How AI Edit by Prompt Works
Type any editing instruction. AI grounds it on your current canvas, plans the steps, and executes via existing tools.
Try it free →Step-by-step process
- 1
Add your image
Drop or select the image you want to process — it stays on your device.
- 2
Run the model in-browser
AI Edit by Prompt runs instantly with no download — the work happens locally in a worker.
- 3
Download the json
Preview the result and download the json. Re-run with different settings anytime.
Frequently asked questions
How does it understand me?
A rule-based planner maps your request to a sequence of real editor actions; an optional in-browser LLM handles freer phrasing.
Is it free to use?
Yes — AI Edit by Prompt 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. This tool downloads nothing and runs on any device.
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?
Yes — it runs on phones and tablets too, since there is no model download.
Where can I see a step-by-step guide?
Yes — there is a full walkthrough at /how-it-works/ai-edit.