mfidabel commited on
Commit
6162149
β€’
1 Parent(s): b123ec9

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -1
app.py CHANGED
@@ -33,6 +33,8 @@ description = """This is a demo on 🧨 ControlNet based on Meta's [Segment Anyt
33
 
34
 
35
  A huge thanks goes out to @Google Cloud, for providing us with powerful TPUs that enabled us to train this model; and to the @HuggingFace Team for organizing the sprint.
 
 
36
  """
37
 
38
  about = """
@@ -40,7 +42,7 @@ about = """
40
 
41
  # πŸ‘¨β€πŸ’» About the model
42
 
43
- This model is based on the [ControlNet Model](https://huggingface.co/blog/controlnet), which allow us to generate Images using some sort of condition image. For this model, we selected the segmentation maps produced by Meta's new segmentation model called [Segment Anything Model](https://github.com/facebookresearch/segment-anything) as the condition image. We then trained the model to generate images based on the structure of the segmentation maps and the text prompts given.
44
 
45
 
46
  # πŸ’Ύ About the dataset
 
33
 
34
 
35
  A huge thanks goes out to @Google Cloud, for providing us with powerful TPUs that enabled us to train this model; and to the @HuggingFace Team for organizing the sprint.
36
+
37
+ Check out our [Model Card 🧨](https://huggingface.co/mfidabel/controlnet-segment-anything)
38
  """
39
 
40
  about = """
 
42
 
43
  # πŸ‘¨β€πŸ’» About the model
44
 
45
+ This [model](https://huggingface.co/mfidabel/controlnet-segment-anything) is based on the [ControlNet Model](https://huggingface.co/blog/controlnet), which allow us to generate Images using some sort of condition image. For this model, we selected the segmentation maps produced by Meta's new segmentation model called [Segment Anything Model](https://github.com/facebookresearch/segment-anything) as the condition image. We then trained the model to generate images based on the structure of the segmentation maps and the text prompts given.
46
 
47
 
48
  # πŸ’Ύ About the dataset