Add AI Talking Photo (Lip-Sync) feature

Generates lip-synced talking animation from a static face image and given text.

talking_photo.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import requests
+import tempfile
+import os
+
+# Hugging Face API Config
+HF_API_TOKEN = "YOUR_HF_API_KEY"  # Apna token lagao
+MODEL_URL = "https://api-inference.huggingface.co/models/DeepFloyd/face-animator"
+HEADERS = {"Authorization": f"Bearer {HF_API_TOKEN}"}
+
+def generate_talking_photo(image, text):
+    """🖼️ Photo + Text → Lip-Sync Video"""
+    if image is None or not text.strip():
+        return None
+    
+    try:
+        # Save image temporarily
+        temp_img = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
+        image.save(temp_img.name)
+
+        payload = {
+            "inputs": {
+                "image": temp_img.name,
+                "text": text
+            }
+        }
+        files = {"image": open(temp_img.name, "rb")}
+        
+        resp = requests.post(MODEL_URL, headers=HEADERS, files=files, data={"text": text})
+
+        if resp.status_code != 200:
+            print("Error:", resp.text)
+            return None
+
+        # Save video output
+        temp_video = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
+        with open(temp_video.name, "wb") as f:
+            f.write(resp.content)
+
+        return temp_video.name
+    except Exception as e:
+        print(f"Error: {e}")
+        return None
+
+# ---------- Gradio UI ----------
+with gr.Blocks() as demo:
+    gr.Markdown("<h2 style='text-align:center'>🗣️ Talking Photo — SaEdit MultiAi</h2>")
+
+    with gr.Row():
+        img_input = gr.Image(type="pil", label="📷 Upload Face Photo")
+        text_input = gr.Textbox(label="💬 What should they say?", lines=2)
+
+    btn = gr.Button("🎬 Generate Talking Video")
+    video_output = gr.Video(label="🖼️ Talking Animation")
+
+    btn.click(generate_talking_photo, inputs=[img_input, text_input], outputs=video_output)
+
+if __name__ == "__main__":
+    demo.launch()