Update space id

app.py

@@ -1,28 +1,21 @@
+import os
 import gradio as gr
-import torch
 
 from gradio_caption import create_demo as create_caption
 from gradio_vqa import create_demo as create_vqa
 
 
-css = """
-#img-display-input {
-    height: auto;
-    max-height: 40vh;
-    }
-#img-display-output {
-    max-height: 40vh;
-    }
-"""
-
-
 description = """
 # Prismer 
 The official demo for **Prismer: A Vision-Language Model with An Ensemble of Experts**.
 Please refer to our [project page](https://shikun.io/projects/prismer) or [github](https://github.com/NVlabs/prismer) for more details.
 """
 
-with gr.Blocks(css=css) as demo:
+if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
+    description += f'<p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p>'
+
+
+with gr.Blocks() as demo:
     gr.Markdown(description)
     with gr.Tab("Zero-shot Image Captioning"):
         create_caption()

gradio_caption.py

@@ -12,18 +12,18 @@ def create_demo():
     with gr.Row():
         with gr.Column(scale=1):
             model_type = gr.Dropdown(["Prismer-Base", "Prismer-Large"], label="Model Size", value="Prismer-Base")
-            rgb = gr.Image(label="Input Image", type='pil', elem_id='img-display-input')
+            rgb = gr.Image(label="Input Image", type='pil')
             submit = gr.Button("Submit")
         with gr.Column(scale=2):
             pred = gr.Textbox(label="Model Prediction")
             with gr.Row():
-                depth = gr.Image(label="Depth", elem_id='img-display-output')
-                edge = gr.Image(label="Edge", elem_id='img-display-output')
-                normals = gr.Image(label="Normals", elem_id='img-display-output')
+                depth = gr.Image(label="Depth")
+                edge = gr.Image(label="Edge")
+                normals = gr.Image(label="Normals")
             with gr.Row():
-                seg = gr.Image(label="Segmentation", elem_id='img-display-output')
-                obj_det = gr.Image(label="Object Detection", elem_id='img-display-output')
-                ocr_det = gr.Image(label="OCR Detection", elem_id='img-display-output')
+                seg = gr.Image(label="Segmentation")
+                obj_det = gr.Image(label="Object Detection")
+                ocr_det = gr.Image(label="OCR Detection")
 
     def on_submit(im, model_type):
         return pred, depth, edge, normals, seg, obj_det, ocr_det