For a beginner also say that your videos are really very friendly, thank you very much. Because of my professional needs and the high learning threshold of flux, I've been using mimicpc to run flux before, it can load the workflow directly, I just want to download the flux model, and it handles the details wonderfully, but after watching your video, I'm using mimicpc to run flux again finally have a different experience, it's like I'm starting to get started! I feel like I'm starting to get the hang of it.
Yes, I think what you said is great. I am using mimicpc which can also achieve such effect. You can try it for free. In comparison, I think the use process of mimicpc is more streamlined and friendly.
Hi 鬼鲛先生, i want to consult you one more thing. For some output images, it doesn't really look similar like the original image, meaning if i show others the output images, they can't guess who the person is. If let say i want it to generate the output images that maintain the original face, but the parts that is below the neck is using the stickers-style body, can i do that? Reason being doing this, i guess at least people can recognize the person based on the output images. Thanks in advance.
You need to install the corresponding plug-in and download it from the management panel. My plugins are complete, so there is no need to download them.
@@guijiao Thanks for the information. I am using AMD CPU Ryzen 7, with 16G RAM and it is really very slow in running the workflow. It ran for almost 3 hours plus and it still stuck at the KSampler1. I just stopped it and planned to start all over again tomorrow 🙂
本课流程讲解：使用comfyUI工作流 配合 ollama 制作卡通贴纸
首先下载！
👋大头贴工作流地址
openart.ai/workflows/datou/stickeryou-simplified-version/diO4RafxrxaqH6RjajjQ
其次安装ollama+docker
如果不想微调模型可以不用微调。（微调模型与贴纸项目无关）
最后，修改comfyUI中的ollama设置参数，即可运行该工作流。
使用该工作流必须开启ollama语言模型。
如果仅仅只想学习如何制作贴纸，只需要学习安装ollama与comfyUI设置即可。
【以下内容与课程无关】
👋flux - GGUF优化模型：
github.com/city96/ComfyUI-GGUF！
For a beginner also say that your videos are really very friendly, thank you very much. Because of my professional needs and the high learning threshold of flux, I've been using mimicpc to run flux before, it can load the workflow directly, I just want to download the flux model, and it handles the details wonderfully, but after watching your video, I'm using mimicpc to run flux again finally have a different experience, it's like I'm starting to get started! I feel like I'm starting to get the hang of it.
👍👍👍，讲得仔细清楚，我这小白也能跟进！
Yes, I think what you said is great. I am using mimicpc which can also achieve such effect. You can try it for free. In comparison, I think the use process of mimicpc is more streamlined and friendly.
可以附上您的PDF文件嗎?想看一下內容!謝謝
drive.google.com/file/d/1OPvv9fGJrTdrZ1ObBS_ESpRBP-pXWaSh/view?usp=sharing
@@guijiao 您好!我的意思是把对应的 PDF 文件上传。然后得到 json 结构，我想知道上傳對應的PDF內容(經典養生祕笈--16條.pdf)是什麼?感謝
@@sct55014 那个与课程无关，只是让CHATGPT参考PDF结构图调出JSON文件，然后训练语言模型，做微调用。如果不做微调可以不需要看后面的内容。只是给语言学习训练用的。
up大大，为啥我的设置里里模型界面是空的，没有任何拉取模型的选项呢
支持
Hi 鬼鲛先生, i want to consult you one more thing. For some output images, it doesn't really look similar like the original image, meaning if i show others the output images, they can't guess who the person is. If let say i want it to generate the output images that maintain the original face, but the parts that is below the neck is using the stickers-style body, can i do that? Reason being doing this, i guess at least people can recognize the person based on the output images. Thanks in advance.
openart.ai/workflows/rui400/stickeryou---1-photo-for-stickers/e8TPNxcEGKdNJ40bQXlU
@@guijiao i tried this, but some photos, it still doesn't look the same 🙂
基本上，我想只是颈项以下会生成, 脸部完全不改变，不知道可以吗·？
换faceID，这个不是脸没有改变吗？
I failed to install PuLID_ComfyUI and ComfyUI InstanceID custom nodes, did you have similar problem?
You need to install the corresponding plug-in and download it from the management panel. My plugins are complete, so there is no need to download them.
@@guijiao Thanks for the information. I am using AMD CPU Ryzen 7, with 16G RAM and it is really very slow in running the workflow. It ran for almost 3 hours plus and it still stuck at the KSampler1. I just stopped it and planned to start all over again tomorrow 🙂
@@tspang1977 AMD graphics cards are not compatible. It is recommended to use cloud deployment. ,AMD NOT HAVE CUDA
@@guijiao Noted. Thanks.
t听晕系列
下次我一定尽力而为
@@guijiao 内容很实用 ，可以把中间过程多余的裁掉，突出重点就好了