# luisa-pixelart3.safetensors

> [LuisaP] Pixel Art LoRA for Qwen-Image (V2) · Pixel-art style LoRA for Qwen-Image

luisa-pixelart3.safetensors is the “QWEN! V2” version of luisa_caotica’s pixel art refiner LoRA, trained for the original Qwen-Image model. Put it in ComfyUI/models/loras and load it with LoraLoaderModelOnly after your Qwen-Image model.

The Civitai listing now leads with a MOSS-Image version. This file is the Qwen version from September 2025; it does not work on MOSS-Image or SDXL.

## Facts

- **Type:** LoRA (style)
- **Format:** Safetensors
- **Size:** 295 MB (295,146,176 bytes)
- **SHA256:** b7a8905ff898756cec1b59aff411773aece222257dff33fe17baf0b68714c14b
- **ComfyUI folder:** ComfyUI/models/loras/
- **Loader node:** LoraLoaderModelOnly
- **License:** See Civitai listing
- **Released:** Sep 17, 2025 · Civitai upload

## What is luisa-pixelart3.safetensors?

luisa_caotica has published pixel-art LoRAs under one Civitai listing since the SD 1.5 days, adding a version for each new base model: SD 1.5, Qwen-Image, Z-Image Turbo and MOSS-Image. luisa-pixelart3.safetensors is the second Qwen-Image version (“QWEN! V2”), published September 17, 2025.

It steers Qwen-Image toward pixel art. LoRAs only work with the base model they were trained on, so pick the version that matches your model: this file for Qwen-Image, pixel-art-moss-image-sft-epoch-10 for MOSS-Image.

## Download and install

- [Civitai · [LuisaP] Pixel Art Refiner](https://civitai.com/models/10706?modelVersionId=2225295) · saves as `luisa-pixelart3.safetensors` · The “QWEN! V2” version. Sign-in may be required.

```sh
cd ComfyUI/models/loras
# Download it from Civitai · [LuisaP] Pixel Art Refiner, then save it here as:
# luisa-pixelart3.safetensors
sha256sum luisa-pixelart3.safetensors
# b7a8905ff898756cec1b59aff411773aece222257dff33fe17baf0b68714c14b
```

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

## How to load it in ComfyUI

LoraLoaderModelOnly patches the base model with this LoRA. Put it between the model loader and the sampler.

- **Base model:** Use the original Qwen-Image (20B) diffusion model, not Qwen Image 2.1 or MOSS-Image.
- **Trigger:** Describe the result as pixel art in the prompt; start the LoRA strength at 1.0.

## Workflows: Uses other Qwen-Image models

These workflows load another Qwen-Image model. Select luisa-pixelart3.safetensors in their LoraLoaderModelOnly node to use it instead.

- [Qwen Image 2512 | Precision AI Image Generator](https://www.runcomfy.com/comfyui-workflows/qwen-image-2512-in-comfyui-realistic-visual-synthesis-workflow)
- [Reallusion AI Render | 3D to ComfyUI Workflows Collection](https://www.runcomfy.com/comfyui-workflows/reallusion-ai-render-3D-workflow-collection)
- [Qwen-Image Lightning | 8-Step Speed Boost](https://www.runcomfy.com/comfyui-workflows/qwen-image-lightning-comfyui-workflow-8-step-fast-generation)

## Same file, other names, and alternatives

- `luisa-pixelart3.safetensors` · This page · Qwen-Image V2 · 295 MB · Qwen-Image
- `qwen_thepixel.safetensors` · Same listing · Qwen-Image V1 · 295 MB · Earlier Qwen version
- `pixel-art-moss-image-sft-epoch-10.safetensors` · Same listing · MOSS-Image · 129 MB · MOSS-Image SFT
- `zimage_experimental_pixelart.safetensors` · Same listing · Z-Image Turbo · 21.3 MB · Z-Image Turbo

## Common errors and fixes

### Value not in list: lora_name: 'luisa-pixelart3.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/loras. Usually the file is missing, sits in a different folder.

Fix: Move the file into ComfyUI/models/loras/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

### SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 295,146,176 bytes and that its SHA256 matches the value above. Download it again from Civitai · [LuisaP] Pixel Art Refiner if not.

## FAQ

### Where do I put luisa-pixelart3.safetensors in ComfyUI?

In `ComfyUI/models/loras/`. Then refresh the node list or restart ComfyUI so LoraLoaderModelOnly lists the file.

### Which ComfyUI node loads luisa-pixelart3.safetensors?

[LoraLoaderModelOnly](/comfyui-nodes/ComfyUI/lora-loader-model-only). It is built into ComfyUI, so no custom nodes are needed.

### Can I use luisa-pixelart3.safetensors commercially?

Civitai’s listing allows commercial use, including selling generated images and the LoRA. Qwen-Image’s own license applies to the base model.

## Sources

- [Civitai model 10706](https://civitai.com/models/10706)

Canonical page: https://www.runcomfy.com/comfyui-workflows/model-files/luisa-pixelart3.safetensors
