Update app.py

app.py

@@ -1,41 +1,36 @@
-# app.py
-import os
-import torch
-import gradio as gr
-from PIL import Image
-from transformers import BlipProcessor, BlipForConditionalGeneration
-
-# Placeholder for MiniGPT-4 (use real model if you have GPU)
-class MiniGPT4:
-    def __init__(self):
-        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-        self.model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(self.device)
-
-    def chat(self, image, prompt=""):
-        if image is None:
-            return "Please upload an image."
-        inputs = self.processor(images=image, return_tensors="pt").to(self.device)
-        out = self.model.generate(**inputs, max_new_tokens=75)
-        caption = self.processor.decode(out[0], skip_special_tokens=True)
-        return f"{prompt}\n\nImage description: {caption}"
-
-# Initialize model
-minigpt4 = MiniGPT4()
-
-def respond(image, prompt):
-    return minigpt4.chat(image, prompt)
-
-demo = gr.Interface(
-    fn=respond,
-    inputs=[
-        gr.Image(type="pil", label="Upload an Image"),
-        gr.Textbox(lines=2, placeholder="Ask something about the image...", label="Your Prompt")
-    ],
-    outputs=gr.Textbox(label="MiniGPT-4 Response"),
-    title="MiniGPT-4 Chat (Image + Text)",
-    description="Upload an image and ask a question. The model will respond based on image and prompt."
-)
-
-if __name__ == "__main__":
-    demo.launch()
+# app.py
+import torch
+import gradio as gr
+from PIL import Image
+from transformers import Blip2Processor, Blip2ForConditionalGeneration
+
+class MiniGPT4Lite:
+    def __init__(self):
+        self.device = torch.device("cpu")  # Force CPU for Hugging Face Space
+        self.processor = Blip2Processor.from_pretrained("Salesforce/blip2-flan-t5-xl")
+        self.model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-flan-t5-xl").to(self.device)
+
+    def chat(self, image, prompt="What is in this image?"):
+        inputs = self.processor(images=image, text=prompt, return_tensors="pt").to(self.device)
+        out = self.model.generate(**inputs, max_new_tokens=100)
+        return self.processor.tokenizer.decode(out[0], skip_special_tokens=True)
+
+# Initialize model
+minigpt = MiniGPT4Lite()
+
+def respond(image, prompt):
+    return minigpt.chat(image, prompt)
+
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Image(type="pil", label="Upload an Image"),
+        gr.Textbox(lines=2, placeholder="Ask a question about the image...", label="Prompt")
+    ],
+    outputs=gr.Textbox(label="MiniGPT-4 Lite Response"),
+    title="MiniGPT-4 Lite (CPU)",
+    description="Upload an image and ask a question. Powered by BLIP-2 + Flan-T5. Works on CPU."
+)
+
+if __name__ == "__main__":
+    demo.launch()