import gradio as gr import torch from spectro import wav_bytes_from_spectrogram_image from diffusers import StableDiffusionPipeline from share_btn import community_icon_html, loading_icon_html, share_js model_id = "riffusion/riffusion-model-v1" pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) pipe = pipe.to("cuda") def predict(prompt): spec = pipe(prompt).images[0] print(spec) wav = wav_bytes_from_spectrogram_image(spec) with open("output.wav", "wb") as f: f.write(wav[0].getbuffer()) return spec, 'output.wav', gr.update(visible=True), gr.update(visible=True), gr.update(visible=True) title = """
Describe a musical prompt, generate music by getting a spectrogram image & sound.
About the model: Riffusion is a latent text-to-image diffusion model capable of generating spectrogram images given any text input. These spectrograms can be converted into audio clips.
—
The Riffusion model was created by fine-tuning the Stable-Diffusion-v1-5 checkpoint.
—
The model is intended for research purposes only. Possible research areas and tasks include
generation of artworks, audio, and use in creative processes, applications in educational or creative tools, research on generative models.
Do you need faster results ? You can skip the queue by duplicating this space:
""" css = ''' #col-container, #col-container-2 {max-width: 510px; margin-left: auto; margin-right: auto;} a {text-decoration-line: underline; font-weight: 600;} div#record_btn > .mt-6 { margin-top: 0!important; } div#record_btn > .mt-6 button { width: 100%; height: 40px; } .footer { margin-bottom: 45px; margin-top: 10px; text-align: center; border-bottom: 1px solid #e5e5e5; } .footer>p { font-size: .8rem; display: inline-block; padding: 0 10px; transform: translateY(10px); background: white; } .dark .footer { border-color: #303030; } .dark .footer>p { background: #0b0f19; } .animate-spin { animation: spin 1s linear infinite; } @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } } #share-btn-container { display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem; } #share-btn { all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;right:0; } #share-btn * { all: unset; } #share-btn-container div:nth-child(-n+2){ width: auto !important; min-height: 0px !important; } #share-btn-container .wrap { display: none !important; } ''' with gr.Blocks(css=css) as demo: with gr.Column(elem_id="col-container"): gr.HTML(title) prompt_input = gr.Textbox(placeholder="a cat diva singing in a New York jazz club", label="Musical prompt", elem_id="prompt-in") send_btn = gr.Button(value="Get a new spectrogram ! ", elem_id="submit-btn") with gr.Column(elem_id="col-container-2"): spectrogram_output = gr.Image(label="spectrogram image result", elem_id="img-out") sound_output = gr.Audio(type='filepath', label="spectrogram sound", elem_id="music-out") with gr.Group(elem_id="share-btn-container"): community_icon = gr.HTML(community_icon_html, visible=False) loading_icon = gr.HTML(loading_icon_html, visible=False) share_button = gr.Button("Share to community", elem_id="share-btn", visible=False) gr.HTML(article) send_btn.click(predict, inputs=[prompt_input], outputs=[spectrogram_output, sound_output, share_button, community_icon, loading_icon]) share_button.click(None, [], [], _js=share_js) demo.queue(max_size=250).launch(debug=True)