Update app.py

app.py

@@ -10,7 +10,7 @@ os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
 
 device='cpu'
 
-model_id = "nttdataspain/vit-gpt2-coco-lora"
+model_id = "nttdataspain/vit-gpt2-stablediffusion2-lora"
 model = VisionEncoderDecoderModel.from_pretrained(model_id)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 feature_extractor = ViTFeatureExtractor.from_pretrained(model_id)
@@ -37,10 +37,15 @@ with gr.Blocks() as demo:
     gr.HTML(
         """
         <div style="text-align: center; max-width: 1200px; margin: 20px auto;">
-        <h1 style="font-weight: 900; font-size: 3rem; margin: 0rem">
-            Bild zu text - Lass Dir Dein Bild beschreiben 📝
-        </h1>   
+        <h2 style="font-weight: 900; font-size: 3rem; margin: 0rem">
+            📸 ViT Image-to-Text with LORA 📝
+        </h2>   
         <h2 style="text-align: left; font-weight: 450; font-size: 1rem; margin-top: 2rem; margin-bottom: 1.5rem">
+        In the field of large language models, the challenge of fine-tuning has long perplexed researchers. Microsoft, however, has unveiled an innovative solution called <b>Low-Rank Adaptation (LoRA)</b>. With the emergence of behemoth models like GPT-3 boasting billions of parameters, the cost of fine-tuning them for specific tasks or domains has become exorbitant.
+        <br>
+        <br>
+        You can find more info here: <u><a href="https://medium.com/@daniel.puenteviejo/fine-tuning-image-to-text-algorithms-with-lora-deb22aa7da27" target="_blank">Medium article</a></u>
+        </h2>
         </div>
         """)