Update app.py

app.py

@@ -8,6 +8,7 @@ import torch
 from diffusers import StableDiffusionXLPipeline, AutoencoderKL
 from blora_utils import BLOCKS, filter_lora, scale_lora
 
+is_shared_ui = True if "fffiloni/B-LoRa-Inference" in os.environ['SPACE_ID'] else False
 hf_token = os.environ.get("YOUR_HF_TOKEN_WITH_READ_PERMISSION")
 login(token=hf_token)
 
@@ -151,6 +152,26 @@ css="""
     margin: 0 auto;
     max-width: 520px;
 }
+div#warning-duplicate {
+    background-color: #ebf5ff;
+    padding: 0 16px 16px;
+    margin: 20px 0;
+}
+div#warning-duplicate > .gr-prose > h2, div#warning-duplicate > .gr-prose > p {
+    color: #0f4592!important;
+}
+div#warning-duplicate strong {
+    color: #0f4592;
+}
+p.actions {
+    display: flex;
+    align-items: center;
+    margin: 20px 0;
+}
+div#warning-duplicate .actions a {
+    display: inline-block;
+    margin-right: 10px;
+}
 """
 
 if torch.cuda.is_available():
@@ -161,6 +182,23 @@ else:
 with gr.Blocks(css=css) as demo:
     
     with gr.Column(elem_id="col-container"):
+        if is_shared_ui:
+            top_description = gr.HTML(f'''
+                <div class="gr-prose">
+                    <h2><svg xmlns="http://www.w3.org/2000/svg" width="18px" height="18px" style="margin-right: 0px;display: inline-block;"fill="none"><path fill="#fff" d="M7 13.2a6.3 6.3 0 0 0 4.4-10.7A6.3 6.3 0 0 0 .6 6.9 6.3 6.3 0 0 0 7 13.2Z"/><path fill="#fff" fill-rule="evenodd" d="M7 0a6.9 6.9 0 0 1 4.8 11.8A6.9 6.9 0 0 1 0 7 6.9 6.9 0 0 1 7 0Zm0 0v.7V0ZM0 7h.6H0Zm7 6.8v-.6.6ZM13.7 7h-.6.6ZM9.1 1.7c-.7-.3-1.4-.4-2.2-.4a5.6 5.6 0 0 0-4 1.6 5.6 5.6 0 0 0-1.6 4 5.6 5.6 0 0 0 1.6 4 5.6 5.6 0 0 0 4 1.7 5.6 5.6 0 0 0 4-1.7 5.6 5.6 0 0 0 1.7-4 5.6 5.6 0 0 0-1.7-4c-.5-.5-1.1-.9-1.8-1.2Z" clip-rule="evenodd"/><path fill="#000" fill-rule="evenodd" d="M7 2.9a.8.8 0 1 1 0 1.5A.8.8 0 0 1 7 3ZM5.8 5.7c0-.4.3-.6.6-.6h.7c.3 0 .6.2.6.6v3.7h.5a.6.6 0 0 1 0 1.3H6a.6.6 0 0 1 0-1.3h.4v-3a.6.6 0 0 1-.6-.7Z" clip-rule="evenodd"/></svg>
+                    Note: you might want to use a private custom B-LoRa model</h2>
+                    <p class="main-message">
+                        To do so, <strong>duplicate the Space</strong> and run it on your own profile using <strong>your own access token</strong> and eventually a GPU (T4-small or A10G-small) for faster inference without waiting in the queue.<br />
+                    </p>
+                    <p class="actions">
+                        <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}?duplicate=true">
+                            <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-lg-dark.svg" alt="Duplicate this Space" />
+                        </a>
+                        to start using private models and skip the queue
+                    </p>
+                </div>
+            ''', elem_id="warning-duplicate")
+        
         gr.Markdown(f"""
         # B-LoRas Inference
         Currently running on {power_device}.