LORA
AI_Imaging
2023 年 8 月 28 日
V1.0
SD 1.5
rramidaa
36.11MB
隐藏内容需要回复可以看见
前言:
分享不易,感谢支持,请小心处理生成的图像,并自行承担风险。
禁止对社区的发展产生不利影响的行为和侵犯个人权利和隐私的使用行为。
禁止用于生产(生成)违反国家禁止传播的内容和行为!!!
禁止商业用途!!!
基于ChilloutMix进行训练,最佳权重为 0.8 到 1。
请记住在提示中添加触发词。
candid photo of rramidaa, shot at eye level, on a Fujifilm X-T4 with a 50mm lens,<lora:rramidaa-12:0.9>, outdoor, cowboy shot,
Negative prompt: ng_deepnegative_v1_75t, (badhandv4:1.2), (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)) watermark, moles,nsfw,Cleavage, text, b&w, illustration, painting, cartoon, 3d, bad art, poorly drawn, blurry, disfigured, deformed, extra limbs
Steps: 30, Size: 512×768, Seed: 1552752409, Model: majicmixRealistic_v6, Version: v1.5.2, Sampler: DPM++ 2M Karras, CFG scale: 7, badhandv4: 5e40d722fc3d”, Model hash: e4a30e4607, Hires steps: 15, “rramidaa-12: f519a62f2d5b”, Hires upscale: 2, Hires upscaler: 4x-UltraSharp, Denoising strength: 0.36, “ng_deepnegative_v1_75t: 54e7e4826d53
666
666