v1.0This model is a face model based on Flux dev 1.0Recommended weights: 0.72-0.85 for standalone Use around 0.5 for mixed face lora. Weight reference look at the preview image.Recommended size: 768*1024,768*1344,720*1280Recommended steps: 22-30 stepsTrigger word: asgCustomized lora can add WeChat: cjw0402 Note the intention.Using completely artificial natural language manual marking training, cue word comprehension is very strong. It is not recommended that the cue word in the form of a word for out of the picture. And the chances of hand collapsing are very small, almost none.Can be free to play, welcome to actively return to the map.<s> </s><ul><li>v1.0</li><li>本模型是一个基于Flux dev 1.0的脸型模型</li><li>推荐权重：单独使用0.72-0.85 混合脸型lora使用在0.5左右。权重参考看预览图。</li><li>推荐尺寸：768*1024，768*1344,720*1280</li><li>推荐步数：22-30步</li><li>触发词：asg</li><li>定制lora可加V：cjw0402 备注来意。</li><li>使用完全人工的自然语言手动打标训练，提示词理解能力非常强。不推荐单词形式的提示词进行出图。并且手部崩坏的几率很小，几乎没有。</li><li>可自由发挥，欢迎大家积极返图。</li></ul>

Files with SHA256: b9f7c3ad3adca5f40ca4995e6adb54d7c1396109652cb4e401b8129b90b01435