<h1 id="style-collection-for-neta-lumina-2">Style Collection for Neta Lumina 2</h1>All cover images are raw output from the model, 1MP resolution, no upscale, no hands/faces inpainting fixes, even no negative prompt.<hr />This is my personal style collection. Anything could be here.Version number means nothing, just my training job ID.By default the LoRA is trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/1612109">Neta Lumina v1.0</a> for better compatibility. So in theory it can be applied to any further finetunes of Neta Lumina. But the cover images may from a finetune.By default trigger words are: "anime illustration."<hr />dcl v0.8:<ul><li>Dataset: from an artist friend. AI-assisted illustrations.</li><li>Style: 2D anime illustration. Thick lines. Muted colors. Generally darker, emphasizing the shadows.</li></ul>cnd naivp v0.2:<ul><li>Same dataset as v0.1, but trained on NoobAI v-pred. Requested by a friend. Too lazy to open a new page for NoobAI, so I just uploaded at here...</li></ul>cnd v0.1:<ul><li>Dataset: from an artist friend. AI-assisted illustrations.</li><li>Style: 2D anime illustration. Thick lines. Muted colors.</li><li>Trained on Neta Lumina v1.0.</li></ul><hr />

Style Collection [Lumina 2]

This is for NoobAI v-pred. Same training data. Requested by a friend.

Files with SHA256: 370b9b92bbf6bc4cd75175e920e2599649416fce7eb7fd1fa432e0d43df0c3f4