Shekswess/pixel-art-xl-neuron

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

Model

Precision

BFloat16 (bf16) For Matrix Multiplication Operations.