Add Lora support to stable diffusion

[JingyaHuang]

What does this PR do?

• Support tracing (one or multiple) lora weights through cli / exporter / Neuron modeling API
• Add tests

---

Example:

• Tiny

optimum-cli export neuron -m hf-internal-testing/tiny-stable-diffusion-torch --task stable-diffusion --batch_size 1 --height 64 --width 64 --num_images_per_prompt 4 --auto_cast matmul --lora_model_ids Jingya/tiny-stable-diffusion-lora-64 --lora_weight_names pytorch_lora_weights.safetensors --lora_adapter_names poke --lora_scales 0.9 --auto_cast_type bf16 tiny_sd_neuron_lora/

• sdxl

optimum-cli export neuron -m stabilityai/stable-diffusion-xl-base-1.0 --task stable-diffusion-xl --batch_size 1 --height 1024 --width 1024 --num_images_per_prompt 4 --auto_cast matmul --lora_model_ids CiroN2022/toy-face --lora_weight_names toy_face_sdxl.safetensors --lora_adapter_names toy --lora_scales 0.9 --auto_cast_type bf16 sd_neuron_lora_xl/

Next:

Add examples and doc.

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.

[michaelbenayoun]

LGTM