Make zeroing prompt embeds for Mochi Pipeline configurable

[DN6]

What does this PR do?

When the entire Mochi Pipeline is placed under the autocast context, zeroing out empty prompts can result in overflow in the T5 embeds resulting in a blank video. This PR disables the behaviour by default, and provides a pipeline init argument to reenable, similar to SDXL.

e.g this will currently produce a blank video

import torch
from diffusers import MochiPipeline
from diffusers.utils import export_to_video

pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview")

# Enable memory savings
pipe.enable_model_cpu_offload()
pipe.enable_vae_tiling()

prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."

with torch.autocast("cuda", torch.bfloat16, cache_enabled=False):
      frames = pipe(prompt, num_frames=84).frames[0]

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[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.

[yiyixuxu]

thanks!