What metadata can this tool detect?

The inspector reads EXIF data, PNG text chunks (tEXt, zTXt, iTXt), XMP metadata, and IPTC fields. It automatically identifies AI-generation metadata from ComfyUI (full workflow JSON, prompt, models), Midjourney (prompt, version, job ID, seed), Stable Diffusion (model, sampler, steps, CFG scale, seed), and other tools.

Is my image uploaded to your servers?

Your file is sent to our server for metadata extraction (the extraction library requires server-side processing), but it is never stored. The file is processed in memory and immediately discarded after extraction. We do not log file contents or extracted metadata.

What file types are supported?

PNG, JPEG, WebP, and MP4 files up to 25MB. PNG files typically contain the richest AI metadata (ComfyUI workflows, Stable Diffusion parameters). JPEG files may contain EXIF and XMP data. MP4 files from tools like ComfyUI may contain embedded workflow metadata.

Why does my image show no metadata?

Some platforms strip metadata when you upload or share images. Social media sites (Twitter, Instagram, Discord) typically remove all embedded metadata. If you downloaded an image from social media, the original metadata is likely gone. For best results, use the original file directly from your AI tool.

How is this different from a regular EXIF viewer?

Standard EXIF viewers only read camera metadata fields. This inspector also parses AI-specific metadata formats: ComfyUI workflow JSON embedded in PNG chunks, Stable Diffusion parameters in the "parameters" text chunk, Midjourney prompt data, and custom node information. It understands the structure of AI generation metadata, not just raw key-value pairs.

What metadata can this tool detect?

The inspector reads EXIF data, PNG text chunks (tEXt, zTXt, iTXt), XMP metadata, and IPTC fields. It automatically identifies AI-generation metadata from ComfyUI (full workflow JSON, prompt, models), Midjourney (prompt, version, job ID, seed), Stable Diffusion (model, sampler, steps, CFG scale, seed), and other tools.

Is my image uploaded to your servers?

Your file is sent to our server for metadata extraction (the extraction library requires server-side processing), but it is never stored. The file is processed in memory and immediately discarded after extraction. We do not log file contents or extracted metadata.

What file types are supported?

PNG, JPEG, WebP, and MP4 files up to 25MB. PNG files typically contain the richest AI metadata (ComfyUI workflows, Stable Diffusion parameters). JPEG files may contain EXIF and XMP data. MP4 files from tools like ComfyUI may contain embedded workflow metadata.

Why does my image show no metadata?

Some platforms strip metadata when you upload or share images. Social media sites (Twitter, Instagram, Discord) typically remove all embedded metadata. If you downloaded an image from social media, the original metadata is likely gone. For best results, use the original file directly from your AI tool.

How is this different from a regular EXIF viewer?

Standard EXIF viewers only read camera metadata fields. This inspector also parses AI-specific metadata formats: ComfyUI workflow JSON embedded in PNG chunks, Stable Diffusion parameters in the "parameters" text chunk, Midjourney prompt data, and custom node information. It understands the structure of AI generation metadata, not just raw key-value pairs.

Free Tool

AI Metadata Inspector

Upload any AI-generated image to see all embedded metadata — workflows, prompts, models, seeds, EXIF data, and more. Free, no login required.

Drop an image here or click to browse

PNG, JPEG, WebP, or MP4 — up to 100MB

Frequently Asked Questions

Quick answers to the most common questions.

Manage AI metadata at scale

Numonic automatically extracts, indexes, and preserves the metadata behind every AI-generated asset — so the workflow, prompt, and parameters you inspected here stay searchable and reproducible across your whole library.

Start free — no credit card Read the full guide