multimodalart HF staff commited on
Commit
e81c441
1 Parent(s): ba23565

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -10,8 +10,8 @@ tags:
10
  ---
11
 
12
  # Perturbed-Attention Guidance for SDXL
13
-
14
- ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6601282b569b30694e67b886/27Lmuol8anwd6L6BLzyWf.jpeg)
15
 
16
  [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)
17
 
@@ -21,7 +21,7 @@ The original Perturbed-Attention Guidance for unconditional models and SD1.5 by
21
 
22
  ## Quickstart
23
 
24
- Loading Custom Piepline:
25
 
26
  ```py
27
  from diffusers import StableDiffusionXLPipeline
@@ -68,7 +68,7 @@ output = pipe(
68
 
69
  `pag_applied_layers`: layer to apply perturbation (ex: ['mid'])
70
 
71
- `pag_applied_layers_index` : index of the layer to apply perturbation (ex: ['m0'])
72
 
73
  ## Stable Diffusion XL Demo
74
 
 
10
  ---
11
 
12
  # Perturbed-Attention Guidance for SDXL
13
+ ![image/jpeg](uncond_generation_pag.jpg)
14
+ ![image/jpeg](cfgpag.jpg)
15
 
16
  [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)
17
 
 
21
 
22
  ## Quickstart
23
 
24
+ Loading Custom Pipeline:
25
 
26
  ```py
27
  from diffusers import StableDiffusionXLPipeline
 
68
 
69
  `pag_applied_layers`: layer to apply perturbation (ex: ['mid'])
70
 
71
+ `pag_applied_layers_index` : index of the layers to apply perturbation (ex: ['m0', 'm1'])
72
 
73
  ## Stable Diffusion XL Demo
74