AI Suite · Understand

AI Image Q&A

Ask any question about an image and get a grounded answer. Best for structured documents, receipts, forms, and spec checks.

Model size: ~280 MB·Typical speed: ~1.8 s·Tier: lite
ModeSpeedQualityBest for
Document Q&A~2s typicalAnswers questions about an imageReceipts, forms, charts, screenshots

AI Image Q&A needs the lite AI tier (0.3 GB model). You’re currently opted into none.

Quick start

See all 6 presets

Drop images here — add as many as you like

or click to browse · processed one at a time · output text

Tier opt-in required before this capability runs.

Want this capability inside the main editor with layers, history, and the full AI panel?

How it works

  1. 1

    Add your image

    Drop or select the image you want to process — it stays on your device.

  2. 2

    Run the model in-browser

    AI Image Q&A loads its model (~280 MB) once, caches it, then runs locally in a worker. No upload.

  3. 3

    Download the text

    Preview the result and download the text. Re-run with different settings anytime.

Common use cases

Asking "what is the total?" on a receiptQuerying fields in a formReading values off a chartExtracting specific info from a screenshot

Why it’s different

100% Private

Every model runs in your browser. Your files never leave your device — nothing is uploaded to a server.

True Alpha Channel

Exports preserve a real straight-alpha transparency channel (PNG / WebP / AVIF), not a baked-on background.

Free Forever

No account, no watermark, no credits. Open the tool and use it.

Works Offline

After the model downloads once it is cached, so the tool keeps working with no connection.

FAQ

What can I ask?

Factual questions about visible content — totals, dates, labels, fields. It is strongest on documents.

Is my document uploaded?

No — the model runs locally in your browser.

Is it free to use?

Yes — AI Image Q&A is completely free. No account, no watermark, no credits, and no usage limits.

Do my files or prompts ever leave my device?

No. Everything runs locally in your browser via WebAssembly/WebGPU — there is no server that receives your files, prompts, or results.

Which browser and hardware do I need?

A modern browser. Chrome and Edge get WebGPU acceleration for the fastest results; Firefox and Safari run via WebAssembly. The model (~280 MB) downloads once, then is cached for offline use.

Can I use the results commercially?

Yes. You own everything you create — NSS makes no claim to the images, videos, or text you process or export.

Does it work on mobile?

Lightweight tools run on phones; heavier models prefer a desktop with a GPU. The tool picks the best path for your device and falls back gracefully where needed.

Where can I see a step-by-step guide?

Yes — there is a full walkthrough at /how-it-works/ai-ask-image.

Ready to try AI Image Q&A?

Free, private, no signup — runs right in your browser.