在COMFYUI中使用FLUX大模型时，怎么才能让多次生成的人物一致

人物一致性控制：控制人物在多场景、多个姿势下的一致性有很多方法，课程后期会介绍。多张图输出的显示问题：一次产出多张图在预览窗口目前不能并排显示。Lora的刷新：将Lora丢到文件夹后，多点几次刷新即可，Web UI中Lora库有刷新按钮。进阶学习途径：提到一些全球交流频道，如Confii生态大会相关频道。关于图像生成与工作流相关问题的讨论Discord使用问题：Discord已荒废很久，对于相关操作存在疑问。图像输出显示问题：探讨了图像输出是否并排显示，可能因误点单张显示导致，叉掉即可恢复并排。图像放大采样问题：放大后模糊需再次编码，放入采样器重新采样。模型训练与应用：训练自己人像可用于生成脸部头像，图像生成后可加载出视频。节点功能及学习方式：节点功能通过实践和需求寻找尝试，而非死记硬背，可参考优秀工作流和节点开发者的成果，如open art网站上的工作流。关于AI绘图提示词及工作流学习的安排

添加噪波：disable。这里关闭，因为是继承上一个采样器，所以不需要再添加噪声。运行后操作：fixed。相当于锁定随机种子的意思。步数：30。迭代的总步数，和之前保持一致。开始降噪步数：20。传递过来之后，是从第20步开始的。结束降噪步数：30。这个数字也可以保持默认，反正就是运行到结束。返回噪波：disable。不用返回了，到这一步已经结束了。但是，现在问题来了。如果我将refiner的模型连上提示词的话，第一个base模型的链接就会断开，怎么样才能让两个模型同时起作用呢？我们来加入一个新节点，右键点击-【新建节点】-【实用工具】-【Primitive元节点】。这个节点很有意思，它连接谁，就会变成谁的属性。在文本节点上单击右键，选择【转换文本为输入】。此时，文本节点上就多了一个文本的连接点。将元节点与文本节点相连接，这时元节点就变成了正向提示词的输入框。同理，可以将负向提示词框也用元节点代替。再复制出一套正负提示词节点，一套给base模型，一套给refiner模型。然后，base模型的那一套输出给第一个采样器节点，refiner模型的那一套输出给第二个采样器节点。

官方说明和操作：DavidH：Hey @everyone @here we're testing a new"Character Reference"feature today This is similar to the"Style Reference"feature,except instead of matching a reference style it tries to make the character match a"Character Reference"image.How it worksType --cref URL after your prompt with a URL to an image of a characterYou can use --cw to modify reference 'strength' from 100 to 0strength 100(--cw 100)is default and uses the face,hair,and clothesAt strength 0(--cw 0)it'll just focus on face(good for changing outfits / hair etc)What it's meant forThis feature works best when using characters made from Midjourney images.It's not designed for real people / photos(and will likely distort them as regular image prompts do)Cref works similarly to regular image prompts except it 'focuses' on the character traitsThe precision of this technique is limited,it won't copy exact dimples / freckles / or tshirt logos.Cref works for both Niji and normal MJ models and also can be combined with --sref Advanced FeaturesYou can use more than one URL to blend the information /characters from multiple images like this --cref URL1 URL2(this is similar to multiple image or style prompts)How does it work on the web alpha?Drag or paste an image into the imagine bar,it now has three icons.selecting these sets whether it is an image prompt,a style reference,or a character reference.Shift+select an option to use an image for multiple categories Remember,while MJ V6 is in alpha this and other features may change suddenly,but V6 official beta is coming soon.We'd love everyone's thoughts in ⁠ideas-and-features We hope you enjoy this early release and hope it helps you play with building stories and worlds