Update app.py

app.py

@@ -8,6 +8,22 @@ from diffusers import DiffusionPipeline
 import torch
 import spaces  # Hugging Face Spaces module
 
+import requests
+
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+
+img_url = 'https://huggingface.co/spaces/noamrot/FuseCap/resolve/main/bike.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+text = "a picture of "
+inputs = processor(raw_image, text, return_tensors="pt").to(device)
+
+out = model.generate(**inputs, num_beams = 3)
+print(processor.decode(out[0], skip_special_tokens=True))
+
+
 
 
 
@@ -22,13 +38,14 @@ login(token=hf_token)
 # Load the processor and model
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+processor1 = BlipProcessor.from_pretrained("noamrot/FuseCap")
+model2 = BlipForConditionalGeneration.from_pretrained("noamrot/FuseCap")
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium")
 
 
-
-pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium")
 device = "cuda" if torch.cuda.is_available() else "cpu"
 pipe.to(device)
-
+model2.to(device)
 model.to(device)
 
 
@@ -50,9 +67,14 @@ def generate_caption_and_image(image):
     selected_fabric = random.choice(fabrics)
     selected_pattern = random.choice(patterns)
     selected_textile_design = random.choice(textile_designs)
+    text = "a picture of "
+    inputs = processor(img, text, return_tensors="pt").to(device)
+    
+    out = model.generate(**inputs, num_beams = 3)
+   
+    
 
-
-    caption2 =""
+    caption2 = processor.decode(out[0], skip_special_tokens=True)
     
     # Generate caption
     inputs = processor(image, return_tensors="pt", padding=True, truncation=True, max_length=250)