Upload 2 files

app.py

@@ -34,7 +34,6 @@ moondream = AutoModelForCausalLM.from_pretrained(
 ).to(device)
 moondream.eval()
 
-
 @spaces.GPU
 def answer_question(img, prompt):
     image_embeds = moondream.encode_image(img)
@@ -96,13 +95,13 @@ with gr.Blocks() as demo:
         prompt = gr.Textbox(label="Input", value="Describe this image.", scale=4)
         submit = gr.Button("Submit")
     with gr.Row():
-        img = gr.Image(type="pil", image_mode="RGB", format="png", label="Upload an Image")
+        img = gr.Image(type="pil", image_mode="RGB", label="Upload an Image")
         with gr.Column():
             output = gr.Markdown(label="Response")
             ann = gr.Image(visible=False, label="Annotated Image")
 
-    submit.click(answer_question, [img, prompt], output)
-    prompt.submit(answer_question, [img, prompt], output)
+    submit.click(answer_question, [img, prompt], output, queue=True)
+    prompt.submit(answer_question, [img, prompt], output, queue=True)
     output.change(process_answer, [img, output], ann, show_progress=False)
 
 demo.queue().launch()

requirements.txt

@@ -3,4 +3,5 @@ transformers>=4.44.0
 einops>=0.8.0
 accelerate>=0.32.1
 numpy<2
-torch==2.4.0
+torch==2.4.0
+torchvision