Update app.py

app.py

@@ -1,111 +1,26 @@
-import re
-import gradio as gr
-import torch
-from PIL import Image
-from transformers import (
-    pipeline,
-    AutoProcessor,
-    AutoModelForVision2Seq,
-    AutoTokenizer,
-    AutoModelForSeq2SeqLM,
-)
-
-# Auto-detect CPU/GPU
-DEVICE = 0 if torch.cuda.is_available() else -1
-
-# Load BLIP captioning model
-processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-blip_model = AutoModelForVision2Seq.from_pretrained("Salesforce/blip-image-captioning-large")
-caption_pipe = pipeline(
-    task="image-to-text",
-    model=blip_model,
-    tokenizer=processor.tokenizer,
-    image_processor=processor.image_processor,
-    device=DEVICE,
-)
-
-# Load Flan-T5 for text-to-text
-FLAN_MODEL = "google/flan-t5-large"
-flan_tokenizer = AutoTokenizer.from_pretrained(FLAN_MODEL)
-flan_model = AutoModelForSeq2SeqLM.from_pretrained(FLAN_MODEL)
-
-category_pipe = pipeline(
-    "text2text-generation",
-    model=flan_model,
-    tokenizer=flan_tokenizer,
-    device=DEVICE,
-    max_new_tokens=32,
-    do_sample=True,
-    temperature=1.0,
-)
-
-analysis_pipe = pipeline(
-    "text2text-generation",
-    model=flan_model,
-    tokenizer=flan_tokenizer,
-    device=DEVICE,
-    max_new_tokens=256,
-    do_sample=True,
-    temperature=1.0,
-)
-
-suggestion_pipe = pipeline(
-    "text2text-generation",
-    model=flan_model,
-    tokenizer=flan_tokenizer,
-    device=DEVICE,
-    max_new_tokens=256,
-    do_sample=True,
-    temperature=1.0,
-)
-
-expansion_pipe = pipeline(
-    "text2text-generation",
-    model=flan_model,
-    tokenizer=flan_tokenizer,
-    device=DEVICE,
-    max_new_tokens=128,
-    do_sample=False,
-)
-
-def get_recommendations():
-    # Returns list of 10 example ad image URLs
-    return [
-        "https://i.imgur.com/InC88PP.jpeg",
-        "https://i.imgur.com/7BHfv4T.png",
-        "https://i.imgur.com/wp3Wzc4.jpeg",
-        "https://i.imgur.com/5e2xOA4.jpeg",
-        "https://i.imgur.com/txjRk98.jpeg",
-        "https://i.imgur.com/rQ4AYl0.jpeg",
-        "https://i.imgur.com/bDzwD04.jpeg",
-        "https://i.imgur.com/fLMngXI.jpeg",
-        "https://i.imgur.com/nYEJzxt.png",
-        "https://i.imgur.com/Xj92Cjv.jpeg",
-    ]
-
 def process(image: Image):
     if image is None:
         return "", "", "", get_recommendations()
 
-    # 1. BLIP caption
+    # 1) BLIP caption
     caption_res = caption_pipe(image, max_new_tokens=64)
     raw_caption = caption_res[0]["generated_text"].strip()
 
-    # 1a. Expand caption if too short
+    # 1a) Expand caption if too short
     if len(raw_caption.split()) < 3:
         exp = expansion_pipe(f"Expand into a detailed description: {raw_caption}")
         desc = exp[0]["generated_text"].strip()
     else:
         desc = raw_caption
 
-    # 2. Category
+    # 2) Category
     cat_prompt = (
         f"Description: {desc}\n\n"
         "Provide a concise category label for this ad (e.g. 'Food', 'Fitness'):"
     )
     cat_out = category_pipe(cat_prompt)[0]["generated_text"].splitlines()[0].strip()
 
-    # 3. Five-sentence analysis
+    # 3) Five-sentence analysis
     ana_prompt = (
         f"Description: {desc}\n\n"
         "Write exactly five sentences explaining what this ad communicates and its emotional impact."
@@ -114,10 +29,10 @@ def process(image: Image):
     sentences = re.split(r'(?<=[.!?])\s+', ana_raw)
     analysis = " ".join(sentences[:5])
 
-    # 4. Five bullet-point suggestions (unique only)
+    # 4) Five bullet-point suggestions, filter for unique & not empty
     sug_prompt = (
         f"Description: {desc}\n\n"
-        "Suggest five unique, practical improvements for this ad. Each must address a different aspect (message, visuals, call-to-action, targeting, layout, or design). Each suggestion must be one sentence and start with '- '. Do NOT repeat suggestions."
+        "Suggest five unique, practical improvements for this ad. Each must address a different aspect (such as message, visuals, CTA, targeting, layout, or design). Each suggestion must be only one sentence and start with '- '. Do NOT repeat suggestions."
     )
     sug_raw = suggestion_pipe(sug_prompt)[0]["generated_text"].strip()
     bullets = []
@@ -136,7 +51,7 @@ def process(image: Image):
                 seen.add(suggestion)
         if len(bullets) == 5:
             break
-    # Add non-repetitive defaults if needed
+    # Add defaults if needed
     defaults = [
         "- Make the main headline more eye-catching.",
         "- Add a clear and visible call-to-action button.",
@@ -150,39 +65,3 @@ def process(image: Image):
     suggestions = "\n".join(bullets[:5])
 
     return cat_out, analysis, suggestions, get_recommendations()
-
-def main():
-    with gr.Blocks(title="Smart Ad Analyzer") as demo:
-        gr.Markdown("## 📢 Smart Ad Analyzer")
-        gr.Markdown(
-            """
-            **Upload your ad image below and instantly get expert feedback.**
-
-            This AI tool will analyze your ad and provide:
-            - 📂 **Category** — What type of ad is this?
-            - 📊 **In-depth Analysis** — Five detailed sentences covering message, visuals, emotional impact, and more.
-            - 🚀 **Improvement Suggestions** — Five actionable, unique ways to make your ad better.
-            - 📸 **Inspiration Gallery** — See other effective ads for ideas.
-
-            Perfect for marketers, founders, designers, and anyone looking to boost ad performance with actionable insights!
-            """
-        )
-        with gr.Row():
-            inp = gr.Image(type='pil', label='Upload Ad Image')
-            with gr.Column():
-                cat_out = gr.Textbox(label='📂 Ad Category', interactive=False)
-                ana_out = gr.Textbox(label='📊 Ad Analysis', lines=5, interactive=False)
-                sug_out = gr.Textbox(label='🚀 Improvement Suggestions', lines=5, interactive=False)
-                btn = gr.Button('Analyze Ad', variant='primary')
-        gallery = gr.Gallery(label='Example Ads')
-        btn.click(
-            fn=process,
-            inputs=[inp],
-            outputs=[cat_out, ana_out, sug_out, gallery],
-        )
-        gr.Markdown('Made by Simon Thalmay')
-    return demo
-
-if __name__ == "__main__":
-    demo = main()
-    demo.launch()