Metadata and forensicsAI image metadata checker

Drop an image to see everything its file says about itself.

AI image detector

ChatGPT, Gemini, Midjourney, Flux and more

What it checks

Content CredentialsC2PA and IPTC labels
Generator fingerprintsSettings AI tools save
Camera dataMake, model and exposure
Visual inspectionHands, text, light, texture

Private. The file is checked on your device.

Drop an image to get a verdict

It names the AI that made it when the file says so, and checks the pixels when it does not.

AI

ChatGPT

Content Credentials in the file

AI

Stable Diffusion

The full prompt, read back

AI

Gemini

IPTC label in the metadata

Real

Camera photo

Make, model and exposure

  • Free, no sign-up
  • Images and video
  • Names the AI that made it
  • Private: files stay on your device

Open the full detector

In short

Drop an image to see everything its file says about itself. Gireta reads EXIF camera data, XMP, the IPTC source type, Content Credentials, and the text chunks where Stable Diffusion, ComfyUI, InvokeAI and NovelAI store the prompt, seed and model. It also draws error level, noise and spectrum views of the pixels.

Where AI tools hide their settings

ToolFieldWhat it holds
Automatic1111, Forge, FooocusPNG text chunk “parameters”Prompt, negative prompt, steps, sampler, CFG scale, seed, model
ComfyUIPNG text chunks “prompt” and “workflow”The full node graph as JSON
InvokeAI“invokeai_metadata” or “sd-metadata”Prompt and generation settings
NovelAI“Software” and “Comment”The tool name and settings as JSON
MidjourneyDescription text and IPTC fieldsPrompt with --ar and --v parameters, job ID
ChatGPT, Gemini, FireflyC2PA manifestThe tool, the source type and the edit history

Error level analysis, noise and spectrum

Error level analysis re-saves the image as a JPEG and shows where it changes most. Areas pasted in or generated separately often stand out, though edges and text always glow a little.

The noise view subtracts a blurred copy to show the fine grain a camera sensor leaves. The spectrum view is a Fourier transform; the upsampling layers in many generators leave a regular grid of bright dots in it. All three are views for a human to read, not scores.

Why Gireta catches what single-model detectors miss

Most detectors run one classifier over the pixels and hand back a score. Gireta starts where the proof is: the signatures AI tools embed in their own files. When ChatGPT, Gemini, Firefly, Sora or Stable Diffusion have labelled an image, Gireta reads that label, confirms the verdict and names the tool.

When the labels have been stripped, four more layers run: generator fingerprints in the file, camera data, a close visual inspection of hands, text, light and texture, and forensic views of the pixels. The verdict comes with the evidence behind it, so you can show your work.

And it all runs in your browser, so you can check sensitive images without uploading them anywhere.

More ways to check

Images

AI image detectorCheck if an image is AI-generated, free. Reads Content Credentials, IPTC labels and generator settings from ChatGPT, Gemini, Midjourney and Stable Diffusion, then inspects the pixels.How to tell if an image is AI generatedTen ways to tell if an image is AI-generated, from the strongest evidence (Content Credentials, metadata, SynthID) to the visual tells in hands, text and light.Content Credentials (C2PA) checkerCheck an image's Content Credentials (C2PA) and IPTC source type online, free. See if it was made or edited with AI, and which tool made it.ChatGPT image detectorCheck if an image was made with ChatGPT, GPT Image or DALL·E. Reads OpenAI's Content Credentials and inspects the image, free and private.Gemini and Nano Banana image detectorCheck if an image was made with Google Gemini, Nano Banana or Imagen. Reads C2PA and IPTC labels in your browser and explains SynthID.Midjourney detectorCheck if an image was made with Midjourney. Reads IPTC labels and prompt text, then inspects the image for Midjourney's look. Free and private.Stable Diffusion detectorCheck if an image was made with Stable Diffusion or SDXL and read its prompt, seed, sampler and model from the file. Works with Automatic1111, Forge, Fooocus and ComfyUI.Flux image detectorCheck if an image was made with Flux. Reads ComfyUI and Forge workflows from the file, names the model, and inspects the image. Free and private.Grok image detectorCheck if an image was made with Grok on X. Reads any embedded labels and inspects the image for the tells of AI generation. Free and private.

Make AI images that stand out

Gireta puts Nano Banana, GPT Image, Seedream and every top image model in one studio, with one balance.

Start creating

Questions

How do I find the prompt used to make an AI image?

If the image came straight from Stable Diffusion, ComfyUI, InvokeAI or NovelAI as a PNG, the prompt is usually in the file: drop it in above. Images from ChatGPT, Midjourney and most apps do not store the full prompt, and any screenshot removes it.

Is error level analysis reliable?

It shows where an image was recompressed differently, which helps spot pasted regions. It has many false positives and should never be read as a verdict on its own.

Do you keep my image?

No. The file is read in your browser and never uploaded. For the visual check, a small preview (at most 1024 pixels wide) is sent, inspected and discarded.

Sources

Last updated October 19, 2026.