README.md

---
language:
- en
pipeline_tag: unconditional-image-generation
tags:
- Diffusion Models
- Stable Diffusion
- Perturbed-Attention Guidance
- PAG
---

# Perturbed-Attention Guidance

![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6601282b569b30694e67b886/27Lmuol8anwd6L6BLzyWf.jpeg)

[Project](https://ku-cvlab.github.io/Perturbed-Attention-Guidance/) / [arXiv](https://arxiv.org/abs/2403.17377) / [GitHub](https://github.com/KU-CVLAB/Perturbed-Attention-Guidance)

This repository is based on [Diffusers](https://huggingface.co/docs/diffusers/index). The pipeline is a modification of StableDiffusionPipeline to support Perturbed-Attention Guidance (PAG).

## Quickstart

Loading Custom Piepline:

```
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    custom_pipeline="hyoungwoncho/sd_perturbed_attention_guidance",
    torch_dtype=torch.float16,
    safety_checker=None
)

device="cuda"
pipe = pipe.to(device)

prompts = ["a corgi"]
```

Sampling with PAG:

```
output = pipe(
    prompts,
    width=512,
    height=512,
    num_inference_steps=50,
    guidance_scale=0.0,
    pag_scale=5.0,
    pag_applied_layers_index=['m0']
).images
```

Sampling with PAG and CFG:

```
output = pipe(
    prompts,
    width=512,
    height=512,
    num_inference_steps=50,
    guidance_scale=4.0,
    pag_scale=3.0,
    pag_applied_layers_index=['m0']
).images
```

## Parameters

guidance_scale : gudiance scale of CFG (ex: 7.5)

pag_scale : gudiance scale of PAG (ex: 5.0)

pag_applied_layers_index : index of the layer to apply perturbation (ex: ['m0'])

## Stable Diffusion Demo

To join a demo of PAG on Stable Diffusion, run [sd_pag_demo.ipynb](https://huggingface.co/hyoungwoncho/sd_perturbed_attention_guidance/blob/main/sd_pag_demo.ipynb).