在base v1版本重新训练,旨在为画风融合提供坚实的勾线,粗糙的传统媒体质感和偏低的饱和度Retrained on the base v1 version, aiming to deliver solid line art and a raw traditional media texture for art style fusion.低强度(0.2~0.4)和高触发词权重可以为anima 自带画师的油腻质感带来改变(或者你的lora练得油腻到爆炸),但会某种程度改变五官面容,以及头发的画法(虽然我很喜欢这两点,但后续可能还会有减低面部特征影响的版本)Low Lora weights(0.2~0.4) and high trigger word weights can modify the greasy texture inherent to the original artist style of Anima(Or your LoRA is trained to be overly greasy and artificial), yet they will alter facial features and hair painting methods to a certain extent. Much as I favor these adjustments, versions that reduce impacts on facial characteristics will be released later, maybe?风格较为鲜明而特殊,也可以提供直观感受当调试不同噪声时间It features a distinct and unique style, and can also deliver intuitive visual effects when adjusting different noise timings.<hr />train on preview v1, but for preview v1~3 and b1, actually It stilly work in case<a target="_blank" rel="ugc" href="https://civarchive.com/models/1585859/xiaohuoguo">https://civarchive.com/models/1585859/xiaohuoguo</a>从该lora蒸馏出来的手绘风格,具有特殊的彩铅手绘笔触。经试验个人认为有相当不错泛化性，在训练素材为纯上半身肖像下训练的情况下能出中远景的图片，且于三种风格lora在1权重叠加时图像线条仍顺畅（但此时已经出现相当程度的性能下降）The hand-drawn style distilled from this Lora features special colored pencil hand-drawn strokes. Through experiments, I personally believe it has quite good generalization ability. When trained with training materials that are purely upper-body portraits, it can generate mid-to-long shot images. Moreover, it can still generate images normally when overlaid with three style Loras at a weight of 1 (but at this point, there has been a considerable degree of performance degradation).

Files with SHA256: f198f8240e84bc4e8004ea14ef0dd87c75aa8d9b9fff96b29c025372e67b20b4