npcpy 1.0.26__py3-none-any.whl → 1.2.32__py3-none-any.whl

npcpy/gen/video_gen.py

@@ -16,7 +16,7 @@ def generate_video_diffusers(
     import os 
     import cv2
 
-    # Load pipeline
+    
     pipe = DiffusionPipeline.from_pretrained(
         "damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float32
     ).to(device)
@@ -32,7 +32,7 @@ def generate_video_diffusers(
 
     def save_frames_to_video(frames, output_path, fps=8):
         """Handle the specific 5D array format (1, num_frames, H, W, 3) with proper type conversion"""
-        # Verify input format
+        
         if not (
             isinstance(frames, np.ndarray)
             and frames.ndim == 5
@@ -42,20 +42,20 @@ def generate_video_diffusers(
                 f"Unexpected frame format. Expected 5D RGB array, got {frames.shape}"
             )
 
-        # Remove batch dimension and convert to 0-255 uint8
-        frames = (frames[0] * 255).astype(np.uint8)  # Shape: (num_frames, H, W, 3)
+        
+        frames = (frames[0] * 255).astype(np.uint8)  
 
-        # Get video dimensions
+        
         height, width = frames.shape[1:3]
 
-        # Create video writer
+        
         fourcc = cv2.VideoWriter_fourcc(*"mp4v")
         video_writer = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
 
         if not video_writer.isOpened():
             raise IOError(f"Could not open video writer for {output_path}")
 
-        # Write frames (convert RGB to BGR for OpenCV)
+        
         for frame in frames:
             video_writer.write(cv2.cvtColor(frame, cv2.COLOR_RGB2BGR))
 
@@ -68,3 +68,49 @@ def generate_video_diffusers(
         output_path = "~/.npcsh/videos/" + prompt[0:8] + ".mp4"
     save_frames_to_video(output.frames, output_path)
     return output_path
+
+
+
+
+def generate_video_veo3(
+    prompt: str,
+    model: str, 
+    negative_prompt: str = "",
+    output_path: str = "",
+):
+    """
+    Generate video using Google's Veo 3 API with synchronized audio.
+    """
+    import time
+    import os
+    from google import genai
+    from google.genai import types
+    api_key =os.environ.get('GEMINI_API_KEY')
+
+    client = genai.Client(        api_key=api_key)
+    
+    config = types.GenerateVideosConfig()
+    if negative_prompt:
+        config.negative_prompt = negative_prompt
+    
+    operation = client.models.generate_videos(
+        model=model,
+        prompt=prompt,
+        config=config,
+    )
+    
+    while not operation.done:
+        time.sleep(20)
+        operation = client.operations.get(operation)
+    
+    generated_video = operation.result.generated_videos[0]
+    
+    os.makedirs(os.path.expanduser("~/.npcsh/videos/"), exist_ok=True)
+    if output_path == "":
+        safe_prompt = "".join(c for c in prompt[:20] if c.isalnum() or c in (' ', '-', '_')).rstrip()
+        output_path = os.path.expanduser("~/.npcsh/videos/") + safe_prompt.replace(" ", "_") + "_veo3.mp4"
+    
+    client.files.download(file=generated_video.video)
+    generated_video.video.save(output_path)
+    
+    return output_path