Verify OpenAI-generated images

Provenance helps people understand where online content came from and whether AI was involved in creating or editing it. This gives people more information when deciding what to trust, share, or report on online.

It can help reduce confusion, deception, and cases where the origin of AI-generated content is unclear. It also gives journalists, platforms, creators, researchers, and the public more context about the media they encounter online.

We believe clearer information about how content was created is an important part of building a more trustworthy online environment.

The tool relies on two types of signals: C2PA Content Credentials and SynthID.

Content Credentials⁠(opens in a new window) are based on an open standard that attaches provenance metadata to digital media. For supported OpenAI-generated images, they can indicate that an image was created using tools such as ChatGPT or the API. They are a strong signal when present, but because they rely on metadata, they can be removed.

SynthID⁠(opens in a new window) is an invisible watermarking technology that embeds a signal directly into generated media. Unlike metadata, the signal is part of the image itself and is designed to stand up to modifications like cropping, adding filters, or lossy compression. For more technical details, see the SynthID research paper⁠(opens in a new window).

No, a detected signal indicates that the image originated from OpenAI tools, but it does not determine whether the image is accurate or presented in the correct context.

A detected signal indicates that the image likely originated from OpenAI tools. Detected signals are reliable, and false positives are rare.

It does not confirm how the image has been used or modified after it was created.

If no signal is detected, it means the tool did not find supported signals in the uploaded image.

The image could still have been generated by OpenAI if the metadata was stripped or has evidence of tampering, the watermark was degraded, the image comes from a legacy image generation model, or it was created before provenance signals were available. Content could also still be AI-generated by another company's model, which the tool currently does not detect.

If the tool isn’t working, try again in a moment—some errors (like rate limits or temporary issues) can occur.

If the problem persists, visit our Help Center⁠(opens in a new window) for support.

The uploaded image is processed to check for supported provenance signals associated with OpenAI-generated content. Uploaded images are not stored unless legally required, and are not used to train our models.