chengkunli commited on
Commit
312a468
β€’
1 Parent(s): bbe286f

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -140,9 +140,9 @@ with gr.Blocks() as app:
140
  gr.HTML(f"<div style='margin: 20px 0;'>{diagram}</div>")
141
  gr.Markdown(
142
  """
143
- πŸ”” This demo showcases the outputs of **Small-i**, **Small-p**, and **Large-i** on three public datasets (word-level, 100 samples each).<br>
144
- ℹ️ Choose a model variant and dataset (IAM, IMGUR5K, HierText), then click 'Sample' to see an input with its corresponding outputs for all three inference types.<br>
145
- πŸ“ Output format: Image or Image+Video. While showing only images are faster, videos can demonstrate the writing process of the inks.<br>
146
  """
147
  )
148
  with gr.Row():
 
140
  gr.HTML(f"<div style='margin: 20px 0;'>{diagram}</div>")
141
  gr.Markdown(
142
  """
143
+ πŸš€ This demo highlights the capabilities of Small-i, Small-p, and Large-i across three public datasets (word-level, with 100 random samples each).<br>
144
+ 🎲 Select a model variant and dataset (IAM, IMGUR5K, HierText), then hit 'Sample' to view a randomly selected input alongside its corresponding outputs for all three types of inference.<br>
145
+ πŸ–ΌοΈ Output options: Image or Image+Video. Opting for images yields quicker results, adding videos offers a dynamic view of the digital ink writing process.<br>
146
  """
147
  )
148
  with gr.Row():