fix: allow pass cpu generator for helios

[DefTruth]

Allow pass cpu generator for helios. w/o this fix, helios distilled pipeline will raise an device mismatch error if we use cpu generator. we should use the device from generator for torch.randn.

  File "/workspace/deftruth/dev/miniconda3/envs/py312-c/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/deftruth/dev/diffusers/src/diffusers/pipelines/helios/pipeline_helios_pyramid.py", line 931, in __call__
    noise = self.sample_block_noise(
            ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/deftruth/dev/diffusers/src/diffusers/pipelines/helios/pipeline_helios_pyramid.py", line 473, in sample_block_noise
    z = torch.randn(block_number, block_size, device=device, generator=generator)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Expected a 'cuda' device type for generator but found 'cpu'

cc @SHYuanBest, @yiyixuxu

[SHYuanBest]

@DefTruth It seems that you need fix batch test like this PR.

https://github.com/huggingface/diffusers/pull/13216/changes/d1828e4273834286a08edea69ec8c90bbd26df48..6ed93db6b172c17d2336b876209fcc3daf73ad70

[DefTruth]

@DefTruth It seems that you need fix batch test like this PR.

https://github.com/huggingface/diffusers/pull/13216/changes/d1828e4273834286a08edea69ec8c90bbd26df48..6ed93db6b172c17d2336b876209fcc3daf73ad70

Thanks~

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.