Product photo checker
Check product photos against marketplace rules before you list: pixel-level size and white-background measurements locally, then a per-photo vision check for subject share, text, watermarks and misleading props.
About this tool
Marketplaces reject or bury listings over photo rules sellers only discover after the fact: a main image that is not pure white, a product that fills too little of the frame, text baked into the shot. This checker runs the rules before you list, per photo and per platform preset — Amazon main image, Shopify or eBay.
The hard numbers are measured, not guessed: dimensions and border whiteness come from the actual pixels on your device. The vision model behind your own key then judges subject share, baked-in text, watermarks and misleading props, and every photo lands in a pass/fail table with the failing rule and the fix named. Export the fix list as CSV and work through it once, instead of relisting three times.
How to use Product photo checker
- Add your provider API key in the key panel (vision-capable model recommended).
- Pick the target platform rule set, then drop up to 20 product photos.
- Pixel-level rules (size, white background) are measured locally first; the vision model then checks subject share, text, watermarks and props per photo.
- Work through the pass/fail table and export the fix list as CSV.
Keep the original files and inspect the exported result before publishing or sharing it.
Frequently asked questions
Which rules are checked locally?
Image dimensions and — for Amazon main images — whether the border pixels are pure white. Those are measured from the actual pixels on your device, never guessed by the model.
What does the vision model check?
How much of the frame the product fills, baked-in text, watermarks or logos, props that could mislead buyers about what is included, and background clutter.
Which platforms are covered?
Amazon main image, Shopify and eBay presets, each with its own size and background rules.
Where do my photos go?
Each photo is sent only to the AI provider behind your own key, directly from your browser.
Related tools
- AI chat — Chat with OpenAI, Claude or Gemini using your own API key. Your key stays in your browser; requests go straight to the provider.
- AI summarizer — Summarize long text with your own OpenAI, Claude or Gemini API key. Brief, detailed or bullet-point summaries, all in your browser.
- AI translator — Translate text between 30 languages with your own OpenAI, Claude or Gemini API key. Private by design: key and text stay with you and the provider.
- AI writing assistant — Improve, expand, shorten or re-tone your writing with your own API key. Six editing modes, direct browser-to-provider calls.
- AI code explainer — Paste code and get a plain-English explanation using your own OpenAI, Claude or Gemini API key. Language auto-detect included.
- AI PDF chat — Upload a PDF and ask questions about it. The PDF is parsed in your browser; only the extracted text and your question go to your chosen AI provider.
- AI image analyzer — Upload an image and let AI describe it, extract text (OCR), or identify objects. Uses vision models from OpenAI, Claude or Gemini with your own key.
- AI voice generator — Turn text into natural-sounding speech with OpenAI TTS. Six voices, speed control, play in the browser and download MP3.
- AI data analyst — Upload a CSV and ask questions in plain English. The file is parsed locally; the AI sees only a schema summary and sample rows.
- AI spend analyzer — Turn your AI provider usage export into an independent cost receipt: per-model and per-day breakdowns, spike alerts and a monthly projection. Runs 100% in your browser — your billing data is never uploaded.