Update README.md

README.md

@@ -2,4 +2,18 @@
 
 This algorithm was proposed in YOSO. 
 
-This model is fine-tuning from PixArt, enabling one step inference to perform text-to-image generation.
+This model is fine-tuning from PixArt, enabling one step inference to perform text-to-image generation.
+
+## usage
+```python
+from diffusers import PixArtAlphaPipeline, LCMScheduler, Transformer2DModel, DPMSolverMultistepScheduler
+
+transformer = Transformer2DModel.from_pretrained(
+    "Yihong666/yoso_pixart512", torch_dtype=torch.float16).to('cuda')
+
+pipe = PixArtAlphaPipeline.from_pretrained("./models--PixArt-alpha--PixArt-XL-2-512x512", 
+                                           transformer=transformer,
+                                           torch_dtype=torch.float16, use_safetensors=True)
+
+pipe = pipe.to('cuda')
+```