Duplicate from fffiloni/Music-To-Image

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/folk.wav filter=lfs diff=lfs merge=lfs -text
+examples/orchestra.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Music To Image
+emoji: 🎶🌅
+colorFrom: red
+colorTo: gray
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+duplicated_from: fffiloni/Music-To-Image
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,135 @@
+import gradio as gr
+import os 
+hf_token = os.environ.get('HF_TOKEN')
+
+lpmc_client = gr.load("seungheondoh/LP-Music-Caps-demo", src="spaces")
+
+from gradio_client import Client
+
+client = Client("https://fffiloni-test-llama-api.hf.space/", hf_token=hf_token)
+
+from diffusers import DiffusionPipeline
+import torch
+
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
+pipe.to("cuda")
+#pipe.enable_model_cpu_offload()
+
+# if using torch < 2.0
+# pipe.enable_xformers_memory_efficient_attention()
+
+from pydub import AudioSegment
+
+def cut_audio(input_path, output_path, max_duration=30000):
+    audio = AudioSegment.from_file(input_path)
+
+    if len(audio) > max_duration:
+        audio = audio[:max_duration]
+
+    audio.export(output_path, format="mp3")
+
+    return output_path
+
+def solo_xd(prompt):
+    images = pipe(prompt=prompt).images[0]
+    return images
+
+def infer(audio_file):
+
+    truncated_audio = cut_audio(audio_file, "trunc_audio.mp3")
+    
+    cap_result = lpmc_client(
+    				truncated_audio,	# str (filepath or URL to file) in 'audio_path' Audio component
+    				api_name="predict"
+    )
+    print(cap_result)
+
+    #summarize_q = f"""
+
+    #I'll give you a list of music descriptions. Create a summary reflecting the musical ambiance. 
+    #Do not processs each segment, but provide a summary for the whole instead.
+    
+    #Here's the list:
+
+    #{cap_result}
+    #"""
+
+    #summary_result = client.predict(
+    #				summarize_q,	# str in 'Message' Textbox component
+    #				api_name="/chat_1"
+    #)
+
+    #print(f"SUMMARY: {summary_result}")
+
+    llama_q = f"""
+    I'll give you a music description, from i want you to provide an illustrative image description that would fit well with the music.
+    Do not processs each segment or song, but provide a summary for the whole instead.
+    Answer with only one image description. Never do lists. Maximum 77 tokens.
+
+    Here's the music description :
+
+    {cap_result}
+    
+    """
+    
+    result = client.predict(
+    				llama_q,	# str in 'Message' Textbox component
+    				api_name="/predict"
+    )
+
+    
+    
+    
+    print(f"Llama2 result: {result}")
+
+    images = pipe(prompt=result).images[0]
+
+    print("Finished")
+    
+    #return cap_result, result, images
+    return images, result, gr.update(visible=True)
+
+css = """
+#col-container {max-width: 510px; margin-left: auto; margin-right: auto;}
+"""
+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;">
+                    Music To Image
+                </h1>
+                </div>
+                <p style="margin-bottom: 10px; font-size: 94%">
+                Sends an audio into <a href="https://huggingface.co/spaces/seungheondoh/LP-Music-Caps-demo" target="_blank">LP-Music-Caps</a>
+                to generate a audio caption which is then translated to an illustrative image description with Llama2, and finally run through 
+                Stable Diffusion XL to generate an image from the audio ! <br /><br />
+                Note: Only the first 30 seconds of your audio will be used for inference.
+                </p>
+            </div>""")
+        audio_input = gr.Audio(label="Music input", type="filepath", source="upload")
+        infer_btn = gr.Button("Generate Image from Music")
+        #lpmc_cap = gr.Textbox(label="Lp Music Caps caption")
+        llama_trans_cap = gr.Textbox(label="Llama translation", visible=False)
+        img_result = gr.Image(label="Image Result")
+        tryagain_btn = gr.Button("Try again ?", visible=False)
+
+        gr.Examples(examples=[["./examples/electronic.mp3"],["./examples/folk.wav"], ["./examples/orchestra.wav"]],
+                    fn=infer,
+                    inputs=[audio_input],
+                    outputs=[img_result, llama_trans_cap, tryagain_btn],
+                    cache_examples=True
+                   )
+
+    #infer_btn.click(fn=infer, inputs=[audio_input], outputs=[lpmc_cap, llama_trans_cap, img_result])
+    infer_btn.click(fn=infer, inputs=[audio_input], outputs=[img_result, llama_trans_cap, tryagain_btn])
+    tryagain_btn.click(fn=solo_xd, inputs=[llama_trans_cap], outputs=[img_result])
+
+demo.queue(max_size=20).launch()

examples/folk.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9c5e4e03b706c464993ab770388fd3a52b240e4c054ec279322dd48c0cb7a8
+size 1918830

examples/orchestra.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97135f273616d39b11db37a1ec61e0bd729b82c085f7dcdc472b26a37affca8a
+size 1323632

requirements.txt

@@ -0,0 +1,6 @@
+pydub
+invisible_watermark
+transformers
+diffusers
+accelerate
+safetensors