Flux.2 Klein(4B) not working

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

i tried to create an image using the latest flux.2 klein 4b distilled model for my 6GB VRam laptop. by watching the tutorial from "Ai search" https://www.youtube.com/watch?v=2OrOufa3eoc
im getting an error saying "UnetLoaderGGUF
Got [32, 32, 32, 32] but expected positional dim 64"
help me solve this.

### Actual Behavior

### Steps to Reproduce

### Debug Logs

```powershell
# ComfyUI Error Report
## Error Details
- **Node ID:** 92:83
- **Node Type:** UnetLoaderGGUF
- **Exception Type:** ValueError
- **Exception Message:** Got [32, 32, 32, 32] but expected positional dim 64

## Stack Trace

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^

File "C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 176, in load_unet
model = comfy.sd.load_diffusion_model_state_dict(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\sd.py", line 1540, in load_diffusion_model_state_dict
model = model_config.get_model(new_sd, "")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\supported_models.py", line 769, in get_model
out = model_base.Flux2(self, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 839, in __init__
super().__init__(model_config, model_type, device=device, unet_model=unet_model)

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 142, in __init__
self.diffusion_model = unet_model(**unet_config, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\ldm\flux\model.py", line 67, in __init__
raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")

## System Information
- **ComfyUI Version:** 0.8.2
- **Arguments:** C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\main.py --user-directory C:\Users\Abhishek\Documents\ComfyUI\user --input-directory C:\Users\Abhishek\Documents\ComfyUI\input --output-directory C:\Users\Abhishek\Documents\ComfyUI\output --front-end-root C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\web_custom_versions\desktop_app --base-directory C:\Users\Abhishek\Documents\ComfyUI --extra-model-paths-config C:\Users\Abhishek\AppData\Roaming\ComfyUI\extra_models_config.yaml --log-stdout --listen 127.0.0.1 --port 8001 --enable-manager
- **OS:** win32
- **Python Version:** 3.12.11 (main, Aug 18 2025, 19:17:54) [MSC v.1944 64 bit (AMD64)]
- **Embedded Python:** false
- **PyTorch Version:** 2.9.1+cu130
## Devices

- **Name:** cuda:0 NVIDIA GeForce RTX 3060 Laptop GPU : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 6441926656
- **VRAM Free:** 5366611968
- **Torch VRAM Total:** 0
- **Torch VRAM Free:** 0

## Logs

2026-01-21T23:02:40.998641 - Adding extra search path custom_nodes C:\Users\Abhishek\Documents\ComfyUI\custom_nodes
2026-01-21T23:02:40.998641 - Adding extra search path download_model_base C:\Users\Abhishek\Documents\ComfyUI\models
2026-01-21T23:02:40.998641 - Adding extra search path custom_nodes C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\custom_nodes
2026-01-21T23:02:40.998641 - Setting output directory to: C:\Users\Abhishek\Documents\ComfyUI\output
2026-01-21T23:02:40.998641 - Setting input directory to: C:\Users\Abhishek\Documents\ComfyUI\input
2026-01-21T23:02:40.998641 - Setting user directory to: C:\Users\Abhishek\Documents\ComfyUI\user
2026-01-21T23:02:41.813617 - [START] Security scan2026-01-21T23:02:41.813617 -
2026-01-21T23:02:51.849094 - [DONE] Security scan2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** ComfyUI startup time:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - 2026-01-21 23:02:51.8492026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** Platform:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - Windows2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** Python version:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - 3.12.11 (main, Aug 18 2025, 19:17:54) [MSC v.1944 64 bit (AMD64)]2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** Python executable:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - C:\Users\Abhishek\Documents\ComfyUI\.venv\Scripts\python.exe2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** ComfyUI Path:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** ComfyUI Base Folder Path:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** User directory:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - C:\Users\Abhishek\Documents\ComfyUI\user2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** ComfyUI-Manager config path:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - C:\Users\Abhishek\Documents\ComfyUI\user\__manager\config.ini2026-01-21T23:02:51.849094 -
2026-01-21T23:02:51.849094 - ** Log path:2026-01-21T23:02:51.849094 - 2026-01-21T23:02:51.849094 - C:\Users\Abhishek\Documents\ComfyUI\user\comfyui.log2026-01-21T23:02:51.849094 -
2026-01-21T23:02:53.002660 - [ComfyUI-Manager] Skipped fixing the 'comfyui-frontend-package' dependency because the ComfyUI is outdated.
2026-01-21T23:02:53.002660 - [PRE] ComfyUI-Manager
2026-01-21T23:03:00.838525 - Checkpoint files will always be loaded safely.
2026-01-21T23:03:01.037513 - Total VRAM 6144 MB, total RAM 40645 MB
2026-01-21T23:03:01.037513 - pytorch version: 2.9.1+cu130
2026-01-21T23:03:01.037513 - Set vram state to: NORMAL_VRAM
2026-01-21T23:03:01.037513 - Device: cuda:0 NVIDIA GeForce RTX 3060 Laptop GPU : cudaMallocAsync
2026-01-21T23:03:01.055769 - Using async weight offloading with 2 streams
2026-01-21T23:03:01.055769 - Enabled pinned memory 18290.0
2026-01-21T23:03:01.062133 - working around nvidia conv3d memory bug.
2026-01-21T23:03:03.273105 - 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']}
2026-01-21T23:03:03.273105 - Found comfy_kitchen backend cuda: {'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']}
2026-01-21T23:03:03.273105 - Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': "ImportError: No module named 'triton'", 'capabilities': []}
2026-01-21T23:03:06.716442 - Using pytorch attention
2026-01-21T23:04:15.598327 - Python version: 3.12.11 (main, Aug 18 2025, 19:17:54) [MSC v.1944 64 bit (AMD64)]
2026-01-21T23:04:15.598327 - ComfyUI version: 0.8.2
2026-01-21T23:04:15.630939 - [Prompt Server] web root: C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\web_custom_versions\desktop_app
2026-01-21T23:04:15.630939 - [START] ComfyUI-Manager
2026-01-21T23:04:16.177459 - [ComfyUI-Manager] network_mode: public
2026-01-21T23:04:16.558909 - [ComfyUI-Manager] The matrix sharing feature has been disabled because the `matrix-nio` dependency is not installed.
To use this feature, please run the following command:
C:\Users\Abhishek\Documents\ComfyUI\.venv\Scripts\python.exe -m pip install matrix-nio

2026-01-21T23:04:17.949215 - Total VRAM 6144 MB, total RAM 40645 MB
2026-01-21T23:04:17.949215 - pytorch version: 2.9.1+cu130
2026-01-21T23:04:17.951221 - Set vram state to: NORMAL_VRAM
2026-01-21T23:04:17.951221 - Device: cuda:0 NVIDIA GeForce RTX 3060 Laptop GPU : cudaMallocAsync
2026-01-21T23:04:17.983390 - Using async weight offloading with 2 streams
2026-01-21T23:04:17.983390 - Enabled pinned memory 18290.0
2026-01-21T23:04:18.576334 - 'resemble-perth' not found. Watermarking will be unavailable.
2026-01-21T23:04:34.283594 - ComfyUI-GGUF: Allowing full torch compile
2026-01-21T23:04:36.737218 - Warning: Could not load sageattention: No module named 'sageattention'
2026-01-21T23:04:36.738232 - sageattention package is not installed, sageattention will not be available
2026-01-21T23:04:37.141451 - WanVideoWrapper WARNING: FantasyPortrait nodes not available: No module named 'onnxruntime'
2026-01-21T23:04:39.600221 - C:\Users\Abhishek\Documents\ComfyUI\.venv\Lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work
warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)
2026-01-21T23:04:39.838675 - [C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ckpts path: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui_controlnet_aux\ckpts
2026-01-21T23:04:39.839600 - [C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using symlinks: False
2026-01-21T23:04:39.841641 - [C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui_controlnet_aux] | INFO -> Using ort providers: ['CUDAExecutionProvider', 'DirectMLExecutionProvider', 'OpenVINOExecutionProvider', 'ROCMExecutionProvider', 'CPUExecutionProvider', 'CoreMLExecutionProvider']
2026-01-21T23:04:40.123865 - C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py:26: UserWarning: DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly
warnings.warn("DWPose: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device. DWPose might run very slowly")
2026-01-21T23:04:40.307820 -
2026-01-21T23:04:40.307820 - [rgthree-comfy] Loaded 48 epic nodes. 🎉2026-01-21T23:04:40.307820 -
2026-01-21T23:04:40.308819 -
2026-01-21T23:04:40.308819 - [rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.
2026-01-21T23:04:40.308819 -
2026-01-21T23:04:40.313824 - Blocked by policy: C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\custom_nodes\ComfyUI-Manager
2026-01-21T23:04:40.317254 -
Import times for custom nodes:
2026-01-21T23:04:40.317254 - 0.0 seconds: C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\custom_nodes\websocket_image_save.py
2026-01-21T23:04:40.318361 - 0.0 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui-segment-anything-2
2026-01-21T23:04:40.318361 - 0.1 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-GGUF
2026-01-21T23:04:40.318361 - 0.1 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\rgthree-comfy
2026-01-21T23:04:40.319358 - 0.4 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui-tensorops
2026-01-21T23:04:40.319358 - 0.4 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui-kjnodes
2026-01-21T23:04:40.319358 - 0.5 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper
2026-01-21T23:04:40.319358 - 0.5 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui_controlnet_aux
2026-01-21T23:04:40.320258 - 1.6 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui-videohelpersuite
2026-01-21T23:04:40.320258 - 2.6 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\comfyui-web-viewer
2026-01-21T23:04:40.320258 - 15.7 seconds: C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-Chatterbox
2026-01-21T23:04:40.320258 -
2026-01-21T23:04:41.096131 - Failed to initialize database. Please ensure you have installed the latest requirements. If the error persists, please report this as in future the database will be required: (sqlite3.OperationalError) unable to open database file
(Background on this error at: https://sqlalche.me/e/20/e3q8)
2026-01-21T23:04:41.189719 - Starting server

2026-01-21T23:04:41.190704 - To see the GUI go to: http://127.0.0.1:8001
2026-01-21T23:04:43.492642 - comfyui-frontend-package not found in requirements.txt
2026-01-21T23:04:44.226680 - [DEPRECATION WARNING] Detected import of deprecated legacy API: /extensions/core/widgetInputs.js. This is likely caused by a custom node extension using outdated APIs. Please update your extensions or contact the extension author for an updated version.
2026-01-21T23:06:42.305884 - FETCH ComfyRegistry Data [DONE]
2026-01-21T23:06:42.602375 - [ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
2026-01-21T23:06:42.638702 - FETCH DATA from: C:\Users\Abhishek\Documents\ComfyUI\user\__manager\cache\1514988643_custom-node-list.json2026-01-21T23:06:42.638702 - 2026-01-21T23:06:42.698975 - [DONE]2026-01-21T23:06:42.698975 -
2026-01-21T23:06:42.743033 - [ComfyUI-Manager] All startup tasks have been completed.
2026-01-21T23:08:25.280230 - got prompt
2026-01-21T23:08:25.354866 - Using pytorch attention in VAE
2026-01-21T23:08:25.356865 - Using pytorch attention in VAE
2026-01-21T23:08:25.518031 - VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
2026-01-21T23:08:25.606846 - Requested to load AutoencoderKL
2026-01-21T23:08:25.755445 - loaded completely; 792.43 MB usable, 160.31 MB loaded, full load: True
2026-01-21T23:08:26.753350 - Found quantization metadata version 1
2026-01-21T23:08:26.754353 - Using MixedPrecisionOps for text encoder
2026-01-21T23:08:27.096718 - CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
2026-01-21T23:08:27.100720 - Requested to load ZImageTEModel_
2026-01-21T23:08:29.186485 - loaded partially; 3662.80 MB usable, 3648.58 MB loaded, 21.09 MB offloaded, 14.22 MB buffer reserved, lowvram patches: 0
2026-01-21T23:08:29.735662 - gguf qtypes: F32 (60), Q8_0 (80), BF16 (9)
2026-01-21T23:08:29.737662 - !!! Exception during processing !!! Got [32, 32, 32, 32] but expected positional dim 64
2026-01-21T23:08:29.820804 - Traceback (most recent call last):
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 176, in load_unet
model = comfy.sd.load_diffusion_model_state_dict(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\sd.py", line 1540, in load_diffusion_model_state_dict
model = model_config.get_model(new_sd, "")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\supported_models.py", line 769, in get_model
out = model_base.Flux2(self, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 839, in __init__
super().__init__(model_config, model_type, device=device, unet_model=unet_model)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 142, in __init__
self.diffusion_model = unet_model(**unet_config, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\ldm\flux\model.py", line 67, in __init__
raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
ValueError: Got [32, 32, 32, 32] but expected positional dim 64

2026-01-21T23:08:29.822804 - Prompt executed in 4.52 seconds
2026-01-21T23:16:18.611714 - got prompt
2026-01-21T23:16:18.645350 - gguf qtypes: F32 (60), Q8_0 (80), BF16 (9)
2026-01-21T23:16:18.648275 - !!! Exception during processing !!! Got [32, 32, 32, 32] but expected positional dim 64
2026-01-21T23:16:18.649325 - Traceback (most recent call last):
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 176, in load_unet
model = comfy.sd.load_diffusion_model_state_dict(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\sd.py", line 1540, in load_diffusion_model_state_dict
model = model_config.get_model(new_sd, "")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\supported_models.py", line 769, in get_model
out = model_base.Flux2(self, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 839, in __init__
super().__init__(model_config, model_type, device=device, unet_model=unet_model)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 142, in __init__
self.diffusion_model = unet_model(**unet_config, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\ldm\flux\model.py", line 67, in __init__
raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
ValueError: Got [32, 32, 32, 32] but expected positional dim 64

2026-01-21T23:16:18.650324 - Prompt executed in 0.02 seconds
2026-01-21T23:17:10.193781 - got prompt
2026-01-21T23:17:10.227767 - gguf qtypes: F32 (60), Q8_0 (80), BF16 (9)
2026-01-21T23:17:10.229773 - !!! Exception during processing !!! Got [32, 32, 32, 32] but expected positional dim 64
2026-01-21T23:17:10.230774 - Traceback (most recent call last):
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 176, in load_unet
model = comfy.sd.load_diffusion_model_state_dict(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\sd.py", line 1540, in load_diffusion_model_state_dict
model = model_config.get_model(new_sd, "")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\supported_models.py", line 769, in get_model
out = model_base.Flux2(self, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 839, in __init__
super().__init__(model_config, model_type, device=device, unet_model=unet_model)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 142, in __init__
self.diffusion_model = unet_model(**unet_config, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\ldm\flux\model.py", line 67, in __init__
raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
ValueError: Got [32, 32, 32, 32] but expected positional dim 64

2026-01-21T23:17:10.231772 - Prompt executed in 0.02 seconds
2026-01-21T23:19:54.396677 - got prompt
2026-01-21T23:19:54.474805 - gguf qtypes: F32 (60), Q8_0 (80), BF16 (9)
2026-01-21T23:19:54.477741 - !!! Exception during processing !!! Got [32, 32, 32, 32] but expected positional dim 64
2026-01-21T23:19:54.479419 - Traceback (most recent call last):
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\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 "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 291, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "C:\Users\Abhishek\Documents\ComfyUI\custom_nodes\ComfyUI-GGUF\nodes.py", line 176, in load_unet
model = comfy.sd.load_diffusion_model_state_dict(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\sd.py", line 1540, in load_diffusion_model_state_dict
model = model_config.get_model(new_sd, "")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\supported_models.py", line 769, in get_model
out = model_base.Flux2(self, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 839, in __init__
super().__init__(model_config, model_type, device=device, unet_model=unet_model)
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_base.py", line 142, in __init__
self.diffusion_model = unet_model(**unet_config, device=device, operations=operations)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Abhishek\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\ldm\flux\model.py", line 67, in __init__
raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
ValueError: Got [32, 32, 32, 32] but expected positional dim 64

2026-01-21T23:19:54.480417 - Prompt executed in 0.06 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