The style of Pettankon.Trigger word is <code>@pettankon</code>. Anima B1 remake of the Illustrious <a target="_blank" rel="ugc" href="https://civarchive.com/models/1115692/pettankon-style-illust">version</a>. Same dataset. You might want to add <code>favourite</code> to the positives, <code>sketch, monochrome, greyscale</code> to the negatives, and <code>nsfw</code> to one or the other.It turned out less pronounced than the IL version (maybe a higher weight can bring it closer?), so I suppose it's probably slightly less interesting for blending, but closer to the artist's actual style. I might retrain this or release an earlier epoch.19.09.2026 - Added regular LoRA version in addition to the DoRA.If you like the style, please support the <a target="_blank" rel="ugc" href="https://nyanpals.com/pettankontent/">original author</a>.

Pettankon style AnimaB1

I realized DoRAs had downsides I hadn't previously considered, so now I'm remaking LoRA versions of my DoRA models. In short:<ul><li>DoRA works better alone and on the same model it was trained for</li><li>LoRA works better in combination with other adapters or on checkpoint finetunes</li><li>LoRA also appears to work better on Anima 3.8B</li></ul>

Files with SHA256: 9a05ee93ad00bdde99cd869a0dfd96a9e0ac648b3e760a1c0d562483726583a7