AI Text-to-Image
Compose an atmospheric scene from a text prompt — procedural palette + gradient composition. 0 MB download, ~200 ms.
| Mode | Speed | Quality | Best for |
|---|---|---|---|
| Procedural composer (Lite) | Instant · 0 MB | Atmospheric, abstract scenes | Backgrounds, gradients, mood art from a prompt |
| SD-Turbo (Pro · WebGPU) | ~2–10s · ~1 GB once | Real diffusion output | Photoreal-ish single-step generation in-browser |
| BYO ONNX (Pro) | Depends on your model | Your hosted SD checkpoint | Bringing your own Stable-Diffusion ONNX endpoint |
Try a preset
See all 6 presets
Want this capability inside the main editor with layers, history, and the full AI panel?
How it works
- 1
Describe the scene
Type a prompt — colours, mood, subject, lighting. Keywords drive the palette and composition.
- 2
Generate locally
On Lite, the procedural composer builds an atmospheric image instantly with no download. On the Pro tier with a WebGPU GPU, SD-Turbo runs a real diffusion model in your browser (~1 GB, cached after the first run).
- 3
Download or refine
Download the PNG, tweak the prompt, switch tiers, or connect your own hosted SD ONNX URL (Pro) for full control.
Common use cases
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
Is this Stable Diffusion?
On the Lite tier the generator is a fast procedural composer (instant, 0 MB, fully private). On the Pro tier with a WebGPU GPU, it runs SD-Turbo — a real diffusion model — entirely in your browser, and you can also connect your own hosted SD ONNX endpoint.
What do I need to run the real diffusion model?
A WebGPU-capable browser/GPU and a Pro-tier opt-in. SD-Turbo is ~1 GB, downloaded once and cached. Without a GPU or Pro opt-in, the tool falls back to the instant procedural composer rather than failing.
Is my prompt sent anywhere?
No. Generation happens entirely in your browser on every tier — the prompt and the output never leave your device.
Is it free to use?
Yes — AI Text-to-Image 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-text-to-image.
Ready to try AI Text-to-Image?
Free, private, no signup — runs right in your browser.