lack of support of loading lora weights in PixArtAlphaPipeline

pipe = PixArtAlphaPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.load_lora_weights("xxx")
When I want to load lora in PixArtAlphaPipeline, it throws this error:
AttributeError: 'PixArtAlphaPipeline' object has no attribute 'load_lora_weights'

May be we can add the lora support in this pipeline?
Using the peft method like this is not convenient, and the effect is not good...
transformer = Transformer2DModel.from_pretrained("PixArt-alpha/PixArt-LCM-XL-2-1024-MS", subfolder="transformer", torch_dtype=torch.float16)
transformer = PeftModel.from_pretrained(transformer, "Your-LoRA-Model-Path")

Start at the PixArtAlphaPipeline entry point and compare its weight-loading behavior with pipelines that support load_lora_weights. Reproduce the shown from_pretrained and load_lora_weights example, then verify PixArt LoRA loading and generation; done means the call no longer raises AttributeError and the pipeline produces the expected result.

Scritto dal modello di indicizzazione a partire dal testo della issue.