Skip to content

TangoFluxSampler: Expected 1-D argument self, but got 2-D #25

@tychobraheastro

Description

@tychobraheastro

I got this error when running the workflow. I have attached the bug report. Any idea I can fix this?

ComfyUI Error Report

Error Details

  • Node ID: 10
  • Node Type: TangoFluxSampler
  • Exception Type: RuntimeError
  • Exception Message: outer: Expected 1-D argument self, but got 2-D

Stack Trace

  File "/home/user/ComfyUI/execution.py", line 496, 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, hidden_inputs=hidden_inputs)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/ComfyUI/execution.py", line 315, 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, hidden_inputs=hidden_inputs)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/ComfyUI/execution.py", line 289, in _async_map_node_over_list
    await process_inputs(input_dict, i)

  File "/home/user/ComfyUI/execution.py", line 277, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^

  File "/home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux/nodes.py", line 203, in sample
    latents = model(
              ^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux/tangoflux/model.py", line 620, in forward
    noise_pred = self.transformer(
                 ^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux/tangoflux/model.py", line 94, in teacache_forward
    image_rotary_emb = self.pos_embed(ids)
                       ^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/diffusers/models/transformers/transformer_flux.py", line 513, in forward
    cos, sin = get_1d_rotary_pos_embed(
               ^^^^^^^^^^^^^^^^^^^^^^^^

  File "/home/user/anaconda3/lib/python3.12/site-packages/diffusers/models/embeddings.py", line 1159, in get_1d_rotary_pos_embed
    freqs = torch.outer(pos, freqs)  # type: ignore   # [S, D/2]
            ^^^^^^^^^^^^^^^^^^^^^^^

System Information

  • ComfyUI Version: 0.3.61
  • Arguments: main.py --port 15070 --listen 0.0.0.0 --cuda-device 3
  • OS: posix
  • Python Version: 3.12.7 | packaged by Anaconda, Inc. | (main, Oct 4 2024, 13:27:36) [GCC 11.2.0]
  • Embedded Python: false
  • PyTorch Version: 2.6.0+cu124

Devices

  • Name: cuda:0 NVIDIA GeForce RTX 2080 Ti : cudaMallocAsync
    • Type: cuda
    • VRAM Total: 11539054592
    • VRAM Free: 11368398848
    • Torch VRAM Total: 0
    • Torch VRAM Free: 0

Logs

2025-10-11T14:12:35.103063 - Set cuda device to: 3
2025-10-11T14:12:36.758687 - Checkpoint files will always be loaded safely.
2025-10-11T14:12:37.022159 - Total VRAM 11004 MB, total RAM 128768 MB
2025-10-11T14:12:37.022258 - pytorch version: 2.6.0+cu124
2025-10-11T14:12:37.022549 - Set vram state to: NORMAL_VRAM
2025-10-11T14:12:37.023474 - Device: cuda:0 NVIDIA GeForce RTX 2080 Ti : cudaMallocAsync
2025-10-11T14:12:38.280944 - Using pytorch attention
2025-10-11T14:12:39.629615 - Python version: 3.12.7 | packaged by Anaconda, Inc. | (main, Oct  4 2024, 13:27:36) [GCC 11.2.0]
2025-10-11T14:12:39.629709 - ComfyUI version: 0.3.61
2025-10-11T14:12:39.633207 - ComfyUI frontend version: 1.26.13
2025-10-11T14:12:39.633850 - [Prompt Server] web root: /home/user/anaconda3/lib/python3.12/site-packages/comfyui_frontend_package/static
2025-10-11T14:12:43.367826 - 
Import times for custom nodes:
2025-10-11T14:12:43.367952 -    0.0 seconds: /home/user/ComfyUI/custom_nodes/websocket_image_save.py
2025-10-11T14:12:43.368002 -    0.1 seconds: /home/user/ComfyUI/custom_nodes/ComfyUI_Sonic
2025-10-11T14:12:43.368043 -    1.7 seconds: /home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux
2025-10-11T14:12:43.368080 - 
2025-10-11T14:12:43.912573 - Context impl SQLiteImpl.
2025-10-11T14:12:43.912669 - Will assume non-transactional DDL.
2025-10-11T14:12:43.913453 - No target revision found.
2025-10-11T14:12:43.921707 - Starting server

2025-10-11T14:12:43.922007 - To see the GUI go to: http://0.0.0.0:15070
2025-10-11T14:14:49.025135 - got prompt
2025-10-11T14:14:49.039181 - Loading config
2025-10-11T14:14:49.039693 - Loading TangoFlux models
2025-10-11T14:14:49.929939 - Enabling TeaCache
2025-10-11T14:14:56.918091 - Loading TangoFlux VAE
2025-10-11T14:14:56.936813 - /home/user/anaconda3/lib/python3.12/site-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
  WeightNorm.apply(module, name, dim)
2025-10-11T14:14:58.576595 - Generating latents with TangoFlux
2025-10-11T14:14:58.881161 - 
  0%|                                                                                                                                | 0/50 [00:00<?, ?it/s]2025-10-11T14:14:58.896048 - !!! Exception during processing !!! outer: Expected 1-D argument self, but got 2-D
2025-10-11T14:14:58.898036 - Traceback (most recent call last):
  File "/home/user/ComfyUI/execution.py", line 496, 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, hidden_inputs=hidden_inputs)
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/ComfyUI/execution.py", line 315, 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, hidden_inputs=hidden_inputs)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/ComfyUI/execution.py", line 289, in _async_map_node_over_list
    await process_inputs(input_dict, i)
  File "/home/user/ComfyUI/execution.py", line 277, in process_inputs
    result = f(**inputs)
             ^^^^^^^^^^^
  File "/home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux/nodes.py", line 203, in sample
    latents = model(
              ^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux/tangoflux/model.py", line 620, in forward
    noise_pred = self.transformer(
                 ^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/ComfyUI/custom_nodes/ComfyUI-TangoFlux/tangoflux/model.py", line 94, in teacache_forward
    image_rotary_emb = self.pos_embed(ids)
                       ^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/diffusers/models/transformers/transformer_flux.py", line 513, in forward
    cos, sin = get_1d_rotary_pos_embed(
               ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/anaconda3/lib/python3.12/site-packages/diffusers/models/embeddings.py", line 1159, in get_1d_rotary_pos_embed
    freqs = torch.outer(pos, freqs)  # type: ignore   # [S, D/2]
            ^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: outer: Expected 1-D argument self, but got 2-D

2025-10-11T14:14:58.900017 - Prompt executed in 9.87 seconds
2025-10-11T14:14:59.156235 - 
  0%|                                                                                                                                | 0/50 [00:00<?, ?it/s]2025-10-11T14:14:59.156310 - 

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions