QwirbelLocal & private
Runs locally on your device

Generate AI images –
right on your own PC

Image generation in Qwirbel runs entirely on your own graphics card. No subscription, no image quotas, no uploads to a provider – whatever you create stays on your drive.

From 30 € · one-time payment, no subscription · for Windows, Linux and macOS

How it works

The essentials

Right in the conversation

You describe the image in chat, Qwirbel creates it and shows it in the same place. No switching tools.

Flux and Qwen-Image

Both model families run locally via ComfyUI. You decide which model is used.

Your own limits

Resolution and step count can be fixed – or you let Qwirbel decide.

Your own workflows

If you like, import your own ComfyUI workflows and set your own limits.

Common questions

What people ask about this

Do I need a powerful graphics card?

For image generation a GPU (NVIDIA or AMD) is clearly recommended – it largely determines how fast an image is done. Qwirbel ships presets for 8, 12, 16 and 32 GB of video memory. For text-only models a CPU works, for images it is not practical.

How many images may I create?

As many as you like. There are no quotas and no per-image billing, because no external service is involved – the limit is your hardware and your time.

Do the generated images belong to me?

The images are created on your machine and stored there. Nothing is transmitted to us or to third parties. What rights generally exist in AI images depends on the model used and applicable law – we do not advise on that.

Do I have to install ComfyUI myself?

Yes, for licensing reasons (GPL) you install ComfyUI and the models yourself. Qwirbel guides you with its “ComfyUI base” feature: the right models can be downloaded into the correct folder with one click – no terminal, no searching.

Qwirbel can do this too

All capabilities live in the same application – one purchase, one key.

Generate AI video locallyGenerate AI music locallyLocal AI voice