[Feature Request]: Support LCM LORA

[taotaow]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

lcm lora can reduce inference steps to 2~8，it's fast,even realtime!
https://huggingface.co/blog/lcm_lora

Proposed workflow

from diffusers import DiffusionPipeline, LCMScheduler
import torch

model_id = "wavymulder/collage-diffusion"
lcm_lora_id = "latent-consistency/lcm-lora-sdv1-5"

pipe = DiffusionPipeline.from_pretrained(model_id, variant="fp16")
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights(lcm_lora_id)
pipe.to(device="cuda", dtype=torch.float16)

prompt = "collage style kid sits looking at the night sky, full of stars"

generator = torch.Generator(device=pipe.device).manual_seed(1337)
images = pipe(
prompt=prompt,
generator=generator,
negative_prompt=negative_prompt,
num_inference_steps=4,
guidance_scale=1,
).images[0]

Additional information

No response