Use randn_tensor to replace torch.randn

[lmxyy]

What does this PR do?

LTX-Video pipeline uses the original torch.randn to create a random tensor. torch.randn requires generator and latents on the same device, while the wrapped function randn_tensor does not have this issue.

Fixes # (issue)
Fix the running issue when the generator and latents on different devices. For example, if you use CPU's random seed to generate a video on CUDA, the original pipeline will raise an error.

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.
@yiyixuxu @asomoza

[lmxyy]

A simple script to reproduce the error:

import torch
from diffusers import LTXPipeline
from diffusers.utils import export_to_video

pipe = LTXPipeline.from_pretrained("a-r-r-o-w/LTX-Video-0.9.1-diffusers", torch_dtype=torch.bfloat16)
pipe.to("cuda")

prompt = (
    "A woman with long brown hair and light skin smiles at another woman with long blonde hair. "
    "The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. "
    "The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, "
    "likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
)
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

video = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=768,
    height=512,
    num_frames=161,
    decode_timestep=0.03,
    decode_noise_scale=0.025,
    num_inference_steps=50,
    generator=torch.Generator().manual_seed(0),
).frames[0]

export_to_video(video, "output.mp4", fps=24)

[a-r-r-o-w]

Perfect, thanks! Sorry for the oversight and will merge once tests pass

[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.