fffiloni commited on
Commit
cf2c91f
·
verified ·
1 Parent(s): 1829498

Add paper abstract

Browse files
Files changed (1) hide show
  1. app.py +9 -0
app.py CHANGED
@@ -1678,6 +1678,15 @@ if __name__ == "__main__":
1678
  with gr.Blocks(css=css) as demo:
1679
  with gr.Column(elem_id="col-container"):
1680
  gr.Markdown("# AccDiffusion: An Accurate Method for Higher-Resolution Image Generation")
 
 
 
 
 
 
 
 
 
1681
  gr.HTML("""
1682
  <div style="display:flex;column-gap:4px;">
1683
  <a href='https://lzhxmu.github.io/accdiffusion/accdiffusion.html'>
 
1678
  with gr.Blocks(css=css) as demo:
1679
  with gr.Column(elem_id="col-container"):
1680
  gr.Markdown("# AccDiffusion: An Accurate Method for Higher-Resolution Image Generation")
1681
+ gr.Markdown("### Paper Abstract")
1682
+ gr.Markdown("""
1683
+ This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation.
1684
+ We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training.
1685
+ An in-depth analysis in this paper reveals an identical text prompt for different patches causes repeated object generation, while no prompt compromises the image details.
1686
+ Therefore, our AccDiffusion, for the first time, proposes to decouple the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of an image patch.
1687
+ Besides, AccDiffusion also introduces dilated sampling with window interaction for better global consistency in higher-resolution image generation.
1688
+ Experimental comparison with existing methods demonstrates that our AccDiffusion effectively addresses the issue of repeated object generation and leads to better performance in higher-resolution image generation.
1689
+ """)
1690
  gr.HTML("""
1691
  <div style="display:flex;column-gap:4px;">
1692
  <a href='https://lzhxmu.github.io/accdiffusion/accdiffusion.html'>