Update app.py

app.py

@@ -39,90 +39,48 @@
 
 
 
-# # Text to 3D
-
-# import streamlit as st
-# import torch
-# from diffusers import ShapEPipeline
-# from diffusers.utils import export_to_gif
-# from PIL import Image
-# import numpy as np
-# # import PyTorch
-
-# # Model loading (Ideally done once at the start for efficiency)
-# ckpt_id = "openai/shap-e"  
-
-# @st.cache_resource  # Caches the model for faster subsequent runs
-
-# def process_image_for_pil(image): 
-#     if isinstance(image, torch.Tensor):   
-#         # Your PyTorch conversion logic here (with correct indentation)
-#     # elif isinstance(image, np.ndarray):   
-#         # Your Numpy conversion logic here (with correct indentation)
-#         image_array = image.astype('uint8')  # Assuming 8-bit conversion is needed
-#         return Image.fromarray(image_array) 
-#     else: 
-#         raise TypeError("Unsupported image format. Please provide conversion logic.")
-
-# test_image = np.random.randint(0, 256, size=(256, 256, 3), dtype=np.uint8)  # Placeholder image  
-# result = process_image_for_pil(test_image)
-
-
+# Text to 3D
 
+import streamlit as st
+import torch
+from diffusers import ShapEPipeline
+from diffusers.utils import export_to_gif
+from PIL import Image
+import numpy as np
+# import PyTorch
 
+# Model loading (Ideally done once at the start for efficiency)
+ckpt_id = "openai/shap-e"  
 
-# def should_resize(image):  # Add 'image' as an argument
-#     """Determines whether to resize images (replace with your own logic)"""
-#     if image.width > 512 or image.height > 512: 
-#         return True   
-#     else:
-#         return False  
-# def load_model():    
-#     return ShapEPipeline.from_pretrained(ckpt_id).to("cuda")  
+@st.cache_resource  # Caches the model for faster subsequent runs
 
-# pipe = load_model()
+def process_image_for_pil(image): 
+    if isinstance(image, torch.Tensor):   
+        # Your PyTorch conversion logic here (with correct indentation)
+    # elif isinstance(image, np.ndarray):   
+        # Your Numpy conversion logic here (with correct indentation)
+        image_array = image.astype('uint8')  # Assuming 8-bit conversion is needed
+        return Image.fromarray(image_array) 
+    else: 
+        raise TypeError("Unsupported image format. Please provide conversion logic.")
 
-# # App Title
-# st.title("Shark 3D Image Generator")
+test_image = np.random.randint(0, 256, size=(256, 256, 3), dtype=np.uint8)  # Placeholder image  
+result = process_image_for_pil(test_image)
 
-# # User Inputs
-# prompt = st.text_input("Enter your prompt:", "a shark")
-# guidance_scale = st.slider("Guidance Scale", 0.0, 20.0, 15.0, step=0.5)
 
-# # Generate and Display Images 
-# if st.button("Generate"):
-#     with st.spinner("Generating images..."):
-#         images = pipe(prompt, guidance_scale=guidance_scale, num_inference_steps=64).images
 
-#         # ... (Process images for PIL conversion)
 
-#         # Resize Images (Optional)
-#         pil_images = []  # Modified to store resized images if needed
-#         for image in images:
-#             processed_image = process_image_for_pil(image)
-#             if should_resize(processed_image):  # Pass image to should_resize
-#                 resized_image = processed_image.resize((256, 256))
-#                 pil_images.append(resized_image) 
-#             else:
-#                 pil_images.append(processed_image)  # Append without resizing
 
-#         gif_path = export_to_gif(pil_images, "shark_3d.gif")
-#         st.image(pil_images[0]) 
-#         st.success("GIF saved as shark_3d.gif")
-
-import streamlit as st
-import torch
-from diffusers import StableDiffusionPipeline
-from diffusers.utils import export_to_gif
-from PIL import Image
-import numpy as np 
+def should_resize(image):  # Add 'image' as an argument
+    """Determines whether to resize images (replace with your own logic)"""
+    if image.width > 512 or image.height > 512: 
+        return True   
+    else:
+        return False  
+def load_model():    
+    return ShapEPipeline.from_pretrained(ckpt_id).to("cuda")  
 
-# Model loading 
-ckpt_id = "openai/shap-e"
-@st.cache_resource
-def load_model():
-    return StableDiffusionPipeline.from_pretrained(ckpt_id, torch_dtype=torch.float16, use_auth_token=True).to("cuda")  
-pipe = load_model()  # Load the model 
+pipe = load_model()
 
 # App Title
 st.title("Shark 3D Image Generator")
@@ -131,26 +89,26 @@ st.title("Shark 3D Image Generator")
 prompt = st.text_input("Enter your prompt:", "a shark")
 guidance_scale = st.slider("Guidance Scale", 0.0, 20.0, 15.0, step=0.5)
 
-def should_resize(image): 
-    if image.width > 512 or image.height > 512: 
-        return True   
-    else:
-        return False 
+# Generate and Display Images 
+if st.button("Generate"):
+    with st.spinner("Generating images..."):
+        images = pipe(prompt, guidance_scale=guidance_scale, num_inference_steps=64).images
 
-# Generate and Display Images
-if st.button("Generate"):        
-    with st.spinner("Generating images..."): 
-        images = pipe(prompt, guidance_scale=guidance_scale, num_inference_steps=64).images 
+        # ... (Process images for PIL conversion)
 
-        pil_images = [] 
+        # Resize Images (Optional)
+        pil_images = []  # Modified to store resized images if needed
         for image in images:
-            # ***Insert image conversion logic here*** 
+            processed_image = process_image_for_pil(image)
+            if should_resize(processed_image):  # Pass image to should_resize
+                resized_image = processed_image.resize((256, 256))
+                pil_images.append(resized_image) 
+            else:
+                pil_images.append(processed_image)  # Append without resizing
+
+        gif_path = export_to_gif(pil_images, "shark_3d.gif")
+        st.image(pil_images[0]) 
+        st.success("GIF saved as shark_3d.gif")
 
-            if should_resize(image): 
-                image = image.resize((256, 256))                
-            pil_images.append(image) 
 
-        gif_path = export_to_gif(pil_images, "shark_3d.gif")         
-        st.image(pil_images[0])          
-        st.success("GIF saved as shark_3d.gif")