Model OverviewThe Vixen series Flux model is specifically designed for female subjects. Due to the nature of Flux, I didn’t use an extensive number of images to create it. Using LoKR, I trained both the UNet and text encoder to preserve as much diversity as possible.To achieve the ideal poses and realistic style, I used a finely curated dataset for training.This model is intended for generating realistic, photography-style images, and I will be using it as the base model for all future Flux LoRA generation.---Recommended Parameters:- Sampler Method: Euler simple- Sampling Steps: 20-30- Recommended Resolution: 1024x1536 or 1280x2048- CFG: 3.0======================================================模型简介Vixen系列的Flux模型是女性类专用模型，由于flux的特性我并没有用特别多的图片去制作它。使用了lokr同时练了unet和text尽可能的保留了更多的多样性。为了理想中的人物姿态和写实类风格，使用精筛集训练。它可以用来制作真人摄影写真方向的图片生成，我将用它来配对之后的所有flux的lora生图底模。---推荐参数：采样方法(Sampler)： Euler simple采样迭代步数(Steps)：20-30推荐尺寸：1024*1536 或 1280*2048CFG：3.0Q交流群： 852450267

kimVixen

kimvixen_v10.safetensors

v1.0

KimVixen

Model IntroductionThe Flux model in the Vixen series is a model specifically designed for women. Due to the characteristics of flux, I didn't use many images to create it. I used lokr to simultaneously practice unet and text to preserve as much diversity as possible.To achieve ideal character poses and realistic styles, precision screening training was utilized.It can be used to generate images for real-life photography, and I will use it to match all future flux Lora character illustrations.======================================================Recommended Parameters:Sampling Method: Euler simpleSampling Iterations (Steps): 20-30Recommended Sizes: 1024*1536 or 1280*2048CFG: 3.0

Files with SHA256: 3df2565b3adeb21cb1e4be13a45754668d5f60ab07772b6ff6bea81c6633c820