KDPM2DiscreteScheduler and KDPM2AncestralDiscreteScheduler Missing use_karras_sigmas argument

[CodeCorrupt]

Describe the bug

Hey HF team, I'm trying to mimic the A1111 samplers using the table listed in the docs but it seems the KDPM2DiscreteScheduler and KDPM2AncestralDiscreteScheduler schedulers don't actually support the use_karras_sigmas=True argument.

Please let me know if I'm just missing something 🤗

Reproduction

from diffusers import KDPM2DiscreteScheduler, KDPM2AncestralDiscreteScheduler

KDPM2DiscreteScheduler(**common_config, use_karras_sigmas=True)
KDPM2AncestralDiscreteScheduler(**common_config, use_karras_sigmas=True)

Logs

[... Trimmed logs ...]
  File "/app/lib/models.py", line 41, in get_all_schedulers
    "DPM2 Karras": KDPM2DiscreteScheduler(**common_config, use_karras_sigmas=True),
  File "/usr/local/lib/python3.8/dist-packages/diffusers/configuration_utils.py", line 636, in inner_init
    init(self, *args, **init_kwargs)
TypeError: __init__() got an unexpected keyword argument 'use_karras_sigmas'

System Info

• diffusers version: 0.20.2
• Platform: Linux-5.4.0-155-generic-x86_64-with-glibc2.29
• Python version: 3.8.10
• PyTorch version (GPU?): 2.0.1+cu117 (True)
• Huggingface_hub version: 0.16.4
• Transformers version: 4.30.2
• Accelerate version: 0.20.3
• xFormers version: not installed
• Using GPU in script?: Yes - A6000
• Using distributed or parallel set-up in script?: No

Who can help?

@patrickvonplaten and @williamberman

[patrickvonplaten]

@yiyixuxu can you give this a try?