sana support

[eaidova]

What does this PR do?

• provided opportunity to select model checkpoint variant for loading
• supported Sana image generation model family

Example of usage:

import torch

from optimum.intel.openvino import OVDiffusionPipeline


pipe = OVDiffusionPipeline.from_pretrained("Efficient-Large-Model/Sana_600M_512px_diffusers", variant="fp16")
prompt = 'a cyberpunk cat in neon style'
image = pipe(
    prompt=prompt,
    generator=torch.Generator(device="cpu").manual_seed(142),
)[0]

image[0].save("sana_fp16.png")

Generated image:

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.

[andrei-kochin]

@echarlaix @IlyasMoutawwakil could you please take a look?

[eaidova]

@IlyasMoutawwakil all comments applied (failed test is not related and already fixed on main), could you please take a look one more time?
Thanks!

[echarlaix]

Thanks for the addition @eaidova