hyoungwoncho
/

sd_perturbed_attention_guidance

Unconditional Image Generation

Diffusion Models

Stable Diffusion

Perturbed-Attention Guidance

Model card Files Files and versions Community

hyoungwoncho commited on Apr 19

Commit

fafd3b5

•

1 Parent(s): b66c6b2

Update README.md

Files changed (1) hide show

README.md +16 -16

README.md CHANGED Viewed

@@ -41,28 +41,28 @@ 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

 ```
 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