Hypnosis Pendulum / Coin on String | SDXL Pony Diffusion v6 LoRA

👇 👀 Read me, read me, read me! 👇 👀

This is the SDXL version of my Hypnosis Pendululm / Coin on String LoRA built for PonyDiffusion v6 XL. In my opinion, it works much better than SD 1.5 with my previous LoRA even though this being my very first SDXL LoRA. Despite what the example image metadata says, I used AutismMix Confetti to generate all these images and SeraphMix v4.1 to upscale them.

This LoRA does not have an activation tag, but I suggest using (pendulum, hypnosis) to have the LoRA work best. Use only pendulum or coin_on_string in your prompt, not both. Using both will likely yield oddities. I like using pendulum more than coin_on_string because coin_on_string seems more likely to add phantom string and get jumbled up with lines in the background. If you plan to use @_@ or spiral_eyes make sure you also specify an eye color, otherwise it will come out weird. Not sure if that's a PonyDiffusion v6 thing or a thing with this LoRA.

A weight of 1.0 seems to work just fine. You can probably go +/- 0.3 without much issue, but from my testing it's unnecessary.

Example prompt: score_9, score_8_up, score_7_up, source_anime, BREAK, ((pendulum), hypnosis), 1girl, from above, cowboy shot, sitting, open mouth, blue hair, pink eyes, spiral eyes, (sleepy), ((unaware, dazed), arms at sides), cheerleader uniform, facial, ??? on body, (gym storeroom), highres, absurdres, masterpiece, best quality, ultra-detailed, illustration, colorful, best quality, ray tracing, (extremely detailed), soft lighting, tracing, soft shadows, detailed face, textured skin, <lora:StS-Pendulum-Hypnosis-Coin-SDXL:1>

Changelog:

Fed. 24, 2024 - Initial release