LTXPipeline should tolerate torch.Generator on CPU by generating the latents on the device where the Generator is

[bghira]

What does this PR do?

When using LTXVideo using a torch.Generator(device="cpu") we encounter error where the noise is generating on device using generator but we should generate the noise on generator.device and move to device after, which resolves the condition.

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.

@sayakpaul @yiyixuxu

[bghira]

oh 🤔 i'm confused, hmm.. my version had torch.randn. is this already resolved through randn_tensor?

[sayakpaul]

Cc: @lmxyy @a-r-r-o-w