<h1>v1.7</h1>该模型的制作借鉴了AOM3的合并方法。并同步更新了针对此版本的负面嵌入，<a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">veryBadImageNegative_v1.3</a>。The production of this model draws on the merging method of AOM3.And synchronously updated negative embeddings for this version,<a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">veryBadImageNegative_v1.3</a>.<h1>v1.3</h1>改动：1、 将vae文件烘焙进去了。2、调整了原料的比例重新进行混合，优化了色调和氛围，使其看起来整体光影效果更具戏剧性。3、训练了一个名为<a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">veryBadImageNegative</a>的负面嵌入，所有的例子均使用了这个负面嵌入。Changes:1. Baked the vae file.2. After adjusting the weight, re-mixing is performed to optimize the tone and atmosphere, making the overall light and shadow effect more dramatic.3. A negative embedding called <a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">veryBadImageNegative </a>is trained, and all examples use this negative embedding.<h1>v1.0</h1>该模型可以生成高质量的动漫风格壁纸、动漫风格角色、自然风景插图。推荐使用pastel-waifu-diffusion.vae.pt，所有例子都是使用这个vae生成的。this model can generate high-quality anime style wallpaper, anime style characters, and natural scenery illustrations.pastel-waifu-diffusion.vae.pt is recommended, all examples are generated using this vae.

viewer-mix_v1.7

v2是针对角色绘制风格进行微调的版本v2 is a version with fine tuning for character painting styles

Files with SHA256: c47e3a94e9bce34d961fdb910da1766d5d1a81fcecfea97af154b91d3926561f