Automatic1111 & WebUI Metadata

Stable Diffusion Image Checker

Inspect PNG and WebP images for Automatic1111 parameter chunks, positive/negative prompts, sampler settings, seeds, and checkpoint names in browser RAM.

Last updated:
What Does a Stable Diffusion Image Checker Do?A Stable Diffusion checker parses PNG text chunks (parameters) and EXIF UserComment fields created by Automatic1111, SD.Next, ComfyUI, and Forge. It extracts positive prompts, negative prompts, steps, samplers, seeds, and LoRA weights directly in browser memory without sending data to the cloud.

Stable Diffusion Parameters:

Most open-source WebUIs embed the complete generation recipe directly into PNG 'parameters' text chunks. Inspect your files locally before public sharing to verify what prompt data is visible.

Drop your image here to check AI metadata

Drag & drop a JPG, PNG, or WebP file (or up to 30 images for batch checking), or click to browse.

Browser-BasedNo Server UploadMetadata-Based

How to use the Stable Diffusion Image Checker

Checks Stable Diffusion images for the parameters text Automatic1111 and Forge save: prompt, negative prompt, seed, sampler, CFG and model.

  1. Step 1: Drop a JPG, PNG or WebP file, or up to 30 images at once for a batch check. The scan starts straight away and runs in your browser.
  2. Step 2: Read the Detailed Signal Report. Each signal is marked Detected, Not detected, Not assessed or Unsupported.
  3. Step 3: Open the PNG text chunks signal to see the parameters text with prompt, seed, sampler and model.
  4. Step 4: Optional: click “Clean Supported Metadata”. The cleaned copy is checked again before you use “Download Clean Image”.

What you'll see

  • The parameters text from PNG text chunks or EXIF, including model or checkpoint and seed.
  • This page uses the same analysis as the AI Image Checker. What changes here is the explanation for this platform or generator, not the scan itself.

How Stable Diffusion Stores Parameters

Automatic1111 and derivative tools write uncompressed text chunks containing full generation logs. While convenient for reproducing images, this metadata reveals proprietary prompts, negative prompts, and local checkpoint filenames:

Prompt & Negative

Full positive prompt text and negative exclusion tokens are preserved as plain text.

Sampler & Steps

Exact inference step count, CFG scale guidance, and denoising sampler algorithms.

Model & Hash

Local base checkpoint filename, LoRA weights, and model hashes.

Frequently Asked Questions

What metadata does Stable Diffusion embed in exported PNGs?

By default, open-source Stable Diffusion interfaces like Automatic1111 WebUI, SD.Next, and Forge write a 'parameters' text chunk into the PNG container. This chunk contains the positive prompt, negative prompt, sampling steps, sampler method (e.g. DPM++ 2M Karras), CFG scale, seed number, resolution, model hash, and checkpoint filename.

Can this tool extract the exact prompt and seed?

Yes. If the image retains its original PNG text chunks, our tool parses the parameters block and displays the exact prompt, seed, model checkpoint, and generation settings.

Can I strip the parameters chunk from my Stable Diffusion images?

Yes. Our integrated cleaner purges the parameters text chunk losslessly, keeping the image pixel-perfect while removing all generation recipe details.

Does saving as JPEG strip Stable Diffusion metadata?

Many WebUIs store parameters in EXIF UserComment when exporting JPEGs. Our checker inspects both PNG chunks and JPEG EXIF UserComment segments to detect Stable Diffusion settings across formats.

Are my proprietary models or private prompts exposed during checking?

No. All parsing runs in client-side volatile memory. No file data or prompt text is ever transmitted over the network or saved to remote databases.

When to use it

  • You want to check what a PNG reveals about your prompt and model before posting it.
  • You want to confirm a cleaned copy no longer carries the parameters text.

When another tool fits better

What the Stable Diffusion Image Checker cannot do

  • It reads metadata only. It does not analyse pixels, so it cannot tell whether an image was made by AI, and pixel watermarks such as SynthID are outside its reach.
  • “Not detected” means none of the supported fields were found. Platforms and screenshots often strip metadata, so a clean result is not proof of anything.

Which tool do I need?

Every tool runs in your browser on the same engine. Pick the one that matches what you want to do.

I want to…Use
Remove AI prompts, EXIF, GPS and Content Credentials in one goAI Metadata Remover
Remove camera details (make, model, dates)EXIF Remover
Check for and remove location dataGPS Location Remover
Remove only C2PA Content CredentialsC2PA Remover
Clean author and software details from a PDFPDF Metadata Remover
See everything a file contains, change nothingImage Metadata Viewer
Read the prompt, seed and model of an AI imageAI Metadata Viewer
Check many images for AI metadata at onceAI Image Checker
Audit every AI field in technical detailAI Metadata Checker
Check who signed an image’s Content CredentialsC2PA Checker
See what a photo reveals about youImage Privacy Checker
Change metadata instead of deleting itMetadata Editor