This LoRA is made from a selection of the strangest images in my catalog (58 in total).<h3 id="expect-the-unexpected.">Expect the unexpected.</h3>From early testing this LoRA does drastically different things on different prompts, I've found it most fun on simple prompts for wild effects and strange amusement. On more complex prompts and more highly tuned models it may create more subtle effects, totally deformed images or just to mostly ignore you prompt.SDXL V2: Trigger change and larger data set, it should be more flexible.

2L Weirding

Trigger change and larger data set, it should be more flexible.

2L_Weirding_2_epoch_10.safetensors

V2 Illus.

Re-up, It's still weird.SDXL versions.V1 is tends towards cartoon/CGI type weirdness.V2 is more illustrative or maybe softer.V3 I made by mistake with the dataset and captioning for the ZIT version.Illus version is made with the V1 dataset and tagging.ZIT made with a pruned version of the V2 dataset captioned instead of tagged.

Files with SHA256: d28a899e70190d42fd4f57406f4d827f98dfcdbcb015594965fd3ad8f74c78aa