Skip to content

Open model checks

Stable Diffusion AI Image Detector

Stable Diffusion files often leave no signed proof. Slop or Not looks for prompt or model metadata first, then visual diffusion traces, so you can check open-model images without handing uploads to a third-party AI service.

  • You can testPhotos, screenshots, product images, receipts, and profile pictures up to 8 MB.
  • ResultA probability verdict, AI score, and source details when the file carries them.
  • PrivacyDeleted the moment the check finishes. We never keep your photo.

AI detection is probabilistic. Results can vary with new AI models and evasion methods. A real photo edited with AI tools can be flagged as AI.

Online checks are deleted after processing.

What it checks

Check Open-Model Images Where Pixel Evidence Matters

Generation hints in EXIF, PNG text chunks, or app metadata

Texture and anatomy artifacts common in diffusion outputs

Visual classifier output when the file has no provenance

Good Uses

  • Checking marketplace or portfolio images
  • Screening assets before accepting them from freelancers
  • Reviewing images from open model communities

Limits to Know

  • Many Stable Diffusion workflows strip or never write metadata
  • High-quality LoRA or fine-tuned outputs may be harder to flag
  • Human edits after generation can blur the signal

FAQ

Stable Diffusion AI Image Detector Questions

Does Stable Diffusion always add metadata?

No. Some Stable Diffusion tools write prompt, model, or sampler details into image metadata, while many exports strip that data. Slop or Not checks both metadata and the pixels.

Can it identify the exact checkpoint?

No. The detector is built for authenticity checks, not exact checkpoint attribution. It reports AI likelihood and visible evidence rather than naming every model variant.

Is this useful for Midjourney too?

Use the general AI image detector for unknown generators, including Midjourney. Use Stable Diffusion detection when an open-model workflow is the likely source.