update diffuser usage

README.md

@@ -27,7 +27,48 @@ Our 4-step (much higher quality, 2X slower) Text-to-Image demo is hosted at [DMD
 Our 1-step Text-to-Image demo is hosted at [DMD2-1step](https://154dfe6ee5c63946cc.gradio.live)
 
 ## Usage
-Please refer to the [code repository](https://github.com/tianweiy/DMD2)
+
+We can use the standard diffuser pipeline:
+
+#### 4-step generation 
+
+```.bash
+import torch
+from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+repo_name = "tianweiy/DMD2"
+ckpt_name = "dmd2_sdxl_4step_unet.bin"
+# Load model.
+unet = UNet2DConditionModel.from_config(base_model_id, subfolder="unet").to("cuda", torch.float16)
+unet.load_state_dict(torch.load(hf_hub_download(repo_name, ckpt_name), map_location="cuda"))
+pipe = DiffusionPipeline.from_pretrained(base_model_id, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+prompt="a photo of a cat"
+image=pipe(prompt=prompt, num_inference_steps=4, guidance_scale=0).images[0]
+```
+
+#### 1-step generation 
+
+```.bash
+import torch
+from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+base_model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+repo_name = "tianweiy/DMD2"
+ckpt_name = "dmd2_sdxl_1step_unet.bin"
+# Load model.
+unet = UNet2DConditionModel.from_config(base_model_id, subfolder="unet").to("cuda", torch.float16)
+unet.load_state_dict(torch.load(hf_hub_download(repo_name, ckpt_name), map_location="cuda"))
+pipe = DiffusionPipeline.from_pretrained(base_model_id, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+prompt="a photo of a cat"
+image=pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0, timesteps=[399]).images[0]
+```
+
+For more information, please refer to the [code repository](https://github.com/tianweiy/DMD2)
 
 
 ## License