训练模型是anythingV5, 生成预览图用的模型是anyhentai20,背景不太好控制，建议多写一些背景提示词或提高其权重（素材没抠图的锅）人物特征提示词：1girl, solo,thigh boots, gloves, streaked hair,long hair, blue eyes, grey hair, fingerless gloves,multicolored hair, breasts, pink hair, black gloves, one side up, skirt, white thighhighs, white footwear, high heels建议使用的反向提示词: holding, simple background, grey background, weapon, blue background, 3d rendering,建议使用分层控制（LoRa Block weight)，预览图我使用的分层控制参数是AACC:1,1,1,1,1,0,1,1,1,1,1,0,1,0,0,0,0.5，

Files with SHA256: 1628b0d0749eff34d0a6ab4078063d724c10695c54aaef8934ea15865e85d8a1