flux pipeline inference with controlnet, inpainting, plus ip-adapter

### Describe the bug

Hi, I would like to utilize flux pipeline. But for now, I have gpu issues to use origin flux pipeline.
If I would like to use nf4 version, How can I set up the inference file on controlnet, inpainting, ip-adapter?
Do I use Fluxcontrol depth or canny and mask, ip-adapter model? or fluxcontrol, fluxfill, ip-adapter?

Thanks,

@hlky, @sayakpaul

### Reproduction

import torch
from diffusers import FluxControlInpaintPipeline
from diffusers.models.transformers import FluxTransformer2DModel
from transformers import T5EncoderModel
from diffusers.utils import load_image, make_image_grid
from image_gen_aux import DepthPreprocessor # https://github.com/huggingface/image_gen_aux
from PIL import Image
import numpy as np

access_token = ""
pipe = FluxControlInpaintPipeline.from_pretrained(
"black-forest-labs/FLUX.1-Depth-dev",
torch_dtype=torch.bfloat16, token=access_token)

# use following lines if you have GPU constraints
# ---------------------------------------------------------------
transformer = FluxTransformer2DModel.from_pretrained(
"sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="transformer", torch_dtype=torch.bfloat16
)
text_encoder_2 = T5EncoderModel.from_pretrained(
"sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="text_encoder_2", torch_dtype=torch.bfloat16
)
pipe.transformer = transformer
pipe.text_encoder_2 = text_encoder_2

pipe.enable_model_cpu_offload()

# ---------------------------------------------------------------
pipe.to("cuda")

prompt = "a blue robot sad expressions"
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")

head_mask = np.zeros_like(image)
head_mask[65:580,300:642] = 255
mask_image = Image.fromarray(head_mask)

processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
control_image = processor(image)[0].convert("RGB")

output = pipe(
prompt=prompt,
image=image,
control_image=control_image,
mask_image=mask_image,
num_inference_steps=30,
strength=1,
guidance_scale=10.0,
generator=torch.Generator().manual_seed(42),
).images[0]
make_image_grid([image, control_image, mask_image, output.resize(image.size)], rows=1, cols=4).save("output.png")

changing depth to canny, and add ip-adapter?

### Logs

```shell

```

### System Info

.

### Who can help?

_No response_

FluxControlInpaintPipeline、FluxTransformer2DModel、nf4 モデルコンポーネントを使用して、提供された再現手順から始めます。Depth または Canny ControlNet、inpainting マスク、IP-Adapter が同時にサポートされているかを判断するため、関連するパイプラインとモデルのドキュメントを確認します。完了とするには、文書化された動作する推論構成が必要ですが、issue ではリポジトリのファイルやテストは特定されていません。

索引モデルが issue の本文から書いたものです。