ValueError: Failed to initialize LatentUpsampler with this configuration: Error while deserializing header: HeaderTooLarge

[oliverban]

SOLVED: See comment.

Getting this error on the "🅛🅣🅧 LTXV Latent Upsampler Model Loader"

EDIT: Temporal works fine.

100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:05<00:00,  1.50it/s]
before guide crop torch.Size([1, 128, 13, 14, 24])
after guide crop torch.Size([1, 128, 13, 14, 24])
!!! Exception during processing !!! Failed to initialize LatentUpsampler with this configuration: Error while deserializing header: HeaderTooLarge
Traceback (most recent call last):
  File "/root/tools/ComfyUI/custom_nodes/ComfyUI-LTXVideo/latent_upsampler.py", line 326, in load_model
    latent_upsampler.load_weights(upscale_model_path)
  File "/root/tools/ComfyUI/custom_nodes/ComfyUI-LTXVideo/latent_upsampler.py", line 228, in load_weights
    sd = safetensors.torch.load_file(weights_path)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/envs/comfy/lib/python3.12/site-packages/safetensors/torch.py", line 313, in load_file
    with safe_open(filename, framework="pt", device=device) as f:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/root/tools/ComfyUI/execution.py", line 349, 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 "/root/tools/ComfyUI/execution.py", line 224, 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 "/root/tools/ComfyUI/execution.py", line 196, in _map_node_over_list
    process_inputs(input_dict, i)
  File "/root/tools/ComfyUI/execution.py", line 185, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/tools/ComfyUI/custom_nodes/ComfyUI-LTXVideo/latent_upsampler.py", line 328, in load_model
    raise ValueError(
ValueError: Failed to initialize LatentUpsampler with this configuration: Error while deserializing header: HeaderTooLarge

Prompt executed in 8.23 seconds
got prompt
!!! Exception during processing !!! Failed to initialize LatentUpsampler with this configuration: Error while deserializing header: HeaderTooLarge
Traceback (most recent call last):
  File "/root/tools/ComfyUI/custom_nodes/ComfyUI-LTXVideo/latent_upsampler.py", line 326, in load_model
    latent_upsampler.load_weights(upscale_model_path)
  File "/root/tools/ComfyUI/custom_nodes/ComfyUI-LTXVideo/latent_upsampler.py", line 228, in load_weights
    sd = safetensors.torch.load_file(weights_path)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/envs/comfy/lib/python3.12/site-packages/safetensors/torch.py", line 313, in load_file
    with safe_open(filename, framework="pt", device=device) as f:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/root/tools/ComfyUI/execution.py", line 349, 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 "/root/tools/ComfyUI/execution.py", line 224, 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 "/root/tools/ComfyUI/execution.py", line 196, in _map_node_over_list
    process_inputs(input_dict, i)
  File "/root/tools/ComfyUI/execution.py", line 185, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/tools/ComfyUI/custom_nodes/ComfyUI-LTXVideo/latent_upsampler.py", line 328, in load_model
    raise ValueError(
ValueError: Failed to initialize LatentUpsampler with this configuration: Error while deserializing header: HeaderTooLarge

[oliverban]

P.S I have re-downloaded the file already to make sure it wasn't corrupt.

[oliverban]

SOLVED: I had to download the file to my computer, then upload to jupyter and THEN it worked. for some reason "wget" kept giving me a bad file! 👎 All good now! 👍