Hugging Face's logo

Spaces:
kokuma
/
img-to-music
Runtime error

App Files Community
img-to-music
File size: 2,696 Bytes 
cddb846
 
 
 
 
 
 
 
8bcacfc
cddb846
 
 
 
 
8099795
 
 
 
 
 
cddb846
 
 
 
 
 
8099795
 
cddb846
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8099795
 
cddb846
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8099795
cddb846
8099795
cddb846
 
 
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
94
95
96
 
import gradio as gr
import os
import requests
import urllib

from os import path
from pydub import AudioSegment

img_to_text = gr.Blocks.load(name="spaces/fffiloni/CLIP-Interrogator-2")
text_to_music = gr.Interface.load("spaces/fffiloni/text-2-music")

def get_prompts(uploaded_image):
  prompt = img_to_text(uploaded_image, "ViT-L (best for Stable Diffusion 1.*)", "fast", fn_index=1)[0]
  music_result = get_music(prompt)
  print(f"""—————
  PROMPT: {prompt}
  ———————
  """)
  return music_result, prompt


def get_music(prompt):
  
  result = text_to_music(prompt, fn_index=0)
  
  print(f"""—————
  MUSIC
  prompt: {result}
  ———————
  """)
  
  url = result
  save_as = "file.mp3"
  
  data = urllib.request.urlopen(url)

  f = open(save_as,'wb')
  f.write(data.read())
  f.close()
  
  wave_file="file.wav"
  
  sound = AudioSegment.from_mp3(save_as)
  sound.export(wave_file, format="wav")
  
  return wave_file


css = """
#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
a {text-decoration-line: underline; font-weight: 600;}
.animate-spin {
    animation: spin 1s linear infinite;
}
@keyframes spin {
    from {
        transform: rotate(0deg);
    }
    to {
        transform: rotate(360deg);
    }
}
"""

with gr.Blocks(css=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 Music
              </h1>
              </div>
              <p style="margin-bottom: 10px; font-size: 94%">
              Sends an image in to <a href="https://huggingface.co/spaces/pharma/CLIP-Interrogator" target="_blank">CLIP Interrogator</a>
              to generate a text prompt which is then run through 
              <a href="https://huggingface.co/Mubert" target="_blank">Mubert</a> text-to-music to generate music from the input image!
              </p>
          </div>""")
    
    
    input_img = gr.Image(type="filepath", elem_id="input-img")
    generate = gr.Button("Generate Music from Image")
  
    music_output = gr.Audio(label="Result", type="filepath", elem_id="music-output")
    prompt_text = gr.Textbox(label="Prompt") 
      
  generate.click(get_prompts, inputs=[input_img], outputs=[music_output, prompt_text], api_name="i2m")

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