Update app.py

app.py

@@ -3,45 +3,30 @@ from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
 from diffusers.utils import export_to_video
 import streamlit as st
 import numpy as np 
+
 # Title and User Input
 st.title("Text-to-Video with Streamlit")
 prompt = st.text_input("Enter your text prompt:", "Spiderman is surfing")
 
 # Button to trigger generation
-
-if st.button("Generate Video"):
-    # Ensure you have 'accelerate' version 0.17.0 or higher
+if st.button("Generate Video"):  
+    # Ensure you have 'accelerate' version 0.17.0 or higher 
     import accelerate 
     if accelerate.__version__ < "0.17.0":
         st.warning("Please upgrade 'accelerate' to version 0.17.0 or higher for CPU offloading.")
     else:
         with st.spinner("Generating video..."):
-            pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b",     
-                                          torch_dtype=torch.float16,                                          
-                                          variant="fp16",                                         
-                                          device="cpu") # Force CPU usage
-            pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-            pipe.enable_model_cpu_offload()  # Assuming 'accelerate' is updated  
+            # ... (Your model loading code)
 
-              
-            
             video_frames = pipe(prompt, num_inference_steps=25).frames  
 
-            # # Reshape for export (assuming your frames have a time dimension)
-            # video_frames = [np.transpose(frame, (1, 2, 0)) for frame in video_frames]  # Swap time and channels axes
-
-            # # Check and adjust axes if needed
-            # for i, frame in enumerate(video_frames):
-            #     if len(frame.shape) == 3:  # Assuming (height, width, channels) format
-            #         video_frames[i] = np.transpose(frame, (1, 0, 2))  # Swap height and width
-
+            # ... (Your potential reshaping code)
 
-            # video_path = export_to_video(video_frames)
-            dummy_frames = [np.ones((256, 256, 3), dtype=np.uint8) for _ in range(20)]  # Example (256x256 RGB images)
+            # Create dummy frames for testing 
+            dummy_frames = [np.ones((256, 256, 3), dtype=np.uint8) for _ in range(20)]  
 
-# Replace with your actual export logic
-video_path = export_to_video(dummy_frames)
+            # Replace with your actual export logic
+            video_path = export_to_video(dummy_frames)
 
-      # Display the video in the Streamlit app            
-st.video(video_path)                      
-               
+            # Display the video in the Streamlit app  
+            st.video(video_path)