Update app.py

app.py

@@ -1,15 +1,14 @@
+# app.py
+
 import re
 import gradio as gr
 from PIL import Image
-from transformers import BlipProcessor, BlipForConditionalGeneration, pipeline
+from transformers import pipeline
 
-# Load BLIP for image captioning (slow processor, no torchvision dependency)
-blip_processor = BlipProcessor.from_pretrained(
-    "Salesforce/blip-image-captioning-base",
-    use_fast=False
-)
-blip_model = BlipForConditionalGeneration.from_pretrained(
-    "Salesforce/blip-image-captioning-base"
+# Use ChatDOC/OCRFlux-3B for image-to-text instead of BLIP
+image_to_text = pipeline(
+    "image-to-text",
+    model="ChatDOC/OCRFlux-3B"
 )
 
 # Helper to create Flan-T5 pipelines (temperature=1.0 for diversity)
@@ -24,12 +23,11 @@ def make_pipeline(model_name, max_tokens):
     )
 
 # Pipelines: category, analysis, suggestions
-category_generator = make_pipeline("google/flan-t5-small", 100)
-analysis_generator = make_pipeline("google/flan-t5-small", 500)
+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
-
 def get_recommendations():
     return [
         "https://i.imgur.com/InC88PP.jpeg",
@@ -44,11 +42,10 @@ def get_recommendations():
         "https://i.imgur.com/Xj92Cjv.jpeg",
     ]
 
-# Step 1: BLIP generates a caption from the image
+# Step 1: Use OCRFlux to get a detailed textual description of 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)
+    result = image_to_text(image)
+    return result[0]["generated_text"].strip()
 
 # Step 2: Flan interprets caption into a concise category label
 def generate_category(caption):
@@ -74,36 +71,39 @@ def generate_suggestions(caption):
         "Each line must start with '- '."
     )
     raw = suggestion_generator(prompt)[0]["generated_text"].strip()
-    lines = [line for line in raw.splitlines() if line.strip().startswith('- ')]
+    lines = [l for l in raw.splitlines() if l.strip().startswith('- ')]
     if len(lines) < 5:
         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)))]
+        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])
 
-# Combine steps into one process
-
+# Full workflow
 def process(image):
-    caption = generate_caption(image)
-    category = generate_category(caption)
-    analysis = generate_analysis(caption)
+    caption     = generate_caption(image)
+    category    = generate_category(caption)
+    analysis    = generate_analysis(caption)
     suggestions = generate_suggestions(caption)
-    recs = get_recommendations()
+    recs        = get_recommendations()
     return category, analysis, suggestions, recs
 
-# Gradio UI layout
+# Gradio UI
 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 an Ad Category, a five-sentence Analysis, five bullet-point Suggestions, 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():
         image_input = gr.Image(type="pil", label="Upload Ad Image")
         with gr.Column():
-            category_out = gr.Textbox(label="Ad Category", interactive=False)
-            analysis_out = gr.Textbox(label="Ad Analysis", lines=5, interactive=False)
+            category_out   = gr.Textbox(label="Ad Category", interactive=False)
+            analysis_out   = gr.Textbox(label="Ad Analysis", lines=5, interactive=False)
             suggestion_out = gr.Textbox(label="Improvement Suggestions", lines=5, interactive=False)
-            btn = gr.Button("Analyze Ad", size="sm", variant="primary")
+            btn            = gr.Button("Analyze Ad", size="sm", variant="primary")
 
     recommendation_gallery = gr.Gallery(label="Recommended Example Ads", show_label=True)
 
@@ -116,4 +116,4 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue")) as demo:
     gr.Markdown("Made by Simon Thalmay")
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()