> Canonical page: https://www.mahieu.nl/en/applications/stijlbeeld/

- [Home](https://www.mahieu.nl/en/)
- [My applications](https://www.mahieu.nl/en/applications/)
- Stijlbeeld

Experiment · AI image generation

# Stijlbeeld: AI images with a consistent style

Stijlbeeld explores a practical question in AI image generation: how do you create a series of illustrations with a recognisable visual style? A model I trained myself provides the foundation.

- Website [stijlbeeld.nl](https://stijlbeeld.nl/) (private access)
- Status experimental application, private access
- At its core a custom style model, a defined visual style and controlled variations
- Output PNG, WebP and SVG (vector)

[

![Stijlbeeld’s gallery of twelve illustrations in a consistent visual style, created from prompts, photographs and uploads](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld.webp)

](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-groot.webp)

What it does

## From an idea or photograph to an illustration in one visual style

[

![Stijlbeeld’s input screen, with tabs for a prompt, URL, image upload and camera, plus format and variant options](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-invoer.webp)

](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-invoer-groot.webp) The input screen: prompt, URL, upload or photograph, with format, variant and advanced settings.

Stijlbeeld turns ideas and photographs into illustrations in a predefined style. The experiment focuses on comparing and choosing variations that work together.

Output is available as PNG and WebP, as well as SVG vector files that scale without loss of quality, from web icons to print.

Getting started

## Four ways to begin

You do not need a detailed brief to get started. Stijlbeeld accepts a plain-language prompt, a URL for inspiration, an uploaded image or a photograph taken with the camera. A built-in improvement button helps refine the prompt, with advanced settings for those who want more control. The complexity stays behind straightforward controls. These screenshots come from the application itself; select an image to enlarge it.

Output

## Four variations to choose from

[

![Stijlbeeld’s output screen: four variations on the same brief in one style, each with PNG and SVG download buttons](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-varianten.webp)

](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-varianten-groot.webp) Four variations on one brief, each available to download as PNG or SVG.

Each request produces up to four variations in the same style. You can choose the image that best expresses your idea without having to generate another set. Each variation can be downloaded as PNG or SVG and published to the shared gallery.

Style consistency

## One visual style, whatever the source

[

![Stijlbeeld’s generation progress view, showing the model loading and the variations being built step by step](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-voortgang.webp)

](https://www.mahieu.nl/assets/img/ai/toepassing-stijlbeeld-voortgang-groot.webp) Generation on my own hardware: the model loads and builds the variations step by step.

The gallery includes examples made from prompts, photographs and uploads, showing how different sources can be interpreted through the same style model.

The technology

## My own model and hardware

**A style model I trained myself.** The visual style is learnt by the model itself. Using around two hundred reference images, I trained a custom LoRA style model on a rented NVIDIA H200 cloud GPU. This technically demanding process embeds the visual style in the model.

**Generation on my own hardware.** Images are generated on my own NVIDIA RTX 5090 hardware. The inputs, outputs and model remain under my control.

Why it matters

## What the experiment demonstrates

Stijlbeeld explores how a custom style model and consistent settings can support a recognisable visual style. Image quality and consistency still depend on the training material, the input and human selection.

## Verifiable evidence

### What the application demonstrates, and its limits

- **Problem:** Generated images can vary considerably in style, making it difficult to maintain a recognisable series for communications.

- **Approach:** A custom style model and fixed generation settings turn prompts, URLs, uploads or photographs into controlled variations.

- **Status:** An experimental application with private access. Generation runs on my own hardware.

- **Demonstrable result:** Each request produces up to four variations in a consistent visual style, with PNG, WebP and SVG output.

- **Limitations:** The application is not publicly accessible. Image quality and consistency depend on the training material, input and human selection.

- **Last reviewed:** August 2026

Contact

## Questions about Stijlbeeld or the technology behind it?

You’re welcome to get in touch.

[Get in touch](https://www.mahieu.nl/en/contact/)

Prefer to contact me directly? Call [+31 6 1400 2312](tel:+31614002312) or email [mwd@mahieu.nl](mailto:mwd@mahieu.nl).

Last updated: 2026-10-14.