This LoRA is designed to generate casual illustrations that mimic the distinctive portrait style of "<a rel="ugc" href="https://store.steampowered.com/app/2135150/Elin/?l=japanese">Elin</a>" by Lafrontier, blending it with a soft, crayon-like aesthetic.The training dataset is based on the "<a rel="ugc" href="https://tensor.art/articles/878601807314561823">Elin Skin/Portrait Assets</a>" portraits I previously generated. The creation of these assets wouldn't have been possible without the following incredible models:<ul><li><a rel="ugc" href="https://civarchive.com/models/827184/wai-illustrious-sdxl?modelVersionId=1761560">WAI-illustrious-v14</a></li><li><a rel="ugc" href="https://tensor.art/models/799183157950773155">Elin Portrait Style</a> LORA</li><li><a rel="ugc" href="https://tensor.art/models/806356844256811271">Anima Crayon Sketch Illustrious</a> LORA</li><li><a rel="ugc" href="https://tensor.art/models/857752026015080288">Illustrious Enhancer</a> LORA</li><li><a rel="ugc" href="https://civarchive.com/models/580163/fantasy-graphite-sketch?modelVersionId=1208517">Fantasy Graphite Sketch [Illustration/Pony]</a> LORA</li></ul>I would like to take this opportunity to express my deepest gratitude to all the creators of these models.

Style > Elin Faux Crayon (ai-generated style)

Initial. (Experimental)A LoRA weight of 1.5 or higher is recommended.MOSS Image recommends detailed natural-language or JSON-based captions. Therefore, training on this Danbooru tag-based dataset is experimental.LORA, MOSS Image Base, dim32/alpha32, AdamW8bit, LR 1e-4, cosine 2000steps, 124images, 1024² res. Captioning: Booru tags only(including some broken English).

Files with SHA256: 65c721b98a7dae5d4e96def060109cbc42d0b73374da5e3e41cab92c21b08480