Trained with 67 images on the AAM - AnyloraAnimeMix checkpoint. The samples were generated with AAM. Recommended settings:<ul><li>Sampler:DPM++ 2M Karras / Euler a - 35 steps</li><li>CFG: 7</li><li>Resolution: 512x768, 768x512, (works with most common SD1.5 resolutions)</li><li>Lora weight: 0.8</li><li>HighRes: 4x_NMKD-Siax_200k, upscale by 2x, 25 steps, 0.35-0.6 denoising</li></ul>Basic prompt:&lt;lora:redacheron_SD:0.75&gt; redacheron, 1girl, long hair, white hair, red eyes, medium breasts, sleeveless shirt, black shorts, cleavage- Additional tags of interest: "red flower", "tattoo" or "bodypaint" (for the red lines on her body), "holding sword"+"katana" (might take a couple of gens before it get's her katana right)Additional notes:<ul><li>Make sure to describe the background/setting in detail, otherwise you will get simple backgrounds.</li><li>I used the FastNegativeV2 embedding by Lykon for the samples.</li><li>Works well with other loras but you might want to drop the weight of the Acheron lora to 0.6.</li><li>Most of the training images didn't have the red flower over her eye, so prompting for it is kind of hard. You can add the flower via inpainting.</li></ul>Prompt for inpainting the red flower:&lt;lora:redacheron_SD:0.8&gt; redacheron, one red flower, white hair<ul><li>Inpaint area: only masked</li><li>Sampler: euler a - 20 steps</li><li>Resize to: 768x768</li><li>Denoising strength: 0.8 (if you're using an inpainting model you can crank it up to 1.)</li></ul>Tested models:<ul><li>AAM - AnyloraAnimeMix v1</li><li>EtherBluMix v6</li><li>Yuzu v1.1</li><li>BloodOrangeMix</li></ul>

Files with SHA256: c46dd30fbfd721b04346367b2a2191903c0b59bf4edd537b9856fa766002d90f