app.py

import gradio as gr

caption = gr.Blocks.load(name="spaces/SRDdev/Image-Caption")
audio_gen = gr.Blocks.load(name="spaces/haoheliu/audioldm-text-to-audio-generation")

def infer(image_input):
    cap = caption(image_input, fn_index=0)
    sound = audio_gen(cap, 5, 2.5, 45, 3, fn_index=0)
    return sound

with gr.Blocks(css="style.css") as demo:
    with gr.Column(elem_id="col-container"):
        
        gr.HTML("""<div style="text-align: center; max-width: 700px; margin: 0 auto;">
                <div
                style="
                    display: inline-flex;
                    align-items: center;
                    gap: 0.8rem;
                    font-size: 1.75rem;
                "
                >
                <h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
                    Image to Sound Effect
                </h1>
                </div>
                <p style="margin-bottom: 10px; font-size: 94%">
                description
                </p>
            </div>""")
    
        input_img = gr.Image(type="filepath", elem_id="input-img")
        sound_output = gr.Video(label="Result", elem_id="sound-output")
        
        generate = gr.Button("Generate Music from Image")
    
    generate.click(infer, inputs=[input_img], outputs=[sound_output], api_name="i2m")

demo.queue(max_size=32, concurrency_count=20).launch()