Open xiehuiqi220 opened 3 months ago
按顺序每个角色单独改变模型注意力即可,所有角色跑一遍后,即可开始推理多个角色同框的图
按顺序每个角色单独添加模型连接即可,所有角色跑一遍后,即可开始推理多个角色同框的图
没太听明白,大佬能解释一下吗?
可调整的参数如id_length, 多角色prompt格式如下:
"[Bob] A man, wearing a black suit\n[Alice]a woman, wearing a white shirt",
[
"[Bob] at home, read new paper",
"[Bob] on the road, near the forest",
"[Alice] is make a call at home",
"[NC]A tiger appeared in the forest, at night ",
"[NC] The car on the road, near the forest",
"[Bob] very frightened, open mouth, in the forest, at night",
"[Alice] very frightened, open mouth, in the forest, at night",
"[Bob] and [Alice] running very fast, in the forest, at night",
"[NC] A house in the forest, at night",
"[Bob] and [Alice] in the house filled with treasure, laughing, at night",
]
您好,预计本周会更新代码,包括效果更好的多角色的实现方式。
您好,预计本周将更新代码,包括效果更好的多角色的实现方式。
你好可以对这部分内容详细说明一下吗
您好,预计本周会更新代码,包括效果更好的多角色的实现方式。
期待。
您好,预计本周会更新代码,包括效果更好的多角色的实现方式。
是否已经更新?
目前我按照文档测试单个图片引用的角色生成了一致的多个画面,但是如果我是多个角色(多个参考图),应该如何设置参数和prompt?我看到官网有介绍多角色一致的图文,但是不知道如何实现。