metadata
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- Neuron
- Inferentia
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: pixel art
widget:
- text: pixel art, a cute corgi, simple, flat colors
output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/6303f37c3926de1f7ec42d3e/SSOQ9lfB1PVhXVWJiL7Mx.jpeg
- text: pixel art, native american goddes
output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/6303f37c3926de1f7ec42d3e/tY19J3xWDlSY2hhTTHySc.jpeg
Pixel Art XL - Neuron
Downscale 8 times to get pixel perfect images (use Nearest Neighbors) Use a fixed VAE to avoid artifacts (0.9 or fp16 fix)
Need more performance?
Use it with a LCM Lora!
Use 8 steps and guidance scale of 1.5 1.2 Lora strength for the Pixel Art XL works better
from diffusers import DPMSolverMultistepScheduler
from optimum.neuron import NeuronStableDiffusionXLPipeline
pipeline = NeuronStableDiffusionXLPipeline.from_pretrained("Shekswess/pixel-art-xl-neuron", device_ids=[0, 1])
pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
prompt = "pixel, a cute corgi"
negative_prompt = "3d render, realistic"
image = pipeline(prompt=prompt, negative_prompt=negative_prompt).images[0].save("output.png")
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
Support the creators further research on Patreon or Twitter
Original Model
Precision
BFloat16 (bf16) For Matrix Multiplication Operations.