
出图策略:建议使用800*1200输出后二次放大1.3~1.6倍
采样器:EULER A
步数:25
触发词:1girl,hanfu01,off shoulder
Output strategy: It is recommended to use an output of 800*1200 and then enlarge it by 1.3~1.6 times.
Sampler: EULER A
Steps: 25
Trigger words: 1girl, hanfu01, off shoulder
本模型支持PONY为底模训练的大模型,通用PONY的2D,3D,写实画风,可变更颜色,可搭配兼容其他LORA使用,模特脸型受大模型影响,开启脸部修复以获得较好效果,
This model supports large models trained on the PONY base, covering PONY’s 2D, 3D, and realistic painting styles. It allows color changes and can be paired with other LORA-compatible uses. The model’s facial structure is influenced by the large model, and activating facial repair can yield better results.
这是爱发电赞助通道,如果您觉得模型实用并且愿意支持我,我将不胜感激,请根据自己的实际情况,千万不要勉强,感谢您的每一份支持,我会持续研究如何进一步优化模型!
描述:
降低该模型权重可以去除衣服上面的类文字图形
训练词语: hanfu01
名称: GK-pony-hanfuwenzi.safetensors
大小 (KB): 223103
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success