Tigger word: L1ghtm4k3r
Weights : 1 -1.5
This is lora was designed to replicate some concept art that I like, the data set mostly focused on 'studio style lighting' and dramatic poses.
Some of the features can be triggers using prompts like "Dramatic shadows, floating hair, rainbow lighting, chromatic aberration" etc..
I have tried it with several illustrious models and it seem to works well flat anime style as well as more 3d styles (though it intended more for the former, I shall update more resources that work with it as I discover them myself).
I am yet to test it working with other loras but give it a shot see what happens :D and thanks for trying our the lora.
Description
FAQ
Comments (6)
This LoRA better pop, because it's absolutely stunning. Great job on this one. It also brings a real strong 80's retro vibe that just oozes at the seams with style.
Thank you, mostly made this for myself because i like playing around with light/colors in my generations, I have a new version of it in the works that expands on some of the limitations, mainly the "same face" issue in female subjects. ill hopefully post it in a few days.
@purplelady looking forward to it! One way, in the meantime, people can combat that is to simply refine with a totally different model while reducing the weight of the LoRA a bit.
@TurinBjorn I already have fixed it i just wanted to add more effects etc. so kept training more version :D