<h3>Iripastel Diffusion SD1.5</h3><p>原始生成参数如图，不知道为啥C站上传图无法读tag</p><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/56f2dd9d-e8f7-4928-f20e-f59e41149300/width=525/56f2dd9d-e8f7-4928-f20e-f59e41149300.jpeg" /><h3>[2023/4/6]</h3><ul><li><p>lines更新</p></li><li><p>使用基于anything3-RE（重置版）训练：</p><p>Training with anything3-RE (Reset version) :</p><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/9409/or-anythingv5v3">万象熔炉 | AnythingV5/V3 | Stable Diffusion Checkpoint | Civitai</a></p></li><li><p>请不要添加“masterpiece”等起手式：</p><p>Please do not add "masterpiece" or other prompt words</p></li><li><p>本模型无需其他VAE修正图片色彩</p><p>No other VAE is required for this model</p></li></ul><h3>[2023/4/7]</h3><ul><li><p>channal更新</p></li><li><p>替换部分训练数据集，更改了训练参数</p><p>Some training data sets are replaced and training parameters are changed</p></li><li><p>替换VAE</p><p>Replace VAE</p></li></ul><h3>特别鸣谢：</h3><ul><li><p><a target="_blank" rel="ugc" href="https://github.com/bmaltais/kohya_ss">GitHub - bmaltais/kohya_ss</a>：训练UI</p></li><li><p><a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/">Automatic1111</a>: SD-WebUI</p></li><li><p>Danbooru：打标器，帮助标准训练集</p></li><li><p><a target="_blank" rel="ugc" href="https://civarchive.com/models/22354?modelVersionId=26689">ClearVAE</a>：Channal版本替换的VAE</p></li><li><p>秋叶的甜品店（频道）：在这里让我有了这个想法</p></li></ul><h3>祝大家玩得开心＜3</h3><ul><li><p>你可以随意将本模型合并到其他地方，但如果你共享该合并模型，别忘了标注一下</p><p>We allow you to merge with another model, but if you share that merge model, don't forget to add me to the credits.</p><h3>禁止户口本只有一页的炼丹阁转载，其他人可随意转载无需给我说明</h3></li></ul>

Files with SHA256: 5a4ee72c59f1e7ce5bef7140d98120472f562bba1157a234c1074b55fdc99c3a