Text-to-Image
Diffusers
stable-diffusion
PeterL1n commited on
Commit
1dcaccf
1 Parent(s): aa15e49

Update readme

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -68,6 +68,8 @@ pipe("A girl smiling", num_inference_steps=4, guidance_scale=0).images[0].save("
68
 
69
  ### 1-Step UNet
70
 
 
 
71
  ```python
72
  import torch
73
  from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler
 
68
 
69
  ### 1-Step UNet
70
 
71
+ The 1-step model uses "sample" prediction instead of "epsilon" prediction! The scheduler needs to be configured correctly.
72
+
73
  ```python
74
  import torch
75
  from diffusers import StableDiffusionXLPipeline, EulerDiscreteScheduler