README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    A cheerful corgi, wearing a vibrant party hat with colorful streamers, and a
    pair of oversized, reflective sunglasses. The corgi's tongue is playfully
    sticking out, and its ears are perked up with excitement. The background is
    filled with festive decorations, including balloons and confetti in a
    variety of bright colors. The overall scene captures a lively and joyful
    celebration, with the corgi at the center, radiating energy and fun.
  output:
    url: images/ComfyUI_00038_.png
- text: >-
    A refined, noblewoman standing gracefully in a lush garden. She has an
    elaborate updo adorned with delicate pearls and flowers, and she wears a
    flowing, pastel-colored gown with intricate lace details. Her serene
    expression is highlighted by soft, natural lighting. The background features
    blooming roses and a classical stone fountain, creating a sense of timeless
    elegance and tranquility.
  output:
    url: images/ComfyUI_00042_.png
- text: >-
    A bearded inventor with wild, curly hair, standing confidently in his
    steampunk workshop. He wears brass goggles on his forehead, a leather apron
    over a white shirt with rolled-up sleeves, and fingerless gloves. His hands
    are slightly stained with grease, and he holds a small, intricate mechanical
    device. The background is cluttered with gears, blueprints, and tools,
    illuminated by the warm glow of oil lamps, giving the scene a creative,
    industrious atmosphere.
  output:
    url: images/ComfyUI_00047_.png
base_model: stabilityai/stable-diffusion-3.5-large
instance_prompt: pixel art
license: apache-2.0
---
# Pixel Art 3.5L

<Gallery />

## Model description 

LoRa aimed to produce pixel perfect and grid aligned 128x128 outputs for Stable Diffusion 3.5 Large.

## Tips
- The best checkpoint is **pixel-art-3.5L-v2_000000300.safetensors**
- Use it with Comfy, make sure you have the latest version
- Add &quot;pixel art&quot; at the start of your prompt to get better results
- Strength 1.0 is the best but you can decrease it to 0.8 and still get better results

## Trigger words

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


## Download model

Weights for this model are available in Safetensors format.

[Download](/nerijs/pixel-art-3.5L/tree/main) them in the Files & versions tab.