---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- qwen-image
- qwen-image-2512
- watercolor-anime
widget:
- output:
    url: images/preview_01.png
  text: watercolor anime of a bamboo grove beside a misty river and distant mountains, transparent watercolor washes, pale paper texture, soft ink linework
- output:
    url: images/preview_02.png
  text: watercolor anime of a blue jay on a branch, transparent watercolor washes, pale paper texture, soft ink linework
- output:
    url: images/preview_03.png
  text: watercolor anime of an array of butterflies of different colors forming to form the number 5, transparent watercolor washes, pale paper texture, soft ink linework
- output:
    url: images/preview_04.png
  text: watercolor anime of a child flying a kite beside green rice fields and bright clouds, soft paper grain, airy watercolor wash
- output:
    url: images/preview_05.png
  text: watercolor anime of a paint brush palette dropping its colors
- output:
    url: images/preview_06.png
  text: watercolor anime of a young woman with long black hair under a red umbrella on a rainy bamboo village street, pale paper texture, soft ink linework
base_model: Qwen/Qwen-Image-2512
instance_prompt: watercolor anime
license: apache-2.0
---
# WATERCOLOR ANIME LORA FOR QWEN IMAGE

<Gallery />

## Model description

# Watercolor Anime - QWEN IMAGE 2512

## Acknowledgment

Trained remotely on Modal using `Qwen/Qwen-Image-2512` as the base model. This repository contains the LoRA adapter only and does not redistribute the base model.

## Description

A LoRA model fine-tuned to generate watercolor anime illustrations with soft ink linework, pale paper texture, transparent washes, muted palettes, and quiet storybook-like scene mood.

The model is best for rainy streets, bamboo landscapes, moonlit rivers, quiet train scenes, rice fields, and gentle character illustrations.

## Trigger words

Use `watercolor anime` to activate the LoRA style/concept.

## Usage

I recommend using this LoRA with **Qwen Image 2512** in ComfyUI, Diffusers, Draw Things, or another compatible LoRA loader.

Recommended starting settings:

- LoRA weight: `0.80-0.95`
- Steps: `25-32`
- Guidance: `3.0-3.3`
- Shift: `2.83`
- Sampler: `FlowMatch` if available, otherwise `UniPC Trailing`
- Resolution: `1024 x 1024`

Preview images use the `images/preview_01.png` through `images/preview_06.png` naming pattern.

Example prompt:

```text
watercolor anime of a quiet bamboo path after rain, pale paper texture, transparent watercolor washes, soft ink linework, muted colors
```

### Training Data

This model was trained on 120 GPT-generated watercolor anime images.

### File

`qwen_image_2512_watercolor_anime_lora.safetensors`

SHA256:

```text
cba3a0f12b9a1a30cf5150256f48f6dd20ca6728ec469f41af906182f15be539
```

## License

This model is licensed under the **Apache License 2.0**.

---

## Trigger words

You should use `watercolor anime` to trigger the image generation.

## Download model

Download the model from the Files & versions tab.