Update README.md

README.md

@@ -1,3 +1,84 @@
----
-license: apache-2.0
----
+---
+license: 
+- apache-2.0
+language:
+- en
+tags:
+- Diffusion Models
+- Stable Diffusion XL
+- Perturbed-Attention Guidance
+- PAG
+---
+# Perturbed-Attention Guidance for SDXL (i2i)
+
+<div style="display:flex">
+  <video width=50% autoplay loop controls>
+    <source src="https://huggingface.co/multimodalart/sdxl_perturbed_attention_guidance/resolve/main/pag_sdxl.mp4" type="video/mp4">
+  </video>
+  <video width=50% autoplay loop controls>
+    <source src="https://huggingface.co/multimodalart/sdxl_perturbed_attention_guidance/resolve/main/pag_uncond.mp4" type="video/mp4">
+  </video>
+</div>
+The original Perturbed-Attention Guidance for unconditional models and SD1.5 by [Hyoungwon Cho](https://huggingface.co/hyoungwoncho) is availiable at [hyoungwoncho/sd_perturbed_attention_guidance](https://huggingface.co/hyoungwoncho/sd_perturbed_attention_guidance)
+
+[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)
+
+Also there is an extra implementation of the Perturbed-Attention Guidance (PAG) on Stable Diffusion XL (SDXL) for the 🧨 diffusers library by [multimodalart](https://huggingface.co/multimodalart)
+[code](https://huggingface.co/multimodalart/sdxl_perturbed_attention_guidance) / [demo](https://huggingface.co/spaces/multimodalart/perturbed-attention-guidance-sdxl) 
+
+This repository is just a simple implementation of the Perturbed-Attention Guidance (PAG) on Stable Diffusion XL (SDXL) for the 🧨 diffusers library to "i2i".
+
+
+## Quickstart
+
+Loading Custom Pipeline:
+
+```py
+from diffusers import StableDiffusionXLImg2ImgPipeline
+pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    custom_pipeline="jyoung105/sdxl_perturbed_attention_guidance_i2i",
+    torch_dtype=torch.float16
+)
+device="cuda"
+pipe = pipe.to(device)
+```
+
+Unconditional sampling with PAG:
+![image/jpeg](uncond_generation_pag.jpg)
+
+```py
+output = pipe(
+        "",
+        image=init_image,
+        strength=0.9,
+        num_inference_steps=50,
+        guidance_scale=0.0,
+        pag_scale=5.0,
+        pag_applied_layers=['mid']
+    ).images
+```
+
+Sampling with PAG and CFG:
+![image/jpeg](cfgpag.jpg)
+```py
+output = pipe(
+        "the spirit of a tamagotchi wandering in the city of Vienna",
+        image=init_image,
+        strength=0.9,
+        num_inference_steps=25,
+        guidance_scale=4.0,
+        pag_scale=3.0,
+        pag_applied_layers=['mid']
+    ).images
+```
+
+## Parameters
+
+`guidance_scale` : guidance scale of CFG (ex: `7.5`)
+
+`pag_scale` : guidance scale of PAG (ex: `4.0`)
+
+`pag_applied_layers`: layer to apply perturbation (ex: ['mid'])
+
+`pag_applied_layers_index` : index of the layers to apply perturbation (ex: ['m0', 'm1'])