Enable Latent Consistency models OpenVINO export and inference

[echarlaix]

Add Latent Consistency models (added in diffusers in huggingface/diffusers#5438 and huggingface/diffusers#5448 ) OpenVINO export + inference

from optimum.intel import OVLatentConsistencyModelPipeline

pipeline= OVLatentConsistencyModelPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", export=True)
prompt = "sailing ship in storm by Leonardo da Vinci"
images = pipeline(prompt=prompt, num_inference_steps=4, guidance_scale=8.0).images

with static shapes :

batch_size, num_images, height, width = 1, 1, 512, 512
pipeline.reshape(batch_size=batch_size, height=height, width=width, num_images_per_prompt=num_images)

Following ONNX integration huggingface/optimum#1469

[echarlaix]

used to trigger tests with skip decorator, will remove before merging

[HuggingFaceDocBuilderDev]

The documentation is not available anymore as the PR was closed or merged.