Update README.md

README.md

@@ -4,6 +4,26 @@
 
 ### 1-step inference
 1-step inference is only allowed based on SD v1.5 for now. And you should prepare the informative initialization according to the paper for better results.
+```python
+pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype = torch.float16)
+pipeline = pipeline.to('cuda')
+pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
+generator = torch.manual_seed(318)
+steps = 1
+bs = 1
+latents = ... # maybe some latent codes of real images or SD generation
+latent_mean = latent.mean(dim=0)
+noise = torch.randn([1,bs,64,64])
+input_latent = pipeline.scheduler.add_noise(latent_mean.repeat(bs,1,1,1),noise,1000)
+imgs= pipeline(prompt="A photo of a dog",
+                    num_inference_steps=steps, 
+                    num_images_per_prompt = 1,
+                        generator = generator,
+                        guidance_scale=1.5,
+                    latents = input_latent,
+                   )[0]
+imgs
+```
 
 ### 2-step inference
 We note that a small CFG can be used to enhance the image quality.