<h3 id="heading-3"><span style="color:rgb(250, 82, 82)">Recommended versions :"vanilla-newlora-ver1","super-vanilla-v4","nekopara-vanilla-v5", the rest are not recommended</span></h3><h3 id="heading-31"><span style="color:#40c057">vanilla-newlora-ver1</span></h3><h3 id="heading-32"><span style="color:#40c057">This version supports multiple people</span></h3><h3 id="heading-33"><span style="color:#40c057">But it will be affected by </span><span style="color:rgb(78, 172, 239)">Hires. fix</span></h3><h3 id="heading-34"><span style="color:#40c057">The most popular were chocolate and vanilla</span></h3><h3 id="heading-35"><strong><span style="color:rgb(230, 73, 128)">It is forbidden to sell the images generated by this model for profit, and it is forbidden to sell this model. Thank you<br />禁止将此模型生成出的图片进行出售盈利行为，禁止出售此模型。谢谢</span></strong><br />Please watch the release introduction for detailed information<br />请观看版本介绍 有详细的信息</h3><h3 id="heading-63"><span style="color:rgb(130, 201, 30)">The model generalizes and transfers very well, and you can use it on almost any submodel (except SDXL).</span><br /><span style="color:rgb(130, 201, 30)">If you want to restore the original painting style, you need a lot of prompt words to correct, the model's data set contains all nekopara images, the game illustrator artbook and fanclub cover, theoretically it can restore all images</span></h3><hr /><p>vanilla-newlora-ver1</p><p>This version is trained for classification</p><p>Older versions of the dataset are discarded</p><p>Stronger support for multiple people</p><p>Supports the human hand model</p><p>The overall painting style shifts towards nekopara4</p><p>More rounds of training were performed on high-quality datasets</p><p>High-quality data sets trigger the word vanilla</p><p>Generalization trigger word xiangcao</p><p>Hand trigger word shouban</p><p>r18 Trigger word nsfw</p><p>Multi-person trigger word girls</p><hr />

LoRA-Nekopara猫娘乐园-vanilla香子兰

<p>This model may not be as good as the previous model in eye detail，The same is true for portability，Probably so</p><p>这个模型在眼部细节上可能不如上个模型，在可迁移性上也一样，可能是这样吧<br />Eye details will be fixed in the next release</p><p>将在下个版本修复眼部细节问题<br />This version crushes the previous version in terms of data volume,The previous version had 300 images, this version had 1300 images,I set the model size to 32MB :D<br />这个版本在数据量上碾压上个版本,上个版本为300张图片，此版本为1300张,我将模型大小设置为了32mb :D</p>

Files with SHA256: d5febdf53b02c789899259022e4abeb39eb5bf079f1a19a30a3872f7e72c7f57