init

app.py

@@ -187,8 +187,8 @@ with gr.Blocks(css=css) as demo:
             inputs=prompt_input,
         )
 
-    with gr.Tab("Multimodal Understanding"):
-        gr.Markdown(value="## Multimodal Understanding")
+    with gr.Tab("Camera Understanding"):
+        gr.Markdown(value="## Camera Understanding")
         image_input = gr.Image()
         with gr.Column():
             question_input = gr.Textbox(label="Question")
@@ -198,11 +198,9 @@ with gr.Blocks(css=css) as demo:
 
         with gr.Accordion("Advanced options", open=False):
             und_seed_input = gr.Number(label="Seed", precision=0, value=42)
-            top_p = gr.Slider(minimum=0, maximum=1, value=0.95, step=0.05, label="top_p")
-            temperature = gr.Slider(minimum=0, maximum=1, value=0.1, step=0.05, label="temperature")
 
         examples_inpainting = gr.Examples(
-            label="Multimodal Understanding examples",
+            label="Camera Understanding examples",
             examples=[
                 [
                     "Is the picture taken in winter?",
@@ -224,7 +222,7 @@ with gr.Blocks(css=css) as demo:
 
     understanding_button.click(
         multimodal_understanding,
-        inputs=[image_input, question_input, und_seed_input, top_p, temperature],
+        inputs=[image_input, question_input, und_seed_input],
         outputs=understanding_output
     )
 

requirements.txt

@@ -1,7 +1,6 @@
 torch
 accelerate
 diffusers
-spaces
 gradio
 torchvision
 safetensors
@@ -11,7 +10,6 @@ mmengine==0.10.7
 numpy==2.2.5
 pillow==11.2.1
 scipy==1.15.2
-six==1.17.0
 timm==0.9.12
 transformers==4.49.0
 transformers-stream-generator==0.0.5