转载自CagliostroLab

Animagine XL 4.0, also stylized as Anim4gine, is the ultimate anime-themed finetuned SDXL model and the latest installment of Animagine XL series. Despite being a continuation, the model was retrained from ****** ********* XL 1.0 with a massive dataset of 8.4M diverse anime-style images from various sources with the knowledge cut-off of January 7th 2025 and finetuned for approximately 2650 GPU hours. Similar to the previous version, this model was trained using tag ordering method for the identity and style training.
Animagine XL 4.0，也写作 Anim4gine，是终极动漫主题微调SDXL 模型，也是 Animagine XL 系列的最新作品。尽管是延续，该模型从****** ********* XL 1.0重新训练，使用了来自各种来源的840万张多样化的动漫风格图像的大量数据集，截止到2025年1月7日，并经过大约 2650个 GPU 小时的微调。与上一版本类似，该模型使用标签排序方法进行身份和风格训练。

使用指南1. 提示结构：该模型使用基于标签的字幕和标签排序方法进行训练。使用此结构化模板：1girl/1boy/1other, character name, from which series, everything else in any order.
2. 质量增强标签：在提示的开头或结尾添加以下标签：masterpiece, high score, great score, absurdres
3. 推荐的负面提示：lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer digits, cropped, worst quality, low quality, low score, bad score, average score, signature, watermark, username, blurry
4. 最佳设置：CFG Scale：5-7（推荐 6）采样步骤：25-28（推荐 25）首选采样器：（Euler a)