---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
    portrait of a cute happy corgi wearing a party hat, pastel color background,
    pixel art style
  parameters:
    negative_prompt: realistic, 3d render, photo
  output:
    url: images/descarga (25).png
- text: >-
    portrait of a cute happy corgi wearing a party hat, pastel color background,
    pixel art style
  parameters:
    negative_prompt: realistic, 3d render, photo
  output:
    url: images/descarasdasga.png
base_model: stabilityai/stable-diffusion-3-medium-diffusers
instance_prompt: pixel art style
license: cc-by-nc-4.0
---
# Pixel Art Medium 128 v0.1

<Gallery />

## Model description 

This is an early version of &quot;Pixel Art Medium&quot; for SD3 Medium. 
Outputs 128x128 pixel art, grid-aligned images.

## Tips
- Always use &quot;pixel art style&quot; at the end of the prompt
- Use &quot;realistic, 3d render, photo&quot; as the negative prompt to get better results
- Add &quot;flat, simple colors&quot; to the prompt for better styling
- Sample images generated using the default Diffusers pipeline at 1.0 strength, default sampler, 28 steps and CFG of 5.0

**Only tested on Diffusers, Comfy support needs to be tested**


## Trigger words

You should use `pixel art style` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/nerijs/pixel-art-medium-128-v0.1/tree/main) them in the Files & versions tab.


## How to use
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6303f37c3926de1f7ec42d3e/aBFWDTgo0oNDRH3ZgXp9k.png)