<h3 id="lora-extract-of-4th-tail-model.-9pexakzbo">LoRa extract of <a target="_blank" rel="ugc" href="https://civarchive.com/models/282341">4th tail</a> model.</h3>2 sizes, XL/L and XL-alt. The bigger - the more accurate.New version was made with some new approach, it should look better and represent more, but compatibility issues may occur. Please report if you meet any, will try to fix it.XL-alt looks a bit different in terms of style but works best to get full color and brightness.<h3 id="before-using-check-out-merge-of-full-weights.-may-be-you-will-find-it-more-satisfying.-kxvhja6un">Before using - check out <a target="_blank" rel="ugc" href="https://civarchive.com/models/568043">merge of full weights</a>. May be you will find it more satisfying.</h3>Original model comes with 8000+ artists styles, lots of anime characters (kemonomimi, gacha, touhous, vtubers, etc.), concepts and some other features.After LoRa compression some artist are fine, some are damped but still works, others barely recognizable. Same for character knowledge, tags, style mixing. Quality tags seems working.But who cares if you only want to use a small part that satisfies you directly on your favourite model?Also consider using higher LoRa weight.Works with PonyDiffusion finetunes/mixes including Autism.Prompting:<pre><code>by ARTISTNAME</code></pre>by is mandatory, then quality tags, your prompt with full character name like on boorus. Check out 4th tail description for more.

4th Tail LoRa extract

4th_tail_extr_0.4.5_lyco_xl.safetensors

0.4.5 XL

0.5.0 XL-alt

0.5.0 XL

0.5.0 L

0.4.5 L legacy

0.4.5 M

v0.4.0 L (simple lora)

v0.4.0 S

0.4.0 M

0.4.0 L

0.3 S

0.3 M

0.3 L

0.2 L

0.2 M

0.2 S

Files with SHA256: 266ccfe6fd9cb224db370181c3f54bd278a636660fea7bcf3a2fbd5f4cef3576