app.py

"""
Copyright (c) Meta Platforms, Inc. and affiliates.
All rights reserved.

This source code is licensed under the license found in the
LICENSE file in the root directory of this source tree.
"""

from tempfile import NamedTemporaryFile
import torch
import gradio as gr
from audiocraft.models import MusicGen

from audiocraft.data.audio import audio_write


MODEL = None

img_to_text = gr.load(name="spaces/fffiloni/CLIP-Interrogator-2")


def load_model(version):
    print("Loading model", version)
    return MusicGen.get_pretrained(version)


def predict(uploaded_image, melody, duration):
    text = img_to_text(uploaded_image, 'best', 4, fn_index=1)[0]
    global MODEL
    topk = int(250)
    if MODEL is None or MODEL.name != "melody":
        MODEL = load_model("melody")

    if duration > MODEL.lm.cfg.dataset.segment_duration:
        raise gr.Error("MusicGen currently supports durations of up to 30 seconds!")
    MODEL.set_generation_params(
        use_sampling=True,
        top_k=250,
        top_p=0,
        temperature=1.0,
        cfg_coef=3.0,
        duration=duration,
    )

    if melody:
        sr, melody = melody[0], torch.from_numpy(melody[1]).to(MODEL.device).float().t().unsqueeze(0)
        print(melody.shape)
        if melody.dim() == 2:
            melody = melody[None]
        melody = melody[..., :int(sr * MODEL.lm.cfg.dataset.segment_duration)]
        output = MODEL.generate_with_chroma(
            descriptions=[text],
            melody_wavs=melody,
            melody_sample_rate=sr,
            progress=False
        )
    else:
        output = MODEL.generate(descriptions=[text], progress=False)

    output = output.detach().cpu().float()[0]
    with NamedTemporaryFile("wb", suffix=".wav", delete=False) as file:
        audio_write(file.name, output, MODEL.sample_rate, strategy="loudness", add_suffix=False)
        #waveform_video = gr.make_waveform(file.name)
    return file.name


with gr.Blocks() as demo:
    gr.Markdown(
        """
        # Image to MusicGen

        This is the demo by @fffiloni for Image to [MusicGen](https://github.com/facebookresearch/audiocraft), a simple and controllable model for music generation
        presented at: ["Simple and Controllable Music Generation"](https://huggingface.co/papers/2306.05284), using Clip Interrogator to get an image description as init text. 
        <br/>
        <a href="https://huggingface.co/spaces/musicgen/MusicGen?duplicate=true" style="display: inline-block;margin-top: .5em;margin-right: .25em;" target="_blank">
        <img style="margin-bottom: 0em;display: inline;margin-top: -.25em;" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
        for longer sequences, more control and no queue.</p>
        """
    )
    with gr.Row():
        with gr.Column():
            with gr.Column():
                uploaded_image = gr.Image(label="Input Image", interactive=True, source="upload", type="filepath")
                melody = gr.Audio(source="upload", type="numpy", label="Melody Condition (optional)", interactive=True)
            with gr.Row():
                submit = gr.Button("Submit")
            #with gr.Row():
            #   model = gr.Radio(["melody", "medium", "small", "large"], label="Model", value="melody", interactive=True)
            with gr.Row():
                duration = gr.Slider(minimum=1, maximum=30, value=10, step=1, label="Duration", interactive=True)
            #with gr.Row():
            #   topk = gr.Number(label="Top-k", value=250, interactive=True)
            #   topp = gr.Number(label="Top-p", value=0, interactive=True)
            #   temperature = gr.Number(label="Temperature", value=1.0, interactive=True)
            #   cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True)
        with gr.Column():
            output = gr.Audio(label="Generated Music")
    submit.click(predict, inputs=[uploaded_image, melody, duration], outputs=[output])
    
    gr.Markdown(
        """
        ### More details

        The model will generate a short music extract based on the image you provided.
        You can generate up to 30 seconds of audio.

        This demo is set to use only the Melody model
        1. Melody -- a music generation model capable of generating music condition on text and melody inputs. **Note**, you can also use text only.
        2. Small -- a 300M transformer decoder conditioned on text only.
        3. Medium -- a 1.5B transformer decoder conditioned on text only.
        4. Large -- a 3.3B transformer decoder conditioned on text only (might OOM for the longest sequences.)

        When using `melody`, ou can optionaly provide a reference audio from
        which a broad melody will be extracted. The model will then try to follow both the description and melody provided.

        You can also use your own GPU or a Google Colab by following the instructions on our repo.
        See [github.com/facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft)
        for more details.
        """
    )

demo.queue(max_size=32).launch()