fix: 🐛 adjust intro markdown text

Signed-off-by: Onuralp SEZER <thunderbirdtr@gmail.com>

app.py

@@ -15,6 +15,40 @@ MASK_ANNOTATOR = sv.MaskAnnotator()
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 VIDEO_TARGET_DIRECTORY = "tmp"
 
+
+INTRO_TEXT = """     
+## PaliGemma 2 Detection with Supervision - Demo
+
+<div style="display: flex; gap: 10px;">
+<a href="https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md">
+    <img src="https://img.shields.io/badge/Github-100000?style=flat&logo=github&logoColor=white" alt="Github">
+</a>
+<a href="https://huggingface.co/blog/paligemma">
+    <img src="https://img.shields.io/badge/Huggingface-FFD21E?style=flat&logo=Huggingface&logoColor=black" alt="Huggingface">
+</a>
+<a href="https://github.com/merveenoyan/smol-vision/blob/main/Fine_tune_PaliGemma.ipynb">
+    <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab">
+</a>
+<a href="https://arxiv.org/abs/2412.03555">
+    <img src="https://img.shields.io/badge/Arvix-B31B1B?style=flat&logo=arXiv&logoColor=white" alt="Paper">
+</a>
+<a href="https://supervision.roboflow.com/">
+    <img src="https://img.shields.io/badge/Supervision-6706CE?style=flat&logo=Roboflow&logoColor=white" alt="Supervision">
+</a>
+</div>
+
+
+PaliGemma 2 is an open vision-language model by Google, inspired by [PaLI-3](https://arxiv.org/abs/2310.09199) and 
+built with open components such as the [SigLIP](https://arxiv.org/abs/2303.15343) 
+vision model and the [Gemma 2](https://arxiv.org/abs/2408.00118) language model. PaliGemma 2 is designed as a versatile 
+model for transfer to a wide range of vision-language tasks such as image and short video caption, visual question 
+answering, text reading, object detection and object segmentation.
+
+This space show how to use PaliGemma 2 for object detection with supervision.
+You can input an image and a text prompt
+"""
+
+
 create_directory(directory_path=VIDEO_TARGET_DIRECTORY)
 model_id = "google/paligemma2-3b-pt-448"
 model = PaliGemmaForConditionalGeneration.from_pretrained(model_id).eval().to(DEVICE)
@@ -33,6 +67,9 @@ def paligemma_detection(input_image, input_text, max_new_tokens):
         result = processor.decode(generation, skip_special_tokens=True)
     return result
 
+
+
+
 def annotate_image(result, resolution_wh, class_names, cv_image):
     
     detections = sv.Detections.from_lmm(
@@ -134,20 +171,7 @@ def process_video(input_video, input_text, class_names, max_new_tokens, progress
     return video_path, results
 
 with gr.Blocks() as app:
-    gr.Markdown("""
-## PaliGemma 2 Detection with Supervision - Demo
-
-[![Github](https://img.shields.io/badge/Github-100000?style=flat&logo=github&logoColor=white)](https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md) [![Huggingface](https://img.shields.io/badge/Huggingface-FFD21E?style=flat&logo=Huggingface&logoColor=black)](https://huggingface.co/blog/paligemma) [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://github.com/merveenoyan/smol-vision/blob/main/Fine_tune_PaliGemma.ipynb) [![Paper](https://img.shields.io/badge/Arvix-B31B1B?style=flat&logo=arXiv&logoColor=white)](https://arxiv.org/abs/2412.03555) [![Supervision](https://img.shields.io/badge/Supervision-6706CE?style=flat&logo=Roboflow&logoColor=white)](https://supervision.roboflow.com/)
-
-PaliGemma 2 is an open vision-language model by Google, inspired by [PaLI-3](https://arxiv.org/abs/2310.09199) and 
-built with open components such as the [SigLIP](https://arxiv.org/abs/2303.15343) 
-vision model and the [Gemma 2](https://arxiv.org/abs/2408.00118) language model. PaliGemma 2 is designed as a versatile 
-model for transfer to a wide range of vision-language tasks such as image and short video caption, visual question 
-answering, text reading, object detection and object segmentation.
-
-This space show how to use PaliGemma 2 for object detection with supervision.
-You can input an image and a text prompt
-    """)
+    gr.Markdown(INTRO_TEXT)
     
     with gr.Tab("Image Detection"):
         with gr.Row():