haoheliu commited on
Commit
b25818a
1 Parent(s): 82cef37

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -200,7 +200,7 @@ with iface:
200
  </h1>
201
  </div>
202
  <p style="margin-bottom: 10px; font-size: 94%">
203
- <a href="https://arxiv.org/abs/2301.12503">[Paper]</a> <a href="https://audioldm.github.io/audioldm2">[Project page]</a>
204
  </p>
205
  </div>
206
  """
@@ -282,7 +282,7 @@ with iface:
282
  gr.HTML(
283
  """
284
  <div class="footer" style="text-align: center; max-width: 700px; margin: 0 auto;">
285
- <p>Follow the latest update of AudioLDM on our<a href="https://github.com/haoheliu/AudioLDM2" style="text-decoration: underline;" target="_blank"> Github repo</a>
286
  </p>
287
  <br>
288
  <p>Model by <a href="https://twitter.com/LiuHaohe" style="text-decoration: underline;" target="_blank">Haohe Liu</a></p>
@@ -338,7 +338,7 @@ with iface:
338
  """
339
  <div class="acknowledgements">
340
  <p>Essential Tricks for Enhancing the Quality of Your Generated Audio</p>
341
- <p>1. Try to use more adjectives to describe your sound. For example: "A man is speaking clearly and slowly in a large room" is better than "A man is speaking". This can make sure AudioLDM understands what you want.</p>
342
  <p>2. Try to use different random seeds, which can affect the generation quality significantly sometimes.</p>
343
  <p>3. It's better to use general terms like 'man' or 'woman' instead of specific names for individuals or abstract objects that humans may not be familiar with, such as 'mummy'.</p>
344
  </div>
 
200
  </h1>
201
  </div>
202
  <p style="margin-bottom: 10px; font-size: 94%">
203
+ <a href="https://arxiv.org/abs/2301.12503">[Paper]</a> <a href="https://audioldm.github.io/audioldm2">[Project page]</a> <a href="https://discord.com/invite/b64SEmdf">[Join Discord]</a>
204
  </p>
205
  </div>
206
  """
 
282
  gr.HTML(
283
  """
284
  <div class="footer" style="text-align: center; max-width: 700px; margin: 0 auto;">
285
+ <p>Follow the latest update of AudioLDM 2 on our<a href="https://github.com/haoheliu/AudioLDM2" style="text-decoration: underline;" target="_blank"> Github repo</a>
286
  </p>
287
  <br>
288
  <p>Model by <a href="https://twitter.com/LiuHaohe" style="text-decoration: underline;" target="_blank">Haohe Liu</a></p>
 
338
  """
339
  <div class="acknowledgements">
340
  <p>Essential Tricks for Enhancing the Quality of Your Generated Audio</p>
341
+ <p>1. Try to use more adjectives to describe your sound. For example: "A man is speaking clearly and slowly in a large room" is better than "A man is speaking". This can make sure AudioLDM 2 understands what you want.</p>
342
  <p>2. Try to use different random seeds, which can affect the generation quality significantly sometimes.</p>
343
  <p>3. It's better to use general terms like 'man' or 'woman' instead of specific names for individuals or abstract objects that humans may not be familiar with, such as 'mummy'.</p>
344
  </div>