Storydiffusion_Sampler: Placeholder storage has not been allocated on MPS device!

[Gyyyyyyyyds]

ComfyUI Error Report

Error Details

• Node Type: Storydiffusion_Sampler
• Exception Type: RuntimeError
• Exception Message: Placeholder storage has not been allocated on MPS device!

Stack Trace

  File "/Users/gaoyuan/ComfyUI/execution.py", line 323, 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 "/Users/gaoyuan/ComfyUI/execution.py", line 198, 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 "/Users/gaoyuan/ComfyUI/execution.py", line 169, in _map_node_over_list
    process_inputs(input_dict, i)

  File "/Users/gaoyuan/ComfyUI/execution.py", line 158, in process_inputs
    results.append(getattr(obj, func)(**inputs))

  File "/Users/gaoyuan/ComfyUI/custom_nodes/ComfyUI_StoryDiffusion/Storydiffusion_node.py", line 1823, in story_sampler
    for value in gen:

  File "/Users/gaoyuan/ComfyUI/custom_nodes/ComfyUI_StoryDiffusion/Storydiffusion_node.py", line 805, in process_generation
    id_image = pipe(

  File "/Users/gaoyuan/miniconda3/envs/comflowy/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)

  File "/Users/gaoyuan/ComfyUI/custom_nodes/ComfyUI_StoryDiffusion/StoryMaker/pipeline_sdxl_storymaker.py", line 634, in __call__
    latents = self.prepare_latents(

  File "/Users/gaoyuan/miniconda3/envs/comflowy/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py", line 709, in prepare_latents
    latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)

  File "/Users/gaoyuan/miniconda3/envs/comflowy/lib/python3.10/site-packages/diffusers/utils/torch_utils.py", line 81, in randn_tensor
    latents = torch.randn(shape, generator=generator, device=rand_device, dtype=dtype, layout=layout).to(device)
![WechatIMG759](https://github.com/user-attachments/assets/f7c0a9a5-7600-4fd5-830e-24986595ace4)

[Gyyyyyyyyds]

[smthemex]

torch.randn don't support MPS, I haven't test this node in any Mac,so i can't help you~

[Gyyyyyyyyds]

So do u know how to solve this problem? if I want to use this model on a Mac, what can I do, do u have any idea

[smthemex]

Give me some time, I need to refactor the code of this node.

[Gyyyyyyyyds]

OK Thanks a lot, looking forward to ur feedback