Update README.md

README.md

@@ -2,8 +2,12 @@
 
 ## Usage
 
-### 2 step inference
-'''python
+### 1-step inference
+1-step inference is only allowed based on SD v1.5.
+
+### 2-step inference
+We note that a small CFG can be used to enhance the image quality.
+```python
 pipeline = DiffusionPipeline.from_pretrained("stablediffusionapi/realistic-vision-v51", torch_dtype = torch.float16)
 pipeline = pipeline.to('cuda')
 pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
@@ -16,4 +20,4 @@ imgs= pipeline(prompt="A photo of a man, XT3",
                         guidance_scale=1.5,
                    )[0]
 imgs
-'''
+```