Update app.py

app.py

@@ -1,154 +1,118 @@
-import gradio as gr
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+# !pip install -q gTTS
+# !pip install -qU "google-genai==1.9.0"
+
+
+# In[3]:
+
+
 import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
+import pandas as pd
+import os
+
+from google import genai
+from google.genai import types
+from IPython.display import display, Image, Markdown, Audio
+from IPython.display import display, Image as IPImage
+from gtts import gTTS
+import IPython.display as ipd
+from PIL import Image as PILImage
+import io
+
+
+# In[4]:
+
+
+GOOGLE_API_KEY = "AIzaSyDuMuSDMX4A33NYki7lgs6x13uxbHirMQk"  # Replace with your key
+client = genai.Client(api_key=GOOGLE_API_KEY)
+
+
+# In[ ]:
+
+
+#!pip install google.api_core
+
+
+# In[8]:
+
+
+from google.api_core import retry
+
+is_retriable = lambda e: (isinstance(e, genai.errors.APIError) and e.code in {429, 503})
+genai.models.Models.generate_content = retry.Retry(
+    predicate=is_retriable
+)(genai.models.Models.generate_content)
+
+
+# In[10]:
+
+
+# Prompt for user input
+user_prompt = input("Enter your prompt: ")
+
+# Request image generation
+generation_response = client.models.generate_content(
+    model="gemini-2.0-flash-exp-image-generation",
+    contents=user_prompt,
+    config=types.GenerateContentConfig(
+        response_modalities=['text', 'image']
+    )
+)
+
+# Process and display the image
+image_bytes = None
+for part in generation_response.candidates[0].content.parts:
+    if part.text:
+        print(part.text)
+    elif part.inline_data:
+        image_bytes = part.inline_data.data
+        display(Image(image_bytes))
+
+
+# In[11]:
+
+
+if image_bytes:
+    pil_image = PILImage.open(io.BytesIO(image_bytes))
+
+    vision_prompt = [
+        "What is in this image? Describe it in detail.",
+        pil_image
+    ]
+
+    vision_response = client.models.generate_content(
+        model='gemini-2.0-flash',
+        contents=vision_prompt
     )
 
-if __name__ == "__main__":
-    demo.launch()
+    display(Markdown("### 🖼️ Image Description:"))
+    display(Markdown(vision_response.text))
+
+
+# In[12]:
+
+
+language = 'en'  # ← change here if you want different language
+
+image_description_text = vision_response.text
+
+tts = gTTS(text=image_description_text, lang=language)
+tts.save("description.mp3")
+
+display(Markdown("### 📝 Image Description (Text):"))
+display(Markdown(image_description_text))
+
+display(Markdown("### 🔊 Image Description (Audio):"))
+ipd.display(ipd.Audio("description.mp3"))
+
+
+# In[ ]:
+
+
+
+