Update app.py

app.py

@@ -7,13 +7,19 @@ import spaces
 import gradio as gr
 
 from diffusers import AutoPipelineForText2Image
+from transformers import CLIPVisionModelWithProjection
 from diffusers.utils import load_image
 from torchvision import transforms
 
 device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
 dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=dtype, device_map="balanced")
-pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    "h94/IP-Adapter",
+    subfolder="models/image_encoder",
+    torch_dtype=dtype
+)
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0",image_encoder=image_encoder, torch_dtype=dtype).to(device)
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter-plus_sdxl_vit-h.safetensors")
 
 def prepare_image(image_path_or_url):
     # Load the image