AI Image Metadata & Prompt Extractor

Read embedded AI generation metadata from original images locally in your browser: NovelAI (standard + Stealth PNG Info + V4 multi-character), Stable Diffusion WebUI / Forge, and ComfyUI workflows.

100% Browser-Local · Zero Upload Free · No Membership
Important Format & Original File Notice: Upload original unedited PNG files (or metadata-preserving original JPEG / WebP). Screenshots, social-app compressed copies, and re-saved images strip embedded chunks and Stealth PNG bits, making recovery impossible.

Drop Original NovelAI / Stable Diffusion / ComfyUI Image

Supports PNG (incl. Stealth PNG Info), A1111/Forge, ComfyUI Workflow · ≤ 30 MB · 100% local

AI art prompt examples and image comparisons

How to Use

1

1. Upload Original Unedited Image

Drop an original PNG export (or metadata-preserving JPEG/WebP). Screenshots and re-saved images strip metadata.

2

2. Automatic Format Detection

Scans PNG tEXt/zTXt/iTXt chunks, NovelAI Alpha/RGB Stealth LSB streams, ComfyUI node graphs, and A1111/Forge parameters.

3

3. Copy Prompts or Export Workflow

Copy prompts and parameters or download the raw ComfyUI workflow JSON.

Common Use Cases

  • Recovering NovelAI prompts, seeds, and V4 multi-character positions from original PNGs or Stealth PNG Info.
  • Extracting an embedded ComfyUI workflow.json from a rendered PNG.
  • Inspecting exact models, LoRAs, CFG, and samplers from A1111 / Forge images.
  • Inspect PNG generation info for positive and negative prompts, model, and seed, and recover an embedded ComfyUI workflow.

Practical Example & Limits

Example: Dropping a ComfyUI PNG extracts prompts, model, sampler params, and Workflow JSON; dropping a compressed screenshot reports that no metadata was detected.

Limits: Reads embedded metadata only (not AI guessing). Messaging/social compression and screenshots wipe metadata. Max 30 MB / 25M pixels, 100% browser-local.

Frequently Asked Questions

How do PNG chunks, Stealth PNG Info, and ComfyUI workflows differ?

A1111/Forge and standard NovelAI use PNG text chunks; NovelAI also hides gzipped JSON in pixel LSBs; ComfyUI embeds prompt and workflow graphs.

Why do compressed images show no metadata?

Platforms and image editors strip PNG chunks and re-encode pixels, permanently erasing prompts.

How are custom ComfyUI nodes handled?

Standard fields are extracted while unknown custom nodes are flagged transparently with full raw JSON preserved.

Recommended Next Tools

All 13 Tools →