sd3 pipeline support

[eaidova]

What does this PR do?

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 make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[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.

[IlyasMoutawwakil]

The changes to be made in this PR after the refactorization are very simple and mostly will make it more readable:

• no need to copy paste modeling from diffusers anymore, you just subclass (OVDiffusionPipeline, StabeldDiffusion3Pipeline) and it should be good in most cases.
• adding tests is as simple as adding the architecture to the task specific tests, I see you haven't added tests yet tho...

I also suggest you take a look at the original refactorization work in huggingface/optimum#2021, I explain there issues with the previous approach and why the refactorization is not only that but also fixing many issues with the previous design (reproducibility of results & numeric consistency with diffusers), which weren't tested before or simply ignored for some architectures/tasks.

[IlyasMoutawwakil]

LGTM, can you run styling and add tests please.

[IlyasMoutawwakil]

• it seems sd3 still doesn't support callbacks (idk if it ever will as it doesn't have a unet), need to be skipped.
• it's also not as numerically consistent with diffusers, which is interesting, we can increase atol and rtol to 1e-3 and 1e-1 for this architecture for now, but worth investigating, especially if each exported component is numerically consistent.
• and finally I guess output_type="latent" is different for this model, again because it uses a transformer instead of unet https://github.com/huggingface/optimum-intel/blob/main/tests/openvino/test_diffusion.py#L419-L422

[IlyasMoutawwakil]

will be merged once tests are updated and passed

[eaidova]

@IlyasMoutawwakil now all relevant tests are fixed, please take a look one more time

[IlyasMoutawwakil]

reference for text_encoder_3 inference test skipping : #965