Update README.md

README.md

@@ -33,6 +33,8 @@ prompt = "mtg style Tony Stark, in a city"
 with torch.cuda.amp.autocast(True):
     image = pipeline(prompt, num_inference_steps=40, guidance_scale=8, height = 512, width = 712, scheduler = "DDIM").images[0]
 image.save(f"img.png")
+```
+
 
 This model was trained using the diffusers dreambooth training example script using prior-preservation loss and finetuning the text encoder on roughly 120 images in 8.000 steps.