Update app.py

app.py

@@ -6,6 +6,7 @@ import subprocess
 import gradio as gr
 import uuid
 from dotenv import load_dotenv
+from urllib.parse import urlparse
 
 # Load environment variables
 load_dotenv()
@@ -15,6 +16,7 @@ B_KEY = os.getenv("B_KEY")
 
 # URLs
 API_URL = os.getenv("API_URL")
+UPLOAD_URL = os.getenv("UPLOAD_URL")  # Make sure to add this to your .env file
 
 def lipsync_api_call(video_url, audio_url):
     headers = {
@@ -80,6 +82,45 @@ def combine_audio_video(video_path, audio_path, output_path):
 
     subprocess.run(cmd, check=True)
 
+def is_image_url(url):
+    parsed = urlparse(url)
+    path = parsed.path.lower()
+    return path.endswith(('.png', '.jpg', '.jpeg', '.gif', '.bmp'))
+
+def create_video_from_image(image_url, output_path, duration=10):
+    # Download the image
+    response = requests.get(image_url)
+    if response.status_code != 200:
+        raise Exception("Failed to download the image")
+    
+    temp_image_path = f"temp_image_{uuid.uuid4()}.jpg"
+    with open(temp_image_path, 'wb') as f:
+        f.write(response.content)
+    
+    # Create a 10-second video from the image
+    cmd = [
+        'ffmpeg', '-loop', '1', '-i', temp_image_path,
+        '-c:v', 'libx264', '-t', str(duration), '-pix_fmt', 'yuv420p',
+        '-vf', 'scale=1920:1080:force_original_aspect_ratio=decrease,pad=1920:1080:(ow-iw)/2:(oh-ih)/2',
+        '-y', output_path
+    ]
+    subprocess.run(cmd, check=True)
+    
+    # Clean up the temporary image file
+    os.remove(temp_image_path)
+    
+    return output_path
+
+def upload_file(file_path):
+    with open(file_path, 'rb') as file:
+        files = {'fileToUpload': (os.path.basename(file_path), file)}
+        data = {'reqtype': 'fileupload'}
+        response = requests.post(UPLOAD_URL, files=files, data=data)
+    
+    if response.status_code == 200:
+        return response.text.strip()
+    return None
+
 def process_video(video_url, audio_url, progress=gr.Progress()):
     if not audio_url:
         return None, "No audio URL provided"
@@ -88,10 +129,20 @@ def process_video(video_url, audio_url, progress=gr.Progress()):
         
     session_id = str(uuid.uuid4())
     
-    progress(0.2, desc="Processing video...")
+    progress(0.2, desc="Processing media...")
     
     try:
-        progress(0.4, desc="Initiating lipsync...")
+        if is_image_url(video_url):
+            progress(0.3, desc="Converting image to video...")
+            video_path = f"temp_video_{session_id}.mp4"
+            create_video_from_image(video_url, video_path)
+            progress(0.4, desc="Uploading converted video...")
+            video_url = upload_file(video_path)
+            if not video_url:
+                raise Exception("Failed to upload converted video")
+            os.remove(video_path)
+        
+        progress(0.5, desc="Initiating lipsync...")
         job_data = lipsync_api_call(video_url, audio_url)
         
         if "error" in job_data or "message" in job_data:
@@ -99,7 +150,7 @@ def process_video(video_url, audio_url, progress=gr.Progress()):
         
         job_id = job_data["id"]
         
-        progress(0.5, desc="Processing lipsync...")
+        progress(0.6, desc="Processing lipsync...")
         result_url = check_job_status(job_id)
         
         if result_url:
@@ -142,7 +193,7 @@ def create_interface():
         gr.Markdown("# JSON 2")
         with gr.Row():
             with gr.Column():
-                video_url_input = gr.Textbox(label="Video URL")
+                video_url_input = gr.Textbox(label="Video or Image URL")
                 audio_url_input = gr.Textbox(label="Audio URL")
                 generate_btn = gr.Button("Generate Video")
             with gr.Column():