Diffusers documentation

Perturbed-Attention Guidance

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Perturbed-Attention Guidance

Perturbed-Attention Guidance (PAG) is a new diffusion sampling guidance that improves sample quality across both unconditional and conditional settings, achieving this without requiring further training or the integration of external modules. PAG is designed to progressively enhance the structure of synthesized samples throughout the denoising process by considering the self-attention mechanisms’ ability to capture structural information. It involves generating intermediate samples with degraded structure by substituting selected self-attention maps in diffusion U-Net with an identity matrix, and guiding the denoising process away from these degraded samples.

This guide will show you how to use PAG for various tasks and use cases.

General tasks

You can apply PAG to the StableDiffusionXLPipeline for tasks such as text-to-image, image-to-image, and inpainting. To enable PAG for a specific task, load the pipeline using the AutoPipeline API with the enable_pag=True flag and the pag_applied_layers argument.

🤗 Diffusers currently only supports using PAG with selected SDXL pipelines and PixArtSigmaPAGPipeline. But feel free to open a feature request if you want to add PAG support to a new pipeline!

Text-to-image
Image-to-image
Inpainting
from diffusers import AutoPipelineForText2Image
from diffusers.utils import load_image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    enable_pag=True,
    pag_applied_layers=["mid"],
    torch_dtype=torch.float16
)
pipeline.enable_model_cpu_offload()

The pag_applied_layers argument allows you to specify which layers PAG is applied to. Additionally, you can use set_pag_applied_layers method to update these layers after the pipeline has been created. Check out the pag_applied_layers section to learn more about applying PAG to other layers.

If you already have a pipeline created and loaded, you can enable PAG on it using the from_pipe API with the enable_pag flag. Internally, a PAG pipeline is created based on the pipeline and task you specified. In the example below, since we used AutoPipelineForText2Image and passed a StableDiffusionXLPipeline, a StableDiffusionXLPAGPipeline is created accordingly. Note that this does not require additional memory, and you will have both StableDiffusionXLPipeline and StableDiffusionXLPAGPipeline loaded and ready to use. You can read more about the from_pipe API and how to reuse pipelines in diffuser here.

pipeline_sdxl = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
pipeline = AutoPipelineForText2Image.from_pipe(pipeline_sdxl, enable_pag=True)

To generate an image, you will also need to pass a pag_scale. When pag_scale increases, images gain more semantically coherent structures and exhibit fewer artifacts. However overly large guidance scale can lead to smoother textures and slight saturation in the images, similarly to CFG. pag_scale=3.0 is used in the official demo and works well in most of the use cases, but feel free to experiment and select the appropriate value according to your needs! PAG is disabled when pag_scale=0.

prompt = "an insect robot preparing a delicious meal, anime style"

for pag_scale in [0.0, 3.0]:
    generator = torch.Generator(device="cpu").manual_seed(0)
    images = pipeline(
        prompt=prompt,
        num_inference_steps=25,
        guidance_scale=7.0,
        generator=generator,
        pag_scale=pag_scale,
    ).images
generated image without PAG
generated image with PAG

PAG with ControlNet

To use PAG with ControlNet, first create a controlnet. Then, pass the controlnet and other PAG arguments to the from_pretrained method of the AutoPipeline for the specified task.

from diffusers import AutoPipelineForText2Image, ControlNetModel
import torch

controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
)

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet,
    enable_pag=True,
    pag_applied_layers="mid",
    torch_dtype=torch.float16
)
pipeline.enable_model_cpu_offload()

If you already have a controlnet pipeline and want to enable PAG, you can use the from_pipe API: AutoPipelineForText2Image.from_pipe(pipeline_controlnet, enable_pag=True)

You can use the pipeline in the same way you normally use ControlNet pipelines, with the added option to specify a pag_scale parameter. Note that PAG works well for unconditional generation. In this example, we will generate an image without a prompt.

from diffusers.utils import load_image
canny_image = load_image(
    "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/pag_control_input.png"
)

for pag_scale in [0.0, 3.0]:
    generator = torch.Generator(device="cpu").manual_seed(1)
    images = pipeline(
        prompt="",
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        image=canny_image,
        num_inference_steps=50,
        guidance_scale=0,
        generator=generator,
        pag_scale=pag_scale,
    ).images
    images[0]
generated image without PAG
generated image with PAG

PAG with IP-Adapter

IP-Adapter is a popular model that can be plugged into diffusion models to enable image prompting without any changes to the underlying model. You can enable PAG on a pipeline with IP-Adapter loaded.

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

image_encoder = CLIPVisionModelWithProjection.from_pretrained(
    "h94/IP-Adapter",
    subfolder="models/image_encoder",
    torch_dtype=torch.float16
)

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

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

pag_scales = 5.0
ip_adapter_scales = 0.8

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

pipeline.set_ip_adapter_scale(ip_adapter_scale)
generator = torch.Generator(device="cpu").manual_seed(0)
images = pipeline(
    prompt="a polar bear sitting in a chair drinking a milkshake",
    ip_adapter_image=image,
    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
    num_inference_steps=25,
    guidance_scale=3.0,
    generator=generator,
    pag_scale=pag_scale,
).images
images[0]

PAG reduces artifacts and improves the overall compposition.

generated image without PAG
generated image with PAG

Configure parameters

pag_applied_layers

The pag_applied_layers argument allows you to specify which layers PAG is applied to. By default, it applies only to the mid blocks. Changing this setting will significantly impact the output. You can use the set_pag_applied_layers method to adjust the PAG layers after the pipeline is created, helping you find the optimal layers for your model.

As an example, here is the images generated with pag_layers = ["down.block_2"] and pag_layers = ["down.block_2", "up.block_1.attentions_0"]

prompt = "an insect robot preparing a delicious meal, anime style"
pipeline.set_pag_applied_layers(pag_layers)
generator = torch.Generator(device="cpu").manual_seed(0)
images = pipeline(
    prompt=prompt,
    num_inference_steps=25,
    guidance_scale=guidance_scale,
    generator=generator,
    pag_scale=pag_scale,
).images
images[0]
down.block_2 + up.block1.attentions_0
down.block_2
< > Update on GitHub