Update app.py

app.py

@@ -453,6 +453,34 @@ def update_scale(scale):
                 value_index += 1
 
 
+@spaces.GPU()
+def load_pipeline():
+    model_id = "runwayml/stable-diffusion-v1-5"
+    vae_model_id = "runwayml/stable-diffusion-v1-5"
+    vae_folder = "vae"
+    guidance_scale_value = 7.5
+    resadapter_model_name = "resadapter_v2_sd1.5"
+    res_range_min = 128 
+    res_range_max = 1024
+
+
+    torch_dtype = torch.float16
+
+    # torch_dtype = torch.float16
+    pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype).to(device)
+    pipe.vae = AutoencoderKL.from_pretrained(vae_model_id, subfolder=vae_folder, torch_dtype=torch_dtype).to(device)
+    pipe.load_lora_weights(
+        hf_hub_download(repo_id="jiaxiangc/res-adapter", subfolder=resadapter_model_name, filename="pytorch_lora_weights.safetensors"), 
+        adapter_name="res_adapter",
+        ) # load lora weights
+    pipe.set_adapters(["res_adapter"], adapter_weights=[1.0])
+    pipe.unet.load_state_dict(
+        load_file(hf_hub_download(repo_id="jiaxiangc/res-adapter", subfolder=resadapter_model_name, filename="diffusion_pytorch_model.safetensors")),
+        strict=False,
+        ) # load norm weights
+    
+    return pipe
+    
 if __name__ == "__main__":
 
     parser = argparse.ArgumentParser()
@@ -480,17 +508,7 @@ if __name__ == "__main__":
     torch_dtype = torch.float16
 
     # torch_dtype = torch.float16
-    pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype).to(device)
-    pipe.vae = AutoencoderKL.from_pretrained(vae_model_id, subfolder=vae_folder, torch_dtype=torch_dtype).to(device)
-    pipe.load_lora_weights(
-        hf_hub_download(repo_id="jiaxiangc/res-adapter", subfolder=resadapter_model_name, filename="pytorch_lora_weights.safetensors"), 
-        adapter_name="res_adapter",
-        ) # load lora weights
-    pipe.set_adapters(["res_adapter"], adapter_weights=[1.0])
-    pipe.unet.load_state_dict(
-        load_file(hf_hub_download(repo_id="jiaxiangc/res-adapter", subfolder=resadapter_model_name, filename="diffusion_pytorch_model.safetensors")),
-        strict=False,
-        ) # load norm weights
+    pipe = load_pipeline()
 
     inverse_scheduler = DDIMInverseScheduler.from_pretrained(model_id, subfolder="scheduler")
     scheduler = DDIMScheduler.from_pretrained(model_id, subfolder="scheduler")