File size: 38,290 Bytes
96ec844 5488167 71922e7 96ec844 5488167 04f880c 5488167 96ec844 04f880c 5488167 96ec844 5488167 96ec844 5488167 48bb372 96ec844 71922e7 96ec844 5488167 48bb372 96ec844 5488167 96ec844 71922e7 5488167 96ec844 71922e7 96ec844 5488167 96ec844 5488167 48bb372 5488167 96ec844 48bb372 5488167 71922e7 5488167 96ec844 5488167 96ec844 5488167 96ec844 5488167 96ec844 71922e7 96ec844 48bb372 96ec844 48bb372 71922e7 48bb372 71922e7 96ec844 48bb372 96ec844 48bb372 71922e7 48bb372 5488167 48bb372 96ec844 71922e7 96ec844 71922e7 48bb372 566c01f 48bb372 71922e7 48bb372 96ec844 48bb372 96ec844 48bb372 96ec844 48bb372 71922e7 48bb372 566c01f 48bb372 71922e7 96ec844 48bb372 566c01f 96ec844 48bb372 71922e7 48bb372 566c01f 48bb372 566c01f 96ec844 71922e7 96ec844 566c01f 96ec844 566c01f 71922e7 566c01f 71922e7 96ec844 566c01f 71922e7 566c01f 96ec844 566c01f 71922e7 566c01f 5488167 96ec844 5488167 96ec844 5488167 71922e7 96ec844 5488167 96ec844 5488167 96ec844 5488167 96ec844 5488167 96ec844 5488167 48bb372 5488167 48bb372 97428c7 96ec844 5488167 96ec844 5488167 |
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 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 |
"""
ACE-Step: A Step Towards Music Generation Foundation Model
https://github.com/ace-step/ACE-Step
Apache 2.0 License
"""
import gradio as gr
import librosa
import os
TAG_DEFAULT = "funk, pop, soul, rock, melodic, guitar, drums, bass, keyboard, percussion, 105 BPM, energetic, upbeat, groovy, vibrant, dynamic"
LYRIC_DEFAULT = """[verse]
Neon lights they flicker bright
City hums in dead of night
Rhythms pulse through concrete veins
Lost in echoes of refrains
[verse]
Bassline groovin' in my chest
Heartbeats match the city's zest
Electric whispers fill the air
Synthesized dreams everywhere
[chorus]
Turn it up and let it flow
Feel the fire let it grow
In this rhythm we belong
Hear the night sing out our song
[verse]
Guitar strings they start to weep
Wake the soul from silent sleep
Every note a story told
In this night we’re bold and gold
[bridge]
Voices blend in harmony
Lost in pure cacophony
Timeless echoes timeless cries
Soulful shouts beneath the skies
[verse]
Keyboard dances on the keys
Melodies on evening breeze
Catch the tune and hold it tight
In this moment we take flight
"""
# First, let's define the presets at the top of the file, after the imports
GENRE_PRESETS = {
"Modern Pop": "pop, synth, drums, guitar, 120 bpm, upbeat, catchy, vibrant, female vocals, polished vocals",
"Rock": "rock, electric guitar, drums, bass, 130 bpm, energetic, rebellious, gritty, male vocals, raw vocals",
"Hip Hop": "hip hop, 808 bass, hi-hats, synth, 90 bpm, bold, urban, intense, male vocals, rhythmic vocals",
"Country": "country, acoustic guitar, steel guitar, fiddle, 100 bpm, heartfelt, rustic, warm, male vocals, twangy vocals",
"EDM": "edm, synth, bass, kick drum, 128 bpm, euphoric, pulsating, energetic, instrumental",
"Reggae": "reggae, guitar, bass, drums, 80 bpm, chill, soulful, positive, male vocals, smooth vocals",
"Classical": "classical, orchestral, strings, piano, 60 bpm, elegant, emotive, timeless, instrumental",
"Jazz": "jazz, saxophone, piano, double bass, 110 bpm, smooth, improvisational, soulful, male vocals, crooning vocals",
"Metal": "metal, electric guitar, double kick drum, bass, 160 bpm, aggressive, intense, heavy, male vocals, screamed vocals",
"R&B": "r&b, synth, bass, drums, 85 bpm, sultry, groovy, romantic, female vocals, silky vocals"
}
# Add this function to handle preset selection
def update_tags_from_preset(preset_name):
if preset_name == "Custom":
return ""
return GENRE_PRESETS.get(preset_name, "")
def create_output_ui(task_name="Text2Music"):
# For many consumer-grade GPU devices, only one batch can be run
output_audio1 = gr.Audio(type="filepath", label=f"{task_name} Generated Audio 1")
# output_audio2 = gr.Audio(type="filepath", label="Generated Audio 2")
with gr.Accordion(f"{task_name} Parameters", open=False):
input_params_json = gr.JSON(label=f"{task_name} Parameters")
# outputs = [output_audio1, output_audio2]
outputs = [output_audio1]
return outputs, input_params_json
def dump_func(*args):
print(args)
return []
def create_text2music_ui(
gr,
text2music_process_func,
sample_data_func=None,
load_data_func=None,
):
with gr.Row():
with gr.Column():
with gr.Row(equal_height=True):
# add markdown, tags and lyrics examples are from ai music generation community
audio_duration = gr.Slider(
-1,
240.0,
step=0.00001,
value=-1,
label="Audio Duration",
interactive=True,
info="-1 means random duration (30 ~ 240).",
scale=9,
)
sample_bnt = gr.Button("Sample", variant="secondary", scale=1)
# audio2audio
with gr.Row(equal_height=True):
audio2audio_enable = gr.Checkbox(label="Enable Audio2Audio", value=False, info="Check to enable Audio-to-Audio generation using a reference audio.", elem_id="audio2audio_checkbox")
lora_name_or_path = gr.Dropdown(
label="Lora Name or Path",
choices=["ACE-Step/ACE-Step-v1-chinese-rap-LoRA", "none"],
value="none",
allow_custom_value=True,
)
ref_audio_input = gr.Audio(type="filepath", label="Reference Audio (for Audio2Audio)", visible=False, elem_id="ref_audio_input", show_download_button=True)
ref_audio_strength = gr.Slider(
label="Refer audio strength",
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.5,
elem_id="ref_audio_strength",
visible=False,
interactive=True,
)
def toggle_ref_audio_visibility(is_checked):
return (
gr.update(visible=is_checked, elem_id="ref_audio_input"),
gr.update(visible=is_checked, elem_id="ref_audio_strength"),
)
audio2audio_enable.change(
fn=toggle_ref_audio_visibility,
inputs=[audio2audio_enable],
outputs=[ref_audio_input, ref_audio_strength],
)
with gr.Column(scale=2):
with gr.Group():
gr.Markdown("""<center>Support tags, descriptions, and scene. Use commas to separate different tags.<br>Tags and lyrics examples are from AI music generation community.</center>""")
with gr.Row():
genre_preset = gr.Dropdown(
choices=["Custom"] + list(GENRE_PRESETS.keys()),
value="Custom",
label="Preset",
scale=1,
)
prompt = gr.Textbox(
lines=1,
label="Tags",
max_lines=4,
value=TAG_DEFAULT,
scale=9,
)
# Add the change event for the preset dropdown
genre_preset.change(
fn=update_tags_from_preset,
inputs=[genre_preset],
outputs=[prompt]
)
with gr.Group():
gr.Markdown("""<center>Support lyric structure tags like [verse], [chorus], and [bridge] to separate different parts of the lyrics.<br>Use [instrumental] or [inst] to generate instrumental music. Not support genre structure tag in lyrics</center>""")
lyrics = gr.Textbox(
lines=9,
label="Lyrics",
max_lines=13,
value=LYRIC_DEFAULT,
)
with gr.Accordion("Basic Settings", open=False):
infer_step = gr.Slider(
minimum=1,
maximum=200,
step=1,
value=60,
label="Infer Steps",
interactive=True,
)
guidance_scale = gr.Slider(
minimum=0.0,
maximum=30.0,
step=0.1,
value=15.0,
label="Guidance Scale",
interactive=True,
info="When guidance_scale_lyric > 1 and guidance_scale_text > 1, the guidance scale will not be applied.",
)
guidance_scale_text = gr.Slider(
minimum=0.0,
maximum=10.0,
step=0.1,
value=0.0,
label="Guidance Scale Text",
interactive=True,
info="Guidance scale for text condition. It can only apply to cfg. set guidance_scale_text=5.0, guidance_scale_lyric=1.5 for start",
)
guidance_scale_lyric = gr.Slider(
minimum=0.0,
maximum=10.0,
step=0.1,
value=0.0,
label="Guidance Scale Lyric",
interactive=True,
)
manual_seeds = gr.Textbox(
label="manual seeds (default None)",
placeholder="1,2,3,4",
value=None,
info="Seed for the generation",
)
with gr.Accordion("Advanced Settings", open=False):
scheduler_type = gr.Radio(
["euler", "heun"],
value="euler",
label="Scheduler Type",
elem_id="scheduler_type",
info="Scheduler type for the generation. euler is recommended. heun will take more time.",
)
cfg_type = gr.Radio(
["cfg", "apg", "cfg_star"],
value="apg",
label="CFG Type",
elem_id="cfg_type",
info="CFG type for the generation. apg is recommended. cfg and cfg_star are almost the same.",
)
use_erg_tag = gr.Checkbox(
label="use ERG for tag",
value=True,
info="Use Entropy Rectifying Guidance for tag. It will multiple a temperature to the attention to make a weaker tag condition and make better diversity.",
)
use_erg_lyric = gr.Checkbox(
label="use ERG for lyric",
value=False,
info="The same but apply to lyric encoder's attention.",
)
use_erg_diffusion = gr.Checkbox(
label="use ERG for diffusion",
value=True,
info="The same but apply to diffusion model's attention.",
)
omega_scale = gr.Slider(
minimum=-100.0,
maximum=100.0,
step=0.1,
value=10.0,
label="Granularity Scale",
interactive=True,
info="Granularity scale for the generation. Higher values can reduce artifacts",
)
guidance_interval = gr.Slider(
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.5,
label="Guidance Interval",
interactive=True,
info="Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)",
)
guidance_interval_decay = gr.Slider(
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.0,
label="Guidance Interval Decay",
interactive=True,
info="Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.",
)
min_guidance_scale = gr.Slider(
minimum=0.0,
maximum=200.0,
step=0.1,
value=3.0,
label="Min Guidance Scale",
interactive=True,
info="Min guidance scale for guidance interval decay's end scale",
)
oss_steps = gr.Textbox(
label="OSS Steps",
placeholder="16, 29, 52, 96, 129, 158, 172, 183, 189, 200",
value=None,
info="Optimal Steps for the generation. But not test well",
)
text2music_bnt = gr.Button("Generate", variant="primary")
with gr.Column():
outputs, input_params_json = create_output_ui()
with gr.Tab("retake"):
retake_variance = gr.Slider(
minimum=0.0, maximum=1.0, step=0.01, value=0.2, label="variance"
)
retake_seeds = gr.Textbox(
label="retake seeds (default None)", placeholder="", value=None
)
retake_bnt = gr.Button("Retake", variant="primary")
retake_outputs, retake_input_params_json = create_output_ui("Retake")
def retake_process_func(json_data, retake_variance, retake_seeds):
return text2music_process_func(
json_data["audio_duration"],
json_data["prompt"],
json_data["lyrics"],
json_data["infer_step"],
json_data["guidance_scale"],
json_data["scheduler_type"],
json_data["cfg_type"],
json_data["omega_scale"],
", ".join(map(str, json_data["actual_seeds"])),
json_data["guidance_interval"],
json_data["guidance_interval_decay"],
json_data["min_guidance_scale"],
json_data["use_erg_tag"],
json_data["use_erg_lyric"],
json_data["use_erg_diffusion"],
", ".join(map(str, json_data["oss_steps"])),
(
json_data["guidance_scale_text"]
if "guidance_scale_text" in json_data
else 0.0
),
(
json_data["guidance_scale_lyric"]
if "guidance_scale_lyric" in json_data
else 0.0
),
retake_seeds=retake_seeds,
retake_variance=retake_variance,
task="retake",
lora_name_or_path="none" if "lora_name_or_path" not in json_data else json_data["lora_name_or_path"]
)
retake_bnt.click(
fn=retake_process_func,
inputs=[
input_params_json,
retake_variance,
retake_seeds,
],
outputs=retake_outputs + [retake_input_params_json],
)
with gr.Tab("repainting"):
retake_variance = gr.Slider(
minimum=0.0, maximum=1.0, step=0.01, value=0.2, label="variance"
)
retake_seeds = gr.Textbox(
label="repaint seeds (default None)", placeholder="", value=None
)
repaint_start = gr.Slider(
minimum=0.0,
maximum=240.0,
step=0.01,
value=0.0,
label="Repaint Start Time",
interactive=True,
)
repaint_end = gr.Slider(
minimum=0.0,
maximum=240.0,
step=0.01,
value=30.0,
label="Repaint End Time",
interactive=True,
)
repaint_source = gr.Radio(
["text2music", "last_repaint", "upload"],
value="text2music",
label="Repaint Source",
elem_id="repaint_source",
)
repaint_source_audio_upload = gr.Audio(
label="Upload Audio",
type="filepath",
visible=False,
elem_id="repaint_source_audio_upload",
show_download_button=True,
)
repaint_source.change(
fn=lambda x: gr.update(
visible=x == "upload", elem_id="repaint_source_audio_upload"
),
inputs=[repaint_source],
outputs=[repaint_source_audio_upload],
)
repaint_bnt = gr.Button("Repaint", variant="primary")
repaint_outputs, repaint_input_params_json = create_output_ui("Repaint")
def repaint_process_func(
text2music_json_data,
repaint_json_data,
retake_variance,
retake_seeds,
repaint_start,
repaint_end,
repaint_source,
repaint_source_audio_upload,
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
):
if repaint_source == "upload":
src_audio_path = repaint_source_audio_upload
audio_duration = librosa.get_duration(filename=src_audio_path)
json_data = {"audio_duration": audio_duration}
elif repaint_source == "text2music":
json_data = text2music_json_data
src_audio_path = json_data["audio_path"]
elif repaint_source == "last_repaint":
json_data = repaint_json_data
src_audio_path = json_data["audio_path"]
return text2music_process_func(
json_data["audio_duration"],
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
retake_seeds=retake_seeds,
retake_variance=retake_variance,
task="repaint",
repaint_start=repaint_start,
repaint_end=repaint_end,
src_audio_path=src_audio_path,
lora_name_or_path="none" if "lora_name_or_path" not in json_data else json_data["lora_name_or_path"]
)
repaint_bnt.click(
fn=repaint_process_func,
inputs=[
input_params_json,
repaint_input_params_json,
retake_variance,
retake_seeds,
repaint_start,
repaint_end,
repaint_source,
repaint_source_audio_upload,
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
],
outputs=repaint_outputs + [repaint_input_params_json],
)
with gr.Tab("edit"):
edit_prompt = gr.Textbox(lines=2, label="Edit Tags", max_lines=4)
edit_lyrics = gr.Textbox(lines=9, label="Edit Lyrics", max_lines=13)
retake_seeds = gr.Textbox(
label="edit seeds (default None)", placeholder="", value=None
)
edit_type = gr.Radio(
["only_lyrics", "remix"],
value="only_lyrics",
label="Edit Type",
elem_id="edit_type",
info="`only_lyrics` will keep the whole song the same except lyrics difference. Make your diffrence smaller, e.g. one lyrc line change.\nremix can change the song melody and genre",
)
edit_n_min = gr.Slider(
minimum=0.0,
maximum=1.0,
step=0.01,
value=0.6,
label="edit_n_min",
interactive=True,
)
edit_n_max = gr.Slider(
minimum=0.0,
maximum=1.0,
step=0.01,
value=1.0,
label="edit_n_max",
interactive=True,
)
def edit_type_change_func(edit_type):
if edit_type == "only_lyrics":
n_min = 0.6
n_max = 1.0
elif edit_type == "remix":
n_min = 0.2
n_max = 0.4
return n_min, n_max
edit_type.change(
edit_type_change_func,
inputs=[edit_type],
outputs=[edit_n_min, edit_n_max],
)
edit_source = gr.Radio(
["text2music", "last_edit", "upload"],
value="text2music",
label="Edit Source",
elem_id="edit_source",
)
edit_source_audio_upload = gr.Audio(
label="Upload Audio",
type="filepath",
visible=False,
elem_id="edit_source_audio_upload",
show_download_button=True,
)
edit_source.change(
fn=lambda x: gr.update(
visible=x == "upload", elem_id="edit_source_audio_upload"
),
inputs=[edit_source],
outputs=[edit_source_audio_upload],
)
edit_bnt = gr.Button("Edit", variant="primary")
edit_outputs, edit_input_params_json = create_output_ui("Edit")
def edit_process_func(
text2music_json_data,
edit_input_params_json,
edit_source,
edit_source_audio_upload,
prompt,
lyrics,
edit_prompt,
edit_lyrics,
edit_n_min,
edit_n_max,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
retake_seeds,
):
if edit_source == "upload":
src_audio_path = edit_source_audio_upload
audio_duration = librosa.get_duration(filename=src_audio_path)
json_data = {"audio_duration": audio_duration}
elif edit_source == "text2music":
json_data = text2music_json_data
src_audio_path = json_data["audio_path"]
elif edit_source == "last_edit":
json_data = edit_input_params_json
src_audio_path = json_data["audio_path"]
if not edit_prompt:
edit_prompt = prompt
if not edit_lyrics:
edit_lyrics = lyrics
return text2music_process_func(
json_data["audio_duration"],
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
task="edit",
src_audio_path=src_audio_path,
edit_target_prompt=edit_prompt,
edit_target_lyrics=edit_lyrics,
edit_n_min=edit_n_min,
edit_n_max=edit_n_max,
retake_seeds=retake_seeds,
lora_name_or_path="none" if "lora_name_or_path" not in json_data else json_data["lora_name_or_path"]
)
edit_bnt.click(
fn=edit_process_func,
inputs=[
input_params_json,
edit_input_params_json,
edit_source,
edit_source_audio_upload,
prompt,
lyrics,
edit_prompt,
edit_lyrics,
edit_n_min,
edit_n_max,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
retake_seeds,
],
outputs=edit_outputs + [edit_input_params_json],
)
with gr.Tab("extend"):
extend_seeds = gr.Textbox(
label="extend seeds (default None)", placeholder="", value=None
)
left_extend_length = gr.Slider(
minimum=0.0,
maximum=240.0,
step=0.01,
value=0.0,
label="Left Extend Length",
interactive=True,
)
right_extend_length = gr.Slider(
minimum=0.0,
maximum=240.0,
step=0.01,
value=30.0,
label="Right Extend Length",
interactive=True,
)
extend_source = gr.Radio(
["text2music", "last_extend", "upload"],
value="text2music",
label="Extend Source",
elem_id="extend_source",
)
extend_source_audio_upload = gr.Audio(
label="Upload Audio",
type="filepath",
visible=False,
elem_id="extend_source_audio_upload",
show_download_button=True,
)
extend_source.change(
fn=lambda x: gr.update(
visible=x == "upload", elem_id="extend_source_audio_upload"
),
inputs=[extend_source],
outputs=[extend_source_audio_upload],
)
extend_bnt = gr.Button("Extend", variant="primary")
extend_outputs, extend_input_params_json = create_output_ui("Extend")
def extend_process_func(
text2music_json_data,
extend_input_params_json,
extend_seeds,
left_extend_length,
right_extend_length,
extend_source,
extend_source_audio_upload,
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
):
if extend_source == "upload":
src_audio_path = extend_source_audio_upload
# get audio duration
audio_duration = librosa.get_duration(filename=src_audio_path)
json_data = {"audio_duration": audio_duration}
elif extend_source == "text2music":
json_data = text2music_json_data
src_audio_path = json_data["audio_path"]
elif extend_source == "last_extend":
json_data = extend_input_params_json
src_audio_path = json_data["audio_path"]
repaint_start = -left_extend_length
repaint_end = json_data["audio_duration"] + right_extend_length
return text2music_process_func(
json_data["audio_duration"],
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
retake_seeds=extend_seeds,
retake_variance=1.0,
task="extend",
repaint_start=repaint_start,
repaint_end=repaint_end,
src_audio_path=src_audio_path,
lora_name_or_path="none" if "lora_name_or_path" not in json_data else json_data["lora_name_or_path"]
)
extend_bnt.click(
fn=extend_process_func,
inputs=[
input_params_json,
extend_input_params_json,
extend_seeds,
left_extend_length,
right_extend_length,
extend_source,
extend_source_audio_upload,
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
],
outputs=extend_outputs + [extend_input_params_json],
)
def json2output(json_data):
return (
json_data["audio_duration"],
json_data["prompt"],
json_data["lyrics"],
json_data["infer_step"],
json_data["guidance_scale"],
json_data["scheduler_type"],
json_data["cfg_type"],
json_data["omega_scale"],
", ".join(map(str, json_data["actual_seeds"])),
json_data["guidance_interval"],
json_data["guidance_interval_decay"],
json_data["min_guidance_scale"],
json_data["use_erg_tag"],
json_data["use_erg_lyric"],
json_data["use_erg_diffusion"],
", ".join(map(str, json_data["oss_steps"])),
(
json_data["guidance_scale_text"]
if "guidance_scale_text" in json_data
else 0.0
),
(
json_data["guidance_scale_lyric"]
if "guidance_scale_lyric" in json_data
else 0.0
),
(
json_data["audio2audio_enable"]
if "audio2audio_enable" in json_data
else False
),
(
json_data["ref_audio_strength"]
if "ref_audio_strength" in json_data
else 0.5
),
(
json_data["ref_audio_input"]
if "ref_audio_input" in json_data
else None
),
)
def sample_data(lora_name_or_path_):
json_data = sample_data_func(lora_name_or_path_)
return json2output(json_data)
sample_bnt.click(
sample_data,
inputs=[lora_name_or_path],
outputs=[
audio_duration,
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
audio2audio_enable,
ref_audio_strength,
ref_audio_input,
],
)
text2music_bnt.click(
fn=text2music_process_func,
inputs=[
audio_duration,
prompt,
lyrics,
infer_step,
guidance_scale,
scheduler_type,
cfg_type,
omega_scale,
manual_seeds,
guidance_interval,
guidance_interval_decay,
min_guidance_scale,
use_erg_tag,
use_erg_lyric,
use_erg_diffusion,
oss_steps,
guidance_scale_text,
guidance_scale_lyric,
audio2audio_enable,
ref_audio_strength,
ref_audio_input,
lora_name_or_path,
],
outputs=outputs + [input_params_json],
)
def create_main_demo_ui(
text2music_process_func=dump_func,
sample_data_func=dump_func,
load_data_func=dump_func,
):
with gr.Blocks(
title="ACE-Step Model 1.0 DEMO",
) as demo:
gr.Markdown(
"""
<h1 style="text-align: center;">ACE-Step: A Step Towards Music Generation Foundation Model</h1>
<p>
<a href="https://ace-step.github.io/" target='_blank'>Project</a> |
<a href="https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B">Checkpoints</a> |
<a href="https://discord.gg/rjAZz2xBdG" target='_blank'>Discord</a>
</p>
"""
)
with gr.Tab("text2music"):
create_text2music_ui(
gr=gr,
text2music_process_func=text2music_process_func,
sample_data_func=sample_data_func,
load_data_func=load_data_func,
)
return demo
if __name__ == "__main__":
demo = create_main_demo_ui()
demo.launch(
server_name="0.0.0.0",
server_port=7860,
)
|