What is DPMSolverMultistepScheduler for?

🧨 Diffusers
1

I’m looking at the code for fine-tuning Stable Diffusion with LoRA and below is the relevant code:

import torch
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler

model_base = "runwayml/stable-diffusion-v1-5"

pipe = StableDiffusionPipeline.from_pretrained(model_base, torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)```

import torch
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler

model_base = "runwayml/stable-diffusion-v1-5"

pipe = StableDiffusionPipeline.from_pretrained(model_base, torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)

Why do we need to define new pipe.sheduler using DPMSolverMultistepScheduler? Can we just use the original scheduler from the base model?