---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: pixel art
widget:
- text: pixel art, a cute corgi, simple, flat colors
datasets:
- fka/awesome-chatgpt-prompts
language:
- aa
metrics:
- accuracy
library_name: adapter-transformers
pipeline_tag: text-classification
---
# Pixel Art XL
## Consider supporting further research on [Patreon](https://www.patreon.com/user?u=29466374) or [Twitter](https://twitter.com/nerijs)

![F1hS8XHXwAQrMEW.jpeg](https://cdn-uploads.huggingface.co/production/uploads/6303f37c3926de1f7ec42d3e/SSOQ9lfB1PVhXVWJiL7Mx.jpeg)
![F1hS489X0AE-PK5.jpeg](https://cdn-uploads.huggingface.co/production/uploads/6303f37c3926de1f7ec42d3e/tY19J3xWDlSY2hhTTHySc.jpeg)


Downscale 8 times to get pixel perfect images (use Nearest Neighbors)
Use a fixed VAE to avoid artifacts (0.9 or fp16 fix)

### Tips:
Don't use refiner

Works great with only 1 text encoder

No style prompt required

No trigger keyword require

Works great with isometric and non-isometric

Works with 0.9 and 1.0

#### Changelog
v1: Initial release