Lokr trained with YUIO's style. some parameters have been changed to make it more generalizable. Please refer to the lora I uploaded before.Use 152 newer images for training, and manually proofread tags. The training images are all female furry. For the latest batch of glaze-processed images, I added them to the training set after some processing.Existing problems: It is not clear what the specific difference between lokr and lora is, and which one is better. I hope you can help test it. In addition, the images generated by this lora seem to have some problems with the gloss of skin or fur.Weight: 0.6 - 0.9 It is generally not recommended to use a weight of 1 or more.Please support the artist: <a target="_blank" rel="ugc" href="https://www.patreon.com/YUIOpatreon">https://www.patreon.com/YUIOpatreon</a>使用YUIO的画风训练的lokr。在先前的lora基础上，改变了一些参数，泛化性更好了。请参考我之前上传的lora。使用152张较新的图片进行训练，手工校对tag。训练图像均为女性furry。对于最新的一批经过glaze处理的图片，我进行了一些处理后加入了训练集。现存问题：不清楚lokr和lora的具体区别体现在哪里，哪个更加优秀，希望各位也能帮忙测一测。另外，该lora所生成的图片，在皮肤或皮毛的光泽上似乎有些问题。Weight: 0.6 - 0.9 一般不推荐使用1或以上的权重。请支持画师：<a target="_blank" rel="ugc" href="https://www.patreon.com/YUIOpatreon">https://www.patreon.com/YUIOpatreon</a>

YUIO Style Lokr for NoobAI

About this versionThis version of lokr is based on Noob-V-Pred-1.0. This version does not have to use Trigger Words. If you want to use it, use (yuiostyle:0.6~1.0).This version is based on the LoRa version I uploaded earlier, with a slightly larger dataset and some modifications to the image tags. It seems to be better than the LoRa version in terms of generalization, and remains to be tested.(All sample images were generated with Noob-V-Pred-1.0 using ComfyUI and using hires-fix.) (Note: In the sample images, the weight of the quality-enhanced lora is lower, at 0.35)Future updates: It seems that models such as pony7 are about to be launched, and I will also train based on them.该版本lokr基于Noob-V-Pred-1.0。该版本不必须使用Trigger Words，如果要用，则用(yuiostyle:0.6~1.0)。该版本基于我先前上传的lora，略微增加了数据集，对图片的tag进行了一些修改。在泛化性方面似乎比lora版本优秀，有待测试。（示例图像全都用Noob-V-Pred-1.0，使用ComfyUI生成，经过了高清修复。）（注意：示例图片中，提升质量的lora的重量都是较低的，为0.35）今后的更新：似乎pony7等模型即将上线，我到时也会基于它们训练。

Files with SHA256: 982bd71288d4f83df9c432839d3a2d28a2730a9080cdf6952998aa4ff78545f5