Add Example of IPAdapterScaleCutoffCallback to Docs

[ParagEkbote]

What does this PR do?

When I was working on a previous PR, I noticed that there was no example showing the usage of IP Adapter Callback to the docs, I've added one in this PR.

1)Script for image without callback:

from diffusers import AutoPipelineForText2Image
from diffusers.utils import load_image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
pipeline.set_ip_adapter_scale(0.6)

image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_diner.png")
generator = torch.Generator(device="cuda").manual_seed(2628670641)
images = pipeline(
    prompt="a tiger sitting in a chair drinking orange juice",
    ip_adapter_image=image,
    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
    num_inference_steps=50,
    generator=generator,
).images
images[0].save("without_callback.png")

2. Script for image with callback:

from diffusers import AutoPipelineForText2Image
from diffusers.callbacks import IPAdapterScaleCutoffCallback
from diffusers.utils import load_image
import torch
 

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", 
    torch_dtype=torch.float16
).to("cuda")


pipeline.load_ip_adapter(
    "h94/IP-Adapter", 
    subfolder="sdxl_models", 
    weight_name="ip-adapter_sdxl.bin"
)

pipeline.set_ip_adapter_scale(0.6)


callback = IPAdapterScaleCutoffCallback(
    cutoff_step_ratio=None, 
    cutoff_step_index=5
)

image = load_image(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_adapter_diner.png"
)

generator = torch.Generator(device="cuda").manual_seed(2628670641)

images = pipeline(
    prompt="a tiger sitting in a chair drinking orange juice",
    ip_adapter_image=image,
    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
    generator=generator,
    num_inference_steps=50,
    callback_on_step_end=callback,
).images

images[0].save("custom_callback_img.png")

For adding the images to the docs, do I have to upload them to this repository on the HF hub and link it back to the page? Please let me know and I will make the necessary changes.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).

Who can review?

@stevhliu

[hlky]

Hi @ParagEkbote. Thanks for this contribution.

do I have to upload them to this repository on the HF hub and link it back to the page

Yes, create a Hub PR that uploads the images somewhere under diffusers, link the PR here and someone will merge it.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[stevhliu]

Nice, thanks for including!