---
title: flat-cartoon-t21-qwen-image-2512
canonical_url: "https://www.modelscope.ai/models/furaidosu/flat-cartoon-t21-qwen-image-2512"
md_url: "https://www.modelscope.ai/models/furaidosu/flat-cartoon-t21-qwen-image-2512.md"
repository: furaidosu/flat-cartoon-t21-qwen-image-2512
last_updated: 2026-02-17
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-2512
base_model_relation: adapter
parameters: 118.0M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
supports_inference: txt2img
downloads: 13
stars: 1
tags:
  - LoRA
  - text-to-image
---

# flat-cartoon-t21-qwen-image-2512

> flat-cartoon-t21-qwen-image-2512 - An open-source model by furaidosu on ModelScope. I trained this LoRA with the goal of expanding representation within the model I use to illustrate children’s stories for kids in my family and among friends, including…

furaidosu/flat-cartoon-t21-qwen-image-2512 is a 118.0M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from Qwen/Qwen-Image-2512. and supports online inference (txt2img).

- **Repository**: furaidosu/flat-cartoon-t21-qwen-image-2512
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 118.0M
- **Base model**: Qwen/Qwen-Image-2512
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 13
- **Stars**: 1
- **Last updated**: 2026-02-17

Source: https://www.modelscope.ai/models/furaidosu/flat-cartoon-t21-qwen-image-2512

---

![Portada](https://www.modelscope.ai/models/furaidosu/flat-cartoon-t21-qwen-image-2512/resolve/master/images/portada.webp)

## Overview

This model generates images in a flat cartoon style. It is specifically trained to include respectful representations of children and adults with Down syndrome.

## Motivation

The motivation for creating this model comes from frequently writing stories for children in my family and among friends — stories in which they can see themselves reflected more clearly than in the books currently available to them.

When illustrating these stories, I found it difficult to generate images of children with Down syndrome using existing image generation models such as Qwen-Image, Flux, and others.

## Training Process

To train this model, I first developed a model capable of generating photographic images of people with Down syndrome.

Then, using that LoRA for Qwen-Image-2512 together with another LoRA I trained for the same base model (Flat Cartoon style: https://www.modelscope.ai/models/furaidosu/flat-cartoon-qwen-image-2512
), I generated a large and diverse set of flat cartoon images depicting children and adults with Down syndrome.

Finally, this curated dataset was used to train the present model.

## Intended Use

This model produces images suitable for respectfully illustrating children’s stories. It may be useful for educators and family members who wish to create inclusive stories for children, helping them feel represented and included.

--------------------------------
#### Model files may be downloaded with ModelScope SDK or through git clone directly.

Download with ModelScope’s Python SDK
```bash
#Install ModelScope
pip install modelscope
```
```python
#Download with ModelScope’s Python SDK
from modelscope import snapshot_download
model_dir = snapshot_download('furaidosu/flat-cartoon-t21-qwen-image-2512')
```
Download with Git clone
```
git clone https://www.modelscope.ai/furaidosu/flat-cartoon-t21-qwen-image-2512.git
```

<p style="color: lightgrey;">If you are a contributor to this model, we invite you to promptly update the model card content according to <a href="https://www.modelscope.ai/docs/contribute/model-integration" style="color: lightgrey; text-decoration: underline;">the model contribution documentation</a>.</p>