Using AMD 7800xt gpu I keep getting issues,

[jan1jan1]

Expected Behavior

command used python main.py --directml --use-quad-cross-attention --lowvram --auto-launch

cant seem to generate image with amd card

Actual Behavior

trying to generate image

Steps to Reproduce

241028_MICKMUMPITZ_CHARACTER_SHEET_2_v01_FLUX_SMPL_FAST.json

Debug Logs

# ComfyUI Error Report
## Error Details
- **Node ID:** 628
- **Node Type:** ApplyPulidFlux
- **Exception Type:** RuntimeError
- **Exception Message:** tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "C:\\__w\\1\\s\\pytorch-directml-plugin\\torch_directml\\csrc\\dml\\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs
## Stack Trace

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 327, in execute
    output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 202, in get_output_data
    return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 174, in _map_node_over_list
    process_inputs(input_dict, i)

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 163, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll\pulidflux.py", line 340, in apply_pulid_flux
    cond.append(pulid_flux.model.get_embeds(id_cond, id_vit_hidden))
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll\pulidflux.py", line 86, in get_embeds
    return self.pulid_encoder(face_embed, clip_embeds)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\anaconda3\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\anaconda3\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll\encoders_flux.py", line 202, in forward
    latents = torch.cat((latents, x), dim=1)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^


## System Information
- **ComfyUI Version:** 0.3.12
- **Arguments:** main.py --directml --use-quad-cross-attention --lowvram --auto-launch
- **OS:** nt
- **Python Version:** 3.12.7 | packaged by Anaconda, Inc. | (main, Oct  4 2024, 13:17:27) [MSC v.1929 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.4.1+cpu
## Devices

- **Name:** privateuseone
  - **Type:** privateuseone
  - **VRAM Total:** 1073741824
  - **VRAM Free:** 1073741824
  - **Torch VRAM Total:** 1073741824
  - **Torch VRAM Free:** 1073741824

## Logs

2025-02-03T11:48:14.697059 - [START] Security scan2025-02-03T11:48:14.697059 - 
2025-02-03T11:48:17.557967 - [DONE] Security scan2025-02-03T11:48:17.557967 - 
2025-02-03T11:48:17.716543 - ## ComfyUI-Manager: installing dependencies done.2025-02-03T11:48:17.716543 - 
2025-02-03T11:48:17.716543 - ** ComfyUI startup time:2025-02-03T11:48:17.717540 -  2025-02-03T11:48:17.717540 - 2025-02-03 11:48:17.7162025-02-03T11:48:17.717540 - 
2025-02-03T11:48:17.717540 - ** Platform:2025-02-03T11:48:17.717540 -  2025-02-03T11:48:17.717540 - Windows2025-02-03T11:48:17.717540 - 
2025-02-03T11:48:17.717540 - ** Python version:2025-02-03T11:48:17.717540 -  2025-02-03T11:48:17.717540 - 3.12.7 | packaged by Anaconda, Inc. | (main, Oct  4 2024, 13:17:27) [MSC v.1929 64 bit (AMD64)]2025-02-03T11:48:17.718537 - 
2025-02-03T11:48:17.718537 - ** Python executable:2025-02-03T11:48:17.718537 -  2025-02-03T11:48:17.718537 - C:\Users\janca\anaconda3\python.exe2025-02-03T11:48:17.718537 - 
2025-02-03T11:48:17.719535 - ** ComfyUI Path:2025-02-03T11:48:17.719535 -  2025-02-03T11:48:17.719535 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI2025-02-03T11:48:17.719535 - 
2025-02-03T11:48:17.719535 - ** ComfyUI Base Folder Path:2025-02-03T11:48:17.719535 -  2025-02-03T11:48:17.719535 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI2025-02-03T11:48:17.719535 - 
2025-02-03T11:48:17.719535 - ** User directory:2025-02-03T11:48:17.719535 -  2025-02-03T11:48:17.720532 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\user2025-02-03T11:48:17.720532 - 
2025-02-03T11:48:17.720532 - ** ComfyUI-Manager config path:2025-02-03T11:48:17.720532 -  2025-02-03T11:48:17.720532 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\user\default\ComfyUI-Manager\config.ini2025-02-03T11:48:17.720532 - 
2025-02-03T11:48:17.720532 - ** Log path:2025-02-03T11:48:17.720532 -  2025-02-03T11:48:17.720532 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\user\comfyui.log2025-02-03T11:48:17.720532 - 
2025-02-03T11:48:21.033361 - 
Prestartup times for custom nodes:
2025-02-03T11:48:21.033361 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\rgthree-comfy
2025-02-03T11:48:21.034358 -    6.6 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-manager
2025-02-03T11:48:21.034358 - 
2025-02-03T11:48:23.334492 - Checkpoint files will always be loaded safely.
2025-02-03T11:48:23.404380 - Using directml with device: 
2025-02-03T11:48:23.405377 - Total VRAM 1024 MB, total RAM 16253 MB
2025-02-03T11:48:23.406375 - pytorch version: 2.4.1+cpu
2025-02-03T11:48:23.407373 - Set vram state to: LOW_VRAM
2025-02-03T11:48:23.407373 - Device: privateuseone
2025-02-03T11:48:24.815533 - Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention
2025-02-03T11:48:28.449451 - ComfyUI version: 0.3.12
2025-02-03T11:48:28.473386 - [Prompt Server] web root: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\web
2025-02-03T11:48:29.950373 - ### Loading: ComfyUI-Impact-Pack (V8.8.1)2025-02-03T11:48:29.950373 - 
2025-02-03T11:48:30.068061 - C:\Users\janca\anaconda3\Lib\site-packages\paramiko\pkey.py:82: CryptographyDeprecationWarning: TripleDES has been moved to cryptography.hazmat.decrepit.ciphers.algorithms.TripleDES and will be removed from this module in 48.0.0.
  "cipher": algorithms.TripleDES,
2025-02-03T11:48:30.111496 - C:\Users\janca\anaconda3\Lib\site-packages\paramiko\transport.py:219: CryptographyDeprecationWarning: Blowfish has been moved to cryptography.hazmat.decrepit.ciphers.algorithms.Blowfish and will be removed from this module in 45.0.0.
  "class": algorithms.Blowfish,
2025-02-03T11:48:30.112493 - C:\Users\janca\anaconda3\Lib\site-packages\paramiko\transport.py:243: CryptographyDeprecationWarning: TripleDES has been moved to cryptography.hazmat.decrepit.ciphers.algorithms.TripleDES and will be removed from this module in 48.0.0.
  "class": algorithms.TripleDES,
2025-02-03T11:48:30.188672 - [Impact Pack] Wildcards loading done.2025-02-03T11:48:30.188672 - 
2025-02-03T11:48:30.195719 - ### Loading: ComfyUI-Impact-Subpack (V1.2.9)
2025-02-03T11:48:30.200586 - [Impact Subpack] ultralytics_bbox: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\ultralytics\bbox
2025-02-03T11:48:30.200586 - [Impact Subpack] ultralytics_segm: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\ultralytics\segm
2025-02-03T11:48:30.205574 - Using directml with device: 
2025-02-03T11:48:30.206571 - Total VRAM 1024 MB, total RAM 16253 MB
2025-02-03T11:48:30.207568 - pytorch version: 2.4.1+cpu
2025-02-03T11:48:30.207568 - Set vram state to: LOW_VRAM
2025-02-03T11:48:30.208566 - Device: privateuseone
2025-02-03T11:48:30.247447 - ### Loading: ComfyUI-Manager (V3.15)
2025-02-03T11:48:30.433525 - ### ComfyUI Version: v0.3.12-28-g13fd4d6e | Released on '2025-01-28'
2025-02-03T11:48:30.926718 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
2025-02-03T11:48:30.973594 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
2025-02-03T11:48:31.219737 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
2025-02-03T11:48:31.322464 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
2025-02-03T11:48:31.407237 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
2025-02-03T11:48:31.912282 - C:\Users\janca\anaconda3\Lib\site-packages\albumentations\__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.2 (you have 1.4.15). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
  check_for_updates()
2025-02-03T11:48:32.627532 - C:\Users\janca\anaconda3\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)
2025-02-03T11:48:32.632519 - Please 'pip install xformers'2025-02-03T11:48:32.632519 - 
2025-02-03T11:48:32.635511 - Nvidia APEX normalization not installed, using PyTorch LayerNorm2025-02-03T11:48:32.635511 - 
2025-02-03T11:48:32.793289 - �[36;20m[comfyui_controlnet_aux] | INFO -> Using ckpts path: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts�[0m
2025-02-03T11:48:32.794286 - �[36;20m[comfyui_controlnet_aux] | INFO -> Using symlinks: False�[0m
2025-02-03T11:48:32.794286 - �[36;20m[comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']�[0m
2025-02-03T11:48:32.822664 - DWPose: Onnxruntime with acceleration providers detected2025-02-03T11:48:32.822664 - 
2025-02-03T11:48:32.913545 - Please 'pip install xformers'2025-02-03T11:48:32.913545 - 
2025-02-03T11:48:32.917534 - Nvidia APEX normalization not installed, using PyTorch LayerNorm2025-02-03T11:48:32.918531 - 
2025-02-03T11:48:34.962023 - �[34mWAS Node Suite: �[0mOpenCV Python FFMPEG support is enabled�[0m2025-02-03T11:48:34.962023 - 
2025-02-03T11:48:34.962023 - �[34mWAS Node Suite �[93mWarning: �[0m`ffmpeg_bin_path` is not set in `C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\pr-was-node-suite-comfyui-47064894\was_suite_config.json` config file. Will attempt to use system ffmpeg binaries if available.�[0m2025-02-03T11:48:34.962023 - 
2025-02-03T11:48:36.403489 - �[34mWAS Node Suite: �[0mFinished.�[0m �[32mLoaded�[0m �[0m218�[0m �[32mnodes successfully.�[0m2025-02-03T11:48:36.404486 - 
2025-02-03T11:48:36.404486 - 
	�[3m�[93m"The future belongs to those who believe in the beauty of their dreams."�[0m�[3m - Eleanor Roosevelt�[0m
2025-02-03T11:48:36.404486 - 
2025-02-03T11:48:36.765470 - 
2025-02-03T11:48:36.765470 - �[92m[rgthree-comfy] Loaded 42 fantastic nodes. 🎉�[00m2025-02-03T11:48:36.766439 - 
2025-02-03T11:48:36.766439 - 
2025-02-03T11:48:36.769431 - 
Import times for custom nodes:
2025-02-03T11:48:36.770428 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\cg-use-everywhere
2025-02-03T11:48:36.770428 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\websocket_image_save.py
2025-02-03T11:48:36.770428 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_faceanalysis
2025-02-03T11:48:36.770428 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-impact-subpack
2025-02-03T11:48:36.770428 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfy-image-saver
2025-02-03T11:48:36.771426 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_ultimatesdupscale
2025-02-03T11:48:36.771426 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\ComfyUI-GGUF
2025-02-03T11:48:36.771426 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-kjnodes
2025-02-03T11:48:36.771426 -    0.0 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_essentials
2025-02-03T11:48:36.771426 -    0.1 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_controlnet_aux
2025-02-03T11:48:36.771426 -    0.1 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll
2025-02-03T11:48:36.772453 -    0.2 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-impact-pack
2025-02-03T11:48:36.772453 -    0.4 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\rgthree-comfy
2025-02-03T11:48:36.772453 -    0.4 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-manager
2025-02-03T11:48:36.772453 -    0.8 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-advancedliveportrait
2025-02-03T11:48:36.772453 -    2.1 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\ComfyUI-PuLID-Flux-Enhanced
2025-02-03T11:48:36.773420 -    3.4 seconds: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\pr-was-node-suite-comfyui-47064894
2025-02-03T11:48:36.773420 - 
2025-02-03T11:48:36.787384 - Starting server

2025-02-03T11:48:36.787384 - To see the GUI go to: http://127.0.0.1:8188
2025-02-03T11:48:37.569263 - FETCH ComfyRegistry Data: 5/322025-02-03T11:48:37.569263 - 
2025-02-03T11:48:38.044989 - FETCH DATA from: C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui-manager\extension-node-map.json2025-02-03T11:48:38.045988 - 2025-02-03T11:48:38.055962 -  [DONE]2025-02-03T11:48:38.055962 - 
2025-02-03T11:48:44.186423 - FETCH ComfyRegistry Data: 10/322025-02-03T11:48:44.186423 - 
2025-02-03T11:48:51.203577 - FETCH ComfyRegistry Data: 15/322025-02-03T11:48:51.203577 - 
2025-02-03T11:48:57.182588 - FETCH ComfyRegistry Data: 20/322025-02-03T11:48:57.182588 - 
2025-02-03T11:48:59.484048 - got prompt
2025-02-03T11:49:00.052009 - Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}2025-02-03T11:49:00.052009 - 
2025-02-03T11:49:00.139170 - find model:2025-02-03T11:49:00.139170 -  2025-02-03T11:49:00.139170 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\insightface\models\antelopev2\1k3d68.onnx2025-02-03T11:49:00.139170 -  2025-02-03T11:49:00.140168 - landmark_3d_682025-02-03T11:49:00.140168 -  2025-02-03T11:49:00.140168 - ['None', 3, 192, 192]2025-02-03T11:49:00.140168 -  2025-02-03T11:49:00.140168 - 0.02025-02-03T11:49:00.140168 -  2025-02-03T11:49:00.140168 - 1.02025-02-03T11:49:00.140168 - 
2025-02-03T11:49:00.185125 - Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}2025-02-03T11:49:00.185125 - 
2025-02-03T11:49:00.190112 - find model:2025-02-03T11:49:00.190112 -  2025-02-03T11:49:00.191110 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\insightface\models\antelopev2\2d106det.onnx2025-02-03T11:49:00.191110 -  2025-02-03T11:49:00.191110 - landmark_2d_1062025-02-03T11:49:00.191110 -  2025-02-03T11:49:00.191110 - ['None', 3, 192, 192]2025-02-03T11:49:00.191110 -  2025-02-03T11:49:00.192107 - 0.02025-02-03T11:49:00.192107 -  2025-02-03T11:49:00.192107 - 1.02025-02-03T11:49:00.192107 - 
2025-02-03T11:49:00.219878 - Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}2025-02-03T11:49:00.219878 - 
2025-02-03T11:49:00.222871 - find model:2025-02-03T11:49:00.222871 -  2025-02-03T11:49:00.222871 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\insightface\models\antelopev2\genderage.onnx2025-02-03T11:49:00.222871 -  2025-02-03T11:49:00.222871 - genderage2025-02-03T11:49:00.222871 -  2025-02-03T11:49:00.222871 - ['None', 3, 96, 96]2025-02-03T11:49:00.222871 -  2025-02-03T11:49:00.223867 - 0.02025-02-03T11:49:00.223867 -  2025-02-03T11:49:00.223867 - 1.02025-02-03T11:49:00.223867 - 
2025-02-03T11:49:00.828625 - Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}2025-02-03T11:49:00.829598 - 
2025-02-03T11:49:01.044025 - find model:2025-02-03T11:49:01.044025 -  2025-02-03T11:49:01.044025 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\insightface\models\antelopev2\glintr100.onnx2025-02-03T11:49:01.044025 -  2025-02-03T11:49:01.045022 - recognition2025-02-03T11:49:01.045022 -  2025-02-03T11:49:01.045022 - ['None', 3, 112, 112]2025-02-03T11:49:01.045022 -  2025-02-03T11:49:01.045022 - 127.52025-02-03T11:49:01.045022 -  2025-02-03T11:49:01.045022 - 127.52025-02-03T11:49:01.045022 - 
2025-02-03T11:49:01.126803 - Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}2025-02-03T11:49:01.126803 - 
2025-02-03T11:49:01.126803 - find model:2025-02-03T11:49:01.127800 -  2025-02-03T11:49:01.127800 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\models\insightface\models\antelopev2\scrfd_10g_bnkps.onnx2025-02-03T11:49:01.127800 -  2025-02-03T11:49:01.127800 - detection2025-02-03T11:49:01.127800 -  2025-02-03T11:49:01.127800 - [1, 3, '?', '?']2025-02-03T11:49:01.127800 -  2025-02-03T11:49:01.127800 - 127.52025-02-03T11:49:01.127800 -  2025-02-03T11:49:01.127800 - 128.02025-02-03T11:49:01.127800 - 
2025-02-03T11:49:01.127800 - set det-size:2025-02-03T11:49:01.128797 -  2025-02-03T11:49:01.128797 - (640, 640)2025-02-03T11:49:01.128797 - 
2025-02-03T11:49:01.128797 - Loaded EVA02-CLIP-L-14-336 model config.
2025-02-03T11:49:01.162706 - Shape of rope freq: torch.Size([576, 64])
2025-02-03T11:49:04.178423 - FETCH ComfyRegistry Data: 25/322025-02-03T11:49:04.178423 - 
2025-02-03T11:49:06.725315 - Loading pretrained EVA02-CLIP-L-14-336 weights (eva_clip).
2025-02-03T11:49:06.725315 - [Impact Subpack] Your torch version is outdated, and security features cannot be applied properly.
2025-02-03T11:49:07.758283 - incompatible_keys.missing_keys: ['visual.rope.freqs_cos', 'visual.rope.freqs_sin', 'visual.blocks.0.attn.rope.freqs_cos', 'visual.blocks.0.attn.rope.freqs_sin', 'visual.blocks.1.attn.rope.freqs_cos', 'visual.blocks.1.attn.rope.freqs_sin', 'visual.blocks.2.attn.rope.freqs_cos', 'visual.blocks.2.attn.rope.freqs_sin', 'visual.blocks.3.attn.rope.freqs_cos', 'visual.blocks.3.attn.rope.freqs_sin', 'visual.blocks.4.attn.rope.freqs_cos', 'visual.blocks.4.attn.rope.freqs_sin', 'visual.blocks.5.attn.rope.freqs_cos', 'visual.blocks.5.attn.rope.freqs_sin', 'visual.blocks.6.attn.rope.freqs_cos', 'visual.blocks.6.attn.rope.freqs_sin', 'visual.blocks.7.attn.rope.freqs_cos', 'visual.blocks.7.attn.rope.freqs_sin', 'visual.blocks.8.attn.rope.freqs_cos', 'visual.blocks.8.attn.rope.freqs_sin', 'visual.blocks.9.attn.rope.freqs_cos', 'visual.blocks.9.attn.rope.freqs_sin', 'visual.blocks.10.attn.rope.freqs_cos', 'visual.blocks.10.attn.rope.freqs_sin', 'visual.blocks.11.attn.rope.freqs_cos', 'visual.blocks.11.attn.rope.freqs_sin', 'visual.blocks.12.attn.rope.freqs_cos', 'visual.blocks.12.attn.rope.freqs_sin', 'visual.blocks.13.attn.rope.freqs_cos', 'visual.blocks.13.attn.rope.freqs_sin', 'visual.blocks.14.attn.rope.freqs_cos', 'visual.blocks.14.attn.rope.freqs_sin', 'visual.blocks.15.attn.rope.freqs_cos', 'visual.blocks.15.attn.rope.freqs_sin', 'visual.blocks.16.attn.rope.freqs_cos', 'visual.blocks.16.attn.rope.freqs_sin', 'visual.blocks.17.attn.rope.freqs_cos', 'visual.blocks.17.attn.rope.freqs_sin', 'visual.blocks.18.attn.rope.freqs_cos', 'visual.blocks.18.attn.rope.freqs_sin', 'visual.blocks.19.attn.rope.freqs_cos', 'visual.blocks.19.attn.rope.freqs_sin', 'visual.blocks.20.attn.rope.freqs_cos', 'visual.blocks.20.attn.rope.freqs_sin', 'visual.blocks.21.attn.rope.freqs_cos', 'visual.blocks.21.attn.rope.freqs_sin', 'visual.blocks.22.attn.rope.freqs_cos', 'visual.blocks.22.attn.rope.freqs_sin', 'visual.blocks.23.attn.rope.freqs_cos', 'visual.blocks.23.attn.rope.freqs_sin']
2025-02-03T11:49:10.347434 - FETCH ComfyRegistry Data: 30/322025-02-03T11:49:10.347434 - 
2025-02-03T11:49:10.798613 - Loading PuLID-Flux model.
2025-02-03T11:49:13.527389 - Using split attention in VAE
2025-02-03T11:49:13.530383 - Using split attention in VAE
2025-02-03T11:49:13.729083 - FETCH ComfyRegistry Data [DONE]2025-02-03T11:49:13.729083 - 
2025-02-03T11:49:13.792911 - [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
2025-02-03T11:49:13.808869 - nightly_channel: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/remote
2025-02-03T11:49:13.808869 - FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json2025-02-03T11:49:13.808869 - 2025-02-03T11:49:13.856741 -  [DONE]2025-02-03T11:49:13.856741 - 
2025-02-03T11:49:13.906609 - [ComfyUI-Manager] All startup tasks have been completed.
2025-02-03T11:49:14.289063 - VAE load device: privateuseone:0, offload device: cpu, dtype: torch.float32
2025-02-03T11:49:19.712701 - C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\ComfyUI-GGUF\loader.py:65: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\utils\tensor_numpy.cpp:212.)
  torch_tensor = torch.from_numpy(tensor.data) # mmap
2025-02-03T11:49:19.715695 - 
ggml_sd_loader:2025-02-03T11:49:19.715695 - 
2025-02-03T11:49:19.716692 -  12                            1442025-02-03T11:49:19.716692 - 
2025-02-03T11:49:19.716692 -  0                              502025-02-03T11:49:19.716692 - 
2025-02-03T11:49:19.717690 -  14                             252025-02-03T11:49:19.717690 - 
2025-02-03T11:49:19.942754 - Requested to load FluxClipModel_
2025-02-03T11:49:19.954723 - loaded completely 9.5367431640625e+25 323.94775390625 True
2025-02-03T11:49:19.956717 - CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16
2025-02-03T11:49:20.171904 - clip missing: ['text_projection.weight']
2025-02-03T11:49:20.273632 - 
ggml_sd_loader:2025-02-03T11:49:20.273632 - 
2025-02-03T11:49:20.273632 -  1                             4762025-02-03T11:49:20.273632 - 
2025-02-03T11:49:20.274629 -  3                             3042025-02-03T11:49:20.274629 - 
2025-02-03T11:49:20.356413 - model weight dtype torch.float32, manual cast: None
2025-02-03T11:49:20.357409 - model_type FLUX
2025-02-03T11:49:21.126587 - Requested to load PulidFluxModel
2025-02-03T11:49:21.126587 - 0 models unloaded.
2025-02-03T11:49:21.157505 - loaded completely 64.0 62.11328125 False
2025-02-03T11:49:21.722996 - [Impact Subpack] Your torch version is outdated, and security features cannot be applied properly.
2025-02-03T11:49:22.032169 - [Impact Subpack] Your torch version is outdated, and security features cannot be applied properly.
2025-02-03T11:49:22.216197 - [Impact Subpack] Your torch version is outdated, and security features cannot be applied properly.
2025-02-03T11:49:22.411675 - C:\Users\janca\anaconda3\Lib\site-packages\insightface\utils\transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
  P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
2025-02-03T11:49:23.514188 - !!! Exception during processing !!! tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "C:\\__w\\1\\s\\pytorch-directml-plugin\\torch_directml\\csrc\\dml\\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs
2025-02-03T11:49:23.518151 - Traceback (most recent call last):
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 327, in execute
    output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 202, in get_output_data
    return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 174, in _map_node_over_list
    process_inputs(input_dict, i)
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\execution.py", line 163, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll\pulidflux.py", line 340, in apply_pulid_flux
    cond.append(pulid_flux.model.get_embeds(id_cond, id_vit_hidden))
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll\pulidflux.py", line 86, in get_embeds
    return self.pulid_encoder(face_embed, clip_embeds)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\anaconda3\Lib\site-packages\torch\nn\modules\module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\anaconda3\Lib\site-packages\torch\nn\modules\module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\janca\Downloads\AMDCOMFY\ComfyUI\custom_nodes\comfyui_pulid_flux_ll\encoders_flux.py", line 202, in forward
    latents = torch.cat((latents, x), dim=1)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "C:\\__w\\1\\s\\pytorch-directml-plugin\\torch_directml\\csrc\\dml\\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs

2025-02-03T11:49:23.520144 - Prompt executed in 24.02 seconds


## Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.

Workflow too large. Please manually upload the workflow from local file system.


## Additional Context
(Please add any additional context or steps to reproduce the error here)

Other

No response