If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivated如果你喜欢我的作品，请给我一个5星评价并点击心形图标。这是免费的，而且能让我保持创作动力。Still, I repeat, the new version may not necessarily be the best. Experience it yourself and have fun!还是那句话，新版本不一定是最好的。自己体验，玩得开心！AI绘画QQ交流群：465435003.5_Mature_EPS如果不够成熟就添加“mature woman.morimee_style”。以前做好的模型，另一个帖子里我发布的One obsession 03版本的延续，是主打成熟丰满的女性illustrious版本。为了更直观，例图均没有添加lora。If you're not mature enough, add "mature woman.morimee_style". The model I made before, which is a continuation of the One Obsession 03 version I posted in another thread, is the illustrious version that focuses on mature and voluptuous women. For a more intuitive presentation, I didn't add LORA to any of the example images.Vpred3.0版本，使用了Rouwei的2025.02的数据集，延续受好评的可爱萝莉风格，提升质感，肢体和色彩调整加强，为了更直观，例图均没有添加lora，其他自己探索吧！The Vpred3.0 version uses Rouwei's 2025.02 dataset, continuing the well-received cute lolita style, improving the quality, and enhancing the adjustment of limbs and colors. For a more intuitive understanding, all the example images have not been added with Lora. You can explore the rest on your own!You can use ADetailer to enhance facial details：https://github.com/Bing-su/adetailer可以使用 ADetailer 来增强面部细节：https://github.com/Bing-su/adetailerUsing "Euler a" will be more clear, while "Euler" will have the messy beauty of painting. Choose according to your painting style as needed.用“Euler a”会更清晰一些，用“Euler”会有绘画的凌乱美，根据画风按需选择。正面词 Positive Prompt：masterpiece, best quality, amazing quality, very awa,absurdres,newest,very aesthetic,反义词 Negative Prompt：bad quality,worst quality,worst detail,sketch,censor,low quality,logo,text,watermark,signature,Recommended settings:Steps: 15-35CFG scale: 2-7Sampler: Euler a or Euler推荐我喜欢的分辨率：768X1280 768X1344 832X1216 896X1152Model Recommended Resolution：768X1280 768X1344 832X1216 896X1152小知识：eps噪声预测的问题是图像明暗度偏中性，很难画出非常暗的图片 对比度不够，XL一般都是eps，vpred噪声预测暗部表现优异，色彩对比度更加激进一些，提示词有的才会画出来，几乎不会矫正和随机，eps则反之，总之vpred比eps高一个门槛，eps模型简单好画一些，随机有惊喜，vpred模型认真写提示词会有惊喜。Tips: The problem with eps noise prediction is that the brightness of the image tends to be neutral, making it difficult to draw very dark images. The contrast is not enough. XL usually uses eps, and vpred noise prediction performs excellently in the dark areas. The color contrast is more aggressive. Some keywords will be drawn out, and it's almost impossible to correct and randomize. Eps is the opposite. In short, vpred is one step higher than eps. The eps model is simpler and easier to draw, and there are surprises in randomness. The vpred model will have surprises if you write keywords carefully.
