<h3 id="vpred-models-are-trained-with-v-parameterization-so-they-will-only-work-on-vpred-models-like-noob-ai-xl-vpred-or-obsession-etc.-ipi28t2ui">VPred models are trained with V-Parameterization so they will only work on VPred models like NOOB-AI-XL-vpred or Obsession, etc.</h3>This is a DoRA so make sure to have your stuff somewhat updated<h3 id="remember-to-check-out-the-artist.-ce3x6g227">Remember to <a target="_blank" rel="ugc" href="https://linktr.ee/gaikiken">check out the artist</a>.</h3>Will remove if requestedNoobAI:For VPred version stick to NoobAI-vpred. It drastically improves style strength compared to Obsession. <a target="_blank" rel="ugc" href="https://civarchive.com/models/1347947/r3mix-illu01nai-v-pred">r3mix </a>can somewhat maintain the style. You can use <a target="_blank" rel="ugc" href="https://civarchive.com/models/1347947/r3mix-illu01nai-v-pred">r3mix</a> to generate the initial image, and then switch to NoobAI-vpred in Hires.fix pass.Turned out pretty good. Used a completely different dataset this time. EPS version is stronger than VPred, though it produces a foil effect on hair sometimes.Pony:It is what it is. Made super quickly using tags from rule34.xxx. Seems to work.(FOR VERSION 1.0) Don't use bright VAEs to not get flashbanged for now. Also, the style doesn't really seem strong enough... Might also curate the tags more and remove many duplicate images (there were a lot) :))Always appreciate seeing your generations tooI still don't know what I'm doing with training settings :3

Gaikiken (Artist Style) | NAI-XL/Illustrious | PonyXL | DoRA

New dataset from Pony version. Overall, it's pretty good, though it creates a weird rainbow foil effect on hair sometimes... the VPred model doesn't do that despite being trained with the same settings (except for v-param and ZT-SNR of course).

Files with SHA256: e33937417f18b251ba969d70acca5074c2714f7af2c2d0181296a6db02495c95