Update app.py

app.py

@@ -365,11 +365,11 @@ _HEADER_ = '''
 </div>
 
 
-<p style="font-size: 1rem; margin-bottom: 1.5rem;">Paper: <a href='https://witcherofresearch.github.io/TeleStyleV2' target='_blank'>PromptRouter: Routing Different Image Customization Tasks via Simple Prompt</a> | Codes: <a href='https://github.com/witcherofresearch/PromptRoute' target='_blank'>GitHub</a>
+<p style="font-size: 1rem; margin-bottom: 1.5rem;">Paper: <a href='' target='_blank'>PromptRouter: Routing Different Image Customization Tasks via Simple Prompt</a> | Codes: <a href='https://github.com/witcherofresearch/PromptRoute' target='_blank'>GitHub</a>
 </p>
-<p style="font-size: 1rem; margin-bottom: 1.5rem;">Please light a star for the <a href='https://github.com/Tele-AI/TeleStyleV2' target='_blank'>Code</a> if you find the demo useful, thank you.</p>
+<p style="font-size: 1rem; margin-bottom: 1.5rem;">Please light a star for the <a href='https://github.com/witcherofresearch/PromptRoute' target='_blank'>Code</a> if you find the demo useful, thank you.</p>
 
-<p style="font-size: 1rem; margin-bottom: 1.5rem;">In this demo, we question whether there exists any conflicts when learning multi-ref subject-driven image generation and content-preserving style transfer given content ref and style ref with a unified model. The conclusion is no and our PromptRoute's solution is simple: we attach "Compose the pictures" for multi-ref subject generation, and "Style Transfer the style of Figure 2 to Figure 1, and keep the content and characteristics of Figure 1." for content-preserving style transfer during training and inference. Such simple prompts distinguish the tasks and eliminate the confusion. </p> 
+<p style="font-size: 1rem; margin-bottom: 1.5rem;">In this demo, we question whether there exist any conflicts when learning multi-ref subject-driven image generation and content-preserving style transfer given content ref and style ref with a unified model. The conclusion is no and our PromptRoute's solution is simple: we attach "Compose the pictures" for multi-ref subject generation, and "Style Transfer the style of Figure 2 to Figure 1, and keep the content and characteristics of Figure 1." for content-preserving style transfer during training and inference. Such simple prompts distinguish the tasks and eliminate the confusion. </p> 
 
 <p style="font-size: 1rem; margin-bottom: 1.5rem;">Caution: If you choose infer with content/style prompt, pls do not forget to clean the prompt box when you run a new  inference. The results of multi-ref subject generation are all 16:9 in this demo. </p>