<h1 id="gurilamash-version-2-e3797fzxk">GurilaMash Version 2</h1>block level merge to produce better lora compatibility.Thanks to Leosam for the idea to merge the SPO lora. It is a welcome addition.<h3 id="version-2-is-incrementally-more-flexible-than-v1.-to-be-clear-gurilamash-is-not-an-attempt-at-a-general-purpose-model.-it's-scientifically-formulated-to-make-porn.-that-is-what-it-does.-it-does-it-very-well.-any-other-use-is-incidental.-vjq8srbli">Version 2 is incrementally more flexible than V1. To be clear, GurilaMash is not an attempt at a general purpose model. It's scientifically formulated to make porn. That is what it does. It does it very well. Any other use is incidental.</h3><h3 id="i-have-about-20-lora's-already-trained-on-this-model.-i-will-try-to-upload-at-least-1-a-day.-6jp3uxg12">I have about 20 lora's already trained on this model. I will try to upload at least 1 a day.</h3><h2 id="people-are-sleeping-on-bigasp-qhhy8u69i">People are sleeping on <a target="_blank" rel="ugc" href="https://civarchive.com/models/502468/bigasp-v1">BigAsp</a></h2><h3 id="it's-basically-the-pony-of-photorealistic-explicit-content-generation-ejrqsvvwz">It's basically the Pony of photorealistic explicit content generation</h3><a target="_blank" rel="ugc" href="https://civarchive.com/articles/5864/mining-the-bigasp-caption-database">I have a short article with some tips i've picked up.</a><h3 id="in-case-anyone-wants-to-try-this-at-home-here's-what-i-did.-pmiccdac3">In case anyone wants to try this at home, here's what I did.</h3><h1 id="version-2-2og7qhy49">Version 2</h1>Block level merge of SDXXL v3, Anteros v1, then that model was merged with Acorn is Boning v1, then finally BigAsp v1. Then a .3 merge of the SPO lora. BigAsp is 70% of this checkpoint, and this model has purposely inherited it's booru-style prompt method. <h1 id="version-1-rxm8tg7s3">Version 1</h1>I did a custom Lycoris extract of <a target="_blank" rel="ugc" href="https://civarchive.com/models/167764?modelVersionId=253250">SDXXXL</a> then merged it into BigAsp at a .7Then i did LORA extracts of <a target="_blank" rel="ugc" href="https://civarchive.com/models/329000?modelVersionId=368680">Acorn Is Boning XL</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/430454?modelVersionId=479579">Anteros XXXL</a> at 128/64, then merged them together at 7/3, then merged that LORA into Bigasp at .7That's it. I just mashed a few buttons. Acorn has amazing prompt adherence and flexibility, and Anteros was trained on a dataset that suits my aesthetic preferences. SDXXXL is the king of quality output.My overriding concern, being a complete novice, is I didn't want to fuck with BigAsp's prompting, so doing lora merges seemed the safest bet as i'm not great with block level merges.If you like what I did, give those guys love if you havn't already. Who am I kidding, if you're here, you've probably already downloaded their models.I have LORA and LYCORIS extracts of all the major models, and my own dataset which I am training now against BigAsp. I also have other merges done, but this is probably the best. So who knows, maybe I'll upload some more shit in the future.

Files with SHA256: 93aff6aef9ef98b4e6cd5f603d3b134416a069d2e13b3d92db259460f1f45f1d