fix desc

app.py

@@ -4,22 +4,15 @@ import gradio as gr
 from demo import query_image
 
 description = """
-Gradio demo for <a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>, 
-introduced in <a href="https://arxiv.org/abs/2205.06230">Simple Open-Vocabulary Object Detection
-with Vision Transformers</a>. 
-\n\nYou can use OWL-ViT to query images with text descriptions of any object. 
-To use it, simply upload an image and enter comma separated text descriptions of objects you want to query the image for. You
-can also use the score threshold slider to set a threshold to filter out low probability predictions. 
-\n\nOWL-ViT is trained on text templates,
-hence you can get better predictions by querying the image with text templates used in training the original model: *"photo of a star-spangled banner"*, 
-*"image of a shoe"*. Refer to the <a href="https://arxiv.org/abs/2103.00020">CLIP</a> paper to see the full list of text templates used to augment the training data.
-\n\n<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/zeroshot_object_detection_with_owlvit.ipynb">Colab demo</a>
+Gradio demo for combining <a href="https://github.com/facebookresearch/segment-anything">Segment-Anything (SAM)</a>
+<a href="https://huggingface.co/docs/transformers/main/en/model_doc/owlvit">OWL-ViT</a>.
+\n\nYou can use OWL-ViT to query boxes with text descriptions of any object, then SAM will segment anything in the boxes.
 """
 demo = gr.Interface(
     query_image, 
     inputs=[gr.Image(), "text"], 
     outputs=["image", "image"],
-    title="Zero-Shot Object Detection with OWL-ViT",
+    title="Segment Anything (SAM) with OWL-ViT",
     description=description,
     examples=[
         ["./demo_images/cats.png", "cats,ears"], 

demo.py

@@ -164,7 +164,7 @@ def query_image(img, text_prompt):
     buf = io.BytesIO()
     plt.savefig(buf)
     buf.seek(0)
-    owlvit_segment_image = Image.open(buf).convert('RGB')
+    owlvit_segment_image = Image.open(buf)
 
     # grounded results
     image_with_box = plot_boxes_to_image(pil_img, pred_dict)[0]