Fix typo: torch_type -> torch_dtype (huggingface#972)

Fix typo: torch_type -> torch_dtype

Author: pcuenca

README.md

@@ -90,7 +90,7 @@ precision while being roughly twice as fast and requiring half the amount of GPU
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_type=torch.float16, revision="fp16")
+pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, revision="fp16")
 pipe = pipe.to("cuda")
 
 prompt = "a photo of an astronaut riding a horse on mars"