Skip to content

C2PA · Stable Diffusion · Generator tags

AI image metadata remover

A free AI metadata remover for generated images. See the prompts, seeds, model names and signed provenance records yours carries — then decide what to do about them.

Where AI image generators hide their metadata

There is no single standard, so the data ends up in several different places:

  • PNG text chunks. Automatic1111, ComfyUI and Forge write a parameters chunk containing the complete prompt, negative prompt, seed, sampler, CFG scale, model name and model hash. Anyone who opens the file in a text editor can read it.
  • C2PA manifests. A JUMBF box holding a cryptographically signed provenance record. In JPEG it lives in an APP11 segment, in PNG a caBX chunk, in HEIC and AVIF a jumb box.
  • EXIF and XMP fields. Generator names appear in Software, UserComment or CreatorTool, plus custom XMP namespaces.

Your prompt is often the most sensitive part. It can contain client names, unreleased product details, or simply a working method you would rather not publish.

What C2PA is, and what removing it means

C2PA Content Credentials are a signed record of how a file was made — which tool, when, and whether AI was involved. They are not a watermark and not DRM. They are closer to a chain of custody, and the signature means tampering is detectable rather than prevented.

Removing a manifest removes the signed history. A verifier then reports the file as having no credentials, which is the same state as any ordinary photo. It does not make the file appear to be something it is not.

There are honest reasons to strip them. A credential can name the account, the tool and the device you used. If you have licensed an image to a client, the embedded chain can also expose your workflow. Read more in C2PA explained, or go straight to the ChatGPT image metadata removerif that is where your images come from.

Where we draw the line

This tool removes metadata. It does not modify your pixels, and it will not implement fingerprint-scrambling designed to defeat AI classifiers. That feature exists elsewhere; we think it makes your image worse in exchange for helping mislead a system built to label content accurately.

Working through a folder of generations rather than one file? Thebulk image metadata remover handles them in a single pass.

Be aware of the surrounding rules too. The EU AI Act's Article 50 transparency obligations apply from 2 August 2026, and most large platforms already ask for AI content to be disclosed. Cleaning metadata for privacy is a normal thing to do. Removing a disclosure to pass work off as something it is not is a different act with different consequences.

Questions

Frequently asked questions

What metadata do AI image generators leave behind?
It varies. Stable Diffusion interfaces write the full prompt, negative prompt, seed, sampler, CFG scale and model hash into PNG text chunks. Adobe Firefly and Photoshop embed C2PA Content Credentials. Others write a generator name into the Software or UserComment field, or into custom XMP properties.
Does removing this make my image undetectable as AI?
No, and you should not assume otherwise. Metadata is only one of several signals. Platforms also use classifiers that look at the pixels themselves, invisible watermarks such as SynthID that survive metadata removal entirely, and upload-side provenance checks. Removing metadata removes metadata.
Is it legal to remove AI metadata from my own images?
Removing metadata from a file you own is generally lawful. Whether you should is a different question, and depends on context. The EU AI Act's Article 50 transparency obligations apply from 2 August 2026, and most large platforms have their own AI disclosure rules. Removing a disclosure to mislead someone can create liability that removing metadata for privacy does not.
Do you modify pixels to defeat detection?
No. Some tools apply small pixel changes specifically to break detector fingerprints. We do not build that, for two reasons: it degrades your image for no benefit to you, and its only purpose is deceiving a system that is trying to label content accurately. This tool removes metadata and leaves your pixels exactly as they are.