File size: 3,652 Bytes
372395e caed802 b19e4a9 f694503 04d2706 caed802 372395e caed802 372395e cb934a1 3efd05b b5357a4 b3ab125 372395e 79b4496 48c215d 79b4496 e7c2915 12bd467 e7c2915 79b4496 372395e 79b4496 372395e cb934a1 ee7056c f694503 372395e 570b690 79b4496 53f5458 79b4496 fdef21e cb934a1 bc6b39c 372395e a63d987 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
import gradio as gr
import os
import time
from moviepy.editor import *
from share_btn import community_icon_html, loading_icon_html, share_js
token = os.environ.get('HF_TOKEN')
caption = gr.Blocks.load(name="spaces/SRDdev/Image-Caption")
audio_gen = gr.Blocks.load(name="spaces/fffiloni/audioldm-text-to-audio-generation-clone", api_key=token)
def infer(image_input, manual_caption):
if manual_caption == None:
cap = caption(image_input, fn_index=0)
else:
cap = manual_caption
sound = audio_gen(cap, 10, 2.5, 45, 3, fn_index=0)
return cap, sound[1], gr.Group.update(visible=True)
title = """
<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%">
Convert an image to a corresponding sound effect generated through GPT2 Image Captioning & AudioLDM
</p>
</div>
"""
article = """
<div class="footer">
<p>
Follow <a href="https://twitter.com/fffiloni" target="_blank">Sylvain Filoni</a> for future updates 🤗
</p>
</div>
<div id="may-like-container" style="display: flex;justify-content: center;flex-direction: column;align-items: center;margin-bottom: 30px;">
<p>You may also like: </p>
<div id="may-like-content" style="display:flex;flex-wrap: wrap;align-items:center;height:20px;">
<svg height="20" width="208" style="margin-left:4px;margin-bottom: 6px;">
<a href="https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation" target="_blank">
<image href="https://img.shields.io/badge/🤗 Spaces-AudioLDM_Text_to_Audio-blue" src="https://img.shields.io/badge/🤗 Spaces-AudioLDM_Text_to_Audio-blue.png" height="20"/>
</a>
</svg>
<svg height="20" width="122" style="margin-left:4px;margin-bottom: 6px;">
<a href="https://huggingface.co/spaces/fffiloni/spectrogram-to-music" target="_blank">
<image href="https://img.shields.io/badge/🤗 Spaces-Riffusion-blue" src="https://img.shields.io/badge/🤗 Spaces-Riffusion-blue.png" height="20"/>
</a>
</svg>
</div>
</div>
"""
with gr.Blocks(css="style.css") as demo:
with gr.Column(elem_id="col-container"):
gr.HTML(title)
input_img = gr.Image(type="filepath", elem_id="input-img")
manual_cap = gr.Textbox(label="Image description (optional)")
caption_output = gr.Textbox(label="Caption", lines=1, visible=False, elem_id="text-caption")
sound_output = gr.Audio(label="Result", elem_id="sound-output")
generate = gr.Button("Generate SFX from Image")
with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
community_icon = gr.HTML(community_icon_html)
loading_icon = gr.HTML(loading_icon_html)
share_button = gr.Button("Share to community", elem_id="share-btn")
gr.HTML(article)
generate.click(infer, inputs=[input_img, manual_cap], outputs=[caption_output, sound_output, share_group], api_name="i2fx")
share_button.click(None, [], [], _js=share_js)
demo.queue(max_size=32).launch(debug=True)
|