SD35.圣诞树懒SD35PandaXmas
1.生图建议:
采用新一代的SD3.5 large基模,超级清晰:迭代步数15-20,CFG根据需要自己填写3-6。权重可以自己调试哦建议在.7-1.1之间。
2.主采样器:dpmpp_2m + sgm_uniform,以SD3.5L为底膜推荐的初步分辨率:832*1248
主采样器:dpmpp_2m + sgm_uniform
CFG:3 + |步骤:30 +
(推荐):CFG:5 | STEPS:40
3.正向:
SD35SlothXmas, solo, looking at viewer, hat, belt, indoors, no humans, box, christmas, gift, santa hat, santa costume, gift box, christmas tree, christmas ornaments
4.建议搭配
stable-diffusion-3.5-large (https://tensor.art/models/787485539642164723)
SD3.5 large (https://huggingface.co/stabilityai/stable-diffusion-3.5-large )
5.召唤词:SD35PandaXmas