Create app.py

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+from PIL import Image
+
+# 1. Initialize the Image-to-Text pipeline
+# This will download the model (approx 900MB) on the first run
+get_prompt = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+
+def generate_prompt(input_img):
+    if input_img is None:
+        return "Please upload an image."
+    try:
+        # 2. Process the image
+        result = get_prompt(input_img)
+        # The model returns a list: [{'generated_text': 'a prompt description'}]
+        return result[0]['generated_text']
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# 3. Build the Interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🔍 Image to Prompt Interrogator")
+    with gr.Row():
+        img_input = gr.Image(type="pil", label="Upload Image")
+        text_output = gr.Textbox(label="Generated AI Prompt", interactive=False, show_copy_button=True)
+    
+    btn = gr.Button("Analyze Image", variant="primary")
+    
+    # Declare API name for the blog
+    btn.click(fn=generate_prompt, inputs=img_input, outputs=text_output, api_name="get_prompt")
+
+# 4. Launch with stable network settings
+if __name__ == "__main__":
+    demo.queue(default_concurrency_limit=1).launch(server_name="0.0.0.0", server_port=7860, ssr_mode=False)