<h3 id="heading-333">3/25/2024 PDXL Update:</h3>I updated this model for use with PDXL. Please see the "About this version" section to the right for details. It's pretty much the same model, just trained on better tags, at a better resolution, and with a better optimizer. It gets her outfit and helmet a lot more consistently, but sometimes forgets the tiny metal belt around her waist. It might be difficult to prompt for 'floating' or 'casting magic', but you can get the results if you try hard enough. Hope you enjoy.Older Description:<hr />The Artificer*! This lora can be yours for the low price of 10 lunar coins...This is a lora trained on 120 hand picked images of the Artificer from Risk of Rain 2. It was mostly trained on digital art, but there is a smidgeon of 3d art to assist. It gets the helmet pretty good, however it seems really biased against her wearing her usual outfit... See notes below for more info. It was trained on danbooru-style tags, so use those when trying to prompt - I've included the tags in a .txt file in the "Training Images" download below.It works pretty well with most ckpts, but I recommend Anything 4.5, I used it for all of the example images.NOTES:-It seems quite biased to give the Artificer wide hips unprompted, and also she doesn't like wearing her usual tabard-thing. Also, the AI seems to think her black bodysuit is her actual skin, so expect some oddities from that. Tags: pelvic_curtain &amp; tabard -- will help her wear her usual outfit... usually.-You can pretty easily make the helmet "blush" if you add relevant tags.-It can generate "male" versions of Artificer if you prompt it correctly.Example prompt: (See example images, all images should still have their metadata. Just drag the images onto the PNG info tab and import it.)Check out my Huntress model here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/20542/huntress-risk-of-rain">https://civarchive.com/models/20542/huntress-risk-of-rain</a>

Artificer - Risk of Rain [PDXL Update]

Updated for use on PDXL! Same dataset, except I changed the tags from danbooru-style to e621-style, since those tags are far more robust. PonyDiffusion's improved resolution, combined with the amount of steps I trained this at, has made her outfit a lot more consistent, especially her odd helmet. Hope you enjoy!

Files with SHA256: b8cb26262eebf597807850653aa9ee8d6089e90cd75545c807a33c72b86b452a