<h1 id="usage-regardless-of-underlaying-model-7rvjjr95k">Usage, regardless of underlaying model</h1>(this is my recommended settings, you are free to test other stuff 😉)<ul><li>Euler a + Beta</li><li>40 steps</li><li>CFG 4</li><li>Clip Skip 2</li><li>Beware of the denoising strength during Adetailer et Hires.Fix. Keep it low, like 0.15 max.</li><li>Negative prompt: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1062439?modelVersionId=1192359">IllusN3g</a>, and optionally "3D" depending on the base model.</li><li>Positive prompt:<pre><code>[whatever you want], Flatline, Flat vector illustration, Black outline, Vivid colors &lt;lora:NJ_Vector_Style:1&gt;</code></pre></li></ul>In the showcase, you'll find tests with my own checkpoints and several popular others to see the effect, including:<ul><li>IXL_AnyLoRA &lt;= for the more simple cute style ❤</li><li>AlterBan V3</li><li>Quirk V2</li><li>WaiNSFWillus</li><li>HassakuXL</li><li>SmoothMix</li><li>iLustMix</li><li>Animij &lt;= gives very good results too 🤩</li></ul>Basically, the simpler and more anime like the model, the "cuter" the effect. But with more "aesthetic" models, included NoobAI, you still get good 2D results :DPS: it does not work well with a V pred model, sorry! You can still try, but then, be sure to switch to Euler + Automatic and the result will be... kinda psychedelic ^^;<h1 id="the-storytm-l97ko2ir7">The Story™</h1>So, i really liked this <a target="_blank" rel="ugc" href="https://civarchive.com/models/1233370/flatline-illus-x-niji-beta?modelVersionId=1389853">LoRA </a>by <a target="_blank" rel="ugc" href="https://civarchive.com/user/MrLoreTaker">MrLoreTaker</a>, but several points bothered me:<ul><li>The overall hue is a bit too shifted</li><li>Strength 2.0 is needed and if you don't RTFM, you can miss it</li><li>The LoRA internal architecture was a mess! What The heck is an "sdxl_a1111_compat" LoRA?!? Why is a 16 dim LoRA so heavy? Why do i get some warning/errors when using it sometimes?</li></ul>So, here is my manual rework on top of his great work:<ul><li>Remade from scratch LoRA architecture, now a correct 16 dim LoRA and not a MB more.</li><li>Adapted weights for hue/saturation. SVD to the rescue. Manual Python and Pytorch stuff all the way, i really hacked into it for fun and learning a bit more this stuff.</li><li>Fixed needed strength. Works out of the box at strength 1.0</li></ul>It took a while to make it cleaner/more to my own taste, Enjoy!NB: when using this LoRA in a merge (if ever), please credit the original author <a target="_blank" rel="ugc" href="https://civarchive.com/user/MrLoreTaker">MrLoreTaker </a>instead of me (if you do things by the rules, otherwise, you aren't reading this anyway isn't it?)

Files with SHA256: ac4118b3df734644ab9e9e5ad431c7f7663bbefa72cf53ebfc312589ad6c10c1