examples

app.py

@@ -55,13 +55,8 @@ def query_image(img, text_queries, score_threshold):
 
 description = """
 \n\nYou can use OWL-ViT to query images with text descriptions of any object.
-To use it, simply input the URL of an image and enter comma separated text descriptions of objects you want to query the image for. You
+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>
 """
 demo = gr.Interface(
     query_image,