Version 2 of the NeurodyneXL LoRA!<hr />After months of accruing Buzz, I finally had enough to train this new version on a larger dataset with higher parameters &amp; a custom checkpoint!<hr />This post will be temporary until I can get V2 on the same page as V1. I did not initially understand how to add a new version to an existing model, but even though I think I've figured it out, Civit is giving me trouble with the upload.

NeurodyneXL - Temp V2 Showcase

Version 2 uses a dataset almost twice the size of V1, trained several times longer at maximum resolution on the Juggernaut XL Ragnarok Checkpoint (see suggested resources below).

NeurodyneXL.safetensors

SDXL LoRA based on the wonderfully monstrous art of Neurodyne!<hr />This is my first attempt at training a LoRA externally with Civit, as I've never gotten a trainer to work locally on my mid-tier hardware (my PC already struggles just as a local generator). Unfortunately, I don't have much Buzz to experiment with, so it may be a while before this gets updated or something different is published.<hr />Version 2 is now available after months of accruing Buzz. I finally had enough to train this new version on a larger dataset with higher parameters &amp; a custom checkpoint!

NeurodyneXL

Version 2: Uses a dataset almost twice the size of V1 (120 images), trained to 15 Epochs at 1024px resolution on the Juggernaut XL Ragnarok Checkpoint (see suggested resources below).

Files with SHA256: 88b587bcfce86f0ed43411317d48339e751117d7de1078912b9c37b87f6466e6