Ziqi commited on
Commit
54b8f2e
·
1 Parent(s): 73f6430
Files changed (1) hide show
  1. app.py +4 -1
app.py CHANGED
@@ -47,9 +47,12 @@ It is recommended to upgrade to GPU in Settings after duplicating this space to
47
  <a href="https://huggingface.co/spaces/Ziqi/ReVersion?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
48
  '''
49
  DETAILDESCRIPTION='''
50
- ReVersion: <R> represents the learned text token for a relation. Use <R> in your prompt for relation-specific generation.
51
  '''
52
  # DETAILDESCRIPTION='''
 
 
 
53
  # Custom Diffusion allows you to fine-tune text-to-image diffusion models, such as Stable Diffusion, given a few images of a new concept (~4-20).
54
  # We fine-tune only a subset of model parameters, namely key and value projection matrices, in the cross-attention layers and the modifier token used to represent the object.
55
  # This also reduces the extra storage for each additional concept to 75MB. Our method also allows you to use a combination of concepts. There's still limitations on which compositions work. For more analysis please refer to our [website](https://www.cs.cmu.edu/~custom-diffusion/).
 
47
  <a href="https://huggingface.co/spaces/Ziqi/ReVersion?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
48
  '''
49
  DETAILDESCRIPTION='''
50
+ ReVersion
51
  '''
52
  # DETAILDESCRIPTION='''
53
+ # ReVersion: <R> represents the learned text token for a relation. Use <R> in your prompt for relation-specific generation.
54
+ # '''
55
+ # DETAILDESCRIPTION='''
56
  # Custom Diffusion allows you to fine-tune text-to-image diffusion models, such as Stable Diffusion, given a few images of a new concept (~4-20).
57
  # We fine-tune only a subset of model parameters, namely key and value projection matrices, in the cross-attention layers and the modifier token used to represent the object.
58
  # This also reduces the extra storage for each additional concept to 75MB. Our method also allows you to use a combination of concepts. There's still limitations on which compositions work. For more analysis please refer to our [website](https://www.cs.cmu.edu/~custom-diffusion/).