Comfy-Org/desktop

Fork 0

mirror of https://github.com/Comfy-Org/desktop.git synced 2026-11-04 23:47:43 +00:00

[GH-ISSUE #1442] [Bug]: #412

New issue

Closed

opened 2026-10-31 22:12:40 +00:00 by bsakaguchi · 3 comments

bsakaguchi commented

2026-10-31 22:12:40 +00:00

Owner

Originally created by @jasonleejx on GitHub (Nov 24, 2025).
Original GitHub issue: https://github.com/Comfy-Org/desktop/issues/1442

App Version

comfyui windows portable 0.371

Expected Behavior

"load QwenImageTEModel" have BUG,
"loaded completely; 95367431640625005117571072.00 MB usable, 7909.74 MB loaded, full load: True"

Actual Behavior

Steps to Reproduce

Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load QwenImageTEModel_
loaded completely; 95367431640625005117571072.00 MB usable, 7909.74 MB loaded, full load: True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16

Debug Logs

Browser Logs

No response

Settings JSON

No response

Other

No response

┆Issue is synchronized with this Notion page by Unito

Originally created by @jasonleejx on GitHub (Nov 24, 2025). Original GitHub issue: https://github.com/Comfy-Org/desktop/issues/1442 ### App Version comfyui windows portable 0.371 ### Expected Behavior "load QwenImageTEModel" have BUG, "loaded completely; 95367431640625005117571072.00 MB usable, 7909.74 MB loaded, full load: True" ### Actual Behavior <img width="1941" height="530" alt="Image" src="https://github.com/user-attachments/assets/89f2cfcf-cb72-46e0-a3ac-5ccaabbe7724" /> ### Steps to Reproduce Using split attention in VAE Using split attention in VAE VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16 Using scaled fp8: fp8 matrix mult: False, scale input: False Requested to load QwenImageTEModel_ loaded completely; 95367431640625005117571072.00 MB usable, 7909.74 MB loaded, full load: True CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16 ### Debug Logs ```powershell ``` ### Browser Logs _No response_ ### Settings JSON _No response_ ### Other _No response_ ┆Issue is synchronized with this [Notion page](https://www.notion.so/Issue-1442-Bug-2b56d73d365081fa8e42e937f12fd73b) by [Unito](https://www.unito.io)

bsakaguchi

2026-10-31 22:12:40 +00:00

closed this issue
added the
bug

Potential Bug
labels

bsakaguchi commented

2026-10-31 22:12:40 +00:00

Author

Owner

@dosubot[bot] commented on GitHub (Nov 24, 2025):

Hi @jasonleejx! I'm Dosu and I’m helping the desktop team.

This is a known issue with QwenImageTEModel: the absurdly large memory value and OS error 1455 (page file too small) are symptoms of a backend or model-level bug, not the desktop app itself. The desktop app just wraps the backend and doesn't manage memory or model loading directly. Similar problems have been reported on other platforms, with memory usage numbers like 9.5e+25 MB and performance regressions when loading QwenImage models (see related issue).

To troubleshoot: try disabling all custom nodes, and launch the backend with flags like --lowvram, --novram, --cpu, --force-fp16, or --use-pytorch-cross-attention to reduce memory usage. If possible, increase your Windows page file size as a workaround for error 1455. If the issue persists even with minimal workflows, it's likely due to a recent backend or model update and not something the desktop app can fix.

If you share more details about your workflow or setup, I can help interpret logs or configuration.

To reply, just mention @dosu.

Docs are dead. Just use Dosu.

@dosubot[bot] commented on GitHub (Nov 24, 2025):  Hi @jasonleejx! I'm [Dosu](https://go.dosu.dev/dosubot) and I’m helping the desktop team.  This is a known issue with QwenImageTEModel: the absurdly large memory value and OS error 1455 (page file too small) are symptoms of a backend or model-level bug, not the desktop app itself. The desktop app just wraps the backend and doesn't manage memory or model loading directly. Similar problems have been reported on other platforms, with memory usage numbers like 9.5e+25 MB and performance regressions when loading QwenImage models [(see related issue)](https://github.com/Comfy-Org/desktop/issues/1250). To troubleshoot: try disabling all custom nodes, and launch the backend with flags like `--lowvram`, `--novram`, `--cpu`, `--force-fp16`, or `--use-pytorch-cross-attention` to reduce memory usage. If possible, increase your Windows page file size as a workaround for error 1455. If the issue persists even with minimal workflows, it's likely due to a recent backend or model update and not something the desktop app can fix. If you share more details about your workflow or setup, I can help interpret logs or configuration.  *To reply, just mention [@dosu](https://go.dosu.dev/dosubot?utm_source=github&utm_medium=bot-comment&utm_campaign=github-comment-footer-20260415&utm_content=reply-with-mention&utm_term=Comfy-Org%2Fdesktop).* --- Docs are dead. Just use [Dosu](https://dosu.dev?utm_source=github&utm_medium=bot-comment&utm_campaign=github-comment-footer-20260415&utm_content=static-docs-tagline&utm_term=Comfy-Org%2Fdesktop). [![Leave Feedback](https://img.shields.io/badge/Leave%20Feedback-555555?style=flat)](https://app.dosu.dev/response-feedback?utm_source=github&utm_medium=bot-comment&utm_campaign=github-comment-footer-20260415&utm_content=static-docs-feedback&utm_term=Comfy-Org%2Fdesktop#message_id=65f52c40-a057-41b1-bc77-8cd1f8966153) [![Ask Dosu about desktop](https://img.shields.io/badge/Ask%20Dosu%20about%20desktop-2f7b3f?style=flat&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iODYiIGhlaWdodD0iODkiIHZpZXdCb3g9IjAgMCA4NiA4OSIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj48cGF0aCBkPSJNNS4yOTIzNiAxMi43OTI4TDE3Ljc1OTMgNi42ODE4OFY3Mi41NjY3TDUuMjkyMzYgODQuMDYxOFYxMi43OTI4WiIgZmlsbD0iI0I0QkI5MSIvPjxwYXRoIGQ9Ik0xOC4yNTc1IDczLjExOTZMNTkuMTMyOSA3Mi43NDhMNTEuNzAxMSA4Mi40MDk1TDI5LjAzMzggODYuMjkxTDYuMjM5NjIgODUuMTU1NEwxOC4yNTc1IDczLjExOTZaIiBmaWxsPSIjNzc4NTYxIi8%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%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%2BPC9zdmc%2B)](https://github.dosu.com/Comfy-Org/desktop?utm_source=github&utm_medium=bot-comment&utm_campaign=github-comment-footer-20260415&utm_content=static-docs-ask-repo&utm_term=Comfy-Org%2Fdesktop) [![Share Dosu with your team](https://img.shields.io/badge/Share%20Dosu%20with%20your%20team-1f6feb?style=flat)](https://app.dosu.dev/signup?referrer=openSource&source=github-footer&utm_source=github&utm_medium=bot-comment&utm_campaign=github-comment-footer-20260415&utm_content=static-docs-share-team&utm_term=Comfy-Org%2Fdesktop)

bsakaguchi commented

2026-10-31 22:12:40 +00:00

Author

Owner

@jasonleejx commented on GitHub (Nov 24, 2025):

Hi,@dosubot! Thanks for your help.
I try to another model, allways have this problem "loaded completely; 95367431640625005117571072.00 MB usable".
Thank you very much!

Powershell

[START] Security scan
[DONE] Security scan

ComfyUI-Manager: installing dependencies done.

** ComfyUI startup time: 2025-11-24 19:57:25.617
** Platform: Windows
** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe
** ComfyUI Path: D:\ComfyUI_windows_portable\ComfyUI
** ComfyUI Base Folder Path: D:\ComfyUI_windows_portable\ComfyUI
** User directory: D:\ComfyUI_windows_portable\ComfyUI\user
** ComfyUI-Manager config path: D:\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini
** Log path: D:\ComfyUI_windows_portable\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
1.7 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Checkpoint files will always be loaded safely.
Total VRAM 22381 MB, total RAM 15993 MB
pytorch version: 2.8.0a0+gitfc14c65
Set: torch.backends.cudnn.enabled = False for better AMD performance.
AMD arch: gfx1150
ROCm version: (6, 4)
Set vram state to: NORMAL_VRAM
Device: cuda:0 AMD Radeon(TM) 880M Graphics : native
Enabled pinned memory 7196.0
Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention
Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
ComfyUI version: 0.3.71
ComfyUI frontend version: 1.28.9
[Prompt Server] web root: D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static
Total VRAM 22381 MB, total RAM 15993 MB
pytorch version: 2.8.0a0+gitfc14c65
Set: torch.backends.cudnn.enabled = False for better AMD performance.
AMD arch: gfx1150
ROCm version: (6, 4)
Set vram state to: NORMAL_VRAM
Device: cuda:0 AMD Radeon(TM) 880M Graphics : native
Enabled pinned memory 7196.0

Loading: ComfyUI-Manager (V3.37.1)

[ComfyUI-Manager] network_mode: public

ComfyUI Revision: 150 [c55fd748] *DETACHED | Released on '2025-11-21'

Import times for custom nodes:
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://127.0.0.1:8188
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
got prompt
Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load QwenImageTEModel_
loaded completely; 95367431640625005117571072.00 MB usable, 7909.74 MB loaded, full load: True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
!!! Exception during processing !!! 页面文件太小，无法完成操作。 (os error 1455)
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 510, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 324, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 298, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 286, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 925, in load_unet
model = comfy.sd.load_diffusion_model(unet_path, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 1370, in load_diffusion_model
sd, metadata = comfy.utils.load_torch_file(unet_path, return_metadata=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 79, in load_torch_file
raise e
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 63, in load_torch_file
with safetensors.safe_open(ckpt, framework="pt", device=device.type) as f:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: 页面文件太小，无法完成操作。 (os error 1455)

Prompt executed in 20.50 seconds
FETCH ComfyRegistry Data: 5/108
FETCH ComfyRegistry Data: 10/108
FETCH ComfyRegistry Data: 15/108
FETCH ComfyRegistry Data: 20/108
FETCH ComfyRegistry Data: 25/108
FETCH ComfyRegistry Data: 30/108
FETCH ComfyRegistry Data: 35/108
FETCH ComfyRegistry Data: 40/108
FETCH ComfyRegistry Data: 45/108
FETCH ComfyRegistry Data: 50/108
FETCH ComfyRegistry Data: 55/108
FETCH ComfyRegistry Data: 60/108
FETCH ComfyRegistry Data: 65/108
FETCH ComfyRegistry Data: 70/108
FETCH ComfyRegistry Data: 75/108
FETCH ComfyRegistry Data: 80/108
FETCH ComfyRegistry Data: 85/108
FETCH ComfyRegistry Data: 90/108
FETCH ComfyRegistry Data: 95/108
FETCH ComfyRegistry Data: 100/108
FETCH ComfyRegistry Data: 105/108
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.

@jasonleejx commented on GitHub (Nov 24, 2025): Hi,@dosubot! Thanks for your help. I try to another model, allways have this problem "loaded completely; 95367431640625005117571072.00 MB usable". Thank you very much! Powershell > [START] Security scan > [DONE] Security scan > ## ComfyUI-Manager: installing dependencies done. > ** ComfyUI startup time: 2025-11-24 19:57:25.617 > ** Platform: Windows > ** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] > ** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe > ** ComfyUI Path: D:\ComfyUI_windows_portable\ComfyUI > ** ComfyUI Base Folder Path: D:\ComfyUI_windows_portable\ComfyUI > ** User directory: D:\ComfyUI_windows_portable\ComfyUI\user > ** ComfyUI-Manager config path: D:\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini > ** Log path: D:\ComfyUI_windows_portable\ComfyUI\user\comfyui.log > > Prestartup times for custom nodes: > 1.7 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager > > Checkpoint files will always be loaded safely. > Total VRAM 22381 MB, total RAM 15993 MB > pytorch version: 2.8.0a0+gitfc14c65 > Set: torch.backends.cudnn.enabled = False for better AMD performance. > AMD arch: gfx1150 > ROCm version: (6, 4) > Set vram state to: NORMAL_VRAM > Device: cuda:0 AMD Radeon(TM) 880M Graphics : native > Enabled pinned memory 7196.0 > Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention > Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] > ComfyUI version: 0.3.71 > ComfyUI frontend version: 1.28.9 > [Prompt Server] web root: D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static > Total VRAM 22381 MB, total RAM 15993 MB > pytorch version: 2.8.0a0+gitfc14c65 > Set: torch.backends.cudnn.enabled = False for better AMD performance. > AMD arch: gfx1150 > ROCm version: (6, 4) > Set vram state to: NORMAL_VRAM > Device: cuda:0 AMD Radeon(TM) 880M Graphics : native > Enabled pinned memory 7196.0 > ### Loading: ComfyUI-Manager (V3.37.1) > [ComfyUI-Manager] network_mode: public > ### ComfyUI Revision: 150 [c55fd748] *DETACHED | Released on '2025-11-21' > > Import times for custom nodes: > 0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py > 0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager > > Context impl SQLiteImpl. > Will assume non-transactional DDL. > No target revision found. > Starting server > > To see the GUI go to: http://127.0.0.1:8188 > [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version. > [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/groupNode.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version. > [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json > [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/buttonGroup.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version. > [DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui/components/button.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version. > [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json > [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json > got prompt > Using split attention in VAE > Using split attention in VAE > VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16 > Using scaled fp8: fp8 matrix mult: False, scale input: False > Requested to load QwenImageTEModel_ > loaded completely; 95367431640625005117571072.00 MB usable, 7909.74 MB loaded, full load: True > CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16 > [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json > [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json > !!! Exception during processing !!! 页面文件太小，无法完成操作。 (os error 1455) > Traceback (most recent call last): > File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 510, in execute > output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs) > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 324, in get_output_data > return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs) > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 298, in _async_map_node_over_list > await process_inputs(input_dict, i) > File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 286, in process_inputs > result = f(**inputs) > ^^^^^^^^^^^ > File "D:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 925, in load_unet > model = comfy.sd.load_diffusion_model(unet_path, model_options=model_options) > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > File "D:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 1370, in load_diffusion_model > sd, metadata = comfy.utils.load_torch_file(unet_path, return_metadata=True) > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > File "D:\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 79, in load_torch_file > raise e > File "D:\ComfyUI_windows_portable\ComfyUI\comfy\utils.py", line 63, in load_torch_file > with safetensors.safe_open(ckpt, framework="pt", device=device.type) as f: > ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ > OSError: 页面文件太小，无法完成操作。 (os error 1455) > > Prompt executed in 20.50 seconds > FETCH ComfyRegistry Data: 5/108 > FETCH ComfyRegistry Data: 10/108 > FETCH ComfyRegistry Data: 15/108 > FETCH ComfyRegistry Data: 20/108 > FETCH ComfyRegistry Data: 25/108 > FETCH ComfyRegistry Data: 30/108 > FETCH ComfyRegistry Data: 35/108 > FETCH ComfyRegistry Data: 40/108 > FETCH ComfyRegistry Data: 45/108 > FETCH ComfyRegistry Data: 50/108 > FETCH ComfyRegistry Data: 55/108 > FETCH ComfyRegistry Data: 60/108 > FETCH ComfyRegistry Data: 65/108 > FETCH ComfyRegistry Data: 70/108 > FETCH ComfyRegistry Data: 75/108 > FETCH ComfyRegistry Data: 80/108 > FETCH ComfyRegistry Data: 85/108 > FETCH ComfyRegistry Data: 90/108 > FETCH ComfyRegistry Data: 95/108 > FETCH ComfyRegistry Data: 100/108 > FETCH ComfyRegistry Data: 105/108 > FETCH ComfyRegistry Data [DONE] > [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes > FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE] > [ComfyUI-Manager] All startup tasks have been completed.

bsakaguchi commented

2026-10-31 22:12:41 +00:00

Author

Owner

@benceruleanlu commented on GitHub (Dec 1, 2025):

Could you reopen this in the core ComfyUI repository? That repository contains the portable code, this repository is the desktop repository.

https://github.com/comfyanonymous/ComfyUI

@benceruleanlu commented on GitHub (Dec 1, 2025): Could you reopen this in the core ComfyUI repository? That repository contains the portable code, this repository is the desktop repository. https://github.com/comfyanonymous/ComfyUI

bsakaguchi referenced this issue

2026-10-31 22:17:28 +00:00

[PR #412] [CLOSED] Add GUI handlers for restore custom nodes #851

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

Comfy-Org/desktop#412

No description provided.

Rows
Columns