Click queue prompt, server stopped and reconnecting

[Wenxuanxi]

Hi, guys, I took 4 hours to deploy my comfyui on my google cloud instance. When I installed and updated all models, I was excited to see my first picture based comfyui. But when I clicked the queue prompt button, it appeared the box with reconnecting, when I switched to the cmd window, nothing happend except got promt and pause. I tried run nvidia and run cpu, both did same. Anyone, could you please tell me what I should do ....

[Lodjuret]

Having a similiar error.

I'm on linux and when clicking queue my terminal closes. No errors and can't find any logs. This is a clean install and running default workspace.

Edit: Using SDXL_v10 and running python 3.11. Have installed Nvidia specific pytorch.

Edit2: Seems to work when i don't use sdXL_v10VAEFix.safetensor. So from that information maybe vae fixed checkpoints does not work? I am a stable diffusion and comfyui noob, but maybe worth to check it out.

[microvswind]

similar error on run_cup.bat

[microvswind]

[camoody1]

I'm getting this exact same issue on a fresh install of the portable installation.

Fresh Windows 11 installation Nvidia RTX 3060 12GB 32GB RAM Using run_nvidia_gpu.bat

I was able to get it to run successfully once, but then I changed the model in the checkpoint node (to Juggernaught v7) and it hasn't worked since. The workflow seems to get stuck with the highlight on the initial checkpoint node and the cmd window just says "pause".

CMD output from server start: ---------------------------------_ H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build ** ComfyUI start up time: 2023-12-02 20:29:38.930459

Prestartup times for custom nodes: 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Total VRAM 12288 MB, total RAM 32695 MB Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3060 : cudaMallocAsync VAE dtype: torch.bfloat16 Using pytorch cross attention Adding extra search path checkpoints H:\Stable_Diffusion_Models\models/Stable-diffusion Adding extra search path configs H:\Stable_Diffusion_Models\models/Stable-diffusion Adding extra search path vae H:\Stable_Diffusion_Models\models/VAE Adding extra search path loras H:\Stable_Diffusion_Models\models/Lora Adding extra search path loras H:\Stable_Diffusion_Models\models/LyCORIS Adding extra search path upscale_models H:\Stable_Diffusion_Models\upscale_models Adding extra search path upscale_models H:\Stable_Diffusion_Models\models/BSRGAN Adding extra search path upscale_models H:\Stable_Diffusion_Models\models/ESRGAN Adding extra search path upscale_models H:\Stable_Diffusion_Models\models/GFPGAN Adding extra search path upscale_models H:\Stable_Diffusion_Models\models/LDSR Adding extra search path upscale_models H:\Stable_Diffusion_Models\models/RealESRGAN Adding extra search path upscale_models H:\Stable_Diffusion_Models\models/SwinIR Adding extra search path embeddings H:\Stable_Diffusion_Models\models/Embeddings Adding extra search path hypernetworks H:\Stable_Diffusion_Models\models/hypernetworks Adding extra search path controlnet H:\Stable_Diffusion_Models\models/ControlNet Bmad-DirtyUndoRedo Loaded. Skip H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bmad-DirtyUndoRedo module for custom nodes due to the lack of NODE_CLASS_MAPPINGS.

Loading: ComfyUI-Impact-Pack (V4.38)

Loading: ComfyUI-Impact-Pack (Subpack: V0.3.2)

Loading: ComfyUI-Manager (V1.6.1)

ComfyUI Revision: 1768 [b2517b4c] | Released on '2023-12-02'

[tinyterraNodes] Loaded WAS Node Suite: BlenderNeko's Advanced CLIP Text Encode found, attempting to enable CLIPTextEncode support. WAS Node Suite: CLIPTextEncode (BlenderNeko Advanced + NSP) node enabled under WAS Suite/Conditioning menu. WAS Node Suite: OpenCV Python FFMPEG support is enabled WAS Node Suite Warning: ffmpeg_bin_path is not set in H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json config file. Will attempt to use system ffmpeg binaries if available. WAS Node Suite: Finished. Loaded 198 nodes successfully.

    "Everything you've ever wanted is on the other side of fear." - George Addair

Import times for custom nodes: 0.0 seconds (IMPORT FAILED): H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Bmad-DirtyUndoRedo 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\cg-use-everywhere 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_ADV_CLIP_emb 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_NestedNodeBuilder 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\OneButtonPrompt 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale 0.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\Derfuu_ComfyUI_ModdedNodes 0.1 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui 0.4 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager 0.8 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_tinyterraNodes 1.0 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Impact-Pack 1.6 seconds: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui

Starting server

To see the GUI go to: http://127.0.0.1:8188 FETCH DATA from: H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json got prompt model_type EPS adm 2816 Using pytorch attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using pytorch attention in VAE

H:\ComfyUI\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable>pause Press any key to continue . . .

[DDWUDI]

我也是这样的错误，有人知道原因吗。

[d3c1m470r]

this is the second ui im trying to use for local generation and it does the same error for me. hours wasted of my life im sick of these terrible releases which dont work for a lot of people rly

[dsegoviap]

I have the same problem. Does anyone know how to fix it?

[ltdrdata]

Usually, this issue occurs due to insufficient memory resources, leading to a forced termination. Monitor the usage of RAM/VRAM to investigate.

[camoody1]

I have the same problem. Does anyone know how to fix it?

I swear to God, my fix for this issue was to change my Windows Swap File settings to allow Windows to manage the swap file for each drive. And this was on a fresh Windows 11 reinstall. By default, my swap drive was under 100MB. After I clicked the other option, Windows assigned, like, 30GB to be a swap drive. That error immediately stopped for me.

[dsegoviap]

I have the same problem. Does anyone know how to fix it?

I swear to God, my fix for this issue was to change my Windows Swap File settings to allow Windows to manage the swap file for each drive. And this was on a fresh Windows 11 reinstall. By default, my swap drive was under 100MB. After I clicked the other option, Windows assigned, like, 30GB to be a swap drive. That error immediately stopped for me.

Thanks friend! that was the solution. I change my Window Swap File up to 32GB.

[camoody1]

Thanks friend! that was the solution. I change my Window Swap File up to 32GB.

Wonderful! I'm glad that fixed it for you, also! Such an odd setting for Windows to mess up.

[hong2610]

我也遇到了同样的问题。有人知道该怎么解决吗？

我发誓，我解决这个问题的方法是更改​​我的 Windows 交换文件设置，以允许 Windows 管理每个驱动器的交换文件。这是在重新安装 Windows 11 时发生的。默认情况下，我的交换驱动器小于 100MB。在我单击另一个选项后，Windows 分配了大约 30GB 作为交换驱动器。那个错误立即停止了。

谢谢朋友！这就是解决方案。我将窗口交换文件更改为 32GB。

Could you please tell me how to do it? I am a computer novice and I have the same problem.

[a-gridnev]

我也遇到了同样的问题。有人知道该怎么解决吗？

我发誓，我解决这个问题的方法是更改​​我的 Windows 交换文件设置，以允许 Windows 管理每个驱动器的交换文件。这是在重新安装 Windows 11 时发生的。默认情况下，我的交换驱动器小于 100MB。在我单击另一个选项后，Windows 分配了大约 30GB 作为交换驱动器。那个错误立即停止了。

谢谢朋友！这就是解决方案。我将窗口交换文件更改为 32GB。

Could you please tell me how to do it? I am a computer novice and I have the same problem.

right click on start button -> Search -> type "performance" -> select "Adjust the appearance and performance of Windows" -> go to tab "Advanced" -> in block "Virtual memory" press to "Change" -> select "System managed size" radio button and then press "Set" -> reboot your PC

screenshots

[BuRZone]

I solved this problem by shutting down processes and increasing the amount of free RAM

[cleverlybulk]

I have the same problem. Does anyone know how to fix it?

I swear to God, my fix for this issue was to change my Windows Swap File settings to allow Windows to manage the swap file for each drive. And this was on a fresh Windows 11 reinstall. By default, my swap drive was under 100MB. After I clicked the other option, Windows assigned, like, 30GB to be a swap drive. That error immediately stopped for me.

it works for me !! thanks!!

[camoody1]

@mhidoart Glad it could help! I was so surprised when it fixed my issue!

[nothingness6]

我也遇到了同样的问题。有人知道该怎么解决吗？

我发誓，我解决这个问题的方法是更改​​我的 Windows 交换文件设置，以允许 Windows 管理每个驱动器的交换文件。这是在重新安装 Windows 11 时发生的。默认情况下，我的交换驱动器小于 100MB。在我单击另一个选项后，Windows 分配了大约 30GB 作为交换驱动器。那个错误立即停止了。

谢谢朋友！这就是解决方案。我将窗口交换文件更改为 32GB。

Could you please tell me how to do it? I am a computer novice and I have the same problem.

right click on start button -> Search -> type "performance" -> select "Adjust the appearance and performance of Windows" -> go to tab "Advanced" -> in block "Virtual memory" press to "Change" -> select "System managed size" radio button and then press "Set" -> reboot your PC screenshots

This one works! Thanks!

[allstar1945]

mine still reconnecting, i thought my GPU the promblem, am i wrong, i have 4070 12GB VRAM and 16GB RAM, any help?, couldn't find any help on google