Spaces:
Paused
Paused
html
Browse files
app.py
CHANGED
@@ -146,15 +146,15 @@ if __name__ == "__main__":
|
|
146 |
|
147 |
gr.HTML(
|
148 |
"""
|
149 |
-
<div style="text-align: center; max-width: 1200px; margin: 20px auto;
|
150 |
-
<h1 style="font-weight: 600; font-size: 2rem; margin: 0rem">
|
151 |
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
|
152 |
</h1>
|
153 |
-
<
|
154 |
-
<
|
155 |
-
<
|
156 |
-
<
|
157 |
-
</
|
158 |
<h2 style="text-align: left; font-weight: 450; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
|
159 |
Our proposed UDiffText is capable of synthesizing accurate and harmonious text in either synthetic or real-word images, thus can be applied to tasks like scene text editing (a), arbitrary text generation (b) and accurate T2I generation (c)
|
160 |
</h2>
|
|
|
146 |
|
147 |
gr.HTML(
|
148 |
"""
|
149 |
+
<div style="text-align: center; max-width: 1200px; margin: 20px auto;">
|
150 |
+
<h1 style="font-weight: 600; font-size: 2rem; margin: 0rem;">
|
151 |
UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models
|
152 |
</h1>
|
153 |
+
<ul style="text-align: center; margin: 0; padding: 0;">
|
154 |
+
<li style="display: inline-block; margin:auto;"><a href='https://arxiv.org/pdf/******'><img src='https://img.shields.io/badge/Arxiv-******-DF826C'></a></li>
|
155 |
+
<li style="display: inline-block; margin:auto;"><a href='https://github.com/ZYM-PKU/UDiffText'><img src='https://img.shields.io/badge/Code-UDiffText-D0F288'></a></li>
|
156 |
+
<li style="display: inline-block; margin:auto;"><a href='https://udifftext.github.io'><img src='https://img.shields.io/badge/Project-UDiffText-8ADAB2'></a></li>
|
157 |
+
</ul>
|
158 |
<h2 style="text-align: left; font-weight: 450; font-size: 1rem; margin-top: 0.5rem; margin-bottom: 0.5rem">
|
159 |
Our proposed UDiffText is capable of synthesizing accurate and harmonious text in either synthetic or real-word images, thus can be applied to tasks like scene text editing (a), arbitrary text generation (b) and accurate T2I generation (c)
|
160 |
</h2>
|