- Futuristic style mecha, shining on the surface of the mecha, pink and red appearance, girl, slender waist, big breasts, big ass, flowing long fiery red hair, transparent face armor, nine-headed body, forward stance, wielding a long sword, holding a weapon in his hand, a long sword, a tail wing on his back, spraying flames, an angel halo on his head, surrounded by ruins, HD, CG image, ultra-wide-angle lens, gigantic
- Negative prompt: (nsfw:1.5),verybadimagenegative_v1.3, ng_deepnegative_v1_75t, (ugly face:0.8),cross-eyed,sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, bad anatomy, DeepNegative, facing away, tilted head, {Multiple people}, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worstquality, low quality, normal quality, jpegartifacts, signature, watermark, username, blurry, bad feet, cropped, poorly drawn hands, poorly drawn face, mutation, deformed, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, extra fingers, fewer digits, extra limbs, extra arms,extra legs, malformed limbs, fused fingers, too many fingers, long neck, cross-eyed,mutated hands, polar lowres, bad body, bad proportions, gross proportions, text, error, missing fingers, missing arms, missing legs, extra digit, extra arms, extra leg, extra foot, ((repeating hair))
- Steps: 36, Seed: -1, Sampler: DPM++ 2M Karras, CFG scale: 14
复制代码
型号信息------------------------------------------------- 基本型号: SD.1.5 用于训练的模型:美丽现实的亚洲或BRA V5(已测试)
接受过第1024号决议的培训。 学习速率 1e-6,最大步数为 3500。 优化 AdamW8Bit,LR 调度程序余弦与重启。 VAE(用于训练):无,抽样方法:K_DPM_2 剪辑跳过:2(您应该使用剪辑跳过 2) 用于训练的图像数量约为 100 张图像(所有非普通图像)
激活词:HighHumanion。 您可以在提示中使用此词(或激活词)作为以下语法:高人性:此处<权重值>, 而且你不会得到什么特别的东西,你可以使用这个词,也可以不使用这个词,它会影响你的提示,但正如我所说,我无法预测会发生什么!
注意。上面的图片来自SeaArt,你应该使用质量是高质量的,但它不会特别,它很可能是BRA V5,高质量,你不会太关心很多问题。 由于质量是SeaArt中的超高质量,因此很难预测结果,它可能会让您感到惊讶或痛苦,因此您应该谨慎对待超高质量。
指导:不要尝试在提示中使用“HighHumanion:<权重值在这里>”,这可能很难使用和预测任何结果;你不应该使用“恢复”这个词,比如恢复面子,这很难预测。但是,使用我的模型很难从提示中的任何单词中预测,所以不要太在意我的本指南,它
仍然是不可预测的
|