update markdown and disclaimer

app.py

@@ -52,9 +52,11 @@ if device == "cuda":
 # with gr.Blocks(css="style.css") as demo:
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown(f""" # Real Time Editing with GNRI Inversion 🍎⚡️
-    This is a demo for our [paper](https://arxiv.org/abs/2312.12540) **GNRI: Lightning-fast Image Inversion and Editing for Text-to-Image Diffusion Models**.
-    Image editing using GNRI for inversion demonstrates significant speed-up and improved quality compared to previous state-of-the-art methods.
-    Take a look at the [project page](https://barakmam.github.io/rnri.github.io/).
+    This is a demo for our [paper](https://arxiv.org/abs/2312.12540) **GNRI: Lightning-fast Image Inversion and Editing 
+    for Text-to-Image Diffusion Models. Accepted to ICLR 2025**.
+    More details can be found in the [project page](https://barakmam.github.io/rnri.github.io/).
+    
+    The demo is based on SDXL. Improved results can be achieved with our FLUX version (examples in project page).
     """)
     inv_state = gr.State()
 
@@ -192,7 +194,9 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     cache_examples=False
                 )
 
-    gr.Markdown(f"""Disclaimer: Performance may be inferior to the reported in the paper due to hardware limitation.""")
+    gr.Markdown(f"""Disclaimer: The results may vary depending on the hyper-parameters. Some typical hyper-parameters 
+    are xxxx. Errors may appear due to resource availability by HF.
+    Performance may be inferior to the reported in the paper due to hardware limitation.""")
 
     input_image.change(set_pipe, inputs=[input_image, description_prompt, edit_guidance_scale, num_inference_steps,
                                          num_inference_steps, inversion_max_step, rnri_iterations, rnri_alpha, rnri_lr],