Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -14,10 +14,6 @@ pipe.to("cuda")
|
|
14 |
# if using torch < 2.0
|
15 |
# pipe.enable_xformers_memory_efficient_attention()
|
16 |
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
from pydub import AudioSegment
|
22 |
|
23 |
def cut_audio(input_path, output_path, max_duration=30000):
|
@@ -77,16 +73,40 @@ def infer(audio_file):
|
|
77 |
|
78 |
images = pipe(prompt=result).images[0]
|
79 |
|
80 |
-
return cap_result, result, images
|
|
|
81 |
|
82 |
-
|
|
|
|
|
|
|
83 |
with gr.Column(elem_id="col-container"):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
audio_input = gr.Audio(type="filepath", source="upload")
|
85 |
infer_btn = gr.Button("Generate")
|
86 |
lpmc_cap = gr.Textbox(label="Lp Music Caps caption")
|
87 |
llama_trans_cap = gr.Textbox(label="Llama translation")
|
88 |
img_result = gr.Image(label="Result")
|
89 |
|
90 |
-
infer_btn.click(fn=infer, inputs=[audio_input], outputs=[lpmc_cap, llama_trans_cap, img_result])
|
|
|
91 |
|
92 |
demo.queue().launch()
|
|
|
14 |
# if using torch < 2.0
|
15 |
# pipe.enable_xformers_memory_efficient_attention()
|
16 |
|
|
|
|
|
|
|
|
|
17 |
from pydub import AudioSegment
|
18 |
|
19 |
def cut_audio(input_path, output_path, max_duration=30000):
|
|
|
73 |
|
74 |
images = pipe(prompt=result).images[0]
|
75 |
|
76 |
+
#return cap_result, result, images
|
77 |
+
return images
|
78 |
|
79 |
+
css = """
|
80 |
+
#col-container {max-width: 510px; margin-left: auto; margin-right: auto;}
|
81 |
+
"""
|
82 |
+
with gr.Blocks(css=css) as demo:
|
83 |
with gr.Column(elem_id="col-container"):
|
84 |
+
gr.HTML("""<div style="text-align: center; max-width: 700px; margin: 0 auto;">
|
85 |
+
<div
|
86 |
+
style="
|
87 |
+
display: inline-flex;
|
88 |
+
align-items: center;
|
89 |
+
gap: 0.8rem;
|
90 |
+
font-size: 1.75rem;
|
91 |
+
"
|
92 |
+
>
|
93 |
+
<h1 style="font-weight: 900; margin-bottom: 7px; margin-top: 5px;">
|
94 |
+
Music To Image
|
95 |
+
</h1>
|
96 |
+
</div>
|
97 |
+
<p style="margin-bottom: 10px; font-size: 94%">
|
98 |
+
Sends an audio in to <a href="https://huggingface.co/spaces/seungheondoh/LP-Music-Caps-demo" target="_blank">LP-Music-Caps</a>
|
99 |
+
to generate a audio cpation which is then translated to an illustrative image description with Llama2, then run through
|
100 |
+
Stable Diffusion XL to generate an image from the audio !
|
101 |
+
</p>
|
102 |
+
</div>""")
|
103 |
audio_input = gr.Audio(type="filepath", source="upload")
|
104 |
infer_btn = gr.Button("Generate")
|
105 |
lpmc_cap = gr.Textbox(label="Lp Music Caps caption")
|
106 |
llama_trans_cap = gr.Textbox(label="Llama translation")
|
107 |
img_result = gr.Image(label="Result")
|
108 |
|
109 |
+
#infer_btn.click(fn=infer, inputs=[audio_input], outputs=[lpmc_cap, llama_trans_cap, img_result])
|
110 |
+
infer_btn.click(fn=infer, inputs=[audio_input], outputs=[img_result])
|
111 |
|
112 |
demo.queue().launch()
|