Spaces:

prithivMLmods
/

Multimodal-VLM-v1.0

Running on Zero

prithivMLmods commited on Oct 3

Commit

8e0481f

verified ·

1 Parent(s): 10c47cf

Update app.py

Files changed (1) hide show

app.py CHANGED Viewed

@@ -287,7 +287,7 @@ def create_gradio_interface():
                             choices=["Camel-Doc-OCR-062825 (OCR)", "MinerU2.5-2509 (General)"],
                             label="Select Model", value= "Camel-Doc-OCR-062825 (OCR)"
                         )
-                        image_input_doc = gr.Image(label="Upload Image", type="pil", sources=['upload'])
                         prompt_input_doc = gr.Textbox(label="Query Input", placeholder="e.g., 'Transcribe the text in this document.'")
                         with gr.Accordion("Advanced Generation Settings", open=False):

                             choices=["Camel-Doc-OCR-062825 (OCR)", "MinerU2.5-2509 (General)"],
                             label="Select Model", value= "Camel-Doc-OCR-062825 (OCR)"
                         )
+                        image_input_doc = gr.Image(label="Upload Image", type="pil", sources=['upload'], height=280)
                         prompt_input_doc = gr.Textbox(label="Query Input", placeholder="e.g., 'Transcribe the text in this document.'")
                         with gr.Accordion("Advanced Generation Settings", open=False):