[LoRA] Raiden Shogun | Realistic Genshin LORA

模型介绍：
samples in: https://youtu.be/Md31qYa78yk

Training without any real person's face in dataset.
▣ Update 23/03/07: The problem about hands and extra fingers is fixed......a little bit?

For everyone: I am not using the official lora loader, so you should use the additional-network webui plugin to use my lora setting.
Recommended weights for txt2img - 0.55-0.75, higher weights may cause some issue.

Thank you for downloading!
Please leave a image with comment if you like it, I would love to see.

If you see anyone selling images that generated by this model on pixiv or other platform please message me on twitter.

~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~

示例提示词和参数：
Prompt: 1girl, blunt bangs, braid, wide sleeves, hair ornament, japanese clothes, (red:0.7) obi, (purple hair:0.95), very long hair, looking at viewer, (photorealistic:1.3), detailed eyes, red eyeshadow, depth of field, symmetry eyes, (ulzzang-6500:0.6), (cyberpunk city:1.1), cleavage, hand on lips, street advertising, from side, (thighs:0.7),

Negative prompt: (worst quality:2), (low quality:2), (normal quality:2), monochrome, grayscale, easynegative, poorly drawn face, bad-picture-chill-75v, badhandv4

Steps: 20, CFG scale: 5, Sampler: DPM++ 2M Karras, Seed: 2713605955, Size: 512x768, Model: chilloutmix_Ni, Version: v1.3.2, Model hash: 7234b76e42, AddNet Enabled: True, AddNet Model 1: RaidenShogun-HandsFix(41b380802849), AddNet Model 2: CustomFace(0015c1c30c88), AddNet Module 1: LoRA, AddNet Module 2: LoRA, AddNet Weight A 1: 0.75, AddNet Weight A 2: 0.2, AddNet Weight B 1: 0.75, AddNet Weight B 2: 0.2