Update app.py

app.py

@@ -2,26 +2,37 @@ import gradio as gr
 import numpy as np
 import random
 
-# import spaces #[uncomment to use ZeroGPU]
+import spaces #[uncomment to use ZeroGPU]
 from diffusers import DiffusionPipeline
 import torch
+from diffusers import DiffusionPipeline, UNet2DConditionModel, LCMScheduler
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+
+model_repo_id = "stabilityai/stable-diffusion-xl-base-1.0"
+repo_name = "tianweiy/DMD2"
+ckpt_name = "dmd2_sdxl_4step_unet_fp16.bin"
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
 
+device = "cuda" if torch.cuda.is_available() else "cpu"
 if torch.cuda.is_available():
-    torch_dtype = torch.float16
+    torch_dtype = torch.bfloat16
 else:
     torch_dtype = torch.float32
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
+# Load model.
+unet = UNet2DConditionModel.from_config(model_repo_id, subfolder="unet").to(device, torch_dtype)
+unet.load_state_dict(torch.load(hf_hub_download(repo_name, ckpt_name)))
+pipe = DiffusionPipeline.from_pretrained(model_repo_id, unet=unet, torch_dtype=torch_dtype).to(device)
+pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+
+
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
 
-# @spaces.GPU #[uncomment to use ZeroGPU]
+@spaces.GPU #[uncomment to use ZeroGPU]
 def infer(
     prompt,
     negative_prompt,
@@ -38,6 +49,7 @@ def infer(
 
     generator = torch.Generator().manual_seed(seed)
 
+    # with network:
     image = pipe(
         prompt=prompt,
         negative_prompt=negative_prompt,
@@ -151,4 +163,4 @@ with gr.Blocks(css=css) as demo:
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()