|
|
| [2026-07-17 15:02:05.133] ** ComfyUI startup time: 2026-07-17 15:02:05.133
|
| [2026-07-17 15:02:05.133] ** Platform: Windows
|
| [2026-07-17 15:02:05.134] ** Python version: 3.13.12 (tags/v3.13.12:1cbe481, Feb 3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)]
|
| [2026-07-17 15:02:05.134] ** Python executable: G:\ComfyUI_windows_portable-G313\python_embeded\python.exe
|
| [2026-07-17 15:02:05.134] ** ComfyUI Path: G:\ComfyUI_windows_portable-G313\ComfyUI
|
| [2026-07-17 15:02:05.134] ** ComfyUI Base Folder Path: G:\ComfyUI_windows_portable-G313\ComfyUI
|
| [2026-07-17 15:02:05.134] ** User directory: G:\ComfyUI_windows_portable-G313\ComfyUI\user
|
| [2026-07-17 15:02:05.135] ** ComfyUI-Manager config path: G:\ComfyUI_windows_portable-G313\ComfyUI\user\__manager\config.ini
|
| [2026-07-17 15:02:05.135] ** Log path: G:\ComfyUI_windows_portable-G313\ComfyUI\user\comfyui.log
|
|
|
| Prestartup times for custom nodes:
|
| [2026-07-17 15:02:07.556] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\rgthree-comfy
|
| [2026-07-17 15:02:07.556] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Easy-Use
|
| [2026-07-17 15:02:07.556] 9.4 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Manager
|
| [2026-07-17 15:02:07.556]
|
| [2026-07-17 15:02:12.792] G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\torch\cuda\__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
|
| import pynvml
|
| [2026-07-17 15:02:16.270] Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'quantize_and_rotate_rowwise', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
|
| [2026-07-17 15:02:16.270] Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
|
| [2026-07-17 15:02:16.270] Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope_split_half', 'apply_rope_split_half1', 'convrot_w4a4_linear', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'gemv_awq_w4a16', 'int8_linear', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'rms_rope', 'rms_rope1', 'rms_rope_split_half', 'rms_rope_split_half1', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'stochastic_rounding_fp8']}
|
| [2026-07-17 15:02:16.307] Checkpoint files will always be loaded safely.
|
| [2026-07-17 15:02:16.503] Total VRAM 12282 MB, total RAM 32576 MB
|
| [2026-07-17 15:02:16.504] pytorch version: 2.12.0+cu130
|
| [2026-07-17 15:02:16.504] Set vram state to: NORMAL_VRAM
|
| [2026-07-17 15:02:16.504] Device: cuda:0 NVIDIA GeForce RTX 4080 Laptop GPU : cudaMallocAsync
|
| [2026-07-17 15:02:16.522] Using async weight offloading with 2 streams
|
| [2026-07-17 15:02:16.522] Enabled pinned memory 13030.0
|
| [2026-07-17 15:02:17.102] Using pytorch attention
|
| [2026-07-17 15:02:33.887] DynamicVRAM support detected and enabled
|
| [2026-07-17 15:02:33.888] Python version: 3.13.12 (tags/v3.13.12:1cbe481, Feb 3 2026, 18:22:25) [MSC v.1944 64 bit (AMD64)]
|
| [2026-07-17 15:02:33.888] ComfyUI version: 0.28.0
|
| [2026-07-17 15:02:33.888] comfy-aimdo version: 0.4.10
|
| [2026-07-17 15:02:33.889] comfy-kitchen version: 0.2.21
|
| [2026-07-17 15:02:33.899] comfyui-frontend-package version: 1.45.21
|
| [2026-07-17 15:02:33.899] comfyui-workflow-templates version: 0.11.9
|
| [2026-07-17 15:02:33.899] comfyui-embedded-docs version: 0.5.8
|
| [2026-07-17 15:02:33.899] comfy-kitchen version: 0.2.21
|
| [2026-07-17 15:02:33.899] comfy-aimdo version: 0.4.10
|
| [2026-07-17 15:02:33.901] [Prompt Server] web root: G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\comfyui_frontend_package\static
|
| [2026-07-17 15:02:33.902] Asset seeder disabled
|
| [2026-07-17 15:02:35.072] No OpenGL_accelerate module loaded: No module named 'OpenGL_accelerate'
|
| [2026-07-17 15:02:35.875] G:\ComfyUI_windows_portable-G313\python_embeded\python.exe
|
| [2026-07-17 15:02:35.902] ComfyUI-GGUF: Allowing full torch compile
|
| [2026-07-17 15:02:39.640] Hello World
|
| [2026-07-17 15:02:39.660] [38;5;141m╔══════════════════════════════════════════════════════════╗[0m
|
| [2026-07-17 15:02:39.660] [1m[38;5;141m║ 🍌 Banana Node Loader ║[0m
|
| [2026-07-17 15:02:39.660] [38;5;141m╚══════════════════════════════════════════════════════════╝[0m
|
| [2026-07-17 15:02:39.660] [38;5;153m[15:02:39][Main] ℹ️ Banana Gemini version V0.02[0m
|
| [2026-07-17 15:02:39.664] [92m[15:02:39][Main] ✅ 成功加载节点文件: Banana_Endpoint_Tester.py[0m
|
| [2026-07-17 15:02:39.668] [92m[15:02:39][Main] ✅ 成功加载节点文件: Gemini_Imagen_Generator.py[0m
|
| [2026-07-17 15:02:39.668] [38;5;153m[15:02:39][Main] ℹ️ 总共加载了 2 个自定义节点[0m
|
| [2026-07-17 15:02:39.668] [38;5;153m[15:02:39][Main] ℹ️ - Banana Endpoint Tester (HeiHe001_BananaEndpointTesterNode)[0m
|
| [2026-07-17 15:02:39.668] [38;5;153m[15:02:39][Main] ℹ️ - Banana-API-3 (HeiHe001_BananaImageNode)[0m
|
| [2026-07-17 15:02:39.692] ComfyUI core already includes Bernini support; skipping patches.
|
| [2026-07-17 15:02:40.060] [Crystools [0;32mINFO[0m] Crystools version: 1.27.4
|
| [2026-07-17 15:02:40.129] [Crystools [0;32mINFO[0m] Platform release: 11
|
| [2026-07-17 15:02:40.129] [Crystools [0;32mINFO[0m] JETSON: Not detected.
|
| [2026-07-17 15:02:40.131] [Crystools [0;32mINFO[0m] CPU: 13th Gen Intel(R) Core(TM) i9-13900HX - Arch: AMD64 - OS: Windows 11
|
| [2026-07-17 15:02:40.146] [Crystools [0;32mINFO[0m] pynvml (NVIDIA) initialized.
|
| [2026-07-17 15:02:40.146] [Crystools [0;32mINFO[0m] GPU/s:
|
| [2026-07-17 15:02:40.162] [Crystools [0;32mINFO[0m] 0) NVIDIA GeForce RTX 4080 Laptop GPU
|
| [2026-07-17 15:02:40.162] [Crystools [0;32mINFO[0m] NVIDIA Driver: 610.62
|
| [2026-07-17 15:02:50.932] [ComfyUI-Easy-Use] server: v1.3.7 Loaded
|
| [2026-07-17 15:02:50.933] [ComfyUI-Easy-Use] web root: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Easy-Use\web_version/v2 Loaded
|
| [2026-07-17 15:02:50.957] ComfyUI-GGUF: Allowing full torch compile
|
| [2026-07-17 15:02:52.124] G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\timm\models\layers\__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
|
| warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
|
| [2026-07-17 15:02:52.133] G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\timm\models\registry.py:4: FutureWarning: Importing from timm.models.registry is deprecated, please import via timm.models
|
| warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.models", FutureWarning)
|
| [2026-07-17 15:02:52.140] G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\timm\models\helpers.py:7: FutureWarning: Importing from timm.models.helpers is deprecated, please import via timm.models
|
| warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.models", FutureWarning)
|
| [2026-07-17 15:02:52.152]
|
| [2026-07-17 15:02:52.419] [Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
|
| [2026-07-17 15:02:52.434] [Impact Pack] Wildcards loading done.
|
| [2026-07-17 15:02:52.448]
|
| [2026-07-17 15:02:52.454] [Impact Pack/Subpack] Using folder_paths to determine whitelist path: G:\ComfyUI_windows_portable-G313\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
|
| [2026-07-17 15:02:52.455] [Impact Pack/Subpack] Ensured whitelist directory exists: G:\ComfyUI_windows_portable-G313\ComfyUI\user\default\ComfyUI-Impact-Subpack
|
| [2026-07-17 15:02:52.462] [Impact Pack/Subpack] Loaded 0 model(s) from whitelist: G:\ComfyUI_windows_portable-G313\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
|
| [2026-07-17 15:02:52.666] [Impact Subpack] ultralytics_bbox: G:\ComfyUI_windows_portable-G313\ComfyUI\models\ultralytics\bbox
|
| [2026-07-17 15:02:52.666] [Impact Subpack] ultralytics_segm: G:\ComfyUI_windows_portable-G313\ComfyUI\models\ultralytics\segm
|
| [2026-07-17 15:02:52.721]
|
| [2026-07-17 15:02:53.055] [llama-cpp_vlm] Model cleanup hook applied!
|
| [2026-07-17 15:02:53.165]
|
| [2026-07-17 15:02:53.165] [ComfyUI-Manager] network_mode: private
|
| [2026-07-17 15:02:53.165] [ComfyUI-Manager] ComfyUI per-queue preview override detected (PR
|
| [2026-07-17 15:02:53.310]
|
| [2026-07-17 15:02:54.574] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
|
| [2026-07-17 15:02:55.165] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
|
| [2026-07-17 15:02:55.367] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
|
| [2026-07-17 15:02:55.382] ⚡ SeedVR2 optimizations check: SageAttention ✅ | Flash Attention ❌ | Triton ✅
|
| [2026-07-17 15:02:55.382] 💡 Optional: pip install flash-attn
|
| [2026-07-17 15:02:55.383] 🔧 Conv3d workaround active: PyTorch 2.12.0, cuDNN 92000 (fixing VAE 3x memory bug)
|
| [2026-07-17 15:02:55.566] 📊 Initial CUDA memory: 10.74GB free / 11.99GB total
|
| [2026-07-17 15:02:57.423] [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
|
| [2026-07-17 15:02:57.606] (pysssss:WD14Tagger) [DEBUG] Available ORT providers: AzureExecutionProvider, CPUExecutionProvider
|
| [2026-07-17 15:02:57.606] (pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
|
| [2026-07-17 15:02:57.657] ------------------------------------------
|
| [2026-07-17 15:02:57.657] Comfyroll Studio v1.76 : 175 Nodes Loaded
|
| [2026-07-17 15:02:57.657] ------------------------------------------
|
| [2026-07-17 15:02:57.657] ** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
|
| [2026-07-17 15:02:57.657] ** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
|
| [2026-07-17 15:02:57.657] ------------------------------------------
|
| [2026-07-17 15:02:57.699] [G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
|
| [2026-07-17 15:02:57.719] [G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
|
| [2026-07-17 15:02:57.739] [G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
|
| [2026-07-17 15:02:57.787] G:\ComfyUI_windows_portable-G313\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")
|
| [2026-07-17 15:02:58.896] [ComfyUI-Manager] Failed to perform initial fetching 'custom-node-list.json': Cannot connect to host raw.githubusercontent.com:443 ssl:default [None]
|
| [2026-07-17 15:02:58.942] Traceback (most recent call last):
|
| [2026-07-17 15:02:58.955] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1474, in _start_tls_connection
|
| tls_transport = await self._loop.start_tls(
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| ...<5 lines>...
|
| )
|
| ^
|
| [2026-07-17 15:02:58.971] File "asyncio\base_events.py", line 1356, in start_tls
|
| [2026-07-17 15:02:58.987] File "asyncio\sslproto.py", line 581, in _on_handshake_complete
|
| [2026-07-17 15:02:59.000] ConnectionResetError
|
| [2026-07-17 15:02:59.015]
|
| The above exception was the direct cause of the following exception:
|
|
|
| [2026-07-17 15:02:59.031] Traceback (most recent call last):
|
| [2026-07-17 15:02:59.063] File "G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_server.py", line 1983, in get_cache
|
| json_obj = await manager_util.get_data(uri, True)
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| [2026-07-17 15:02:59.081] File "G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Manager\glob\manager_util.py", line 192, in get_data
|
| async with session.get(uri, headers=headers) as resp:
|
| ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^
|
| [2026-07-17 15:02:59.101] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\client.py", line 1521, in __aenter__
|
| self._resp: _RetType = await self._coro
|
| ^^^^^^^^^^^^^^^^
|
| [2026-07-17 15:02:59.119] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\client.py", line 788, in _request
|
| resp = await handler(req)
|
| ^^^^^^^^^^^^^^^^^^
|
| [2026-07-17 15:02:59.144] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\client.py", line 742, in _connect_and_send_request
|
| conn = await self._connector.connect(
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| req, traces=traces, timeout=real_timeout
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| )
|
| ^
|
| [2026-07-17 15:02:59.181] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\connector.py", line 672, in connect
|
| proto = await self._create_connection(req, traces, timeout)
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| [2026-07-17 15:02:59.207] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1249, in _create_connection
|
| _, proto = await self._create_proxy_connection(req, traces, timeout)
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| [2026-07-17 15:02:59.233] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1717, in _create_proxy_connection
|
| return await self._start_tls_connection(
|
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| ...<5 lines>...
|
| )
|
| ^
|
| [2026-07-17 15:02:59.254] File "G:\ComfyUI_windows_portable-G313\python_embeded\Lib\site-packages\aiohttp\connector.py", line 1507, in _start_tls_connection
|
| raise client_error(req.connection_key, exc) from exc
|
| [2026-07-17 15:02:59.279] aiohttp.client_exceptions.ClientConnectorError: Cannot connect to host raw.githubusercontent.com:443 ssl:default [None]
|
| [2026-07-17 15:02:59.280] [ComfyUI-Manager] The private comfyregistry is not yet supported in `network_mode=private`.
|
| [2026-07-17 15:02:59.280] [ComfyUI-Manager] All startup tasks have been completed.
|
| [2026-07-17 15:03:03.404]
|
|
|
| [2026-07-17 15:03:03.405] Node -> ArgosTranslateNode: ArgosTranslateCLIPTextEncodeNode, ArgosTranslateTextNode [Loading]
|
| [2026-07-17 15:03:03.405] Node -> ChatGLMNode: ChatGLM4TranslateCLIPTextEncodeNode, ChatGLM4TranslateTextNode, ChatGLM4InstructNode, ChatGLM4InstructMediaNode, ChatGLMImageGenerateNode, ChatGLMVideoGenerateNode [Loading]
|
| [2026-07-17 15:03:03.405] Node -> DeepTranslatorNode: DeepTranslatorCLIPTextEncodeNode, DeepTranslatorTextNode [Loading]
|
| [2026-07-17 15:03:03.406] Node -> ExtrasNode: PreviewTextNode, HexToHueNode, ColorsCorrectNode [Loading]
|
| [2026-07-17 15:03:03.406] Node -> GoogleTranslateNode: GoogleTranslateCLIPTextEncodeNode, GoogleTranslateTextNode [Loading]
|
| [2026-07-17 15:03:03.406] Node -> IDENode: IDENode [Loading]
|
| [2026-07-17 15:03:03.406] Node -> PainterNode: PainterNode [Loading]
|
| [2026-07-17 15:03:03.407] Node -> PoseNode: PoseNode [Loading]
|
| [2026-07-17 15:03:03.407]
|
| [2026-07-17 15:03:04.306] ✨提示词小助手 V2.0.6 已启动
|
| [2026-07-17 15:03:04.385] USDU batch patches applied successfully.
|
| [2026-07-17 15:03:04.385] USDU batch patches applied successfully.
|
| [2026-07-17 15:03:04.503] [G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfy_mtb] | INFO -> loaded 111 nodes successfuly
|
| [2026-07-17 15:03:04.548] [G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfy_mtb] | INFO -> Some nodes (2) could not be loaded. This can be ignored, but go to http://127.0.0.1:8188/mtb if you want more information.
|
| [2026-07-17 15:03:05.007] Using pytorch attention
|
| [2026-07-17 15:03:05.040] (RES4LYF) Init
|
| [2026-07-17 15:03:05.041] (RES4LYF) Importing beta samplers.
|
| [2026-07-17 15:03:05.079] (RES4LYF) Importing legacy samplers.
|
| [2026-07-17 15:03:05.146]
|
| [2026-07-17 15:03:05.146] [rgthree-comfy] Loaded 48 fantastic nodes. 🎉
|
| [2026-07-17 15:03:05.146]
|
| [2026-07-17 15:03:05.146] [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.
|
| [2026-07-17 15:03:05.146]
|
| [2026-07-17 15:03:05.853] WAS Node Suite: OpenCV Python FFMPEG support is enabled
|
| [2026-07-17 15:03:05.853] WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
|
| [2026-07-17 15:03:06.524] WAS Node Suite: Finished. Loaded 220 nodes successfully.
|
| [2026-07-17 15:03:06.525]
|
| "Believe you deserve it and the universe will serve it." - Unknown
|
| [2026-07-17 15:03:06.526]
|
| [2026-07-17 15:03:06.598]
|
| Import times for custom nodes:
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\masquerade-nodes-comfyui
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_GPT_Image_2_v2
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyUI-llama-TE
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\websocket_image_save.py
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_EasySize
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\Comfyui-Memory_Cleanup
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-DD-Translation
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Florence2
|
| [2026-07-17 15:03:06.599] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\Comfyui-reverse_promp_v11
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-GGUF
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-WanMoeKSampler
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_IPAdapter_plus
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-ConditioningKrea2Rebalance
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Easy-IndexTTS2
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-WD14-Tagger
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-VFI
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-WanAnimatePreprocess
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-SCAIL-Pose
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Inpaint-CropAndStitch
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-MelBandRoFormer
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui-Banana-API-35
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_essentials
|
| [2026-07-17 15:03:06.600] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Custom-Scripts
|
| [2026-07-17 15:03:06.601] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui-inpaint-nodes
|
| [2026-07-17 15:03:06.601] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\gguf
|
| [2026-07-17 15:03:06.601] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-qwenmultiangle
|
| [2026-07-17 15:03:06.601] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-BFSNodes
|
| [2026-07-17 15:03:06.601] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\WhatDreamsCost-ComfyUI
|
| [2026-07-17 15:03:06.601] 0.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-PromptRelay
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\rgthree-comfy
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-LTXVideo
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-llama-cpp_vllm
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui_prompt_assistant
|
| [2026-07-17 15:03:06.601] 0.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-KJNodes
|
| [2026-07-17 15:03:06.601] 0.2 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfyui_controlnet_aux
|
| [2026-07-17 15:03:06.601] 0.2 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\comfy_mtb
|
| [2026-07-17 15:03:06.602] 0.2 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Impact-Subpack
|
| [2026-07-17 15:03:06.602] 0.3 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_LayerStyle
|
| [2026-07-17 15:03:06.602] 0.3 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
|
| [2026-07-17 15:03:06.602] 0.4 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-SeedVR2_VideoUpscaler
|
| [2026-07-17 15:03:06.602] 0.5 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Crystools
|
| [2026-07-17 15:03:06.602] 0.5 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\RES4LYF
|
| [2026-07-17 15:03:06.602] 0.5 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_LayerStyle_Advance
|
| [2026-07-17 15:03:06.602] 0.7 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Easy-Sam3
|
| [2026-07-17 15:03:06.602] 0.7 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Manager
|
| [2026-07-17 15:03:06.602] 0.8 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
|
| [2026-07-17 15:03:06.602] 1.0 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
|
| [2026-07-17 15:03:06.602] 1.2 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-GIMM-VFI
|
| [2026-07-17 15:03:06.602] 1.4 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-MMAudio
|
| [2026-07-17 15:03:06.602] 1.4 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\was-node-suite-comfyui
|
| [2026-07-17 15:03:06.602] 3.8 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Apt_Preset
|
| [2026-07-17 15:03:06.602] 5.6 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI_Custom_Nodes_AlekPet
|
| [2026-07-17 15:03:06.602] 10.1 seconds: G:\ComfyUI_windows_portable-G313\ComfyUI\custom_nodes\ComfyUI-Easy-Use
|
| [2026-07-17 15:03:06.603]
|
| [2026-07-17 15:03:06.612] Context impl SQLiteImpl.
|
| [2026-07-17 15:03:06.613] Will assume non-transactional DDL.
|
| [2026-07-17 15:03:06.822] Using RAM pressure cache.
|
| [2026-07-17 15:03:06.822] Starting server
|
|
|
| [2026-07-17 15:03:06.823] To see the GUI go to: http://127.0.0.1:8188
|
| [2026-07-17 15:03:10.578] [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.
|
| [2026-07-17 15:03:10.580] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/clipspace.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.
|
| [2026-07-17 15:03:10.583] [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.
|
| [2026-07-17 15:03:10.588] [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.
|
| [2026-07-17 15:03:10.597] [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.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.
|
| [2026-07-17 15:03:23.423] [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.
|
| [2026-07-17 15:06:56.187] got prompt
|
| [2026-07-17 15:06:56.281] [llama-cpp_vlm] Loading model...
|
| [2026-07-17 15:06:56.705] [llama-cpp_vlm] Loading clip: mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf
|
| [2026-07-17 15:06:56.745] [llama-cpp_vlm] Loading model: Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf
|
| [2026-07-17 15:06:56.746] [llama-cpp_vlm] n_gpu_layers = -1
|
| [2026-07-17 15:07:11.652] llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
|
| [2026-07-17 15:07:11.722] [llama-cpp_vlm] Start processing 1 images
|
| [2026-07-17 15:07:11.725]
Processing: 0%| | 0/1 [00:00<?, ?it/s][2026-07-17 15:07:11.802] load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
|
| [2026-07-17 15:07:11.802] load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
|
| [2026-07-17 15:07:11.802] load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842
|
|
|
| [2026-07-17 15:07:27.527] find_slot: non-consecutive token position 83 after 82 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.528] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.528] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.528] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.531] find_slot: non-consecutive token position 83 after 82 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.564] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.703] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.841] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:07:27.971] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 270 new tokens
|
| [2026-07-17 15:07:27.971] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 270 new tokens
|
| [2026-07-17 15:07:28.098] find_slot: non-consecutive token position 154 after 83 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:07:28.099] find_slot: non-consecutive token position 154 after 83 for sequence 0 with 11 new tokens
|
|
Processing: 100%|████████████████████████████████████████████████████████████████████████| 1/1 [00:37<00:00, 37.01s/it]
Processing: 100%|████████████████████████████████████████████████████████████████████████| 1/1 [00:37<00:00, 37.01s/it]
|
| [2026-07-17 15:08:00.649] llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
|
| [2026-07-17 15:08:00.838] load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
|
| [2026-07-17 15:08:00.839] load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
|
| [2026-07-17 15:08:00.839] load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842
|
|
|
| [2026-07-17 15:08:03.219] find_slot: non-consecutive token position 25 after 24 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:08:03.221] find_slot: non-consecutive token position 25 after 25 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:08:03.222] find_slot: non-consecutive token position 25 after 24 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:08:03.256] find_slot: non-consecutive token position 25 after 25 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:08:03.371] find_slot: non-consecutive token position 67 after 25 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:08:03.371] find_slot: non-consecutive token position 67 after 25 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:08:11.137] Prompt executed in 74.93 seconds
|
| [2026-07-17 15:10:13.711] got prompt
|
| [2026-07-17 15:10:21.378] llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
|
| [2026-07-17 15:10:21.503] load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
|
| [2026-07-17 15:10:21.504] load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
|
| [2026-07-17 15:10:21.504] load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842
|
|
|
| [2026-07-17 15:10:24.348] find_slot: non-consecutive token position 25 after 24 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:10:24.348] find_slot: non-consecutive token position 25 after 25 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:10:24.349] find_slot: non-consecutive token position 25 after 24 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:10:24.397] find_slot: non-consecutive token position 25 after 25 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:10:24.552] find_slot: non-consecutive token position 67 after 25 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:10:24.553] find_slot: non-consecutive token position 67 after 25 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:10:32.772] Prompt executed in 19.05 seconds
|
| [2026-07-17 15:12:12.100] got prompt
|
| [2026-07-17 15:12:19.182] llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
|
| [2026-07-17 15:12:19.356] load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
|
| [2026-07-17 15:12:19.357] load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
|
| [2026-07-17 15:12:19.357] load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842
|
|
|
| [2026-07-17 15:12:21.793] find_slot: non-consecutive token position 83 after 82 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:12:21.795] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:12:21.795] find_slot: non-consecutive token position 83 after 82 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:12:21.832] find_slot: non-consecutive token position 83 after 83 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:12:21.949] find_slot: non-consecutive token position 125 after 83 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:12:21.950] find_slot: non-consecutive token position 125 after 83 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:12:36.518] Prompt executed in 24.41 seconds
|
| [2026-07-17 15:12:50.919] got prompt
|
| [2026-07-17 15:12:57.965] llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
|
| [2026-07-17 15:12:58.084] load_hparams: Qwen-VL models require at minimum 1024 image tokens to function correctly on grounding tasks
|
| [2026-07-17 15:12:58.084] load_hparams: if you encounter problems with accuracy, try adding --image-min-tokens 1024
|
| [2026-07-17 15:12:58.084] load_hparams: more info: https://github.com/ggml-org/llama.cpp/issues/16842
|
|
|
| [2026-07-17 15:13:00.654] find_slot: non-consecutive token position 25 after 24 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:13:00.655] find_slot: non-consecutive token position 25 after 25 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:13:00.655] find_slot: non-consecutive token position 25 after 24 for sequence 0 with 512 new tokens
|
| [2026-07-17 15:13:00.705] find_slot: non-consecutive token position 25 after 25 for sequence 0 with 128 new tokens
|
| [2026-07-17 15:13:00.873] find_slot: non-consecutive token position 67 after 25 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:13:00.875] find_slot: non-consecutive token position 67 after 25 for sequence 0 with 11 new tokens
|
| [2026-07-17 15:13:09.945] Prompt executed in 19.01 seconds
|
|
|
