Видео

你好你好，ReActor明明已经安装缺失节点了，但是一直显示导入失败，这怎么办呢

so where i can download mask fade out video?

非常感谢老师的分享，可惜我能力有限报错”IPAdapter加载器 IPAdapter model not found.”怎么解决？谢谢了，研究一天了

Where's the V3 workflow? The one available at openart doesnt has the lighting nodes :(

且工作流的上面标题显示为“标签”，咋破

workflowMask Control、workflowIPA Controler这两个节点找不到了，哪里可以找到

Would this work with SDXL Lightening models and Controlnet? For some reason this workflow is really slow on my Google Colab, takes like 20min for a single image rendering using a T4 GPU

Despite all my attempts, the depthmap and lineart previews I get in the “ControlNet 背景/前景控制 深度图/线稿编辑（操作区）” group section do not reflect the entire image.

工作流能分享吗？

It's been a long time, we are waiting for new videos :D, Features about Cahange X,

Really great training, thank you, how can we do the selection process using our own special mask, on hair that is very complex, biref does not perform adequately.

Thanks for this masterpiece! I have a question: even though the missing nodes no longer show up in the manager after the installation, there are still a few red rectangles appearing. When I open the workflow, it says, "When loading the graph, the following node types were not found: LayerColor: Brightness Contrast🔍, workflowIPA Controller🔍, workflowMask Control🔍." Could you share the link to those nodes that aren't appearing in the manager? Thanks!

提示我缺少以下节点： ComfyUI InstantID (Native Support) GitHub Logo Author:cubiq ReActor Node for ComfyUI GitHub Logo Author:Gourieff PuLID_ComfyUI GitHub Logo Author:cubiq 但是我都按github上的下载步骤下载的其他的插件，还是不行，可以指导一下吗

为什么我生成的背景图总会有一个人呢，跟主题图摞在一起，但是能看出后米娜有手有脚

这是我看过的作品效果展示最棒的解说。看了就想拜师学艺。

你能指导我如何在 Google Colab 上使用吗？

大神 請問哪裡能打賞,太讚歎了！！

I have this problem LayerMask: SegmentAnythingUltra V2 PytorchStreamReader failed reading zip archive: failed finding central directory

翻译成中文: 你有微信账号吗？

where do I download from and to which folder should I put BiRefNet-general-epoch_244.pth

遇到問題 還請您協助一下 我遇到兩個問題 1. ComfyUI-BiRefNet-ZHO 無法匯入 有安裝 就是無法正常顯示 2. #1782 有問題 但是我找不到這個節點 拜託版主開釋一下 感謝

你就是我的神！感谢大佬

已用最新版本。全部通过一直到 k sampler 有这个错误。'NoneType' object has no attribute 'shape' 这么搞都搞不懂哪里错了。 用的是sd 15 and vae. dreamshaper

Thanks for your inspiring sharing. Do you have email or wechat to contact with?

Hello, Thank you very much for sharing this workflow with the community! I’m encountering a couple of issues while using it. Error Related to ExecutionBlocker: I’m seeing the following error message: File "D:\StabilityMatrix\Packages\ComfyUI\execution.py", line 182, in <listcomp> output.append([x for o in results for x in o[i]]) TypeError: 'ExecutionBlocker' object is not iterable FaceDetailer Error: Additionally, there is a TypeError 2153 Facedetailer showing up in the queue bar of ComfyUI, highlighted in red. I have reviewed the node configurations and their connections but haven’t been able to resolve these issues. It seems the ExecutionBlocker might be causing problems with data handling, and the Facedetailer error might be related to this or another issue in the workflow. Any guidance or suggestions you can provide to help resolve these issues would be greatly appreciated. Thanks again for your support and for sharing your work with the community! Best regards,

mark

遮罩细化(节点束) 報錯 zeros_like(): argument 'input' (position 1) must be Tensor, not NoneType..請問是甚麼原因? 感謝~

Xin lỗi vì làm phiền, tôi bị cảnh báo lỗi và cần bạn giúp đỡ khắc phục : ReActorFaceSwap reactor.execute() got an unexpected keyword argument 'face_boost'

IPAdapter Unified Loader的模型在那里下载啊

为什么工作流中的地址都没有一个能打开，好奇怪啊，国内

为什么跑IMG3 IMG4的时候选择相同的3和4强度跑不了，选择强度2才可以跑

"我已经安装了ComfyUI Easy Use，进行了更新，并运行了install.bat，但仍然无法删除书签部分的红色错误（7个标记）。它一直在那里，我不确定它是否对流程有任何支持。如果它只是一个附加功能，我希望它被移除。无论我重装或更新多少次，书签仍然显示为红色。"

node simple math in 主要操作区 error. how to fix ? SimpleMath+ 2593: - Return type mismatch between linked nodes: b, FLOAT != INT,FLOAT - Return type mismatch between linked nodes: a, FLOAT != INT,FLOAT

Can I ask why the character's face changes (not retaining its original features) when enabling the high-resolution upscaling mode? When I disable it, the issue goes away, thank you!

That's awesome. Thanks for sharing

why my workflow render output anime style @@

大佬的工作流工整美观，注释详细，解答错误到位，太棒了，要是有时间出一期讲解创作思路就太感谢了，我是个小白，喜欢学COMFYUI，看到这些节点就有点像看到一堆乐高方块，完全不懂怎么拼得出想要的样 子，不知道还有没救？可否请大佬指点一下应该怎么可以系统地学起，谢谢。

我看了工作流，不禁感叹一句，真佩服脑子好的人，这么复杂的工作流，得花好多时间去弄吧，关键是怎么知道该用什么节点来实现什么功能，太神奇了，受小弟真心的一拜

Looks great. Thanks for sharing it 😊

Error occurred when executing DetailerForEachDebug: DetailerForEachTest.doit() missing 1 required positional argument: 'model' File "G:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 313, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 188, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 165, in map_node_over_list process_inputs(input_dict, i) File "G:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 154, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ fix giúp em lỗi này là lỗi gì vậy ạ

I have an issue when Import node Comfyui-ergouzi-Nodes , Traceback (most recent call last): File "C:\Working\ComfyUI_windows_portable\ComfyUI odes.py", line 1941, in load_custom_node module_spec.loader.exec_module(module) File "<frozen importlib._bootstrap_external>", line 940, in exec_module File "<frozen importlib._bootstrap>", line 241, in call_with_frames_removed File "C:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-ergouzi-Nodes_init.py", line 57, in <module> from .nodes.EGDZXLJZ import SequentialImageLoader File "C:\Working\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-ergouzi-Nodes odes\EGDZXLJZ.py", line 5, in <module> import tkinter as tk ModuleNotFoundError: No module named 'tkinter' can you help me bro

Thanks for sharing, appreciate you so much!

I can't find the 切换人脸开关(1：原图2：参考图) node anywhere. Neither the download nor the online version.

謝謝你的分享感覺很厲害，但是出現找了好多天仍然找不到的模型，請問大大能分享下載連結嗎😖 謝謝你

Hi, I need you help this error: When loading the graph, the following node types were not found: LayerColor: Brightness Contrast 🔗 I install this node but still not fix @@

Thank you for sharing the workflow, even better with the video tutorial. I wish you would update the inpaint process with the Flux model too!

工作流牛啊。能拆分下吗？好多节点弹框框

openart.ai/workflows/grinlau/change-background/DoiYOkLj6ikwIbygd4gY

Thank you! When I first saw this video and workflow, I thought would be big probs running. Turns out it worked fine! Word of warning tho - rendering on a 4060ti 16vram did push the process to use low vram mode...so definitely not a workflow for potatoes. Still figuring some of the work flow out - so make sure to watch the video when playing with it!!

视频好棒，可以分享整合包吗