[GH-ISSUE #49] RuntimeError: VRAM reservation failed #18

New issue

Closed

opened 2026-10-26 22:23:38 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-26 22:23:38 +00:00

Owner

Originally created by @jovan2009 on GitHub (May 12, 2026).
Original GitHub issue: https://github.com/Comfy-Org/comfy-aimdo/issues/49

Second run of a Wan 2.2 I2V workflow ends in error during low noise ksampler. This is behavior is new to me, I would say it started today with version comfy-aimdo ver. 0.4.0. Not many other things has changed (except I did a git pull on ComfyUI today and I updated the nvidia driver to latest but this error started to happen before the driver update).

If I want to be precise the second run (that fails) is not an identical workflow with the first run, it is different by having one extra Lora in each chain (3 loras instead of 2). If I restore the Lora configuration back (2 Lora on High, 2 Lora on Low) the error doesn't happen.

setup plugin alembic.autogenerate.schemas
setup plugin alembic.autogenerate.tables
setup plugin alembic.autogenerate.types
setup plugin alembic.autogenerate.constraints
setup plugin alembic.autogenerate.defaults
setup plugin alembic.autogenerate.comments
Adding extra search path checkpoints E:\ComfyUI\models\checkpoints
Adding extra search path text_encoders E:\ComfyUI\models\text_encoders
Adding extra search path text_encoders E:\ComfyUI\models\clip\  # legacy location still supported
Adding extra search path clip_vision E:\ComfyUI\models\clip_vision
Adding extra search path configs E:\ComfyUI\models\configs
Adding extra search path controlnet E:\ComfyUI\models\controlnet
Adding extra search path diffusion_models E:\ComfyUI\models\diffusion_models
Adding extra search path diffusion_models E:\ComfyUI\models\unet
Adding extra search path embeddings E:\ComfyUI\models\embeddings
Adding extra search path loras E:\ComfyUI\models\loras
Adding extra search path upscale_models E:\ComfyUI\models\upscale_models
Adding extra search path vae E:\ComfyUI\models\vae
Adding extra search path audio_encoders E:\ComfyUI\models\audio_encoders
Adding extra search path model_patches E:\ComfyUI\models\model_patches
Adding extra search path latent_upscale_models E:\ComfyUI\models\latent_upscale_models
Found triton 3.7.0. Enabling comfy-kitchen triton backend.
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_int8', 'dequantize_int8_simple', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'mm_int8', 'quantize_int8', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_int8', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend triton: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_int8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'quantize_int8', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_int8']}
Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Checkpoint files will always be loaded safely.
Total VRAM 16023 MB, total RAM 65465 MB
pytorch version: 2.13.0.dev20260512+cu132
MSLK running in python-only mode — skipping native library loading
xformers version: 0.0.35+ca6d2aa.d20260509
Enabled fp16 accumulation.
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5060 Ti : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 26185.0
Using sage attention
aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks
aimdo: src-win/cuda-detour.c:28:DEBUG:install_hook_entries: hooks successfully installed
aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 5060 Ti runtime_luid=00000000:000093d3 dxgi_luid=00000000:000093d3
aimdo: src/control.c:237:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 5060 Ti (VRAM: 16022 MB)
DynamicVRAM support detected and enabled
Python version: 3.14.5 (main, May 10 2026, 20:29:46) [MSC v.1944 64 bit (AMD64)]
ComfyUI version: 0.21.0
comfy-aimdo version: 0.4.0
comfy-kitchen version: 0.2.8
ComfyUI frontend version: 1.43.18
[Prompt Server] web root: F:\Python314\install\Lib\site-packages\comfyui_frontend_package\static
Asset seeder disabled
Unable to parse pyproject.toml due to lack dependency pydantic-settings, please run 'pip install -r requirements.txt': Illegal character '\n' (at line 3, column 101)
ComfyUI-QuantOps: Enabled comfy-kitchen triton backend
ComfyUI-QuantOps: Registered quantops_int8 backend
ComfyUI-QuantOps: Registered quantops_fp8 backend
ComfyUI-QuantOps: Registered TensorWiseINT8Layout
ComfyUI-QuantOps: Registered TensorCoreMXFP8Layout
ComfyUI-QuantOps: Registered HybridMXFP8Layout
ComfyUI-QuantOps: Registered layouts: ['BlockWiseINT8Layout', 'TensorWiseINT8Layout', 'RowWiseFP8Layout', 'BlockWiseFP8Layout', 'TensorCoreMXFP8Layout']
Error: File not found - extra_help_file.yaml
No customize audios loading path found, use default path.
ColorMod: Ignoring node 'CV2TonemapDurand' due to cv2 edition/version
IAMCCS compat: enabled local Qwen Multi-Gen seed widget patch
[IAMCCS] WARNING: IAMCCS_QWEN_VL_FLF could not load — [IAMCCS_QWEN_VL_FLF] Cannot find QwenVLBase. Make sure ComfyUI-QwenVL is installed under custom_nodes/ComfyUI-QwenVL.
[IAMCCS]   Make sure ComfyUI-QwenVL is installed in custom_nodes/ComfyUI-QwenVL

  ___    _    __  __  ____ ____  ____   ____            _
 |_ _|  / \  |  \/  |/ ___/ ___|/ ___| |  _ \ ___   ___| | _____
  | |  / _ \ | |\/| | |  | |    \___ \ | |_) / _ \ / __| |/ / __|
  | | / ___ \| |  | | |__| |___  ___) ||  __/ (_) | (__|   <\__ \
 |___/_/   \_\_|  |_|\____\____||____/ |_|   \___/ \___|_|\_\___/


by IAMCCS (follow me on patreon.com/IAMCCS or carminecristalloscalzi.com)
IAMCCS nodes loaded: 190
- IAMCCS-SuperNodes AU+IMG2VID Exec Finalize, IAMCCS-SuperNodes AU+IMG2VID Exec Planner, IAMCCS-SuperNodes AU+IMG2VID Exec Render, IAMCCS-SuperNodes AU+IMG2VID Exec VAE, IAMCCS-SuperNodes Second Stage, IAMCCS_AUIMG2VID_AudioTimeline, IAMCCS_AUIMG2VID_Continuity, IAMCCS_AUIMG2VID_DiskExtension, IAMCCS_AUIMG2VID_Finalize, IAMCCS_AUIMG2VID_KeyframeTimeline
- IAMCCS_AUIMG2VID_Planner, IAMCCS_AUIMG2VID_ProjectTimelinePlanner, IAMCCS_AUIMG2VID_ReanchorLatent, IAMCCS_AUIMG2VID_RefreshPolicy, IAMCCS_AUIMG2VID_RuntimeBridge, IAMCCS_ApplyLoRAHooksToConditioning, IAMCCS_ApplyScheduledWanLoRAFromConditioning, IAMCCS_AudioExtender, IAMCCS_AudioExtensionMath, IAMCCS_AudioSegmentAutoPlanner
- IAMCCS_AudioTimelineAssembler, IAMCCS_AudioTimelineGate, IAMCCS_AutoLinkArguments, IAMCCS_AutoLinkConverter, IAMCCS_BuildScheduledWanModelBank, IAMCCS_CineAllInOneFLFEngine, IAMCCS_CineAudioPromptDirector, IAMCCS_CineFLFEngineSimple, IAMCCS_CineFLFLengthCompensator, IAMCCS_CineInfo
- IAMCCS_CineLTXSequencer, IAMCCS_CineLTXSequencerExact, IAMCCS_CineLineStacker, IAMCCS_CineMultiGenDirector, IAMCCS_CineMusicVideoPlanner, IAMCCS_CinePromptComposer, IAMCCS_CinePromptRelayAdapter, IAMCCS_CinePromptRelayLatentShapeSync, IAMCCS_CinePromptRelaySafeEncode, IAMCCS_CinePromptRelayTimeline
- IAMCCS_CineRefLatentControl, IAMCCS_CineReferenceBoard, IAMCCS_CineRelayOrBypass, IAMCCS_CineShotAudioDirector, IAMCCS_CineShotLineBuilder, IAMCCS_CineShotPlanner, IAMCCS_CineShotboardLite, IAMCCS_CineShotboardPlannerPro, IAMCCS_CineShotboardPlannerProLegacy, IAMCCS_CineShotboardPlannerProV2
- IAMCCS_CineShotboardTimelinePro, IAMCCS_CineSwitch, IAMCCS_CineV2VAssetSelector, IAMCCS_CineV2VTimelineDirector, IAMCCS_CineV2VTimelineLineBuilder, IAMCCS_CineWorkflowInspector, IAMCCS_FluxKleinMultiGen, IAMCCS_GGUF_accelerator, IAMCCS_GetAutoLink, IAMCCS_HWProbeRecommendations
- IAMCCS_HardMemoryPurge, IAMCCS_HwSupporter, IAMCCS_HwSupporterAny, IAMCCS_ImageBatchRangeLite, IAMCCS_ImageResizeBatchSafe, IAMCCS_IntValueMonitor, IAMCCS_LTX2_BlendLatentBridge, IAMCCS_LTX2_ConditionNextLatentWithPrevOverlap, IAMCCS_LTX2_ContextLatent, IAMCCS_LTX2_ControlPreprocess
- IAMCCS_LTX2_EnsureFrames8nPlus1, IAMCCS_LTX2_EnsureMinFrames, IAMCCS_LTX2_ExtendSampler, IAMCCS_LTX2_ExtensionModule, IAMCCS_LTX2_ExtensionModule_Disk, IAMCCS_LTX2_ExtensionModule_simple, IAMCCS_LTX2_FirstLastFramesController, IAMCCS_LTX2_FirstLastLatentControl, IAMCCS_LTX2_FirstLastLatentControl_Pro, IAMCCS_LTX2_FrameCountValidator
- IAMCCS_LTX2_FrameRateSync, IAMCCS_LTX2_GetImageFromBatch, IAMCCS_LTX2_ImageBatchCropByPad, IAMCCS_LTX2_ImageBatchPadReflect, IAMCCS_LTX2_InitLatentSampler, IAMCCS_LTX2_JointRefreshLatent, IAMCCS_LTX2_JointRefreshLatent_Disk, IAMCCS_LTX2_LastFrameBridgeLoad, IAMCCS_LTX2_LastFrameBridgeSave, IAMCCS_LTX2_LoRAStack
- IAMCCS_LTX2_LoRAStackModelIO, IAMCCS_LTX2_LoRAStackSegmented6, IAMCCS_LTX2_LoRAStackStaged, IAMCCS_LTX2_LoadLatentBridge, IAMCCS_LTX2_LongVideoWrapperPrep, IAMCCS_LTX2_LongVideoWrapperPrepDisk, IAMCCS_LTX2_LoopingSampler, IAMCCS_LTX2_MiddleFrames, IAMCCS_LTX2_ModelWithLoRA_Segmented6, IAMCCS_LTX2_OneShotLowRAMLooper
- IAMCCS_LTX2_ReferenceImageSwitch, IAMCCS_LTX2_ReferenceStartFramesInjector, IAMCCS_LTX2_SaveLatentBridge, IAMCCS_LTX2_SegmentQueueLoop, IAMCCS_LTX2_TimeFrameCount, IAMCCS_LTX2_Validator, IAMCCS_LatentTailSlice, IAMCCS_LazyAnySwitch, IAMCCS_LoadImagesFromDirLite, IAMCCS_LoadResizeSegmentFromDir
- IAMCCS_Ltx2HelperModules_AudioTimeline, IAMCCS_Ltx2HelperModules_Continuity, IAMCCS_Ltx2HelperModules_DiskExtension, IAMCCS_Ltx2HelperModules_Finalize, IAMCCS_Ltx2HelperModules_KeyframeTimeline, IAMCCS_Ltx2HelperModules_Planner, IAMCCS_Ltx2HelperModules_ProjectTimelinePlanner, IAMCCS_Ltx2HelperModules_ReanchorLatent, IAMCCS_Ltx2HelperModules_RefreshPolicy, IAMCCS_Ltx2HelperModules_RuntimeBridge
- IAMCCS_ModelWithLoRA, IAMCCS_ModelWithLoRA_LTX2, IAMCCS_ModelWithLoRA_LTX2_Staged, IAMCCS_ModelWithLoRA_RuntimeBridge, IAMCCS_MotionBridgeLoad, IAMCCS_MotionBridgeSave, IAMCCS_MotionScale, IAMCCS_MotionScaleAdvanced, IAMCCS_MoveAhead, IAMCCS_MoveAheadEnforcer
- IAMCCS_MultiSwitch, IAMCCS_MultilinePromptSplitter8, IAMCCS_ProjectTimelinePlanner, IAMCCS_QwenMultiGen, IAMCCS_SamplerAdvancedVersion1, IAMCCS_SegmentPlanFromPlanner, IAMCCS_SegmentPlanner, IAMCCS_SegmentPlannerLinked, IAMCCS_SegmentPlannerSettings, IAMCCS_SegmentSwitch
- IAMCCS_SelectScheduledWanModelFromConditioning, IAMCCS_SelectScheduledWanModelPairFromConditioning, IAMCCS_SetAutoLink, IAMCCS_SourceFramesToDisk, IAMCCS_SourceRangeFromSegmentPlan, IAMCCS_StartDirToVideoLatent, IAMCCS_StartImagesToVideoLatent, IAMCCS_SupernodeBase, IAMCCS_SupernodeModule, IAMCCS_ThreeSegmentPlanner
- IAMCCS_TwoSegmentPlanner, IAMCCS_VAEDecodeTiledSafe, IAMCCS_VAEDecodeToDisk, IAMCCS_VRAMCleanup, IAMCCS_VRAMFlushLatent, IAMCCS_VideoCombineFromDir, IAMCCS_WDC_LTXKeyframer, IAMCCS_WDC_LTXSequencer, IAMCCS_WDC_LTXSequencerFixed5, IAMCCS_WDC_MultiImageLoader
- IAMCCS_WanContinuityGuide, IAMCCS_WanImageBatchFrameSelect, IAMCCS_WanImageMotion, IAMCCS_WanImageMotionInductive, IAMCCS_WanImageMotionPro, IAMCCS_WanImageMotionProLegacy, IAMCCS_WanImageMotionProPlus, IAMCCS_WanImageMotionProPlus_Simple, IAMCCS_WanImageMotionPro_AdaIN, IAMCCS_WanImageMotion_AdaIN
- IAMCCS_WanIndexedPromptEncode, IAMCCS_WanLoRAHookSchedule, IAMCCS_WanLoRARuntimeBridge, IAMCCS_WanLoRASchedule, IAMCCS_WanLoRAStack, IAMCCS_WanLoRAStackModelIO, IAMCCS_WanLongPlanner, IAMCCS_WanPrevTailPrep, IAMCCS_WanPromptLoopInfo, IAMCCS_WanPromptPhasePlanner
- IAMCCS_WanSVIToFLFBridgeProPlus, IAMCCS_WanSVIToFLFBridgeProPlus_Simple, IAMCCS_WanSviFlfTimeline, IAMCCS_WanSviFlfTimelinePick, IAMCCS_bus_group, WanImageMotionPro, WanImageMotionProLegacy, WanImageMotionProPlus, WanMotionProTrimmer, iamccs_ltx2_lora_stack
Failed to load node module lyrics_groq_node: No module named 'groq'
Failed to load node module transcribe_faster_whisper_load_node: No module named 'faster_whisper'
Failed to load node module transcribe_faster_whisper_node: No module named 'faster_whisper'
Failed to load node module transcribe_faster_whisper_save_node: No module named 'faster_whisper'
🎵 ACE-Step Nodes loaded: 85 nodes registered

Import times for custom nodes:
   0.0 seconds: C:\ComfyUI\custom_nodes\websocket_image_save.py
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_EmbeddingToolkit
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-dotWaveform
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-MelBandRoFormer
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-DiffusersLoader
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_ColorMod
   0.0 seconds: C:\ComfyUI\custom_nodes\comfyui_acetricks
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-QuantOps
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-KJNodes
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_SamplingUtils
   0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-ModelUtils
   0.1 seconds: C:\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved
   0.1 seconds: C:\ComfyUI\custom_nodes\IAMCCS-nodes
   0.3 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Whisper-Boyo
   0.4 seconds: C:\ComfyUI\custom_nodes\Nvidia_RTX_Nodes_ComfyUI
   0.6 seconds: C:\ComfyUI\custom_nodes\ComfyUI-AudioScheduler
   0.7 seconds: C:\ComfyUI\custom_nodes\ComfyUI-LTXVideo
   0.7 seconds: C:\ComfyUI\custom_nodes\scromfyUI-AceStep
   0.7 seconds: C:\ComfyUI\custom_nodes\ComfyUI_AudioTools
   0.8 seconds: C:\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
   1.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_DiffRhythm
   1.6 seconds: C:\ComfyUI\custom_nodes\ComfyUI-EulerDiscreteScheduler

Context impl SQLiteImpl.
Will assume non-transactional DDL.
Starting server

To see the GUI go to: http://127.0.0.1:8188
[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.
Exception in callback _ProactorBasePipeTransport._call_connection_lost()
handle: <Handle _ProactorBasePipeTransport._call_connection_lost()>
Traceback (most recent call last):
  File "F:\Python314\install\Lib\asyncio\events.py", line 94, in _run
    self._context.run(self._callback, *self._args)
    ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "F:\Python314\install\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
    self._sock.shutdown(socket.SHUT_RDWR)
    ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
got prompt
Using xformers attention in VAE
Using xformers attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Found quantization metadata version 1
Using MixedPrecisionOps for text encoder
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load WanTEModel
Model WanTEModel prepared for dynamic VRAM loading. 8422MB Staged. 0 patches attached. Force pre-loaded 217 weights: 784 KB.
Model WanTEModel prepared for dynamic VRAM loading. 8422MB Staged. 0 patches attached. Force pre-loaded 217 weights: 784 KB.
Requested to load WanVAE
0 models unloaded.
Model WanVAE prepared for dynamic VRAM loading. 242MB Staged. 0 patches attached. Force pre-loaded 52 weights: 28 KB.
Found quantization metadata version 1
Detected mixed precision quantization
Using mixed precision operations
model weight dtype torch.float16, manual cast: torch.float16
model_type FLOW
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_HIGH_Lightx2v_20251030_FP16.safetensors' strength=1.0
[IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_HIGH_NVFP4_n200.safetensors' strength=1.0
Requested to load WAN21
0 models unloaded.
Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached.
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:06<00:00, 33.24s/it]
Found quantization metadata version 1
Detected mixed precision quantization
Using mixed precision operations
model weight dtype torch.float16, manual cast: torch.float16
model_type FLOW
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_LOW_Lightx2v_20251030_FP16.safetensors' strength=1.0
[IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_LOW_NVFP4_n300.safetensors' strength=1.0
Requested to load WAN21
0 models unloaded.
Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached.
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:09<00:00, 34.78s/it]
Model WanVAE prepared for dynamic VRAM loading. 242MB Staged. 0 patches attached. Force pre-loaded 52 weights: 28 KB.
Prompt executed in 299.43 seconds
Exception in callback _ProactorBasePipeTransport._call_connection_lost()
handle: <Handle _ProactorBasePipeTransport._call_connection_lost()>
Traceback (most recent call last):
  File "F:\Python314\install\Lib\asyncio\events.py", line 94, in _run
    self._context.run(self._callback, *self._args)
    ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "F:\Python314\install\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost
    self._sock.shutdown(socket.SHUT_RDWR)
    ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
got prompt
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan2.2_HIGH_rCM4.0_rank256_FP16.safetensors' strength=0.7
[IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_HIGH_Lightx2v_20251030_FP16.safetensors' strength=0.7
[IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_HIGH_NVFP4_n200.safetensors' strength=1.0
Requested to load WAN21
Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached.
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:07<00:00, 33.57s/it]
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B
[IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan2.2_LOW_rCM1.0_rank256_FP16.safetensors' strength=0.7
[IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_LOW_Lightx2v_20251030_FP16.safetensors' strength=0.7
[IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_LOW_NVFP4_n300.safetensors' strength=1.0
Requested to load WAN21
Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached.
  0%|                                                                                                                                                                                                                                                                                                  | 0/2 [00:00<?, ?it/s,   Model Initializing ...  ]
!!! Exception during processing !!! VRAM reservation failed
Traceback (most recent call last):
  File "C:\ComfyUI\execution.py", line 535, 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, v3_data=v3_data)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\execution.py", line 335, 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, v3_data=v3_data)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\execution.py", line 309, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "C:\ComfyUI\execution.py", line 297, in process_inputs
    result = f(**inputs)
  File "C:\ComfyUI\comfy_api\internal\__init__.py", line 149, in wrapped_func
    return method(locked_class, **inputs)
  File "C:\ComfyUI\comfy_api\latest\_io.py", line 1833, in EXECUTE_NORMALIZED
    to_return = cls.execute(*args, **kwargs)
  File "C:\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 963, in execute
    samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed)
  File "C:\ComfyUI\comfy\samplers.py", line 1052, in sample
    output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
  File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute
    return self.original(*args, **kwargs)
           ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\samplers.py", line 995, in outer_sample
    output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
  File "C:\ComfyUI\comfy\samplers.py", line 981, in inner_sample
    samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
  File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute
    return self.original(*args, **kwargs)
           ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\samplers.py", line 751, in sample
    samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
  File "F:\Python314\install\Lib\site-packages\torch\utils\_contextlib.py", line 124, in decorate_context
    return func(*args, **kwargs)
  File "C:\ComfyUI\comfy\k_diffusion\sampling.py", line 205, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
  File "C:\ComfyUI\comfy\samplers.py", line 400, in __call__
    out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
  File "C:\ComfyUI\comfy\samplers.py", line 954, in __call__
    return self.outer_predict_noise(*args, **kwargs)
           ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\samplers.py", line 961, in outer_predict_noise
    ).execute(x, timestep, model_options, seed)
      ~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute
    return self.original(*args, **kwargs)
           ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\samplers.py", line 964, in predict_noise
    return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
  File "C:\ComfyUI\comfy\samplers.py", line 380, in sampling_function
    out = calc_cond_batch(model, conds, x, timestep, model_options)
  File "C:\ComfyUI\comfy\samplers.py", line 205, in calc_cond_batch
    return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
  File "C:\ComfyUI\comfy\samplers.py", line 213, in _calc_cond_batch_outer
    return executor.execute(model, conds, x_in, timestep, model_options)
           ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute
    return self.original(*args, **kwargs)
           ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\samplers.py", line 325, in _calc_cond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
             ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\model_base.py", line 182, in apply_model
    return comfy.patcher_extension.WrapperExecutor.new_class_executor(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    ...<2 lines>...
        comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.APPLY_MODEL, transformer_options)
        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    ).execute(x, t, c_concat, c_crossattn, control, transformer_options, **kwargs)
    ~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute
    return self.original(*args, **kwargs)
           ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\model_base.py", line 226, in _apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\ComfyUI\comfy\ldm\wan\model.py", line 644, in forward
    return comfy.patcher_extension.WrapperExecutor.new_class_executor(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    ...<2 lines>...
        comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options)
        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    ).execute(x, timestep, context, clip_fea, time_dim_concat, transformer_options, **kwargs)
    ~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute
    return self.original(*args, **kwargs)
           ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\ldm\wan\model.py", line 664, in _forward
    return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, **kwargs)[:, :, :t, :h, :w]
           ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\ldm\wan\model.py", line 561, in forward_orig
    e = self.time_embedding(
        sinusoidal_embedding_1d(self.freq_dim, t.flatten()).to(dtype=x[0].dtype))
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\container.py", line 253, in forward
    input = module(input)
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
  File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\ComfyUI\comfy\ops.py", line 1231, in forward
    output = self.forward_comfy_cast_weights(input, compute_dtype, want_requant=isinstance(input, QuantizedTensor))
  File "C:\ComfyUI\comfy\ops.py", line 1174, in forward_comfy_cast_weights
    weight, bias, offload_stream = cast_bias_weight(self, input, offloadable=True, compute_dtype=compute_dtype, want_requant=want_requant)
                                   ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\ComfyUI\comfy\ops.py", line 302, in cast_bias_weight
    offload_stream = cast_modules_with_vbar([s], dtype, device, bias_dtype, non_blocking)
  File "C:\ComfyUI\comfy\ops.py", line 163, in cast_modules_with_vbar
    xfer_dest = get_cast_buffer(dest_size)
  File "C:\ComfyUI\comfy\ops.py", line 122, in get_cast_buffer
    cast_buffer = comfy.model_management.get_aimdo_cast_buffer(offload_stream, device)
  File "C:\ComfyUI\comfy\model_management.py", line 1221, in get_aimdo_cast_buffer
    cast_buffer = comfy_aimdo.vram_buffer.VRAMBuffer(DEFAULT_AIMDO_CAST_BUFFER_RESERVATION_SIZE, device.index)
  File "F:\Python314\install\Lib\site-packages\comfy_aimdo\vram_buffer.py", line 33, in __init__
    raise RuntimeError("VRAM reservation failed")
RuntimeError: VRAM reservation failed

Prompt executed in 88.48 seconds

Originally created by @jovan2009 on GitHub (May 12, 2026). Original GitHub issue: https://github.com/Comfy-Org/comfy-aimdo/issues/49 Second run of a Wan 2.2 I2V workflow ends in error during low noise ksampler. This is behavior is new to me, I would say it started today with version `comfy-aimdo` ver. 0.4.0. Not many other things has changed (except I did a git pull on ComfyUI today and I updated the nvidia driver to latest but this error started to happen before the driver update). If I want to be precise the second run (that fails) is not an identical workflow with the first run, it is different by having one extra Lora in each chain (3 loras instead of 2). If I restore the Lora configuration back (2 Lora on High, 2 Lora on Low) the error doesn't happen. ``` setup plugin alembic.autogenerate.schemas setup plugin alembic.autogenerate.tables setup plugin alembic.autogenerate.types setup plugin alembic.autogenerate.constraints setup plugin alembic.autogenerate.defaults setup plugin alembic.autogenerate.comments Adding extra search path checkpoints E:\ComfyUI\models\checkpoints Adding extra search path text_encoders E:\ComfyUI\models\text_encoders Adding extra search path text_encoders E:\ComfyUI\models\clip\ # legacy location still supported Adding extra search path clip_vision E:\ComfyUI\models\clip_vision Adding extra search path configs E:\ComfyUI\models\configs Adding extra search path controlnet E:\ComfyUI\models\controlnet Adding extra search path diffusion_models E:\ComfyUI\models\diffusion_models Adding extra search path diffusion_models E:\ComfyUI\models\unet Adding extra search path embeddings E:\ComfyUI\models\embeddings Adding extra search path loras E:\ComfyUI\models\loras Adding extra search path upscale_models E:\ComfyUI\models\upscale_models Adding extra search path vae E:\ComfyUI\models\vae Adding extra search path audio_encoders E:\ComfyUI\models\audio_encoders Adding extra search path model_patches E:\ComfyUI\models\model_patches Adding extra search path latent_upscale_models E:\ComfyUI\models\latent_upscale_models Found triton 3.7.0. Enabling comfy-kitchen triton backend. Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_int8', 'dequantize_int8_simple', 'dequantize_mxfp8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'mm_int8', 'quantize_int8', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_int8', 'scaled_mm_mxfp8', 'scaled_mm_nvfp4']} Found comfy_kitchen backend triton: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_int8', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'int8_linear', 'quantize_int8', 'quantize_int8_rowwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_int8']} Found comfy_kitchen backend cuda: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']} Checkpoint files will always be loaded safely. Total VRAM 16023 MB, total RAM 65465 MB pytorch version: 2.13.0.dev20260512+cu132 MSLK running in python-only mode — skipping native library loading xformers version: 0.0.35+ca6d2aa.d20260509 Enabled fp16 accumulation. Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 5060 Ti : cudaMallocAsync Using async weight offloading with 2 streams Enabled pinned memory 26185.0 Using sage attention aimdo: src-win/cuda-detour.c:38:INFO:aimdo_setup_hooks: installing 6 hooks aimdo: src-win/cuda-detour.c:28:DEBUG:install_hook_entries: hooks successfully installed aimdo: src-win/shmem-detect.c:80:INFO:comfy-aimdo WDDM adapter match: NVIDIA GeForce RTX 5060 Ti runtime_luid=00000000:000093d3 dxgi_luid=00000000:000093d3 aimdo: src/control.c:237:INFO:comfy-aimdo inited for GPU: NVIDIA GeForce RTX 5060 Ti (VRAM: 16022 MB) DynamicVRAM support detected and enabled Python version: 3.14.5 (main, May 10 2026, 20:29:46) [MSC v.1944 64 bit (AMD64)] ComfyUI version: 0.21.0 comfy-aimdo version: 0.4.0 comfy-kitchen version: 0.2.8 ComfyUI frontend version: 1.43.18 [Prompt Server] web root: F:\Python314\install\Lib\site-packages\comfyui_frontend_package\static Asset seeder disabled Unable to parse pyproject.toml due to lack dependency pydantic-settings, please run 'pip install -r requirements.txt': Illegal character '\n' (at line 3, column 101) ComfyUI-QuantOps: Enabled comfy-kitchen triton backend ComfyUI-QuantOps: Registered quantops_int8 backend ComfyUI-QuantOps: Registered quantops_fp8 backend ComfyUI-QuantOps: Registered TensorWiseINT8Layout ComfyUI-QuantOps: Registered TensorCoreMXFP8Layout ComfyUI-QuantOps: Registered HybridMXFP8Layout ComfyUI-QuantOps: Registered layouts: ['BlockWiseINT8Layout', 'TensorWiseINT8Layout', 'RowWiseFP8Layout', 'BlockWiseFP8Layout', 'TensorCoreMXFP8Layout'] Error: File not found - extra_help_file.yaml No customize audios loading path found, use default path. ColorMod: Ignoring node 'CV2TonemapDurand' due to cv2 edition/version IAMCCS compat: enabled local Qwen Multi-Gen seed widget patch [IAMCCS] WARNING: IAMCCS_QWEN_VL_FLF could not load — [IAMCCS_QWEN_VL_FLF] Cannot find QwenVLBase. Make sure ComfyUI-QwenVL is installed under custom_nodes/ComfyUI-QwenVL. [IAMCCS] Make sure ComfyUI-QwenVL is installed in custom_nodes/ComfyUI-QwenVL ___ _ __ __ ____ ____ ____ ____ _ |_ _| / \ | \/ |/ ___/ ___|/ ___| | _ \ ___ ___| | _____ | | / _ \ | |\/| | | | | \___ \ | |_) / _ \ / __| |/ / __| | | / ___ \| | | | |__| |___ ___) || __/ (_) | (__| <\__ \ |___/_/ \_\_| |_|\____\____||____/ |_| \___/ \___|_|\_\___/ by IAMCCS (follow me on patreon.com/IAMCCS or carminecristalloscalzi.com) IAMCCS nodes loaded: 190 - IAMCCS-SuperNodes AU+IMG2VID Exec Finalize, IAMCCS-SuperNodes AU+IMG2VID Exec Planner, IAMCCS-SuperNodes AU+IMG2VID Exec Render, IAMCCS-SuperNodes AU+IMG2VID Exec VAE, IAMCCS-SuperNodes Second Stage, IAMCCS_AUIMG2VID_AudioTimeline, IAMCCS_AUIMG2VID_Continuity, IAMCCS_AUIMG2VID_DiskExtension, IAMCCS_AUIMG2VID_Finalize, IAMCCS_AUIMG2VID_KeyframeTimeline - IAMCCS_AUIMG2VID_Planner, IAMCCS_AUIMG2VID_ProjectTimelinePlanner, IAMCCS_AUIMG2VID_ReanchorLatent, IAMCCS_AUIMG2VID_RefreshPolicy, IAMCCS_AUIMG2VID_RuntimeBridge, IAMCCS_ApplyLoRAHooksToConditioning, IAMCCS_ApplyScheduledWanLoRAFromConditioning, IAMCCS_AudioExtender, IAMCCS_AudioExtensionMath, IAMCCS_AudioSegmentAutoPlanner - IAMCCS_AudioTimelineAssembler, IAMCCS_AudioTimelineGate, IAMCCS_AutoLinkArguments, IAMCCS_AutoLinkConverter, IAMCCS_BuildScheduledWanModelBank, IAMCCS_CineAllInOneFLFEngine, IAMCCS_CineAudioPromptDirector, IAMCCS_CineFLFEngineSimple, IAMCCS_CineFLFLengthCompensator, IAMCCS_CineInfo - IAMCCS_CineLTXSequencer, IAMCCS_CineLTXSequencerExact, IAMCCS_CineLineStacker, IAMCCS_CineMultiGenDirector, IAMCCS_CineMusicVideoPlanner, IAMCCS_CinePromptComposer, IAMCCS_CinePromptRelayAdapter, IAMCCS_CinePromptRelayLatentShapeSync, IAMCCS_CinePromptRelaySafeEncode, IAMCCS_CinePromptRelayTimeline - IAMCCS_CineRefLatentControl, IAMCCS_CineReferenceBoard, IAMCCS_CineRelayOrBypass, IAMCCS_CineShotAudioDirector, IAMCCS_CineShotLineBuilder, IAMCCS_CineShotPlanner, IAMCCS_CineShotboardLite, IAMCCS_CineShotboardPlannerPro, IAMCCS_CineShotboardPlannerProLegacy, IAMCCS_CineShotboardPlannerProV2 - IAMCCS_CineShotboardTimelinePro, IAMCCS_CineSwitch, IAMCCS_CineV2VAssetSelector, IAMCCS_CineV2VTimelineDirector, IAMCCS_CineV2VTimelineLineBuilder, IAMCCS_CineWorkflowInspector, IAMCCS_FluxKleinMultiGen, IAMCCS_GGUF_accelerator, IAMCCS_GetAutoLink, IAMCCS_HWProbeRecommendations - IAMCCS_HardMemoryPurge, IAMCCS_HwSupporter, IAMCCS_HwSupporterAny, IAMCCS_ImageBatchRangeLite, IAMCCS_ImageResizeBatchSafe, IAMCCS_IntValueMonitor, IAMCCS_LTX2_BlendLatentBridge, IAMCCS_LTX2_ConditionNextLatentWithPrevOverlap, IAMCCS_LTX2_ContextLatent, IAMCCS_LTX2_ControlPreprocess - IAMCCS_LTX2_EnsureFrames8nPlus1, IAMCCS_LTX2_EnsureMinFrames, IAMCCS_LTX2_ExtendSampler, IAMCCS_LTX2_ExtensionModule, IAMCCS_LTX2_ExtensionModule_Disk, IAMCCS_LTX2_ExtensionModule_simple, IAMCCS_LTX2_FirstLastFramesController, IAMCCS_LTX2_FirstLastLatentControl, IAMCCS_LTX2_FirstLastLatentControl_Pro, IAMCCS_LTX2_FrameCountValidator - IAMCCS_LTX2_FrameRateSync, IAMCCS_LTX2_GetImageFromBatch, IAMCCS_LTX2_ImageBatchCropByPad, IAMCCS_LTX2_ImageBatchPadReflect, IAMCCS_LTX2_InitLatentSampler, IAMCCS_LTX2_JointRefreshLatent, IAMCCS_LTX2_JointRefreshLatent_Disk, IAMCCS_LTX2_LastFrameBridgeLoad, IAMCCS_LTX2_LastFrameBridgeSave, IAMCCS_LTX2_LoRAStack - IAMCCS_LTX2_LoRAStackModelIO, IAMCCS_LTX2_LoRAStackSegmented6, IAMCCS_LTX2_LoRAStackStaged, IAMCCS_LTX2_LoadLatentBridge, IAMCCS_LTX2_LongVideoWrapperPrep, IAMCCS_LTX2_LongVideoWrapperPrepDisk, IAMCCS_LTX2_LoopingSampler, IAMCCS_LTX2_MiddleFrames, IAMCCS_LTX2_ModelWithLoRA_Segmented6, IAMCCS_LTX2_OneShotLowRAMLooper - IAMCCS_LTX2_ReferenceImageSwitch, IAMCCS_LTX2_ReferenceStartFramesInjector, IAMCCS_LTX2_SaveLatentBridge, IAMCCS_LTX2_SegmentQueueLoop, IAMCCS_LTX2_TimeFrameCount, IAMCCS_LTX2_Validator, IAMCCS_LatentTailSlice, IAMCCS_LazyAnySwitch, IAMCCS_LoadImagesFromDirLite, IAMCCS_LoadResizeSegmentFromDir - IAMCCS_Ltx2HelperModules_AudioTimeline, IAMCCS_Ltx2HelperModules_Continuity, IAMCCS_Ltx2HelperModules_DiskExtension, IAMCCS_Ltx2HelperModules_Finalize, IAMCCS_Ltx2HelperModules_KeyframeTimeline, IAMCCS_Ltx2HelperModules_Planner, IAMCCS_Ltx2HelperModules_ProjectTimelinePlanner, IAMCCS_Ltx2HelperModules_ReanchorLatent, IAMCCS_Ltx2HelperModules_RefreshPolicy, IAMCCS_Ltx2HelperModules_RuntimeBridge - IAMCCS_ModelWithLoRA, IAMCCS_ModelWithLoRA_LTX2, IAMCCS_ModelWithLoRA_LTX2_Staged, IAMCCS_ModelWithLoRA_RuntimeBridge, IAMCCS_MotionBridgeLoad, IAMCCS_MotionBridgeSave, IAMCCS_MotionScale, IAMCCS_MotionScaleAdvanced, IAMCCS_MoveAhead, IAMCCS_MoveAheadEnforcer - IAMCCS_MultiSwitch, IAMCCS_MultilinePromptSplitter8, IAMCCS_ProjectTimelinePlanner, IAMCCS_QwenMultiGen, IAMCCS_SamplerAdvancedVersion1, IAMCCS_SegmentPlanFromPlanner, IAMCCS_SegmentPlanner, IAMCCS_SegmentPlannerLinked, IAMCCS_SegmentPlannerSettings, IAMCCS_SegmentSwitch - IAMCCS_SelectScheduledWanModelFromConditioning, IAMCCS_SelectScheduledWanModelPairFromConditioning, IAMCCS_SetAutoLink, IAMCCS_SourceFramesToDisk, IAMCCS_SourceRangeFromSegmentPlan, IAMCCS_StartDirToVideoLatent, IAMCCS_StartImagesToVideoLatent, IAMCCS_SupernodeBase, IAMCCS_SupernodeModule, IAMCCS_ThreeSegmentPlanner - IAMCCS_TwoSegmentPlanner, IAMCCS_VAEDecodeTiledSafe, IAMCCS_VAEDecodeToDisk, IAMCCS_VRAMCleanup, IAMCCS_VRAMFlushLatent, IAMCCS_VideoCombineFromDir, IAMCCS_WDC_LTXKeyframer, IAMCCS_WDC_LTXSequencer, IAMCCS_WDC_LTXSequencerFixed5, IAMCCS_WDC_MultiImageLoader - IAMCCS_WanContinuityGuide, IAMCCS_WanImageBatchFrameSelect, IAMCCS_WanImageMotion, IAMCCS_WanImageMotionInductive, IAMCCS_WanImageMotionPro, IAMCCS_WanImageMotionProLegacy, IAMCCS_WanImageMotionProPlus, IAMCCS_WanImageMotionProPlus_Simple, IAMCCS_WanImageMotionPro_AdaIN, IAMCCS_WanImageMotion_AdaIN - IAMCCS_WanIndexedPromptEncode, IAMCCS_WanLoRAHookSchedule, IAMCCS_WanLoRARuntimeBridge, IAMCCS_WanLoRASchedule, IAMCCS_WanLoRAStack, IAMCCS_WanLoRAStackModelIO, IAMCCS_WanLongPlanner, IAMCCS_WanPrevTailPrep, IAMCCS_WanPromptLoopInfo, IAMCCS_WanPromptPhasePlanner - IAMCCS_WanSVIToFLFBridgeProPlus, IAMCCS_WanSVIToFLFBridgeProPlus_Simple, IAMCCS_WanSviFlfTimeline, IAMCCS_WanSviFlfTimelinePick, IAMCCS_bus_group, WanImageMotionPro, WanImageMotionProLegacy, WanImageMotionProPlus, WanMotionProTrimmer, iamccs_ltx2_lora_stack Failed to load node module lyrics_groq_node: No module named 'groq' Failed to load node module transcribe_faster_whisper_load_node: No module named 'faster_whisper' Failed to load node module transcribe_faster_whisper_node: No module named 'faster_whisper' Failed to load node module transcribe_faster_whisper_save_node: No module named 'faster_whisper' 🎵 ACE-Step Nodes loaded: 85 nodes registered Import times for custom nodes: 0.0 seconds: C:\ComfyUI\custom_nodes\websocket_image_save.py 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_EmbeddingToolkit 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-dotWaveform 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-MelBandRoFormer 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-DiffusersLoader 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_ColorMod 0.0 seconds: C:\ComfyUI\custom_nodes\comfyui_acetricks 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-QuantOps 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-KJNodes 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_SamplingUtils 0.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI-ModelUtils 0.1 seconds: C:\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved 0.1 seconds: C:\ComfyUI\custom_nodes\IAMCCS-nodes 0.3 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Whisper-Boyo 0.4 seconds: C:\ComfyUI\custom_nodes\Nvidia_RTX_Nodes_ComfyUI 0.6 seconds: C:\ComfyUI\custom_nodes\ComfyUI-AudioScheduler 0.7 seconds: C:\ComfyUI\custom_nodes\ComfyUI-LTXVideo 0.7 seconds: C:\ComfyUI\custom_nodes\scromfyUI-AceStep 0.7 seconds: C:\ComfyUI\custom_nodes\ComfyUI_AudioTools 0.8 seconds: C:\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper 1.0 seconds: C:\ComfyUI\custom_nodes\ComfyUI_DiffRhythm 1.6 seconds: C:\ComfyUI\custom_nodes\ComfyUI-EulerDiscreteScheduler Context impl SQLiteImpl. Will assume non-transactional DDL. Starting server To see the GUI go to: http://127.0.0.1:8188 [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. Exception in callback _ProactorBasePipeTransport._call_connection_lost() handle: <Handle _ProactorBasePipeTransport._call_connection_lost()> Traceback (most recent call last): File "F:\Python314\install\Lib\asyncio\events.py", line 94, in _run self._context.run(self._callback, *self._args) ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\Python314\install\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^ ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host got prompt Using xformers attention in VAE Using xformers attention in VAE VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16 Found quantization metadata version 1 Using MixedPrecisionOps for text encoder CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16 Requested to load WanTEModel Model WanTEModel prepared for dynamic VRAM loading. 8422MB Staged. 0 patches attached. Force pre-loaded 217 weights: 784 KB. Model WanTEModel prepared for dynamic VRAM loading. 8422MB Staged. 0 patches attached. Force pre-loaded 217 weights: 784 KB. Requested to load WanVAE 0 models unloaded. Model WanVAE prepared for dynamic VRAM loading. 242MB Staged. 0 patches attached. Force pre-loaded 52 weights: 28 KB. Found quantization metadata version 1 Detected mixed precision quantization Using mixed precision operations model weight dtype torch.float16, manual cast: torch.float16 model_type FLOW [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_HIGH_Lightx2v_20251030_FP16.safetensors' strength=1.0 [IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_HIGH_NVFP4_n200.safetensors' strength=1.0 Requested to load WAN21 0 models unloaded. Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached. 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:06<00:00, 33.24s/it] Found quantization metadata version 1 Detected mixed precision quantization Using mixed precision operations model weight dtype torch.float16, manual cast: torch.float16 model_type FLOW [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_LOW_Lightx2v_20251030_FP16.safetensors' strength=1.0 [IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_LOW_NVFP4_n300.safetensors' strength=1.0 Requested to load WAN21 0 models unloaded. Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached. 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:09<00:00, 34.78s/it] Model WanVAE prepared for dynamic VRAM loading. 242MB Staged. 0 patches attached. Force pre-loaded 52 weights: 28 KB. Prompt executed in 299.43 seconds Exception in callback _ProactorBasePipeTransport._call_connection_lost() handle: <Handle _ProactorBasePipeTransport._call_connection_lost()> Traceback (most recent call last): File "F:\Python314\install\Lib\asyncio\events.py", line 94, in _run self._context.run(self._callback, *self._args) ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\Python314\install\Lib\asyncio\proactor_events.py", line 165, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^ ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host got prompt [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan2.2_HIGH_rCM4.0_rank256_FP16.safetensors' strength=0.7 [IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_HIGH_Lightx2v_20251030_FP16.safetensors' strength=0.7 [IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_HIGH_NVFP4_n200.safetensors' strength=1.0 Requested to load WAN21 Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached. 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [01:07<00:00, 33.57s/it] [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStack] Detected Wan 2.1 format - converted lora_down/up → lora_A/B [IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan2.2_LOW_rCM1.0_rank256_FP16.safetensors' strength=0.7 [IAMCCS_WanLoRAStackModelIO] ✅ 'D_Wan_2.2_I2V_LOW_Lightx2v_20251030_FP16.safetensors' strength=0.7 [IAMCCS_WanLoRAStackModelIO] ✅ 'Lora_Wan_2.2_I2V_LOW_NVFP4_n300.safetensors' strength=1.0 Requested to load WAN21 Model WAN21 prepared for dynamic VRAM loading. 7990MB Staged. 406 patches attached. 0%| | 0/2 [00:00<?, ?it/s, Model Initializing ... ] !!! Exception during processing !!! VRAM reservation failed Traceback (most recent call last): File "C:\ComfyUI\execution.py", line 535, 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, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\execution.py", line 335, 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, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\execution.py", line 309, in _async_map_node_over_list await process_inputs(input_dict, i) File "C:\ComfyUI\execution.py", line 297, in process_inputs result = f(**inputs) File "C:\ComfyUI\comfy_api\internal\__init__.py", line 149, in wrapped_func return method(locked_class, **inputs) File "C:\ComfyUI\comfy_api\latest\_io.py", line 1833, in EXECUTE_NORMALIZED to_return = cls.execute(*args, **kwargs) File "C:\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 963, in execute samples = guider.sample(noise.generate_noise(latent), latent_image, sampler, sigmas, denoise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=noise.seed) File "C:\ComfyUI\comfy\samplers.py", line 1052, in sample output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes) File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute return self.original(*args, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\samplers.py", line 995, in outer_sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes) File "C:\ComfyUI\comfy\samplers.py", line 981, in inner_sample samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute return self.original(*args, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\samplers.py", line 751, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options) File "F:\Python314\install\Lib\site-packages\torch\utils\_contextlib.py", line 124, in decorate_context return func(*args, **kwargs) File "C:\ComfyUI\comfy\k_diffusion\sampling.py", line 205, in sample_euler denoised = model(x, sigma_hat * s_in, **extra_args) File "C:\ComfyUI\comfy\samplers.py", line 400, in __call__ out = self.inner_model(x, sigma, model_options=model_options, seed=seed) File "C:\ComfyUI\comfy\samplers.py", line 954, in __call__ return self.outer_predict_noise(*args, **kwargs) ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\samplers.py", line 961, in outer_predict_noise ).execute(x, timestep, model_options, seed) ~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute return self.original(*args, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\samplers.py", line 964, in predict_noise return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed) File "C:\ComfyUI\comfy\samplers.py", line 380, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) File "C:\ComfyUI\comfy\samplers.py", line 205, in calc_cond_batch return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options) File "C:\ComfyUI\comfy\samplers.py", line 213, in _calc_cond_batch_outer return executor.execute(model, conds, x_in, timestep, model_options) ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute return self.original(*args, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\samplers.py", line 325, in _calc_cond_batch output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks) ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\model_base.py", line 182, in apply_model return comfy.patcher_extension.WrapperExecutor.new_class_executor( ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ...<2 lines>... comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.APPLY_MODEL, transformer_options) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ).execute(x, t, c_concat, c_crossattn, control, transformer_options, **kwargs) ~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute return self.original(*args, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\model_base.py", line 226, in _apply_model model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds) File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl return forward_call(*args, **kwargs) File "C:\ComfyUI\comfy\ldm\wan\model.py", line 644, in forward return comfy.patcher_extension.WrapperExecutor.new_class_executor( ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ...<2 lines>... comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ).execute(x, timestep, context, clip_fea, time_dim_concat, transformer_options, **kwargs) ~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\patcher_extension.py", line 112, in execute return self.original(*args, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\ldm\wan\model.py", line 664, in _forward return self.forward_orig(x, timestep, context, clip_fea=clip_fea, freqs=freqs, transformer_options=transformer_options, **kwargs)[:, :, :t, :h, :w] ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\ldm\wan\model.py", line 561, in forward_orig e = self.time_embedding( sinusoidal_embedding_1d(self.freq_dim, t.flatten()).to(dtype=x[0].dtype)) File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl return forward_call(*args, **kwargs) File "F:\Python314\install\Lib\site-packages\torch\nn\modules\container.py", line 253, in forward input = module(input) File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "F:\Python314\install\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl return forward_call(*args, **kwargs) File "C:\ComfyUI\comfy\ops.py", line 1231, in forward output = self.forward_comfy_cast_weights(input, compute_dtype, want_requant=isinstance(input, QuantizedTensor)) File "C:\ComfyUI\comfy\ops.py", line 1174, in forward_comfy_cast_weights weight, bias, offload_stream = cast_bias_weight(self, input, offloadable=True, compute_dtype=compute_dtype, want_requant=want_requant) ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ComfyUI\comfy\ops.py", line 302, in cast_bias_weight offload_stream = cast_modules_with_vbar([s], dtype, device, bias_dtype, non_blocking) File "C:\ComfyUI\comfy\ops.py", line 163, in cast_modules_with_vbar xfer_dest = get_cast_buffer(dest_size) File "C:\ComfyUI\comfy\ops.py", line 122, in get_cast_buffer cast_buffer = comfy.model_management.get_aimdo_cast_buffer(offload_stream, device) File "C:\ComfyUI\comfy\model_management.py", line 1221, in get_aimdo_cast_buffer cast_buffer = comfy_aimdo.vram_buffer.VRAMBuffer(DEFAULT_AIMDO_CAST_BUFFER_RESERVATION_SIZE, device.index) File "F:\Python314\install\Lib\site-packages\comfy_aimdo\vram_buffer.py", line 33, in __init__ raise RuntimeError("VRAM reservation failed") RuntimeError: VRAM reservation failed Prompt executed in 88.48 seconds ```

bsakaguchi closed this issue

2026-10-26 22:23:38 +00:00

bsakaguchi commented

2026-10-26 22:23:39 +00:00

Author

Owner

@jovan2009 commented on GitHub (May 12, 2026):

Shuffling things around I came to the conclusion that the error happens only in a narrow set of 3 conditions

Starting ComfyUI with --fast options (FP16 accumulation + fp8_matrix_mult + cublas_ops)
Using exactly those 3 + 3 Lora's ( For high and low noise)
Using for loading the Lora's the nodes from this custom node https://github.com/IAMCCS/IAMCCS-nodes.git

If I eliminate/change any of those 3 the error doesn't happen. For example if load the Lora's through standard ComfyUI nodes everything is alright.

I imagine it's impossible to reproduce this because on top of using custom nodes all the safetensors involved are made by me one way or the other (Wan 2.2 nvfp4 quantizations, fp8 quantized text encoder, extracted Lora's from distilled models).

@jovan2009 commented on GitHub (May 12, 2026): Shuffling things around I came to the conclusion that the error happens only in a narrow set of 3 conditions - Starting ComfyUI with `--fast` options (FP16 accumulation + fp8_matrix_mult + cublas_ops) - Using exactly those 3 + 3 Lora's ( For high and low noise) - Using for loading the Lora's the nodes from this custom node https://github.com/IAMCCS/IAMCCS-nodes.git If I eliminate/change any of those 3 the error doesn't happen. For example if load the Lora's through standard ComfyUI nodes everything is alright. I imagine it's impossible to reproduce this because on top of using custom nodes all the safetensors involved are made by me one way or the other (Wan 2.2 nvfp4 quantizations, fp8 quantized text encoder, extracted Lora's from distilled models).

bsakaguchi commented

2026-10-26 22:23:39 +00:00

Author

Owner

@jovan2009 commented on GitHub (May 16, 2026):

Things got worse (with version 0.4.1) before they got better (with version 0.4.2). With version 0.4.1 I would get errors every time if I used NVFP4 safetensors in the workflow (as soon I replaced them with their FP16 versions errors disappeared). But with version 0.4.2 everything seems alright now. The issue that I had apparently was fixed before I could update this thread with the errors I had with 0.4.1. I think I will close now, thanks a lot!

@jovan2009 commented on GitHub (May 16, 2026): Things got worse (with version `0.4.1`) before they got better (with version `0.4.2`). With version `0.4.1` I would get errors every time if I used NVFP4 safetensors in the workflow (as soon I replaced them with their FP16 versions errors disappeared). But with version `0.4.2` everything seems alright now. The issue that I had apparently was fixed before I could update this thread with the errors I had with `0.4.1`. I think I will close now, thanks a lot!

No labels

pull-request

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/comfy-aimdo#18

No description provided.

Rows
Columns