-
-
4
-
326
-
0
-
1Int-🔬 就是这个
-
0
-
11一直增加到差不到90%才会继续跑,这一步是怎么回事?第二张图就快了几十秒就好了,关了comfyui再启动就会又来一次,我的模型是FLUX 16G大小的一个版本,显卡8G,显卡,电脑32G内存。用的秋叶的comfyui包,怎么能加速这一步骤,求指教,谢谢。
-
1大家在使用comfyui使用过程中遇到的各种困惑和问题,可以提供详细线索信息,帮助分析、识别和解决。
-
1求助大佬,为什么已经安装了manager但是进去之后还是没有显示
-
11
-
1
-
1请问一下,如果我要使两个AI角色同框,那么该如何使它们与之前出现过的形象保持一致性呢
-
2
-
5
-
0这三个节点,是一个节点嘛,按那个比较好,3个全安装冲不冲突?
-
0
-
2
-
1F:\ComfyUI-aki\ComfyUI-aki-v1.6\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly") Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success! Skip F:\ComfyUI-aki\ComfyUI-aki-v
-
2
-
0大家好 我的提示词是 A dog is sleeping,出来的效果图会变成多只的狗 而且还是连体的 也就是所谓的k型 是哪方面设置出错?
-
0
-
3
-
0如题,不加lora正常占用16g显存,用一个300m的lora直接导致显存24g爆了是为什么?? 还有秋叶启动器里的使用虚拟内存勾选不上是为什么??点了但无效
-
0D:\UI\ComfyUI-aki-v1.3\models\nsfw_detector\vit-base-nsfw-detector does not appear to have a file named config.json. Checkout 'https://huggingface.co/D:\UI\ComfyUI-aki-v1.3\models\nsfw_detector\vit-base-nsfw-detector/None' for available files.报错,求大佬分享一下文件夹的文件
-
0
-
7用了秋叶整合包,现在都是在默认模式下生图。一换模型就报错或者闪退
-
0提示vaedecode错误: MPS backend out of memory (MPS allocated: 6.45 GB, other . max alowed:36.27 GB), Tried to alocate 146.25 MB on prvae pOO. US PYTORCH MPS HIGH WATERMARK RAT10=0.0 to disable uper imit for memony alocations (ma ilocations: 29.68 GB cause system failure). 这个要在哪里设置?
-
0各位佬,现在生成的格式是webp的,怎么才能换mp4的。
-
1每次生成的汉服角色,各种飘,头发飘,裙摆飘,有没有办法像游戏原画那样,衣服是静止的
-
0
-
1请问有什么笔记本能带的动comfyui中等级别模型的,现在2g显存只能跑1.5模型的,出一张图也要八九分钟。
-
5
-
0CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 6.00 GiB of which 0 bytes is free. Of the allocated memory 5.25 GiB is allocated by PyTorch, and 122.82 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-vari) ComfyUI Error Report ## Error Details - **Node ID:** 22 - **Node Type:** SUPIR_Upscale - **Exception Type:** torch.OutOfMemoryError - **E
-
2秋叶版的管理器怎么安装大神告知一下呗
-
1
-
0不知道能不能 白嫖一个Dream Tech XL | 筑梦工业XL_v7.0版本 或v7.0以上的模型呢?
-
10
-
4mimicmotionwrapper DWpose 缺失yolox_l.torchscript.pt
-
6
-
1
-
0有时候17秒出图有时候要等80多秒到底什么原因啊在网上搜教程也没有!
-
2大佬们有没有关于局部重绘的相关教程
-
2
-
5
-
0
-
5使用comfyui的新的joy caption two提示词反推模型,照着github一步步来安装的 报错代码: # ComfyUI Error Report ## Error Details - **Node Type:** Joy_caption_two_load - **Exception Type:** RuntimeError - **Exception Message:** PytorchStreamReader failed reading file data/16: invalid header or archive is corrupted ## Stack Trace ``` File "E:\AIGC\ComfyUI\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, 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_c