enable_vae_tiling is not found SD image to image and inpaint pipeline

[MrSyee]

Describe the bug

I tried to use vae_tiling in StableDiffusionImg2ImgPipeline and StableDiffusionInpaintPipeline, but the function was not defined. This option is probably needed to save memory when generating large images.

I noticed that it is enabled for StableDiffusionPipeline and ControlNet Pipeline. Is there any other reason why you didn't apply it to Img2Img?
If there are no major issues, I'd like to see it applied and I'll try to create a PR.

Thank you!

Reproduction

import torch
from diffusers import AutoPipelineForImage2Image

pipe = AutoPipelineForImage2Image.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16,
    use_safetensors=True,
).to("cuda")
pipe.enable_vae_tiling()

Logs

Loading pipeline components...:   0%|                                                                                                                                                                                  | 0/7 [00:00<?, ?it/s]`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden.
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden.
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:12<00:00,  1.82s/it]
Traceback (most recent call last):
  File "/home/khwankim_dc/workspace/project/sea_drawing/test.py", line 9, in <module>
    pipe.enable_vae_tiling()
  File "/home/khwankim_dc/.pyenv/versions/project/lib/python3.10/site-packages/diffusers/configuration_utils.py", line 138, in __getattr__
    raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")
AttributeError: 'StableDiffusionImg2ImgPipeline' object has no attribute 'enable_vae_tiling'

System Info

• diffusers version: 0.24.0
• Platform: Linux-5.4.0-65-generic-x86_64-with-glibc2.31
• Python version: 3.10.13
• PyTorch version (GPU?): 2.0.1+cu117 (True)
• Huggingface_hub version: 0.20.3
• Transformers version: 4.35.2
• Accelerate version: 0.24.1
• xFormers version: not installed
• Using GPU in script?:
• Using distributed or parallel set-up in script?:

Who can help?

@yiyixuxu @DN6 @sayakpaul @patrickvonplaten

[sayakpaul]

That is because StableDiffusionImg2ImgPipeline doesn't have the method implemented: https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py. Would you be willing to open a PR?

[MrSyee]

That is because StableDiffusionImg2ImgPipeline doesn't have the method implemented: https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py. Would you be willing to open a PR?

@sayakpaul I've opend PR. Please check this PR.