that writes image specs and generates infographic listing images
- Agent / tool
- Claude Code Gemini
- Source
- Blog post by Alex Willen (The Automated Operator) (@Willenation)
- Date
- Jan 15, 2026
What they did
A seller who previously paid an Upwork designer $35 per listing image had Claude Code (Opus 4.5) build a local web app. It sends product info to Gemini 3 Pro to propose six image specs and a style guide, generates four style options with Nano Banana Pro, then generates the remaining images in the chosen style. He later added single-image generation, image-to-image restyling for A/B tests, and whitebox photo generation.
How it went
He says that apart from one bug it 'just worked.' Claude had hallucinated the Gemini model names and fixed them after being shown the terminal logs. He calls the output 'great' in the grand scheme of Amazon images, says he'll judge styles by Amazon A/B test results, and upgraded to Claude Max to keep building.
We only report what the source says. Results are self-reported unless noted.
Worth knowing
Early generations reused the same photos, which he fixed by raising the upload limit to 20.
Copy-paste prompt
I would like to build an application that generates images for Amazon listings. These will be infographic-style images that have photos of the relevant product along with informational text and/or graphics. The application should work as follows: 1. User fills out a web form with the following info: - Text entry: Describe the product. - Text entry: How would you describe the desired brand look and feel? - Text entry: What are the main pieces of information you wish to convey about the product? - File picker: Select and upload up to 6 images. You should be able to select files at which point previews of them are shown. You can add more and delete existing ones. 2. The app then sends all of the text to the Gemini API (mode: Gemini 3 Pro), which comes back with a written description of six different images that it proposes creating. The written descriptions should include any text (with high-level formatting notes about each piece of text - e.g. Title, subtitle, bullets). They should also describe any visuals that must be included in each image. Lastly, it should have a separate section that shows the proposed look and feel, including colors, font styles, and any illustration/iconography styles. Each of the image descriptions should be in its own text box, as should the look and feel info, and the user should be able to edit any of them. 3. When the user is satisfied with everything, he clicks a "Generate Style Examples" image. This should create four versions of the first image in the list. These should each be created with independent calls to the Nano Banana Pro API. [...] When use this style is clicked, the app should make calls to Nano Banana Pro to generate the other five images. Those calls should include the selected image with instructions to NBP to match the style. Each generated image should have a Reroll and a Download button next to it. Other context: 1. This is going to run locally on my machine so no concerns about auth, security, etc. 2. All images generated should be in 2k resolution and 1:1 aspect ratio
This prompt is quoted or closely adapted from the original source. Replace anything in [brackets].
Original source
https://theautomatedoperator.substack.com/p/opus-45-codes-gemini-3-writes-the