Fantasy reality fusion_XL(Chinese style)

详情

模型描述

该模型加入了中国古风风格元素,融合了中式脸型与汉服元素,优化了亚洲人脸型,避免了SDXL固有的亚洲脸型刻板印象。新版本还增添了其他元素,修复了测试版中遇到的问题,提升了细节表现,大部分场景下无需开启AD面部修复,但特殊宽幅场景仍需依赖ADetailer或Face Editor进行辅助。

版本建议(Version suggestion)

此版本推荐提示词(This version recommends prompt words):

注意:此版本设有触发词(Note that this version has trigger words):

脸型触发词(Face trigger words):chinese girls

汉服触发词(Hanfu trigger words):hanfu

正面提示(Recommended prompt)Best quality, chinese girls,

负面提示(Negative prompt)(worst quality, low quality, blurry, bad eye), (wrong hand, bad anatomy, wrong anatomy), (cgi, illustration, cartoon, poorly drawn, watermark), head out of frame,

采样方法(sampler):

dpm++ 3m sde exponential     45步及以上

dpm++ 3m sde karras        45步及以上

高清修复(hires.fix):4x-ultrasharp,高分迭代步数 1015,重绘幅度 0.30.5

clip skip:2

本地生图可开启ADetailer

模型内置VAE,无需额外添加VAE模型(vae is built into the model and there is no need to add additional vae models)

————————————————————————————————————————

若融合本模型,请注明原模型出处,以免产生不必要的误会。

The author of the fusion my model please indicate the original model to avoid unnecessary misunderstanding

————————————————————————————————————————

模型用途声明(Model purpose statement)

1. 您不得将本模型及其衍生版本(如融合模型版本)托管于旨在盈利或接受捐赠的网站/应用程序。若您需将本模型及其衍生版本用于商业目的(如生成式服务、售卖图片、将图片用于短视频平台公开文章或出版物等),请通过站内私信联系本人。

1. You may not host this model and its derivative versions (such as the Fusion Model version) on websites/applications that plan to generate income or donations. If you need to use this model and its derivative versions for commercial purposes (such as generating services, selling images, using images for public publication in articles or publications on short video platforms, etc.), please contact me via the site

2. 您不得直接售卖本模型生成的图片,除非您对该图片进行了充分的人工修改,使其在法律上可被明确判定为您的个人原创作品。如违反本条款,由此产生的一切法律后果由您自行承担,本人概不负责。

2. You may not directly sell images generated from this model unless you have manually modified the image to a sufficient degree that it can be legally judged to be your own work. If you violate this article, all legal consequences caused by you personally bear, I will not be responsible.

3. 您不得利用本模型故意制作或传播非法、有害内容,请遵守公序良俗,将本模型用于积极正面的用途。

3. You cannot use this model to intentionally create or share illegal or harmful content dissemination and output, please abide by the public order and good virtue, use this model for positive purposes.

  • 模型反馈请通过站内私信

本模型不包含任何真人素材图像源,训练代码均来源于互联网,仅用于科研兴趣交流。

This model does not contain any real human material image source and training code from the Internet, the model is only used for scientific research interest communication

此模型生成的图像

未找到图像。