Fix HunyuanVideo 1.5 I2V by preprocessing image at pixel resolution i…

[akshan-main]

…nstead of latent resolution

What does this PR do?

Fixes #13439

prepare_cond_latents_and_mask shadows the pixel height/width parameters with latent dims from latents.shape (line 614):

batch, channels, frames, height, width = latents.shape  # overwrites pixel h/w with latent h/w

This causes _get_image_latents to preprocess the conditioning image at latent resolution (~30x44) instead of pixel resolution (480x704).

Renamed to latent_height/latent_width so the original pixel dims are preserved for image preprocessing.

The original Tencent implementation (HunyuanVideo-1.5) resizes at pixel resolution.

Found while working on the modular pipeline for HunyuanVideo 1.5 (#13389).

Fixes #13439

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?

@yiyixuxu @DN6 @sayakpaul

[yiyixuxu]

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.

[akshan-main]

These failures are not related to my PRs. Happened with #13406 too