ComfyUI
Full workflow graphs
Reads the embedded node workflow and resolves the effective prompt, model, sampler and seed from the graph.
Free Tool
View Stable Diffusion & ComfyUI metadata from any PNG.
Drop a generated PNG below to see its prompt, negative prompt, model, sampler, seed and full workflow — parsed instantly in your browser. Your image is never uploaded anywhere.
Got a whole folder of these? Image MetaHub searches your entire local library the same way — for free.
Drag & drop a PNG here
or click to choose a file — nothing leaves your device
Raw metadata (JSON)
Got a whole folder of these?
Image MetaHub searches your entire local library by prompt, model, LoRA and seed — instantly, without uploading anything.
ComfyUI workflows using very custom or "bridge" nodes (widget-relay helpers, uncommon sampler/scheduler
selectors, etc.) may only resolve partially — the raw JSON above always has everything that was embedded.
Hit a workflow that should have worked?
Open a GitHub issue
with the file attached and we'll take a look. For guaranteed complete, structured metadata on every save, use the
MetaHub Save Node
in your ComfyUI workflow instead of the standard Save Image node.
Works with every major AI image generator.
The same parser that powers Image MetaHub's desktop library — reads embedded PNG metadata, no guessing.
Automatic1111 / Forge
Standard parameters block
Prompt, negative prompt, steps, CFG scale, sampler, seed, size, model hash and LoRAs.
InvokeAI
Structured JSON metadata
Positive/negative prompt, model, VAE, scheduler and generation mode.
More formats
SwarmUI, Fooocus, SD.Next, Easy Diffusion, Draw Things
And Image MetaHub's own MetaHub Save Node payload for ComfyUI.
Frequently asked questions
Is this a ComfyUI metadata viewer?
Yes. Drop any PNG saved by ComfyUI and this tool reads the embedded workflow JSON to show the resolved prompt, model, sampler, seed and full node graph — entirely in your browser, nothing uploaded. Workflows built on very custom or "bridge" nodes may only resolve partially, but the raw embedded JSON is always shown in full and downloadable as workflow.json.
Is this a Stable Diffusion metadata viewer?
Yes. It reads the parameters block that Stable Diffusion tools like Automatic1111, Forge, InvokeAI and SD.Next embed in PNG files — prompt, negative prompt, model, sampler, steps, CFG scale and seed — instantly, with nothing uploaded.
What if my ComfyUI workflow isn't fully parsed?
The raw metadata panel always shows everything that was embedded in the file, and you can download the complete workflow.json. If a workflow should have resolved and didn't, open a GitHub issue with the file attached — custom node support gets added from real examples.
Does this upload my image anywhere?
No. The PNG is read and parsed entirely in your browser using JavaScript. It's never sent to a server.
What is PNG metadata for AI images?
Stable Diffusion, ComfyUI, A1111, InvokeAI and Forge embed the prompt, model, seed, sampler and (for ComfyUI) the full node workflow directly inside the PNG's text chunks.
Why does it say no metadata was found?
Some tools strip metadata on export, and social/messaging apps often re-encode images and remove it. Screenshots never had it to begin with.
Save Image node vs. the MetaHub Save Node?
ComfyUI can reopen the workflow from any PNG it saved — that's built in, not specific to any node. The MetaHub Save Node additionally writes clean, pre-resolved fields (prompt, model, seed, tags, notes, analytics) so tools don't have to reverse-engineer the graph.
Came here looking for "PNG Info"?
This is the same parser as the PNG Info Online tool, framed around Automatic1111's classic PNG Info tab instead of ComfyUI/Stable Diffusion metadata directly. Use whichever page matches what you searched for — they read the same files the same way.
Got a folder full of these?
Image MetaHub searches your whole local library by prompt, model, LoRA and seed — instantly, without uploading anything. Free to start.