What Is It?
This LoRA is trained to emulate prism photography - creating artful distortions similar to when a photo is taken with a prism. It may lean towards portrait photography.
How To
All generations in the samples are used with this LoRA applied by itself, and a face detail node. Generated using euler/beta @ 27 steps, CFG 2.5 for Flux and CFG 4.0 for Krea. I find the lora applies more consistently with a prompt that begins with "a photo taken through a prism, lens distortions and kaleidoscope effects, ", but as always experimentation is key.
on the left w/lora on the right without:
a photo of a woman posing under a tree in spring, prismatic aberrations as if taken through a prism
Suggested Weight: 0.4-1.0
No effort was made to train NSFW concepts.