Qwen Image 2512 | Precision AI Image Generator
LoraLoaderModelOnly
Qwen-Image-2512-Lightning-4steps-V1.0-fp32.safetensors
Replace with luisa-pixelart3.safetensors
ComfyUI model file · LoRA (style)
[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.
luisa-pixelart3.safetensors
The short version
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.
Install
ComfyUI/ └─ models/ ├─ … └─ loras/ └─ luisa-pixelart3.safetensors
$ 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.
Use
LoraLoaderModelOnly patches the base model with this LoRA. Put it between the model loader and the sampler.
MODEL
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.
Run it
We match workflows by the model files they load: this exact file first, then other versions of it, then workflows built for the same use, then other models from the same family.
3 workflows
These workflows load another Qwen-Image model. Select luisa-pixelart3.safetensors in their LoraLoaderModelOnly node to use it instead.
LoraLoaderModelOnly
Qwen-Image-2512-Lightning-4steps-V1.0-fp32.safetensors
Replace with luisa-pixelart3.safetensors
LoraLoaderModelOnly
Qwen-Image-Lightning-4steps-V1.0.safetensors
Replace with luisa-pixelart3.safetensors
LoraLoaderModelOnly
Qwen-Image-Lightning-8steps-V1.0.safetensors
Replace with luisa-pixelart3.safetensors
Compare
| File | Relation | Size | Best for |
|---|---|---|---|
| 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 |
Troubleshoot
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.
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.
Rather skip the setup?
Run Qwen Image 2512 in your browser on a cloud GPU. Nothing to download.
FAQ
ComfyUI/models/loras/. Then refresh the node list or restart ComfyUI so LoraLoaderModelOnly lists the file.Sources: Civitai model 10706
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.