torch compile breaks the output images on z-image turbo

works perfect without torch compile, but breaked with torch compile

log:

(venv) root@6ee658d76ef4:/workspace/ComfyUI# ^C
(venv) root@6ee658d76ef4:/workspace/ComfyUI# ^C
(venv) root@6ee658d76ef4:/workspace/ComfyUI# ^C
(venv) root@6ee658d76ef4:/workspace/ComfyUI# cd /workspace/ComfyUI
source venv/bin/activate
python main.py --listen 0.0.0.0 --port 9999 --cuda-device 0 --gpu-only --use-sage-attention --force-channels-last --preview-method none --auto-launch --cuda-malloc --fast --fp16-unet --fp16-text-enc --fp16-vae --force-non-blocking --disable-smart-memory
[ComfyUI-Manager] Using uv as Python module for pip operations.
Using Python 3.12.3 environment at: venv
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2025-11-28 15:41:17.081
** Platform: Linux
** Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
** Python executable: /workspace/ComfyUI/venv/bin/python
** ComfyUI Path: /workspace/ComfyUI
** ComfyUI Base Folder Path: /workspace/ComfyUI
** User directory: /workspace/ComfyUI/user
** ComfyUI-Manager config path: /workspace/ComfyUI/user/default/ComfyUI-Manager/config.ini
** Log path: /workspace/ComfyUI/user/comfyui.log
Using Python 3.12.3 environment at: venv
Using Python 3.12.3 environment at: venv

Prestartup times for custom nodes:
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Easy-Use
0.0 seconds: /workspace/ComfyUI/custom_nodes/rgthree-comfy
5.4 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Manager

Set cuda device to: 0
Checkpoint files will always be loaded safely.
Total VRAM 32109 MB, total RAM 190812 MB
pytorch version: 2.8.0+cu128
Enabled fp16 accumulation.
Set vram state to: HIGH_VRAM
Disabling smart memory management
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 181271.0
Using sage attention
Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
ComfyUI version: 0.3.75
ComfyUI frontend version: 1.32.9
[Prompt Server] web root: /workspace/ComfyUI/venv/lib/python3.12/site-packages/comfyui_frontend_package/static
Total VRAM 32109 MB, total RAM 190812 MB
pytorch version: 2.8.0+cu128
Enabled fp16 accumulation.
Set vram state to: HIGH_VRAM
Disabling smart memory management
Device: cuda:0 NVIDIA GeForce RTX 5090 : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 181271.0
### Loading: ComfyUI-Inspire-Pack (V1.23)
**************导入block_sparse_attn失败,调用临时函数;Using wrapper block_sparse_attn ,need to install block_sparse_attn to get better performance*************

[FlashVSR] Loading nodes...
[FlashVSR] ✓ SageAttention detected (~20-30% speedup enabled)
[FlashVSR] ✓ Loaded 2 node(s)

Warning: Could not register custom types for StarNodes settings
Traceback (most recent call last):
File "/workspace/ComfyUI/venv/lib/python3.12/site-packages/wand/api.py", line 159, in
libraries = load_library()
^^^^^^^^^^^^^^
File "/workspace/ComfyUI/venv/lib/python3.12/site-packages/wand/api.py", line 148, in load_library
raise IOError('cannot find library; tried paths: ' + repr(tried_paths))
OSError: cannot find library; tried paths: []

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/workspace/ComfyUI/nodes.py", line 2136, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 995, in exec_module
File "", line 488, in _call_with_frames_removed
File "/workspace/ComfyUI/custom_nodes/ComfyUI-MagickWand/__init__.py", line 1, in
from .nodes import NODE_CLASS_MAPPINGS
File "/workspace/ComfyUI/custom_nodes/ComfyUI-MagickWand/nodes.py", line 2, in
from wand.image import Image
File "/workspace/ComfyUI/venv/lib/python3.12/site-packages/wand/image.py", line 18, in
from . import assertions
File "/workspace/ComfyUI/venv/lib/python3.12/site-packages/wand/assertions.py", line 156, in
from .color import Color # noqa: E402
^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/ComfyUI/venv/lib/python3.12/site-packages/wand/color.py", line 10, in
from .api import library
File "/workspace/ComfyUI/venv/lib/python3.12/site-packages/wand/api.py", line 183, in
raise ImportError('MagickWand shared library not found.\n'
ImportError: MagickWand shared library not found.
You probably had not installed ImageMagick library.
Try to install:
https://docs.wand-py.org/en/latest/guide/install.html

Cannot import /workspace/ComfyUI/custom_nodes/ComfyUI-MagickWand module for custom nodes: MagickWand shared library not found.
You probably had not installed ImageMagick library.
Try to install:
https://docs.wand-py.org/en/latest/guide/install.html
### Loading: ComfyUI-Impact-Subpack (V1.3.5)
[Impact Pack/Subpack] Using folder_paths to determine whitelist path: /workspace/ComfyUI/user/default/ComfyUI-Impact-Subpack/model-whitelist.txt
[Impact Pack/Subpack] Ensured whitelist directory exists: /workspace/ComfyUI/user/default/ComfyUI-Impact-Subpack
[Impact Pack/Subpack] Loaded 0 model(s) from whitelist: /workspace/ComfyUI/user/default/ComfyUI-Impact-Subpack/model-whitelist.txt
[Impact Subpack] ultralytics_bbox: /workspace/ComfyUI/models/ultralytics/bbox
[Impact Subpack] ultralytics_segm: /workspace/ComfyUI/models/ultralytics/segm
Web extensions folder found at /workspace/ComfyUI/web/extensions/ComfyLiterals
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite: `ffmpeg_bin_path` is set to: /usr/bin/ffmpeg
WAS Node Suite: Finished. Loaded 220 nodes successfully.

"The best way to predict the future is to create it." - Peter Drucker

__ ______ ____ ____ ____ _ _
\ \ / / _ \ / ___| __ _ _ __ ___ ___| _ \ _____ __/ ___(_)_ __| |
\ \ / /| |_) | | _ / _` | '_ ` _ \ / _ \ | | |/ _ \ \ / / | _| | '__| |
\ V / | _ <| |_| | (_| | | | | | | __/ |_| | __/\ V /| |_| | | | | |
\_/ |_| \_\\____|\__,_|_| |_| |_|\___|____/ \___| \_/ \____|_|_| |_|

🎮 VRGameDevGirl custom nodes loaded successfully! 🎞️

All packages from requirements.txt are installed and up to date.
llama-cpp installed
All packages from requirements.txt are installed and up to date.
Found NVIDIA GPU: True
LP >>> Your python has the 'onnxruntime' library installed, although your computer supports 'onnxruntime-gpu'.
LP >>> Solution: If other node packages do not use the 'onnxruntime' library, then remove the 'onnxruntime' library for your python.
LP >>> Close ComfyUI and run the script at .\ComfyUI\custom_nodes\ComfyUI-LevelPixel-Advanced\scripts\remove_onnxruntime.bat
[Recognize Anything] RAM models found:
⚡ SeedVR2 optimizations check: Flash Attention ✅ | Triton ✅
📊 Initial CUDA memory: 30.86GB free / 31.36GB total
2025-11-28 15:43:48.787 | INFO | lightx2v.common.ops.attn.flash_attn::15 - flash_attn_varlen_func_v3 not found, please install flash_attn3 first
2025-11-28 15:43:48.878 | INFO | lightx2v.common.ops.attn.flash_attn::21 - torch_mlu_ops not found.
2025-11-28 15:43:48.965 | INFO | lightx2v.common.ops.attn.sage_attn::33 - torch_mlu_ops not found.
W1128 15:43:50.484000 12875 venv/lib/python3.12/site-packages/torch/utils/cpp_extension.py:2425] TORCH_CUDA_ARCH_LIST is not set, all archs for visible cards are included for compilation.
W1128 15:43:50.484000 12875 venv/lib/python3.12/site-packages/torch/utils/cpp_extension.py:2425] If this is not desired, please set os.environ['TORCH_CUDA_ARCH_LIST'] to specific architectures.
INFO 11-28 15:43:53 [__init__.py:216] Automatically detected platform cuda.
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite: `ffmpeg_bin_path` is set to: /usr/bin/ffmpeg
WAS Node Suite: Finished. Loaded 220 nodes successfully.

"Art is the lie that enables us to recognize the truth." - Friedrich Nietzsche

[/workspace/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ckpts path: /workspace/ComfyUI/custom_nodes/comfyui_controlnet_aux/ckpts
[/workspace/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using symlinks: False
[/workspace/ComfyUI/custom_nodes/comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
xFormers not available
xFormers not available
xFormers not available
xFormers not available
[ComfyUI-Easy-Use] server: v1.3.4 Loaded
[ComfyUI-Easy-Use] web root: /workspace/ComfyUI/custom_nodes/ComfyUI-Easy-Use/web_version/v2 Loaded

[rgthree-comfy] Loaded 48 epic nodes. 🎉

[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.

[CRT-Nodes __init__] Importing node classes...
Loading crt-nodes module
✅ ControlNet Aux loaded from 'comfyui_controlnet_aux' with 47 preprocessors
[CRT-Nodes __init__] Registering custom model paths...
... 'ultralytics_bbox' path registered.
... 'ultralytics_segm' path registered.
[CRT-Nodes __init__] INITIALIZATION COMPLETE.
### Loading: ComfyUI-Impact-Pack (V8.28)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
✅ 成功加载模块: banana imagesize by ratio.py
✅ 成功加载模块: TEXTSAVE_PATH_v3.py
✅ 成功加载模块: Mask_selector.py
✅ 成功加载模块: txt.py
✅ 成功加载模块: string_empty_word.py
✅ 成功加载模块: string_del_word.py
✅ 成功加载模块: show.py
✅ 成功加载模块: random prompt_v1.py
✅ 成功加载模块: png.py
✅ 成功加载模块: mask.py
✅ 成功加载模块: logic.py
✅ 成功加载模块: imageconcante_V1.py
✅ 成功加载模块: imageblend_v1.py
✅ 成功加载模块: imagebach.py
✅ 成功加载模块: image_text_V1.py
✅ 成功加载模块: image_resize_v3.py
✅ 成功加载模块: image_resize_v2.py
✅ 成功加载模块: image_resize_v1.py
✅ 成功加载模块: image_ratio_V1.py
✅ 成功加载模块: add_label.py
✅ 成功加载模块: Textsave_PATH_v2.py
✅ 成功加载模块: TEXTSAVE_PATH_v1.py
✅ 成功加载模块: PDimage_corp_v2.py
✅ 成功加载模块: PDimage_corp_v1.py
✅ 成功加载模块: PDimage.py
✅ 成功加载模块: PD_image_ratiosize.py
✅ 成功加载模块: PD_image_crop_v2.py
✅ 成功加载模块: PD_Text Overlay Node.py
✅ 成功加载模块: PD_RemoveWhiteBorder.py
✅ 成功加载模块: PD_Image_Rotate_v1.py
✅ 成功加载模块: PD_ImageListForSort.py
✅ 成功加载模块: PD_CropBorder.py
✅ 成功加载模块: PDMaskSelection.py
✅ 成功加载模块: Image Blend and White.py
✅ 成功加载模块: IMAGESAVE_PATH_v3.py
✅ 成功加载模块: IMAGESAVE_PATH_v2.py
✅ 成功加载模块: IMAGESAVE_PATH_v1.py
✅ 成功加载模块: Fill_mask.py
==================================================
🎨 Comfyui_PDuse 节点套件加载完成
==================================================
📦 总计加载节点数量: 47
📋 已加载的节点:
• PD：banana imagesize by ratio
• PDTEXT:SAVE_PATH_V3
• PD_Mask Selector
• PDstring:removecolorwords
• PDstring:del_EmptyLine
• PD_empty_word
• PD_del_word
• PD Show Text
• PD: Random Prompt
• PD:remove_background
• PD:Select_Mask
• PD:String
• PD:stringconcate
• PD:imageconcante_V1
• PD:Image Blend V1
• PDIMAGE:ImageCombine
• PD:Image_and_Text
• PD:image_resize_V3
• PD:image_resize_V2
• PD:image_resize_v1
• PD:Image Ratio Crop
• PD_Add Label
• PDTEXT:SAVE_PATH_V2
• PDTEXT:SAVE_PATH_V1
• PD:Image Crop V2
• PD:Image Crop V1
• PD:Image Crop Location
• PD:Image centerCrop
• PD:GetImageSize
• PD:GetImageRatio
• PDIMAGE:LongerSize
• PD_image ratiosize
• PD Image Crop Location_V2
• PD_Text Overlay Node
• PD_RemoveWhiteBorder
• PD:Image Rotate
• PD Image List Sort
• PD Image List Sort (With Metadata)
• PD_BatchCropBlackBorder
• PD_CropBorder
• PD:MASK SELECTION
• PD:Add White Background
• PDIMAGE:SAVE_PATH_V3
• PDIMAGE:SAVE_PATH_V2
• PDIMAGE:SAVE_PATH
• PD:Mask Fill Holes
• PD:Mask Remove Small Objects
==================================================
------------------------------------------
Comfyroll Studio v1.76 : 175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------

Initializing ControlAltAI Nodes
[MultiGPU Core Patching] Patching mm.soft_empty_cache for Comprehensive Memory Management (VRAM + CPU + Store Pruning)
[MultiGPU Core Patching] Patching mm.get_torch_device, mm.text_encoder_device, mm.unet_offload_device
[MultiGPU DEBUG] Initial current_device: cuda:0
[MultiGPU DEBUG] Initial current_text_encoder_device: cuda:0
[MultiGPU DEBUG] Initial current_unet_offload_device: cuda:0
[MultiGPU] Initiating custom_node Registration. . .
-----------------------------------------------
custom_node Found Nodes
-----------------------------------------------
ComfyUI-LTXVideo N 0
ComfyUI-Florence2 Y 2
ComfyUI_bitsandbytes_NF4 N 0
x-flux-comfyui N 0
ComfyUI-MMAudio Y 3
ComfyUI-GGUF Y 18
PuLID_ComfyUI N 0
ComfyUI-WanVideoWrapper Y 20
-----------------------------------------------
[MultiGPU] Registration complete. Final mappings: CheckpointLoaderAdvancedMultiGPU, CheckpointLoaderAdvancedDisTorch2MultiGPU, UNetLoaderLP, UNETLoaderMultiGPU, VAELoaderMultiGPU, CLIPLoaderMultiGPU, DualCLIPLoaderMultiGPU, TripleCLIPLoaderMultiGPU, QuadrupleCLIPLoaderMultiGPU, CLIPVisionLoaderMultiGPU, CheckpointLoaderSimpleMultiGPU, ControlNetLoaderMultiGPU, DiffusersLoaderMultiGPU, DiffControlNetLoaderMultiGPU, UNETLoaderDisTorch2MultiGPU, VAELoaderDisTorch2MultiGPU, CLIPLoaderDisTorch2MultiGPU, DualCLIPLoaderDisTorch2MultiGPU, TripleCLIPLoaderDisTorch2MultiGPU, QuadrupleCLIPLoaderDisTorch2MultiGPU, CLIPVisionLoaderDisTorch2MultiGPU, CheckpointLoaderSimpleDisTorch2MultiGPU, ControlNetLoaderDisTorch2MultiGPU, DiffusersLoaderDisTorch2MultiGPU, DiffControlNetLoaderDisTorch2MultiGPU, Florence2ModelLoaderMultiGPU, DownloadAndLoadFlorence2ModelMultiGPU, MMAudioModelLoaderMultiGPU, MMAudioFeatureUtilsLoaderMultiGPU, MMAudioSamplerMultiGPU, UnetLoaderGGUFDisTorchMultiGPU, UnetLoaderGGUFAdvancedDisTorchMultiGPU, CLIPLoaderGGUFDisTorchMultiGPU, DualCLIPLoaderGGUFDisTorchMultiGPU, TripleCLIPLoaderGGUFDisTorchMultiGPU, QuadrupleCLIPLoaderGGUFDisTorchMultiGPU, UnetLoaderGGUFDisTorch2MultiGPU, UnetLoaderGGUFAdvancedDisTorch2MultiGPU, CLIPLoaderGGUFDisTorch2MultiGPU, DualCLIPLoaderGGUFDisTorch2MultiGPU, TripleCLIPLoaderGGUFDisTorch2MultiGPU, QuadrupleCLIPLoaderGGUFDisTorch2MultiGPU, UnetLoaderGGUFMultiGPU, UnetLoaderGGUFAdvancedMultiGPU, CLIPLoaderGGUFMultiGPU, DualCLIPLoaderGGUFMultiGPU, TripleCLIPLoaderGGUFMultiGPU, QuadrupleCLIPLoaderGGUFMultiGPU, LoadWanVideoT5TextEncoderMultiGPU, WanVideoTextEncodeMultiGPU, WanVideoTextEncodeCachedMultiGPU, WanVideoTextEncodeSingleMultiGPU, WanVideoVAELoaderMultiGPU, WanVideoTinyVAELoaderMultiGPU, WanVideoBlockSwapMultiGPU, WanVideoImageToVideoEncodeMultiGPU, WanVideoDecodeMultiGPU, WanVideoModelLoaderMultiGPU, WanVideoSamplerMultiGPU, WanVideoVACEEncodeMultiGPU, WanVideoEncodeMultiGPU, LoadWanVideoClipTextEncoderMultiGPU, WanVideoClipVisionEncodeMultiGPU, WanVideoControlnetLoaderMultiGPU, FantasyTalkingModelLoaderMultiGPU, Wav2VecModelLoaderMultiGPU, WanVideoUni3C_ControlnetLoaderMultiGPU, DownloadAndLoadWav2VecModelMultiGPU
xFormers not available
xFormers not available
[Crystools INFO] Crystools version: 1.27.4
[Crystools INFO] Platform release: 6.8.0-85-generic
[Crystools INFO] JETSON: Not detected.
[Crystools INFO] CPU: AMD Ryzen 9 9950X 16-Core Processor - Arch: x86_64 - OS: Linux 6.8.0-85-generic
[Crystools INFO] pynvml (NVIDIA) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce RTX 5090
[Crystools INFO] NVIDIA Driver: 580.95.05
Using sage attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.
(RES4LYF) Importing legacy samplers.
# 😺dzNodes: LayerStyle -> Cannot import name 'guidedFilter' from 'cv2.ximgproc'
A few nodes cannot works properly, while most nodes are not affected. Please REINSTALL package 'opencv-contrib-python'.
For detail refer to https://github.com/chflame163/ComfyUI_LayerStyle/issues/5
Ib Custom Nodes: Loaded
ComfyUI-GGUF: Allowing full torch compile
[MultiGPU Core Patching] text_encoder_device_patched returning device: cuda:0 (current_text_encoder_device=cuda:0)
[MultiGPU Core Patching] text_encoder_device_patched returning device: cuda:0 (current_text_encoder_device=cuda:0)
Efficiency Nodes: Attempting to add Control Net options to the 'HiRes-Fix Script' Node (comfyui_controlnet_aux add-on)...Success!
Loaded Efficiency nodes from /workspace/ComfyUI/custom_nodes/efficiency-nodes-comfyui
Loaded comfyui_controlnet_aux nodes from /workspace/ComfyUI/custom_nodes/comfyui_controlnet_aux
Could not find AdvancedControlNet nodes
Could not find AnimateDiff nodes
Could not find IPAdapter nodes
Loaded VideoHelperSuite from /workspace/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
### Loading: ComfyUI-Impact-Pack (V8.28)
### Loading: ComfyUI-Impact-Pack (V8.28)
Loaded ImpactPack nodes from /workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Manager (V3.37.2)
[ComfyUI-Manager] network_mode: public
### ComfyUI Version: v0.3.75-18-g52e778ff | Released on '2025-11-28'

Import times for custom nodes:
0.0 seconds: /workspace/ComfyUI/custom_nodes/websocket_image_save.py
0.0 seconds: /workspace/ComfyUI/custom_nodes/comfyui-imageautotone
0.0 seconds: /workspace/ComfyUI/custom_nodes/comfy-image-saver
0.0 seconds: /workspace/ComfyUI/custom_nodes/masquerade-nodes-comfyui
0.0 seconds: /workspace/ComfyUI/custom_nodes/comfyui-detail-daemon
0.0 seconds: /workspace/ComfyUI/custom_nodes/wanblockswap
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-WanMoeKSampler
0.0 seconds: /workspace/ComfyUI/custom_nodes/comfyui-saveimage-plus
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI_Ib_CustomNodes
0.0 seconds: /workspace/ComfyUI/custom_nodes/cg-use-everywhere
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Image-Size-Tools
0.0 seconds: /workspace/ComfyUI/custom_nodes/comfyui_ttp_toolset
0.0 seconds: /workspace/ComfyUI/custom_nodes/soundflow
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Inpaint-CropAndStitch
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-VAE-Utils
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-MagCache
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-mxToolkit
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Basic-Math
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyLiterals
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-MelBandRoFormer
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-SoundFlow
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-GGUF
0.0 seconds: /workspace/ComfyUI/custom_nodes/LanPaint
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Florence2
0.0 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-WanAnimatePreprocess
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Unusual-Tools
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI_essentials
0.1 seconds: /workspace/ComfyUI/custom_nodes/comfyui-various
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Image-Saver
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-MultiGPU
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-KJNodes
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-RadialAttn
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Custom-Scripts
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-DepthAnythingV2
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Chibi-Nodes
0.1 seconds: /workspace/ComfyUI/custom_nodes/ControlAltAI-Nodes
0.1 seconds: /workspace/ComfyUI/custom_nodes/derfuu_comfyui_moddednodes
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation
0.1 seconds: /workspace/ComfyUI/custom_nodes/comfyui-vrgamedevgirl
0.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-FlashVSR
0.2 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Video-Depth-Anything
0.2 seconds: /workspace/ComfyUI/custom_nodes/comfyui-dream-video-batches
0.2 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-segment-anything-2
0.2 seconds: /workspace/ComfyUI/custom_nodes/comfyui_controlnet_aux
0.2 seconds: /workspace/ComfyUI/custom_nodes/Comfyui_PDuse
0.3 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI_Comfyroll_CustomNodes
0.3 seconds: /workspace/ComfyUI/custom_nodes/rgthree-comfy
0.4 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
0.5 seconds: /workspace/ComfyUI/custom_nodes/comfyui-art-venture
0.5 seconds: /workspace/ComfyUI/custom_nodes/efficiency-nodes-comfyui
0.5 seconds: /workspace/ComfyUI/custom_nodes/kaytool
0.6 seconds: /workspace/ComfyUI/custom_nodes/audio-separation-nodes-comfyui
0.7 seconds: /workspace/ComfyUI/custom_nodes/comfyui-dynamicprompts
0.7 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-WanVideoWrapper
0.8 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack
0.9 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Impact-Pack
0.9 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI_LayerStyle
1.0 seconds: /workspace/ComfyUI/custom_nodes/comfyui-impact-subpack
1.0 seconds: /workspace/ComfyUI/custom_nodes/CRT-Nodes
1.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-SeedVR2_VideoUpscaler
1.4 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Easy-Use
1.4 seconds: /workspace/ComfyUI/custom_nodes/comfyui-ollama
1.4 seconds (IMPORT FAILED): /workspace/ComfyUI/custom_nodes/ComfyUI-MagickWand
1.5 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-MMAudio
1.7 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Crystools
1.8 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Inspyrenet-Rembg
1.9 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-Manager
2.3 seconds: /workspace/ComfyUI/custom_nodes/comfyui-propost
2.5 seconds: /workspace/ComfyUI/custom_nodes/RES4LYF
3.1 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-GIMM-VFI
4.6 seconds: /workspace/ComfyUI/custom_nodes/comfyui-levelpixel-advanced
5.7 seconds: /workspace/ComfyUI/custom_nodes/was-node-suite-comfyui
6.2 seconds: /workspace/ComfyUI/custom_nodes/rembg-comfyui-node
6.5 seconds: /workspace/ComfyUI/custom_nodes/was-ns
10.7 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI-LightVAE
26.9 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI_StarNodes
38.2 seconds: /workspace/ComfyUI/custom_nodes/ComfyUI_FlashVSR

[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/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://0.0.0.0:9999
FETCH ComfyRegistry Data: 5/108
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
FETCH ComfyRegistry Data: 10/108
VAE load device: cuda:0, offload device: cuda:0, dtype: torch.float16
[MultiGPU Core Patching] text_encoder_device_patched returning device: cuda:0 (current_text_encoder_device=cuda:0)
Requested to load ZImageTEModel_
loaded completely; 95367431640625005117571072.00 MB usable, 7672.25 MB loaded, full load: True
CLIP/text encoder model load device: cuda:0, offload device: cuda:0, current: cuda:0, dtype: torch.float16
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
Using scaled fp8: fp8 matrix mult: False, scale input: False
model weight dtype torch.float16, manual cast: None
model_type FLOW
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
unet missing: ['norm_final.weight']
TorchCompileModelAdvanced: Compile key list:
- diffusion_model.layers.0
- diffusion_model.layers.1
- diffusion_model.layers.2
- diffusion_model.layers.3
- diffusion_model.layers.4
- diffusion_model.layers.5
- diffusion_model.layers.6
- diffusion_model.layers.7
- diffusion_model.layers.8
- diffusion_model.layers.9
- diffusion_model.layers.10
- diffusion_model.layers.11
- diffusion_model.layers.12
- diffusion_model.layers.13
- diffusion_model.layers.14
- diffusion_model.layers.15
- diffusion_model.layers.16
- diffusion_model.layers.17
- diffusion_model.layers.18
- diffusion_model.layers.19
- diffusion_model.layers.20
- diffusion_model.layers.21
- diffusion_model.layers.22
- diffusion_model.layers.23
- diffusion_model.layers.24
- diffusion_model.layers.25
- diffusion_model.layers.26
- diffusion_model.layers.27
- diffusion_model.layers.28
- diffusion_model.layers.29
FETCH ComfyRegistry Data: 105/108
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
Requested to load Lumina2
loaded completely; 95367431640625005117571072.00 MB usable, 5870.29 MB loaded, full load: True
0%| | 0/4 [00:00