Install Retouchable in ChatGPT Retouch your product photos from a ChatGPT chat. Install in ChatGPT
  1. Turn on Developer mode

    In ChatGPT, open Settings → Security and login and switch on Developer mode.

  2. Copy the address, open ChatGPT

    https://api.retouchable.ai/api/mcp

    Copy & open ChatGPT ↗
  3. Create the app

    On ChatGPT's Plugins page, select + and choose Create MCP App. Name it Retouchable, paste the address, set authentication to OAuth and create it.

  4. Sign in to Retouchable

    ChatGPT opens our sign-in. New to Retouchable? That starts your 14-day free trial, no card.

Then, in a chat, choose Retouchable under Developer mode and ask: “Grade the photos on my store” or “Put my product photo on white.”

Needs ChatGPT Plus, Pro, Business, Enterprise or Edu, on the web. Menus look different? OpenAI's steps

Content Credentials (C2PA) on Product Images

What a signed record on a product photo actually says, why a real photo can come out labelled as AI, and when signing your catalog is worth the effort.

|AI product photography e-commerce imagery product image requirements

A photo taken on a Pixel 10 now leaves the phone carrying a signed record saying it was captured by a camera. Google's security team confirmed in September 2025 that the Pixel Camera app attaches Content Credentials (C2PA) to every JPEG it shoots, and Google Photos adds a new entry whenever the image is edited, AI edits included. Content Credentials on product images are no longer a newsroom curiosity: they are arriving in sellers' phones whether anyone asked for them or not.

Most writing on C2PA for merchants is about compliance: how to label AI-generated images under the EU AI Act and marketplace rules. We have covered that in how to label AI-generated product images. This post is about the other side of the record: what a credential says about a real product photo, why a lightly retouched photo can end up wearing an "AI" label it did not earn, and how to check what your live listings actually carry.

The short version: a credential is only as useful as the chain behind it, and almost every e-commerce pipeline breaks that chain somewhere. Knowing where tells you whether signing is worth your time.

What Content Credentials on a product photo actually say

A C2PA manifest is a signed list of claims attached to the file (the mechanics are in our labeling guide). For a merchant, what matters is not the cryptography but the handful of statements a viewer will read back. They fall into three groups.

What the record saysWhat it means for a listingHow a platform tends to treat it
Captured with a cameraA signing device took the original exposureStrongest authenticity signal available
Edited (crop, colour, exposure)Ordinary adjustments recorded as actions after captureUsually no label
Edited with generative AIA model re-drew part of the frame, however smallOften an "AI info" style label
Created using generative AIThe whole image came from a modelLabelled, and required to be on some channels
No credential at allNothing can be said either wayTreated as unknown, not as fake

Two of those rows map onto the IPTC vocabulary platforms already read: trainedAlgorithmicMedia ("Created using Generative AI") and compositeWithTrainedAlgorithmicMedia ("Edited with Generative AI"). If you have read our guide to product image metadata, these are the same distinctions, now signed so they cannot be quietly rewritten.

The last row is the one most product photos sit in today, and it is worth being clear about: a missing credential proves nothing. The vast majority of genuine photos on the web carry none, because most cameras do not sign and most pipelines strip what is there.

Why a real, retouched photo can get labelled as AI

The most practical risk for a seller is not being caught using AI. It is a genuine photo being presented as AI-made because of one small edit.

Meta learned this in public. In 2024 its "Made with AI" label began appearing on real photographs that had been touched up in Photoshop; PetaPixel's tests found that removing a single speck with Generative Fill was enough to trigger it. After photographers complained, Meta renamed the label "AI info" in July 2024, and in September moved it into the post menu for content that was only edited rather than generated. The detection did not change: Meta still reads C2PA and IPTC metadata, and a generative edit still records itself as one.

The trap

A credential records which tool touched the pixels, not how much of the product changed. Removing a dust speck with a generative fill and inventing a whole scene can produce the same "edited with generative AI" assertion.

For a product photo this cuts both ways. If you use a generative tool for the background but leave the product as shot, the honest record still says "edited with generative AI", and a shopper or platform will read it that way. If you want a photo to read as a straight capture, the edits on it have to be ones that record as ordinary adjustments: crop, exposure, colour, and non-generative cleanup.

That is a decision to make per image type, not per file. Hero shots that need to prove the product is real are candidates for a clean chain. Lifestyle scenes built with AI should be labelled as such, and our post on AI image disclosure and customer trust covers how to do that without hurting conversion.

Where the chain breaks in an e-commerce pipeline

A credential survives only if every step between camera and shopper either keeps it or adds a signed entry of its own. Product images pass through more steps than most photos do.

Typical steps a product photo passes through, and what each does to a credential
Capture (signing camera)
Writes it
Editor that re-signs
Extends it
Editor that re-encodes
Usually drops it
DAM / export preset
Depends on settings
Storefront CDN resize
Often strips it

The weakest links are the steps that re-encode. Any editor, retouching service or AI tool that decodes the image and writes a new file will drop the manifest unless it is built to sign its output. That is not a fault of any one product; most image tools today, including AI retouching tools, write a fresh file without a manifest. Treat it as the default and plan around it.

Delivery is the other weak point. Until early 2025, Cloudflare Images discarded credentials on every transform. Since February 2025 it has offered a Preserve Content Credentials setting that keeps the existing record and appends a signed entry for the resize or format change Cloudflare made. With the setting off, credentials are still discarded. Other CDNs and storefront image services vary, and few document it, which is why the only reliable answer comes from testing your own live image.

Rule of thumb

If a step in your pipeline makes a new file and does not say it signs, assume the credential ends there.

How to check what your live listings carry

You do not need engineering help to find out whether your product images carry credentials. It takes about ten minutes per channel.

  1. Pick a test photo with a known credential. A JPEG straight from a Pixel 10 camera works, as does an image exported from a tool that signs its output.
  2. Inspect the original. Drop it into the Content Authenticity Initiative's free verify page at contentcredentials.org/verify, or run the open-source c2patool on it from a terminal. Note what it reports: captured, edited, which tools.
  3. Run it through your normal workflow. Retouch it, export it, upload it to the product exactly as you would a real listing.
  4. Download the image a shopper actually receives. Open the live product page, save the image the browser loads (not the file in your admin), and inspect it again.
  5. Repeat per channel. Your own store, each marketplace and each social shop can treat the same file differently.

Record the result in one line per channel: "kept", "kept and extended", or "stripped". That table tells you whether signing anything is worth the effort before you buy a camera or change a tool.

Checking the wrong file

  • Inspecting the master in your DAM
  • Inspecting the file in the store admin
  • Assuming the tool's spec sheet is your pipeline

Checking the right file

  • Saving the image from the live product page
  • Testing each channel separately
  • Re-testing after any CDN or theme change

Trust signals for real photos: when signing is worth it

For most catalogs, a full signed chain from camera to shopper is not achievable today, and that is fine. The question is where a credential earns its keep.

Level 2C2PA assurance Google claims for Pixel 10's camera
Sept 2025Nikon revokes Z6III credentials after a signing flaw
Feb 2025Cloudflare adds credential-preserving delivery

It is worth it where authenticity is the product. Resale and pre-owned goods, collectibles, vintage, art and anything where condition drives price all benefit from proof that the photo shows the actual item. A signed capture of the scuff on a pre-owned bag is a stronger answer to "is that really the one I'll receive" than any caption.

It is worth it when you supply images to others. Wholesale partners, marketplaces and press increasingly ask where an image came from. A credential on your masters answers that once, and our guide to image handoffs covers keeping that information intact when files change hands.

It is rarely worth it for routine catalog shots of new, identical stock, where nobody doubts the product exists and the pipeline would strip the record anyway.

Keep the limits in view. Credentials depend on the signer being trustworthy: in September 2025 Nikon suspended its Z6III authenticity service after a user showed the camera could sign an image it had not taken, and the company later revoked the certificates it had issued. A credential is evidence, not proof, and a platform's reading of it can change.

Generated images: where credentials are not optional

For fully AI-generated product images the question flips from "is it worth it" to "do not remove it". Google Merchant Center's policy asks that images created with generative AI carry the IPTC trainedAlgorithmicMedia tag and that sellers do not strip embedded metadata such as the IPTC DigitalSourceType from images made with generative tools. The EU's transparency rules point the same way, which our post on EU AI Act labeling covers in detail.

Practically, that means a generated image needs its origin recorded somewhere your team can rely on, even if a CDN later drops the embedded copy:

  • Keep the tool's original output, with whatever metadata it wrote, as the master.
  • Track which images were generated or edited with AI in your catalog data, not only in the file.
  • Re-apply the IPTC DigitalSourceType at export if your editor dropped it.

The second point is the one teams skip, and it is the one that survives every re-encode. Choosing settings helps here too: in Retouchable's Studio, every setting the model works on is marked ✦ before you press, and Exact keeps the product's pixels as shot, so you know at the moment of making an image which kind it is. Whichever tool you use, write that distinction down where your listing data lives.

A simple policy for a mixed catalog

Most stores now hold three kinds of product image side by side: straight captures, real photos with AI-assisted edits, and fully generated scenes. A one-page policy keeps the credentials question from becoming a per-image debate.

Image typeCredential goalVisible label
Straight capture, ordinary editsKeep the capture record where your pipeline allowsNone needed
Real product, AI-built background or cleanupLet the record say "edited with generative AI"Light disclosure where a channel asks
Fully generated scene or modelNever strip; re-apply IPTC at exportRequired on some channels
Pre-owned or one-of-a-kind itemSign at capture, minimal edits, preserve end to end"Photo of the actual item"

Revisit it twice a year. Camera support, platform labels and CDN settings are all moving, and the right answer for your catalog in spring may be different by autumn. The test in the section above is the cheapest way to know when it has changed.

Frequently Asked Questions

What are Content Credentials on a product image?

Content Credentials are the consumer-facing name for C2PA: a signed record attached to an image file stating how it was made, for example captured by a camera, edited, or created with generative AI. Platforms and verification tools can read that record back.

Will a retouched product photo be labelled as AI-generated?

Only if the edit was made with a generative AI tool that records itself. Ordinary crop, colour and exposure changes record as edits, while even a tiny generative fill can record as "edited with generative AI", which platforms such as Meta show as an AI info label.

Does Shopify keep C2PA metadata on product images?

Do not assume either way. Upload a photo with a known credential, save the image the live product page actually serves, and check it at contentcredentials.org/verify or with c2patool. Many image CDNs strip metadata when they resize or convert files.

Do I need Content Credentials on my product photos?

Not for routine catalog shots. They are most useful for pre-owned, collectible and one-of-a-kind goods where proving the photo shows the actual item matters, and they should never be stripped from fully AI-generated images, which some channels require to stay labelled.

Is a photo without Content Credentials fake?

No. Most genuine photos on the web carry no credential, because most cameras do not sign and most pipelines strip metadata. A missing credential means nothing can be said either way.

Know which photos the AI touched

In Retouchable every AI setting is marked before you press, so you know which product images will need a label.

Try Retouchable Free No credit card required