Update app.py

app.py

@@ -3,7 +3,7 @@ import gradio as gr
 from PIL import Image
 from transformers import BlipProcessor, BlipForConditionalGeneration, pipeline
 
-# Initialize BLIP for image captioning (slow mode avoids torchvision dependency)
+# Load BLIP for image captioning (slow processor, no torchvision dependency)
 blip_processor = BlipProcessor.from_pretrained(
     "Salesforce/blip-image-captioning-base",
     use_fast=False
@@ -12,20 +12,24 @@ blip_model = BlipForConditionalGeneration.from_pretrained(
     "Salesforce/blip-image-captioning-base"
 )
 
-# Flan-T5-small pipelines (temperature=1 for diversity, max_new_tokens increased for depth)
-gen_pipeline = lambda model_name, tokens: pipeline(
-    "text2text-generation",
-    model=model_name,
-    tokenizer=model_name,
-    max_new_tokens=tokens,
-    do_sample=True,
-    temperature=1.0
-)
-category_generator = gen_pipeline("google/flan-t5-small", 100)
-analysis_generator = gen_pipeline("google/flan-t5-small", 500)
-suggestion_generator = gen_pipeline("google/flan-t5-small", 500)
+# Helper to create Flan-T5 pipelines (temperature=1.0 for diversity)
+def make_pipeline(model_name, max_tokens):
+    return pipeline(
+        "text2text-generation",
+        model=model_name,
+        tokenizer=model_name,
+        max_new_tokens=max_tokens,
+        do_sample=True,
+        temperature=1.0
+    )
+
+# Pipelines: category, analysis, suggestions
+category_generator = make_pipeline("google/flan-t5-small", 100)
+analysis_generator = make_pipeline("google/flan-t5-small", 500)
+suggestion_generator = make_pipeline("google/flan-t5-small", 500)
+
+# Example ads URLs for gallery
 
-# Example URLs for gallery
 def get_recommendations():
     return [
         "https://i.imgur.com/InC88PP.jpeg",
@@ -40,26 +44,23 @@ def get_recommendations():
         "https://i.imgur.com/Xj92Cjv.jpeg",
     ]
 
-# Step 1: BLIP caption from image
+# Step 1: BLIP generates a caption from the image
 def generate_caption(image):
     inputs = blip_processor(images=image, return_tensors="pt")
     outputs = blip_model.generate(**inputs)
     return blip_processor.decode(outputs[0], skip_special_tokens=True)
 
-# Step 2: Flan interprets caption into a category label
+# Step 2: Flan interprets caption into a concise category label
 def generate_category(caption):
-    prompt = (
-        f"Caption: {caption}\n"
-        "Provide a concise category label for this ad (e.g. 'Food Ad', 'Fitness Promotion')."
-    )
+    prompt = f"Caption: {caption}\nProvide a concise category label for this ad."
     raw = category_generator(prompt)[0]["generated_text"].strip()
     return raw.splitlines()[0]
 
-# Step 3: Flan produces a five-sentence analysis of the caption
+# Step 3: Flan writes exactly five sentences of analysis
 def generate_analysis(caption):
     prompt = (
         f"Caption: {caption}\n"
-        "Write exactly five sentences explaining what the ad conveys, its core message, and its emotional impact."
+        "In exactly five sentences, explain what this ad communicates and its emotional impact."
     )
     raw = analysis_generator(prompt)[0]["generated_text"].strip()
     sentences = re.split(r'(?<=[.!?])\s+', raw)
@@ -69,18 +70,18 @@ def generate_analysis(caption):
 def generate_suggestions(caption):
     prompt = (
         f"Caption: {caption}\n"
-        "Suggest five distinct improvements for this ad as a bullet list. "
-        "Each line must start with '- ' and describe one actionable change."
+        "Suggest five distinct improvements as bullet points. "
+        "Each line must start with '- '."
     )
     raw = suggestion_generator(prompt)[0]["generated_text"].strip()
     lines = [line for line in raw.splitlines() if line.strip().startswith('- ')]
-    # ensure exactly five bullets
     if len(lines) < 5:
-        fallback = [line for line in raw.splitlines() if line.strip()]
-        lines = ['- ' + fallback[i] if not fallback[i].startswith('- ') else fallback[i] for i in range(min(5, len(fallback)))]
+        all_lines = [l.strip() for l in raw.splitlines() if l.strip()]
+        lines = [('- ' + all_lines[i]) if not all_lines[i].startswith('- ') else all_lines[i] for i in range(min(5, len(all_lines)))]
     return "\n".join(lines[:5])
 
-# Full workflow
+# Combine steps into one process
+
 def process(image):
     caption = generate_caption(image)
     category = generate_category(caption)
@@ -89,11 +90,11 @@ def process(image):
     recs = get_recommendations()
     return category, analysis, suggestions, recs
 
-# Gradio UI
+# Gradio UI layout
 with gr.Blocks(theme=gr.themes.Default(primary_hue="blue")) as demo:
     gr.Markdown("## 📢 Smart Ad Analyzer")
     gr.Markdown(
-        "Upload an image ad to see: a category, five-sentence analysis, five bullet-point improvements, and example ads."
+        "Upload an image ad to see an Ad Category, a five-sentence Analysis, five bullet-point Suggestions, and Example Ads."
     )
 
     with gr.Row():