---
title: pixel_spritesheet_4walk_combat_32x48_v1
canonical_url: "https://www.modelscope.ai/models/svntax/pixel_spritesheet_4walk_combat_32x48_v1"
md_url: "https://www.modelscope.ai/models/svntax/pixel_spritesheet_4walk_combat_32x48_v1.md"
repository: svntax/pixel_spritesheet_4walk_combat_32x48_v1
last_updated: 2026-03-18
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Qwen/Qwen-Image-Edit-2511
base_model_relation: adapter
parameters: 294.9M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - Pytorch
supports_inference: img2img
downloads: 44
stars: 1
tags:
  - LoRA
  - text-to-image
---

# pixel_spritesheet_4walk_combat_32x48_v1

> pixel_spritesheet_4walk_combat_32x48_v1 - An open-source model by svntax on ModelScope. A pixel art spritesheet LoRA for small 32x48 characters, with animation frames for walking up/down/left/right, 2 attack frames with an arm swing, and 1 hurt frame. Images…

svntax/pixel_spritesheet_4walk_combat_32x48_v1 is a 294.9M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from Qwen/Qwen-Image-Edit-2511. and supports online inference (img2img).

- **Repository**: svntax/pixel_spritesheet_4walk_combat_32x48_v1
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 294.9M
- **Base model**: Qwen/Qwen-Image-Edit-2511
- **Online inference**: img2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 44
- **Stars**: 1
- **Last updated**: 2026-03-18

Source: https://www.modelscope.ai/models/svntax/pixel_spritesheet_4walk_combat_32x48_v1

---

### You can access the model files in the "Files and versions" tab.
#### Model files may be downloaded with ModelScope SDK or through git clone directly.

### LoRA Description

A pixel art spritesheet LoRA for small 32x48 pixel characters, with animation frames for walking up/down/left/right, 2 attack frames with an arm swing, and 1 hurt/damaged frame.

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('svntax/pixel_spritesheet_4walk_combat_32x48_v1')
```
Download with Git clone
```
git clone https://www.modelscope.ai/svntax/pixel_spritesheet_4walk_combat_32x48_v1.git
```

### How to use

Use a reference image of a character, and make sure the output image is 768x768 because that's the size of the spritesheets used in training.

Prompt:
```
Create a pixel art spritesheet of the character in the image. Keep the appearance the same. The spritesheet is a 6 by 4 grid of four rows and six columns of frames - First row is 3 walking frames facing down, 2 arm swing attack frames facing down, and 1 hurt frame facing down. Second row is 3 walking frames facing left, 2 arm swing attack frames facing left, and 1 hurt frame facing left. Third row is 3 walking frames facing right, 2 arm swing attack frames facing right, and 1 hurt frame facing right. Fourth row is 3 walking frames back view facing up, 2 arm swing attack frames back view facing up, and 1 hurt frame back view facing up.
```

### How to get pixel-perfect images

To get pixel-perfect images, downscale by a factor of 4. So 768x768 output images should downscale to 192x192. Using k-centroid scaling, for example, works well.

<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>
