LoRA based on more or less weird anime images with people and objects coming apart or being segmented; but not in a gory way.

Disclaimer: You probably won't automagically get great results; you need to prompt what you want to see. Flux is your friend, just tell it what to do - or tell ChatGPT to write a prompt for you.

This LoRA is a sibling of Flux Bing Anime Lucid. They are both trained on 80-90s style anime images generated with Dall-E in Bing, so they can do pretty cool/weird things when combined.

All example images use the aiai-Glimra stylizer LoRA

Trigger is aiai-4p4rt, but works without it.