Less Details in Pixel Art (minit) for Stable Diffusion 3.5 Large版本v1s6000 (ID: 1050265)

Trained a LoRA on a bunch of screenshots from Minit which turned out to be really useful for reducing the palette and details in a computationally expensive but pretty impressive way. I also greatly enjoy the "MMDiT" style dithering it can occasionally produce.

My only prompting recommendation is to use pixel art in the positive prompt! ?

You can also make it hallucinate horrible 1-bit mess that looks suspiciously almost like Minit..

This image appears to be a screenshot from the indie video game "Minit featuring an underground cave-like environment with black walls and minimal lighting.

It wasn't explicitly trained with text in mind, but occasionally it manages some half-decent attempts with zer0int/CLIP-GmP-ViT-L-14

Don't forget to show me the weird stuff you make by clicking the + Add Post button down in the Gallery, and just maybe, give a thumbs up if you are up to it!

描述:

训练词语: