Update README.md

README.md

@@ -9,24 +9,25 @@ tags:
 - PAG
 ---
 
-# Perturbed-Attention Guidance
+# Perturbed-Attention Guidance SDXL
 
 ![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).
+This repository is based on [Diffusers](https://huggingface.co/docs/diffusers/index). The pipeline is a modification of StableDiffusionXLPipeline to add Perturbed-Attention Guidance (PAG).
+The original Perturbed-Attention Guidance by [Hyoungwon Cho](https://huggingface.co/hyoungwoncho) is availiable at [hyoungwoncho/sd_perturbed_attention_guidance](https://huggingface.co/hyoungwoncho/sd_perturbed_attention_guidance)
 
 ## Quickstart
 
 Loading Custom Piepline:
 
 ```
-from diffusers import StableDiffusionPipeline
+from diffusers import StableDiffusionXLPipeline
 
-pipe = StableDiffusionPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    custom_pipeline="hyoungwoncho/sd_perturbed_attention_guidance",
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    custom_pipeline="multimodalart/sdxl_perturbed_attention_guidance",
     torch_dtype=torch.float16
 )
 
@@ -34,17 +35,15 @@ device="cuda"
 pipe = pipe.to(device)
 ```
 
-Sampling with PAG:
+Unconditional 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']
+        pag_applied_layers=['mid']
     ).images
 ```
 
@@ -52,24 +51,24 @@ Sampling with PAG and CFG:
 
 ```
 output = pipe(
-        prompts,
-        width=512,
-        height=512,
-        num_inference_steps=50,
+        "the spirit of a tamagotchi wandering in the city of Vienna",
+        num_inference_steps=25,
         guidance_scale=4.0,
         pag_scale=3.0,
-        pag_applied_layers_index=['m0']
+        pag_applied_layers=['mid']
     ).images
 ```
 
 ## Parameters
 
-guidance_scale : gudiance scale of CFG (ex: 7.5)
+`guidance_scale` : gudiance scale of CFG (ex: `7.5`)
+
+`pag_scale` : gudiance scale of PAG (ex: `4.0`)
 
-pag_scale : gudiance scale of PAG (ex: 5.0)
+`pag_applied_layers`: layer to apply perturbation (ex: ['mid'])
 
-pag_applied_layers_index : index of the layer to apply perturbation (ex: ['m0'])
+`pag_applied_layers_index` : index of the layer to apply perturbation (ex: ['m0'])
 
-## Stable Diffusion Demo
+## Stable Diffusion XL 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).