Add an End-To-End Tutorial for Efficient-Large-Model/Sana_600M_512px_diffusers

[ParagEkbote]

Description

I've reopened the PR which got closed due to it being stale by the stale bot.

Related Issue

Fixes #93

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

Additional Notes

---

Note

Adds a new Jupyter tutorial to optimize Sana diffusers with Pruna and deploy via Hugging Face, and links it from the tutorials index.

• Docs/Tutorials:
  • New notebook: docs/tutorials/deploying_sana_tutorial.ipynb
    • Optimizes Efficient-Large-Model/Sana_600M_512px_diffusers using Pruna SmashConfig with torchao.
    • Saves smashed model locally and shows optional push to Hugging Face Hub.
    • Loads data-is-better-together/open-image-preferences-v1-binarized with PrunaDataModule for evaluation.
    • Evaluates with EvaluationAgent using TotalTimeMetric and LatencyMetric.
    • Provides a gradio demo app to generate images from prompts.
  • Index update: docs/tutorials/index.rst
    • Adds a grid card linking to deploying_sana_tutorial.ipynb with brief description.

^{Written by Cursor Bugbot for commit 79f6bab. This will update automatically on new commits. Configure here.}

[ParagEkbote]

@davidberenstein1957

I have rebased on main and fix any merge conflicts as well. You might need to squash and merge this branch :)

Could you please review?

[davidberenstein1957]

Looks good. I think we need a final rebase to rsolve the failing tests :)

[minettekaum]

The link to google colab is broken and there was a typo in import torch. Otherwise it looks good!

[minettekaum]

lgtm :)

[ParagEkbote]

Is this PR ready to be merged? Could you please let me know?

cc: @davidberenstein1957