Update

app.py

@@ -134,8 +134,10 @@ with gr.Blocks() as g:
     gr.HTML("""<h1>LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models</h1>
             <p>This is a space that allows you to explore the layouts generated by ChatGPT on your own with a simplified set of examples. The layout-to-image generation part will be added.</p>
             <p>Read our <a href='https://llm-grounded-diffusion.github.io/'>a brief introduction on our project page</a> or <a href='https://arxiv.org/pdf/2305.13655.pdf'>our work on arxiv</a>. <a href='https://llm-grounded-diffusion.github.io/#citation'>Cite our work</a> if our ideas inspire you.</p>
-            <p>Tips: you can perform multi-round specification by giving ChatGPT follow-up requests (e.g., make the object boxes bigger).</p>
-            <p>Tips: you can also try prompts in Simplified Chinese. If you want to try prompts in another language, translate the first line of last example to your language.<p>""")
+            <p><b>Tips:</b><p>
+            <p>1. If ChatGPT doesn't generate layout, add/remove the trailing space (added by default) and/or use GPT-4.</p>
+            <p>2. You can perform multi-round specification by giving ChatGPT follow-up requests (e.g., make the object boxes bigger).</p>
+            <p>3. You can also try prompts in Simplified Chinese. If you want to try prompts in another language, translate the first line of last example to your language.<p>""")
     with gr.Tab("Image Prompt to ChatGPT"):
         with gr.Row():
             with gr.Column(scale=1):