Update message about usage for research purposes

#10
by osanseviero - opened
Files changed (1) hide show
  1. app.py +2 -1
app.py CHANGED
@@ -32,6 +32,7 @@ if not model_dir.exists():
32
  local_dir=model_dir)
33
 
34
  DESCRIPTION = '# [ModelScope Text to Video Synthesis](https://modelscope.cn/models/damo/text-to-video-synthesis/summary)'
 
35
  if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
36
  DESCRIPTION += f'\n<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>'
37
 
@@ -91,7 +92,7 @@ with gr.Blocks(css='style.css') as demo:
91
  Despite how impressive being able to turn text into video is, beware to the fact that this model may output content that reinforces or exacerbates societal biases. The training data includes LAION5B, ImageNet, Webvid and other public datasets. The model was not trained to realistically represent people or events, so using it to generate such content is beyond the model's capabilities.
92
  </p>
93
  <p>
94
- It is not intended to generate content that is demeaning or harmful to people or their environment, culture, religion, etc. Similarly, it is not allowed to generate pornographic, violent and bloody content generation. The model is meant for research purposes.
95
  </p>
96
  <p>
97
  To learn more about the model, head to its <a href="https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis" style="text-decoration: underline;" target="_blank">model card</a>.
 
32
  local_dir=model_dir)
33
 
34
  DESCRIPTION = '# [ModelScope Text to Video Synthesis](https://modelscope.cn/models/damo/text-to-video-synthesis/summary)'
35
+ DESCRIPTION += '\n<p>This model can only be used for non-commercial purposes. To learn more about the model, take a look at the <a href="https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis" style="text-decoration: underline;" target="_blank">model card</a>.</p>'
36
  if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
37
  DESCRIPTION += f'\n<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>'
38
 
 
92
  Despite how impressive being able to turn text into video is, beware to the fact that this model may output content that reinforces or exacerbates societal biases. The training data includes LAION5B, ImageNet, Webvid and other public datasets. The model was not trained to realistically represent people or events, so using it to generate such content is beyond the model's capabilities.
93
  </p>
94
  <p>
95
+ It is not intended to generate content that is demeaning or harmful to people or their environment, culture, religion, etc. Similarly, it is not allowed to generate pornographic, violent and bloody content generation. <b>The model is meant for research purposes</b>.
96
  </p>
97
  <p>
98
  To learn more about the model, head to its <a href="https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis" style="text-decoration: underline;" target="_blank">model card</a>.