dreambooth-hackathon-evaluator

Runtime error

ysharma HF Staff commited on Jan 5, 2023

Commit

07e7ef5

1 Parent(s): 595acb5

Update layout

Files changed (1) hide show

app.py CHANGED Viewed

@@ -1,6 +1,6 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
-# %% auto 0
 __all__ = ['block', 'make_clickable_model', 'make_clickable_user', 'get_submissions']
 # %% app.ipynb 0
@@ -76,7 +76,7 @@ with block:
     gr.Markdown(
         """# Gradio-powered leaderboard for the DreamBooth Hackathon
-    Welcome to this Gradio-powered leaderboard! Select a theme and one of the dreambooth models trained by hacakthon-participants, and key in your prompt as shown (eg., a photo of Shiba dog in a jungle)
     <br>**If you like a model demo, click on the model name in the table below and UPVOTE the model on Huggingface hub**<br><br>
     DreamBooth Hackathon - is an ongoing community event where particpants **personalise a Stable Diffusion model** by fine-tuning it with a powerful technique called [_DreamBooth_](https://arxiv.org/abs/2208.12242). This technique allows one to implant a subject into the output domain of the model such that it can be synthesized with a _unique identifier_ (eg., shiba dog) in the prompt.
         This competition is composed of 5 _themes_ - Animals, Science, Food, Lanscapes, and Wildcards. For details on how to participate, check out the hackathon's guide [here](https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/README.md).

 # AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
+# %% auto 0
 __all__ = ['block', 'make_clickable_model', 'make_clickable_user', 'get_submissions']
 # %% app.ipynb 0
     gr.Markdown(
         """# Gradio-powered leaderboard for the DreamBooth Hackathon
+    Welcome to this Gradio-powered leaderboard! Select a theme and one of the dreambooth models trained by hacakthon-participants, and key in your prompt as shown (eg., a photo of Shiba dog in a jungle). Note that, the image generation might take long (around 400 seconds) as it will have to load the respective model pipeline into memory.
     <br>**If you like a model demo, click on the model name in the table below and UPVOTE the model on Huggingface hub**<br><br>
     DreamBooth Hackathon - is an ongoing community event where particpants **personalise a Stable Diffusion model** by fine-tuning it with a powerful technique called [_DreamBooth_](https://arxiv.org/abs/2208.12242). This technique allows one to implant a subject into the output domain of the model such that it can be synthesized with a _unique identifier_ (eg., shiba dog) in the prompt.
         This competition is composed of 5 _themes_ - Animals, Science, Food, Lanscapes, and Wildcards. For details on how to participate, check out the hackathon's guide [here](https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/README.md).