This dataset was created from AI images generated using this LoRA - Pixel Art - sakuemonq Artist Style [Pony].
Many thanks to lojq. I just wanted to use it with the ILXL model...
It's a Illustrious-XL model.
You don't need to use "pixel art" in the prompt.
This lora almost generates only 8x larger pixels, so you can use sd-webui-pixelart (in Auto1111's Webui ) for 8x Downscale, to get a more pixel-perfect style.
…However, since I use ComfyUI, I use the workflow embedded in the EXIF data of the image below for pixelation and upscaling.
like this.
(including ComfyUI metadata)
to this:
(including ComfyUI metadata)