using workflow hyvideo_ip2v_experimental_dango

[ghost]

hello,

i've done some hunyuan video with my config : RTX 4070 12Go, 64Go RAM, core I7 12th
at resolution : 384 * 720, 221 frames

but this workflow found in comfyui hyvideo_ip2v_experimental_dango already hang into :

got prompt
Resizing image from 768x768 to 256x256 (1:1 aspect ratio)
Unused or unrecognized kwargs: device.
vlm prompt attention_mask shape: torch.Size([1, 235]), masked tokens: 235
clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 41
Input (height, width, video_length) = (256, 256, 25)
The config attributes {'use_flow_sigmas': True, 'prediction_type': 'flow_prediction'} were passed to FlowMatchDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 7.5), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])
!!! Exception during processing !!! Allocation on device 
Traceback (most recent call last):
  File "/home/emmanuel/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 "/home/emmanuel/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 "/home/emmanuel/ComfyUI/execution.py", line 174, in _map_node_over_list
    process_inputs(input_dict, i)
  File "/home/emmanuel/ComfyUI/execution.py", line 163, in process_inputs
    results.append(getattr(obj, func)(**inputs))
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/emmanuel/ComfyUI/custom_nodes/comfyui-hunyuanvideowrapper/nodes.py", line 1330, in process
    transformer.to(device)
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/diffusers/models/modeling_utils.py", line 1077, in to
    return super().to(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1174, in to
    return self._apply(convert)
           ^^^^^^^^^^^^^^^^^^^^
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply
    module._apply(fn)
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply
    module._apply(fn)
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply
    module._apply(fn)
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 805, in _apply
    param_applied = fn(param)
                    ^^^^^^^^^
  File "/home/emmanuel/miniconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1160, in convert
    return t.to(
           ^^^^^
torch.OutOfMemoryError: Allocation on device 

Got an OOM, unloading all loaded models.

even downsize to 256 * 256, 25 frames !

so where is the problem ?

thanks