---
title: flat-cartoon-qwen-image-2512
canonical_url: "https://www.modelscope.ai/models/furaidosu/flat-cartoon-qwen-image-2512"
md_url: "https://www.modelscope.ai/models/furaidosu/flat-cartoon-qwen-image-2512.md"
repository: furaidosu/flat-cartoon-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: 15
stars: 2
tags:
  - LoRA
  - text-to-image
---

# flat-cartoon-qwen-image-2512

> flat-cartoon-qwen-image-2512 - An open-source model by furaidosu on ModelScope. Model trained on synthetic dataset. The dataset was generated using Nano Banana. I showed Nano Banana 10 images created by me, and asked to generate many more replicating my…

furaidosu/flat-cartoon-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-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**: 15
- **Stars**: 2
- **Last updated**: 2026-02-17

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

---

# Flat Cartoon

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

## Overview

This model excels at generating stylized flat-cartoon characters, especially suited for storybooks and video games.

I created it to assist me in designing characters for children’s tales and for a point-and-click game I am developing as a hobby.

## Training Process

To train the model, I first showed Nano Banana about ten drawings I made myself. Then I asked it to generate new characters in that same style.
I selected the best results and refined them in Photoshop.

Using this synthetic dataset, I trained this model.

## Uses

This model produces very high-quality stylized characters on a white background, with clean shapes and no outlines.

I also frequently combine it with other LoRAs when I need outline-free stylized images — a look that many image generation models struggle to produce, as they tend to add borders around figures.

---
#### 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/tadv-char-v1-qwen-image-2512')
```
Download with Git clone
```
git clone https://www.modelscope.ai/furaidosu/tadv-char-v1-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>