isGenAI.com

AI image detector by file format

TIFF AI image detector: provenance in the tag directory

TIFF stores provenance as directory tags, EXIF in a sub-IFD, XMP and IPTC as byte tags and C2PA in its own tag, and isGenAI’s AI image detector, EXIF viewer and C2PA checker accept a classic single-page TIFF up to 20 MiB and read those records from the original bytes.

Tool support and container facts as of October 2026. Updated .

Check an image nowFrequently asked questions
Code-drawn illustration for TIFF

Illustration · PNG file

  1. Signature + IHDR
  2. iTXt XML:com.adobe.xmprecord
  3. tEXt parameters
  4. tEXt prompt / workflow
  5. tEXt invokeai_metadata
  6. eXIf
  7. caBX C2PA manifest
  8. IDAT pixels
  9. IEND

AI source type declared

The file labels itself as AI-made.

IPTC DigitalSourceType such as trainedAlgorithmicMedia is read from XMP and shown with its exact value.

Check an image →
AI source type declared: where this record sits inside a PNG file and what the isGenAI report says about it. The picture is a code-drawn illustration.

Where TIFF keeps provenance

A TIFF begins with a byte-order mark and an image file directory of numbered tags. EXIF sits in a sub-IFD pointed to by tag 34665, XMP is stored in tag 700 as an XML packet and IPTC-IIM in tag 33723. The C2PA specification defines a tag for the JUMBF manifest store. Because TIFF is lossless and common in archives and print, it often keeps records that JPEG copies have lost.

AUTOMATIC1111 does not normally write TIFF, so saved prompts are not expected in this format.

What isGenAI reads from a TIFF

The AI image detector accepts classic TIFF up to 20 MiB and 40 million pixels: single page, no BigTIFF, no sub-images or pyramids. It validates the C2PA manifest, reads the IPTC source type from XMP, quotes AI statements and reports matching copies, using the original bytes rather than a transcoded copy. The EXIF viewer reads classic TIFF in your browser. The C2PA checker accepts TIFF as well.

The TIFF guide walks through a real example and explains the limits.

Converting a TIFF

Export a PNG copy for sharing; the converter writes pixels only. A multipage or pyramid TIFF must be flattened to one image in your editor before checking, and that export is a new file whose records may differ from the original.

Keep the archive TIFF as the evidence copy.

How to check a file in this format

  1. Keep the original bytes. Do not open and re-save the file in an editor before checking it.
  2. Use the tool that accepts the format: the AI image detector for PNG, JPEG, WebP, AVIF and TIFF; the C2PA checker for those plus HEIC, PDF, MP4 and MOV.
  3. Read each finding with its source field. The report names the container record it came from.
  4. If you must convert, convert a copy and compare both files with the image metadata compare tool so you know what the conversion dropped.

Check an image now

Frequently asked questions

Does isGenAI accept TIFF?

Yes. Classic single-page TIFF up to 20 MiB and 40 million pixels is accepted by the AI image detector, the EXIF viewer and the C2PA checker. BigTIFF, multipage and pyramid TIFFs are refused.

Can a TIFF carry C2PA Content Credentials?

Yes. The C2PA specification defines a TIFF tag for the manifest store, and isGenAI validates it.

Why was my TIFF refused?

It is BigTIFF, has more than one page, contains sub-images, or exceeds 20 MiB or 40 million pixels. Export a single flattened image and try again.

Does a TIFF keep an AI prompt?

Rarely. The saved-prompt formats isGenAI reads are PNG text chunks and EXIF UserComment in JPEG and WebP. A TIFF may still carry an IPTC source type or a manifest.

Sources

Container facts come from the published specifications. Tool support describes isGenAI as deployed in October 2026.