This LoRa is aimed to recreate the style of the artist k1ko [<a target="_blank" rel="ugc" href="https://linktr.ee/justk1ko">https://linktr.ee/justk1ko</a>] CHECK THEM OUT!!!A good range is (0.6 to 0.7) :DIt's very good at making bottom heavy and feline like characters, anything else and you will have to play around with weighing prompts and negative usage to get what you're afterD2 Version is compatible with most if not all IL models while remaining faithful to the stlye and easier to prompt with <h3 id="there's-a-chance-the-d1-version-will-introduce-a-watermark-to-the-image">There's a chance the D1 version will introduce a watermark to the image 😿</h3><h3 id="d2-solves-that-issue-nwn">D2 Solves that issue nwn</h3><h3 id="will-remove-if-asked">Will remove if asked</h3>

k1ko Style [Illustrious]

Compatible with a lot if not all IL models and more faithful to the artist's style

K1ko_style_ILL.safetensors

This LoRA is aimed to recreate the style of the artist k1ko CHECK THEM OUT!!! FOR SOME REASON LINKS ARE BLOCKED CHECK THEM OUT HERE [ https://linktr[.]ee/justk1ko ]Just remove the [] from the link and leave the dotA good range is ( 0.65 to 0.70 ) :DIt's very good at making bottom heavy and feline like characters, anything else and you will have to play around with weighing prompts and negatives to get what you're afterVERSIONS:<ul><li>V1: It doesn't match as closely to the the style but works great for most use cases since poses are less rigid</li><li>V1.5: It matches more closely to the style but somewhat more rigid</li><li>V2: It matches the style even more closely and is very forgiving!, only downside is that it's only workable on NovaFurryXL v5.0 and above, it can kind of work on Noob but there may be more glaring errors during generations</li><li>V2.5: Version is compatible with most if not all Illustrious models while remaining faithful to the stlye and easier to prompt with, Noob compatibility TBD, dare if you're brave o3o</li></ul>Stiff!Depending on what you're doing i'd recommend adding the included negative tags because if you use the LoRa at a high strength (0.70&lt;) the stiffness of the training data can be quite noticeable!. Mostly to take into consideration with V2 and belowWill remove if asked

Compatible with a lot if not all IL models and more faithful to the artist's style

Files with SHA256: 59dcae9042a120ace09df6874bc696213c4e47ba03e2d20929af345b4c34f763