LTXV2 SamplerCustomAdvanced - AttributeError: module 'torch' has no attribute 'float4_e2m1fn_x2' #11712
Description
Custom Node Testing
- I have tried disabling custom nodes and the issue persists (see how to disable custom nodes if you need help)
Your question
Both official and Kijai WF fail. Tried to save a bit on memory by going fp8 gemma and fp4 checkpoint.
Portable: .\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --cuda-malloc --reserve-vram 2.0 --use-sage-attention (tried without sage or cross attention, still fails)
Win11, 5070 Ti 16GB, 64GB RAM
pytorch version: 2.7.0+cu128
Python version: 3.12.10
ComfyUI version: 0.8.0
ComfyUI frontend version: 1.35.9
ltx-2-19b-dev-fp4.safetensors
gemma_3_12B_it_fp8_e4m3fn.safetensors
in the console there's a wall of text starting: "unet unexpected: ['audio_embeddin..."
Logs
D:\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --cuda-malloc --reserve-vram 2.0
[START] Security scan
[DONE] Security scan
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-01-08 01:40:21.440
** Platform: Windows
** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
** Python executable: D:\ComfyUI_windows_portable\python_embeded\python.exe
** ComfyUI Path: D:\ComfyUI_windows_portable\ComfyUI
** ComfyUI Base Folder Path: D:\ComfyUI_windows_portable\ComfyUI
** User directory: D:\ComfyUI_windows_portable\ComfyUI\user
** ComfyUI-Manager config path: D:\ComfyUI_windows_portable\ComfyUI\user\__manager\config.ini
** Log path: D:\ComfyUI_windows_portable\ComfyUI\user\comfyui.log
[SAM3] ComfyUI-SAM3 prestartup script running...
[SAM3] Script directory: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-sam3
[SAM3] ComfyUI root: D:\ComfyUI_windows_portable\ComfyUI
[SAM3] Copying image assets to D:\ComfyUI_windows_portable\ComfyUI\input...
[SAM3] Image assets: 0 copied, 4 skipped
[SAM3] Prestartup script completed
Prestartup times for custom nodes:
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-easy-use
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-sam3
2.6 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager
Checkpoint files will always be loaded safely.
Total VRAM 16303 MB, total RAM 63143 MB
pytorch version: 2.7.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5070 Ti : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 28414.0
Found comfy_kitchen backend cuda: {'available': False, 'disabled': True, 'unavailable_reason': 'DLL load failed while importing _C: The specified module could not be found.', 'capabilities': []}
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend triton: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8']}
Using pytorch attention
Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)]
ComfyUI version: 0.8.0
ComfyUI frontend version: 1.35.9
[Prompt Server] web root: D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static
Total VRAM 16303 MB, total RAM 63143 MB
pytorch version: 2.7.0+cu128
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 5070 Ti : cudaMallocAsync
Using async weight offloading with 2 streams
Enabled pinned memory 28414.0
2026-01-08 01:40:27.710143: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2026-01-08 01:40:28.308614: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
[D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-mtb] | INFO -> loaded 108 nodes successfuly
Web extensions folder found at D:\ComfyUI_windows_portable\ComfyUI\web\extensions\ComfyLiterals
[Crystools INFO] Crystools version: 1.27.4
[Crystools INFO] Platform release: 11
[Crystools INFO] JETSON: Not detected.
[Crystools INFO] CPU: AMD Ryzen 7 9800X3D 8-Core Processor - Arch: AMD64 - OS: Windows 11
[Crystools INFO] pynvml (NVIDIA) initialized.
[Crystools INFO] GPU/s:
[Crystools INFO] 0) NVIDIA GeForce RTX 5070 Ti
[Crystools INFO] NVIDIA Driver: 591.44
[ComfyUI-DepthAnythingV3] Initializing custom node...
[ComfyUI-DepthAnythingV3] [OK] Node classes imported successfully
[ComfyUI-DepthAnythingV3] [OK] Loaded successfully!
[ComfyUI-Easy-Use] server: v1.3.4 Loaded
[ComfyUI-Easy-Use] web root: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-easy-use\web_version/v2 Loaded
loading...
ComfyUI-GGUF: Partial torch compile only, consider updating pytorch
### Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (1.81 MB) is within cache limit (50.00 MB). Using full cache mode.
### Loading: ComfyUI-Impact-Subpack (V1.3.5)
[Impact Pack/Subpack] Using folder_paths to determine whitelist path: D:\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Pack/Subpack] Ensured whitelist directory exists: D:\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack
[Impact Pack/Subpack] Loaded 0 model(s) from whitelist: D:\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Pack] Wildcards loading done.
[Impact Subpack] ultralytics_bbox: D:\ComfyUI_windows_portable\ComfyUI\models\ultralytics\bbox
[Impact Subpack] ultralytics_segm: D:\ComfyUI_windows_portable\ComfyUI\models\ultralytics\segm
### Loading: ComfyUI-Inspire-Pack (V1.23)
jjk_util loding
### Loading: ComfyUI-Manager (V3.39.1)
[ComfyUI-Manager] network_mode: personal_cloud
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
### ComfyUI Version: v0.8.0-2-g3cd7b32f | Released on '2026-01-07'
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[QwenVL] Loaded 1 custom legacy models
Error loading module AILab_QwenVL_GGUF_PromptEnhancer: No module named 'llama_cpp'
### Loading: ComfyUI-RBG-SmartSeedVariance ###
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\timm\models\layers\__init__.py:48: 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)
[ComfyUI-RMBG] v2.9.6 | 33 nodes Loaded
[SAM3] ComfyUI-SAM3 v3.0.0 initializing...
[SAM3] [OK] Registered model folder: D:\ComfyUI_windows_portable\ComfyUI\models\sam3
[SAM3] [OK] Node classes imported successfully
[SAM3 Server] Registered routes: /sam3/prepare, /sam3/detect
[SAM3] [OK] API endpoints registered
[SAM3] [OK] Loaded successfully!
[SAM3] Available nodes: LoadSAM3Model, SAM3Grounding, SAM3Segmentation, SAM3MultipromptSegmentation, SAM3CreateBox, SAM3CreatePoint, SAM3CombineBoxes, SAM3CombinePoints, SAM3VideoSegmentation, SAM3Propagate, SAM3VideoOutput, SAM3PointCollector, SAM3BBoxCollector, SAM3MultiRegionCollector
[SAM3] Interactive SAM3 Detector: Right-click any IMAGE/MASK node -> 'Open in SAM3 Detector'
⚡ SeedVR2 optimizations check: SageAttention ✅ | Flash Attention ❌ | Triton ✅
💡 Optional: pip install flash-attn
📊 Initial CUDA memory: 14.57GB free / 15.92GB total
### ComfyUI-Workflow-Encrypt: Copy .js from 'D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-workflow-encrypt\js\comfyui-workflow-encrypt.js' to 'D:\ComfyUI_windows_portable\ComfyUI\web\extensions\comfyui-workflow-encrypt'
------------------------------------------
Comfyroll Studio v1.76 : 175 Nodes Loaded
------------------------------------------
** For changes, please see patch notes at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/blob/main/Patch_Notes.md
** For help, please see the wiki at https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes/wiki
------------------------------------------
[D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
[D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
DWPose: Onnxruntime with acceleration providers detected
[WAS LMStudio Easy-Query] has loaded 8 nodes.
Nodes: LM Studio Model, LM Studio Query, LM Studio Easy-Caption, LM Studio Chat, LM Studio Options, WAS Load Image Directory, LM Studio Easy-Caption Dataset, LM Studio Caption Dataset
[Mira:Tagger] Initializing ONNX model list...
[Mira:Tagger] ONNX model path: D:\ComfyUI_windows_portable\ComfyUI\models\onnx
[Mira:Tagger] No D:\ComfyUI_windows_portable\ComfyUI\models\onnx ONNX Model found.
Initializing ControlAltAI Nodes
[CRT-Nodes __init__] Importing node classes...
Loading crt-nodes module
[comfyui_controlnet_aux] | INFO -> Using ckpts path: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
[comfyui_controlnet_aux] | INFO -> Using symlinks: False
[comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
✅ ControlNet Aux loaded from 'comfyui_controlnet_aux' with 47 preprocessors
[CRT-Nodes __init__] Registering custom model paths...
... 'ultralytics_bbox' path registered.
... 'ultralytics_segm' path registered.
[CRT-Nodes __init__] INITIALIZATION COMPLETE.
WIDEN logging configured: level=INFO, memory_logs=False, diagnostics=False
[DonutNodes] Server routes registered
==================================================
LOADING DONUTWIDENMERGECLIP VERSION 7.0 - FULL ZERO-ACCUMULATION - BUGFIXED
==================================================
[DonutHotReload] Stopped any existing file watching on import
[DonutPromptReceiver] Server started on port 8001
[DonutPromptReceiver] POST http://localhost:8001/prompt
[DonutPromptReceiver] Server ready on port 8001
Using pytorch attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.
(RES4LYF) Importing legacy samplers.
[rgthree-comfy] Loaded 48 epic nodes. 🎉
[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.
[Santodan Nodes] Initializing wildcard API routes...
✅ [Santodan Nodes] EXECUTING: initialize_prompt_list_routes()
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: `ffmpeg_bin_path` is not set in `D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-ns\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 220 nodes successfully.
"The best way to predict the future is to create it." - Peter Drucker
Import times for custom nodes:
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-unsafe-torch
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Z-Engineer-master
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanLightx2vScheduler
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_SigmoidOffsetScheduler
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Z-Engineer
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\scale-image-to-total-pixels-advanced
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\Ttl_ComfyUi_NNLatentUpscale
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_memory_cleanup
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\skimmed_cfg
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-mxtoolkit
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanMoeKSampler
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\WanMoEScheduler
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-ranbooru
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-gelbooru
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\wlsh_nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\cg-use-everywhere
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-detail-daemon
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Miaoshouai-Tagger
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyUI-LongLook
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Jjk-Nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyLiterals
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_sam3
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_instantid
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-automaticcfg
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-seedvr2-tilingupscaler
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-RBG-SmartSeedVariance
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\erosdiffusion-eulerflowmatchingdiscretescheduler
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\mikey_nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_experiments
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\wan22fmlf
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-florence2
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_ipadapter_plus
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Simple_Readable_Metadata-SG
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-image-saver
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_HavocsCall_Custom_Nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AutoCropFaces
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\whiterabbit
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyMath
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-image-saver
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-various
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_essentials
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\lopi999-nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_LMStudio_EasyQuery
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_ultimatesdupscale
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-Resolution-Master
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-custom-scripts
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Chibi-Nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-QwenVL
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\sd-webui-prompt-postprocessor
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-frame-interpolation
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\controlaltai-nodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\derfuu_comfyui_moddednodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Qwen3-VL-Instruct
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-kjnodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Mira
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rapidfire
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\gguf
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-sam3
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\flashvsr_ultra_fast
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-bleh
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-ppm
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_image_metadata_extension
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\basic_data_handling
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-workflow-encrypt
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\santodan-custom-nodes-comfyui
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_Comfyroll_CustomNodes
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-inspire-pack
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-LTXVideo
0.0 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\crt-nodes
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-dynamicprompts
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\donutnodes
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-pack
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_layerstyle
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-DepthAnythingV3
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\RES4LYF
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
0.1 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-SeedVR2_VideoUpscaler
0.2 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Crystools
0.2 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-utils-nodes
0.2 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-MelBandRoFormer
0.3 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-videohelpersuite
0.5 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager
0.6 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-subpack
0.7 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Rife-Tensorrt
0.8 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-ns
1.6 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-rmbg
1.8 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-easy-use
4.5 seconds: D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-mtb
Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 5/118
[DEPRECATION WARNING] Detected import of deprecated legacy API: /scripts/ui.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
[DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/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.
[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.
[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.
[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.
Note: Could not pre-load character names: File not found at: H:\imagegen checkpoints\loras\kiseki_illustrious_v2\prompts\kiseki-noclothes-illustrious_weighted.txt
Note: Could not pre-load character names: File not found at: H:\imagegen checkpoints\loras\kiseki_illustrious_v2\prompts\kiseki-noclothes-illustrious_weighted.txt
[DEBUG] INPUT_TYPES called
[DEBUG] INPUT_TYPES called
{"client": "<lmstudio.sync_api.Client object at 0x000002C3AB567DD0>", "event": "Websocket handling thread started", "thread_id": "Thread-17"}
FETCH ComfyRegistry Data: 10/118
Error fetching models: LM Studio is not reachable at any default port. Is LM Studio running?
Error fetching models: Local API host port is not yet resolved.
FETCH ComfyRegistry Data: 15/118
[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.
FETCH ComfyRegistry Data: 20/118
FETCH ComfyRegistry Data: 25/118
FETCH ComfyRegistry Data: 30/118
FETCH ComfyRegistry Data: 35/118
FETCH ComfyRegistry Data: 40/118
got prompt
Found quantization metadata version 1
Detected mixed precision quantization
Using mixed precision operations
FETCH ComfyRegistry Data: 45/118
model weight dtype torch.bfloat16, manual cast: torch.bfloat16
model_type FLUX
unet unexpected: ['audio_embeddings_connector.learnable_registers', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.k_norm.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.q_norm.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_k.bias', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_k.weight', 'audio_embeddings_connector.transformer_1d_blocks.0.attn1.to_out.0.bias',
SNIP
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load LTXAVTEModel_
FETCH ComfyRegistry Data: 70/118
loaded partially; 12045.80 MB usable, 11483.30 MB loaded, 14480.73 MB offloaded, 562.50 MB buffer reserved, lowvram patches: 0
loaded partially; 11501.00 MB usable, 10938.50 MB loaded, 15025.53 MB offloaded, 562.50 MB buffer reserved, lowvram patches: 0
Requested to load LTXAV
FETCH ComfyRegistry Data: 75/118
FETCH ComfyRegistry Data: 80/118
FETCH ComfyRegistry Data: 85/118
loaded partially; 11996.47 MB usable, 11948.46 MB loaded, 1830.81 MB offloaded, 48.01 MB buffer reserved, lowvram patches: 0
0%| | 0/8 [00:02<?, ?it/s]
!!! Exception during processing !!! module 'torch' has no attribute 'float4_e2m1fn_x2'
Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 518, 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 "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 329, 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 "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy_api\internal\__init__.py", line 149, in wrapped_func
return method(locked_class, **inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy_api\latest\_io.py", line 1570, in EXECUTE_NORMALIZED
to_return = cls.execute(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy_extras\nodes_custom_sampler.py", line 950, 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 "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 1050, in sample
output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 994, in outer_sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed, latent_shapes=latent_shapes)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 980, in inner_sample
samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-TiledDiffusion\utils.py", line 34, in KSAMPLER_sample
return orig_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 752, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable/ComfyUI\comfy\k_diffusion\sampling.py", line 202, in sample_euler
denoised = model(x, sigma_hat * s_in, **extra_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 401, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 953, in __call__
return self.outer_predict_noise(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 960, in outer_predict_noise
).execute(x, timestep, model_options, seed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 963, 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 "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 381, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 206, in calc_cond_batch
return _calc_cond_batch_outer(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 214, in _calc_cond_batch_outer
return executor.execute(model, conds, x_in, timestep, model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\samplers.py", line 326, in _calc_cond_batch
output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_base.py", line 163, in apply_model
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\model_base.py", line 205, in _apply_model
model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\av_model.py", line 828, in forward
return super().forward(
^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\model.py", line 745, in forward
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\patcher_extension.py", line 112, in execute
return self.original(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\model.py", line 792, in _forward
x = self._process_transformer_blocks(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\av_model.py", line 745, in _process_transformer_blocks
vx, ax = block(
^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\av_model.py", line 186, in forward
vx += self.attn1(norm_vx, pe=v_pe, transformer_options=transformer_options) * vgate_msa
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\model.py", line 367, in forward
q = self.to_q(x)
^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 676, in forward
output = self._forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 645, in _forward
return torch.nn.functional.linear(input, weight, bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfy_kitchen\tensor\base.py", line 346, in __torch_dispatch__
return op_handlers[parent_cls](qt, args, kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfy_kitchen\tensor\nvfp4.py", line 246, in _handle_nvfp4_linear
result = ck.scaled_mm_nvfp4(
^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfy_kitchen\__init__.py", line 160, in scaled_mm_nvfp4
return torch.ops.comfy_kitchen.scaled_mm_nvfp4(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\_ops.py", line 1158, in __call__
return self._op(*args, **(kwargs or {}))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\_library\custom_ops.py", line 335, in backend_impl
result = self._backend_fns[device_type](*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\_compile.py", line 51, in inner
return disable_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\_dynamo\eval_frame.py", line 838, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\_library\custom_ops.py", line 367, in wrapped_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfy_kitchen\backends\eager\quantization.py", line 379, in _op_scaled_mm_nvfp4
return impl(**kwargs)
^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfy_kitchen\backends\eager\quantization.py", line 178, in scaled_mm_nvfp4
a.view(torch.float4_e2m1fn_x2),
^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\__init__.py", line 2688, in __getattr__
raise AttributeError(f"module '{__name__}' has no attribute '{name}'")
AttributeError: module 'torch' has no attribute 'float4_e2m1fn_x2'Other
No response