Update app.py

app.py

@@ -1,23 +1,28 @@
 import gradio as gr
 from diffusers import StableDiffusionPipeline
 import torch
+from transformers import pipeline
 
-# Load the model (Stable Diffusion XL)
+# 🎨 Load Stable Diffusion model
 pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0")
-pipe.to("cpu")  # CPU mode (free tier compatible)
+pipe.to("cpu")
 
-# Function to generate an image
-def generate_image(prompt):
+# 🗣️ Load Text-to-Speech model
+tts = pipeline("text-to-speech", model="nineninesix/kani-tts-370m")
+
+# Image generation function
+def generate_media(prompt):
     image = pipe(prompt).images[0]
-    return image
+    audio = tts(prompt)
+    return image, (audio["audio"],)
 
-# Gradio interface
+# Gradio UI
 demo = gr.Interface(
-    fn=generate_image,
-    inputs=gr.Textbox(label="Enter your image prompt"),
-    outputs="image",
-    title="Stable Diffusion XL (Free CPU Version)",
-    description="Generate images for free using CPU mode on Hugging Face"
+    fn=generate_media,
+    inputs=gr.Textbox(label="Enter your prompt"),
+    outputs=[gr.Image(label="Generated Image"), gr.Audio(label="AI Voice")],
+    title="AI Image + Voice Generator",
+    description="Generates an image with a matching AI voiceover using Stable Diffusion XL and KaniTTS"
 )
 
 demo.launch()