File size: 35,574 Bytes
b68ef84 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 |
from inspect import cleandoc
from typing import Optional
from typing_extensions import override
from comfy_api.latest import ComfyExtension, Input, io as comfy_io
from comfy_api_nodes.apis.stability_api import (
StabilityUpscaleConservativeRequest,
StabilityUpscaleCreativeRequest,
StabilityAsyncResponse,
StabilityResultsGetResponse,
StabilityStable3_5Request,
StabilityStableUltraRequest,
StabilityStableUltraResponse,
StabilityAspectRatio,
Stability_SD3_5_Model,
Stability_SD3_5_GenerationMode,
get_stability_style_presets,
StabilityTextToAudioRequest,
StabilityAudioToAudioRequest,
StabilityAudioInpaintRequest,
StabilityAudioResponse,
)
from comfy_api_nodes.apis.client import (
ApiEndpoint,
HttpMethod,
SynchronousOperation,
PollingOperation,
EmptyRequest,
)
from comfy_api_nodes.apinode_utils import (
bytesio_to_image_tensor,
tensor_to_bytesio,
validate_string,
audio_bytes_to_audio_input,
audio_input_to_mp3,
)
from comfy_api_nodes.util.validation_utils import validate_audio_duration
import torch
import base64
from io import BytesIO
from enum import Enum
class StabilityPollStatus(str, Enum):
finished = "finished"
in_progress = "in_progress"
failed = "failed"
def get_async_dummy_status(x: StabilityResultsGetResponse):
if x.name is not None or x.errors is not None:
return StabilityPollStatus.failed
elif x.finish_reason is not None:
return StabilityPollStatus.finished
return StabilityPollStatus.in_progress
class StabilityStableImageUltraNode(comfy_io.ComfyNode):
"""
Generates images synchronously based on prompt and resolution.
"""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityStableImageUltraNode",
display_name="Stability AI Stable Image Ultra",
category="api node/image/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.String.Input(
"prompt",
multiline=True,
default="",
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines" +
"elements, colors, and subjects will lead to better results. " +
"To control the weight of a given word use the format `(word:weight)`," +
"where `word` is the word you'd like to control the weight of and `weight`" +
"is a value between 0 and 1. For example: `The sky was a crisp (blue:0.3) and (green:0.8)`" +
"would convey a sky that was blue and green, but more green than blue.",
),
comfy_io.Combo.Input(
"aspect_ratio",
options=[x.value for x in StabilityAspectRatio],
default=StabilityAspectRatio.ratio_1_1.value,
tooltip="Aspect ratio of generated image.",
),
comfy_io.Combo.Input(
"style_preset",
options=get_stability_style_presets(),
tooltip="Optional desired style of generated image.",
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for creating the noise.",
),
comfy_io.Image.Input(
"image",
optional=True,
),
comfy_io.String.Input(
"negative_prompt",
default="",
tooltip="A blurb of text describing what you do not wish to see in the output image. This is an advanced feature.",
force_input=True,
optional=True,
),
comfy_io.Float.Input(
"image_denoise",
default=0.5,
min=0.0,
max=1.0,
step=0.01,
tooltip="Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
optional=True,
),
],
outputs=[
comfy_io.Image.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(
cls,
prompt: str,
aspect_ratio: str,
style_preset: str,
seed: int,
image: Optional[torch.Tensor] = None,
negative_prompt: str = "",
image_denoise: Optional[float] = 0.5,
) -> comfy_io.NodeOutput:
validate_string(prompt, strip_whitespace=False)
# prepare image binary if image present
image_binary = None
if image is not None:
image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
else:
image_denoise = None
if not negative_prompt:
negative_prompt = None
if style_preset == "None":
style_preset = None
files = {
"image": image_binary
}
auth = {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
}
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/stable-image/generate/ultra",
method=HttpMethod.POST,
request_model=StabilityStableUltraRequest,
response_model=StabilityStableUltraResponse,
),
request=StabilityStableUltraRequest(
prompt=prompt,
negative_prompt=negative_prompt,
aspect_ratio=aspect_ratio,
seed=seed,
strength=image_denoise,
style_preset=style_preset,
),
files=files,
content_type="multipart/form-data",
auth_kwargs=auth,
)
response_api = await operation.execute()
if response_api.finish_reason != "SUCCESS":
raise Exception(f"Stable Image Ultra generation failed: {response_api.finish_reason}.")
image_data = base64.b64decode(response_api.image)
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
return comfy_io.NodeOutput(returned_image)
class StabilityStableImageSD_3_5Node(comfy_io.ComfyNode):
"""
Generates images synchronously based on prompt and resolution.
"""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityStableImageSD_3_5Node",
display_name="Stability AI Stable Diffusion 3.5 Image",
category="api node/image/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.String.Input(
"prompt",
multiline=True,
default="",
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
),
comfy_io.Combo.Input(
"model",
options=[x.value for x in Stability_SD3_5_Model],
),
comfy_io.Combo.Input(
"aspect_ratio",
options=[x.value for x in StabilityAspectRatio],
default=StabilityAspectRatio.ratio_1_1.value,
tooltip="Aspect ratio of generated image.",
),
comfy_io.Combo.Input(
"style_preset",
options=get_stability_style_presets(),
tooltip="Optional desired style of generated image.",
),
comfy_io.Float.Input(
"cfg_scale",
default=4.0,
min=1.0,
max=10.0,
step=0.1,
tooltip="How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)",
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for creating the noise.",
),
comfy_io.Image.Input(
"image",
optional=True,
),
comfy_io.String.Input(
"negative_prompt",
default="",
tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.",
force_input=True,
optional=True,
),
comfy_io.Float.Input(
"image_denoise",
default=0.5,
min=0.0,
max=1.0,
step=0.01,
tooltip="Denoise of input image; 0.0 yields image identical to input, 1.0 is as if no image was provided at all.",
optional=True,
),
],
outputs=[
comfy_io.Image.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(
cls,
model: str,
prompt: str,
aspect_ratio: str,
style_preset: str,
seed: int,
cfg_scale: float,
image: Optional[torch.Tensor] = None,
negative_prompt: str = "",
image_denoise: Optional[float] = 0.5,
) -> comfy_io.NodeOutput:
validate_string(prompt, strip_whitespace=False)
# prepare image binary if image present
image_binary = None
mode = Stability_SD3_5_GenerationMode.text_to_image
if image is not None:
image_binary = tensor_to_bytesio(image, total_pixels=1504*1504).read()
mode = Stability_SD3_5_GenerationMode.image_to_image
aspect_ratio = None
else:
image_denoise = None
if not negative_prompt:
negative_prompt = None
if style_preset == "None":
style_preset = None
files = {
"image": image_binary
}
auth = {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
}
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/stable-image/generate/sd3",
method=HttpMethod.POST,
request_model=StabilityStable3_5Request,
response_model=StabilityStableUltraResponse,
),
request=StabilityStable3_5Request(
prompt=prompt,
negative_prompt=negative_prompt,
aspect_ratio=aspect_ratio,
seed=seed,
strength=image_denoise,
style_preset=style_preset,
cfg_scale=cfg_scale,
model=model,
mode=mode,
),
files=files,
content_type="multipart/form-data",
auth_kwargs=auth,
)
response_api = await operation.execute()
if response_api.finish_reason != "SUCCESS":
raise Exception(f"Stable Diffusion 3.5 Image generation failed: {response_api.finish_reason}.")
image_data = base64.b64decode(response_api.image)
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
return comfy_io.NodeOutput(returned_image)
class StabilityUpscaleConservativeNode(comfy_io.ComfyNode):
"""
Upscale image with minimal alterations to 4K resolution.
"""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityUpscaleConservativeNode",
display_name="Stability AI Upscale Conservative",
category="api node/image/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.Image.Input("image"),
comfy_io.String.Input(
"prompt",
multiline=True,
default="",
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
),
comfy_io.Float.Input(
"creativity",
default=0.35,
min=0.2,
max=0.5,
step=0.01,
tooltip="Controls the likelihood of creating additional details not heavily conditioned by the init image.",
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for creating the noise.",
),
comfy_io.String.Input(
"negative_prompt",
default="",
tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.",
force_input=True,
optional=True,
),
],
outputs=[
comfy_io.Image.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(
cls,
image: torch.Tensor,
prompt: str,
creativity: float,
seed: int,
negative_prompt: str = "",
) -> comfy_io.NodeOutput:
validate_string(prompt, strip_whitespace=False)
image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read()
if not negative_prompt:
negative_prompt = None
files = {
"image": image_binary
}
auth = {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
}
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/stable-image/upscale/conservative",
method=HttpMethod.POST,
request_model=StabilityUpscaleConservativeRequest,
response_model=StabilityStableUltraResponse,
),
request=StabilityUpscaleConservativeRequest(
prompt=prompt,
negative_prompt=negative_prompt,
creativity=round(creativity,2),
seed=seed,
),
files=files,
content_type="multipart/form-data",
auth_kwargs=auth,
)
response_api = await operation.execute()
if response_api.finish_reason != "SUCCESS":
raise Exception(f"Stability Upscale Conservative generation failed: {response_api.finish_reason}.")
image_data = base64.b64decode(response_api.image)
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
return comfy_io.NodeOutput(returned_image)
class StabilityUpscaleCreativeNode(comfy_io.ComfyNode):
"""
Upscale image with minimal alterations to 4K resolution.
"""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityUpscaleCreativeNode",
display_name="Stability AI Upscale Creative",
category="api node/image/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.Image.Input("image"),
comfy_io.String.Input(
"prompt",
multiline=True,
default="",
tooltip="What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results.",
),
comfy_io.Float.Input(
"creativity",
default=0.3,
min=0.1,
max=0.5,
step=0.01,
tooltip="Controls the likelihood of creating additional details not heavily conditioned by the init image.",
),
comfy_io.Combo.Input(
"style_preset",
options=get_stability_style_presets(),
tooltip="Optional desired style of generated image.",
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for creating the noise.",
),
comfy_io.String.Input(
"negative_prompt",
default="",
tooltip="Keywords of what you do not wish to see in the output image. This is an advanced feature.",
force_input=True,
optional=True,
),
],
outputs=[
comfy_io.Image.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(
cls,
image: torch.Tensor,
prompt: str,
creativity: float,
style_preset: str,
seed: int,
negative_prompt: str = "",
) -> comfy_io.NodeOutput:
validate_string(prompt, strip_whitespace=False)
image_binary = tensor_to_bytesio(image, total_pixels=1024*1024).read()
if not negative_prompt:
negative_prompt = None
if style_preset == "None":
style_preset = None
files = {
"image": image_binary
}
auth = {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
}
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/stable-image/upscale/creative",
method=HttpMethod.POST,
request_model=StabilityUpscaleCreativeRequest,
response_model=StabilityAsyncResponse,
),
request=StabilityUpscaleCreativeRequest(
prompt=prompt,
negative_prompt=negative_prompt,
creativity=round(creativity,2),
style_preset=style_preset,
seed=seed,
),
files=files,
content_type="multipart/form-data",
auth_kwargs=auth,
)
response_api = await operation.execute()
operation = PollingOperation(
poll_endpoint=ApiEndpoint(
path=f"/proxy/stability/v2beta/results/{response_api.id}",
method=HttpMethod.GET,
request_model=EmptyRequest,
response_model=StabilityResultsGetResponse,
),
poll_interval=3,
completed_statuses=[StabilityPollStatus.finished],
failed_statuses=[StabilityPollStatus.failed],
status_extractor=lambda x: get_async_dummy_status(x),
auth_kwargs=auth,
node_id=cls.hidden.unique_id,
)
response_poll: StabilityResultsGetResponse = await operation.execute()
if response_poll.finish_reason != "SUCCESS":
raise Exception(f"Stability Upscale Creative generation failed: {response_poll.finish_reason}.")
image_data = base64.b64decode(response_poll.result)
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
return comfy_io.NodeOutput(returned_image)
class StabilityUpscaleFastNode(comfy_io.ComfyNode):
"""
Quickly upscales an image via Stability API call to 4x its original size; intended for upscaling low-quality/compressed images.
"""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityUpscaleFastNode",
display_name="Stability AI Upscale Fast",
category="api node/image/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.Image.Input("image"),
],
outputs=[
comfy_io.Image.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(cls, image: torch.Tensor) -> comfy_io.NodeOutput:
image_binary = tensor_to_bytesio(image, total_pixels=4096*4096).read()
files = {
"image": image_binary
}
auth = {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
}
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/stable-image/upscale/fast",
method=HttpMethod.POST,
request_model=EmptyRequest,
response_model=StabilityStableUltraResponse,
),
request=EmptyRequest(),
files=files,
content_type="multipart/form-data",
auth_kwargs=auth,
)
response_api = await operation.execute()
if response_api.finish_reason != "SUCCESS":
raise Exception(f"Stability Upscale Fast failed: {response_api.finish_reason}.")
image_data = base64.b64decode(response_api.image)
returned_image = bytesio_to_image_tensor(BytesIO(image_data))
return comfy_io.NodeOutput(returned_image)
class StabilityTextToAudio(comfy_io.ComfyNode):
"""Generates high-quality music and sound effects from text descriptions."""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityTextToAudio",
display_name="Stability AI Text To Audio",
category="api node/audio/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.Combo.Input(
"model",
options=["stable-audio-2.5"],
),
comfy_io.String.Input("prompt", multiline=True, default=""),
comfy_io.Int.Input(
"duration",
default=190,
min=1,
max=190,
step=1,
tooltip="Controls the duration in seconds of the generated audio.",
optional=True,
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for generation.",
optional=True,
),
comfy_io.Int.Input(
"steps",
default=8,
min=4,
max=8,
step=1,
tooltip="Controls the number of sampling steps.",
optional=True,
),
],
outputs=[
comfy_io.Audio.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(cls, model: str, prompt: str, duration: int, seed: int, steps: int) -> comfy_io.NodeOutput:
validate_string(prompt, max_length=10000)
payload = StabilityTextToAudioRequest(prompt=prompt, model=model, duration=duration, seed=seed, steps=steps)
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/audio/stable-audio-2/text-to-audio",
method=HttpMethod.POST,
request_model=StabilityTextToAudioRequest,
response_model=StabilityAudioResponse,
),
request=payload,
content_type="multipart/form-data",
auth_kwargs= {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
)
response_api = await operation.execute()
if not response_api.audio:
raise ValueError("No audio file was received in response.")
return comfy_io.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio)))
class StabilityAudioToAudio(comfy_io.ComfyNode):
"""Transforms existing audio samples into new high-quality compositions using text instructions."""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityAudioToAudio",
display_name="Stability AI Audio To Audio",
category="api node/audio/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.Combo.Input(
"model",
options=["stable-audio-2.5"],
),
comfy_io.String.Input("prompt", multiline=True, default=""),
comfy_io.Audio.Input("audio", tooltip="Audio must be between 6 and 190 seconds long."),
comfy_io.Int.Input(
"duration",
default=190,
min=1,
max=190,
step=1,
tooltip="Controls the duration in seconds of the generated audio.",
optional=True,
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for generation.",
optional=True,
),
comfy_io.Int.Input(
"steps",
default=8,
min=4,
max=8,
step=1,
tooltip="Controls the number of sampling steps.",
optional=True,
),
comfy_io.Float.Input(
"strength",
default=1,
min=0.01,
max=1.0,
step=0.01,
display_mode=comfy_io.NumberDisplay.slider,
tooltip="Parameter controls how much influence the audio parameter has on the generated audio.",
optional=True,
),
],
outputs=[
comfy_io.Audio.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(
cls, model: str, prompt: str, audio: Input.Audio, duration: int, seed: int, steps: int, strength: float
) -> comfy_io.NodeOutput:
validate_string(prompt, max_length=10000)
validate_audio_duration(audio, 6, 190)
payload = StabilityAudioToAudioRequest(
prompt=prompt, model=model, duration=duration, seed=seed, steps=steps, strength=strength
)
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/audio/stable-audio-2/audio-to-audio",
method=HttpMethod.POST,
request_model=StabilityAudioToAudioRequest,
response_model=StabilityAudioResponse,
),
request=payload,
content_type="multipart/form-data",
files={"audio": audio_input_to_mp3(audio)},
auth_kwargs= {
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
)
response_api = await operation.execute()
if not response_api.audio:
raise ValueError("No audio file was received in response.")
return comfy_io.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio)))
class StabilityAudioInpaint(comfy_io.ComfyNode):
"""Transforms part of existing audio sample using text instructions."""
@classmethod
def define_schema(cls):
return comfy_io.Schema(
node_id="StabilityAudioInpaint",
display_name="Stability AI Audio Inpaint",
category="api node/audio/Stability AI",
description=cleandoc(cls.__doc__ or ""),
inputs=[
comfy_io.Combo.Input(
"model",
options=["stable-audio-2.5"],
),
comfy_io.String.Input("prompt", multiline=True, default=""),
comfy_io.Audio.Input("audio", tooltip="Audio must be between 6 and 190 seconds long."),
comfy_io.Int.Input(
"duration",
default=190,
min=1,
max=190,
step=1,
tooltip="Controls the duration in seconds of the generated audio.",
optional=True,
),
comfy_io.Int.Input(
"seed",
default=0,
min=0,
max=4294967294,
step=1,
display_mode=comfy_io.NumberDisplay.number,
control_after_generate=True,
tooltip="The random seed used for generation.",
optional=True,
),
comfy_io.Int.Input(
"steps",
default=8,
min=4,
max=8,
step=1,
tooltip="Controls the number of sampling steps.",
optional=True,
),
comfy_io.Int.Input(
"mask_start",
default=30,
min=0,
max=190,
step=1,
optional=True,
),
comfy_io.Int.Input(
"mask_end",
default=190,
min=0,
max=190,
step=1,
optional=True,
),
],
outputs=[
comfy_io.Audio.Output(),
],
hidden=[
comfy_io.Hidden.auth_token_comfy_org,
comfy_io.Hidden.api_key_comfy_org,
comfy_io.Hidden.unique_id,
],
is_api_node=True,
)
@classmethod
async def execute(
cls,
model: str,
prompt: str,
audio: Input.Audio,
duration: int,
seed: int,
steps: int,
mask_start: int,
mask_end: int,
) -> comfy_io.NodeOutput:
validate_string(prompt, max_length=10000)
if mask_end <= mask_start:
raise ValueError(f"Value of mask_end({mask_end}) should be greater then mask_start({mask_start})")
validate_audio_duration(audio, 6, 190)
payload = StabilityAudioInpaintRequest(
prompt=prompt,
model=model,
duration=duration,
seed=seed,
steps=steps,
mask_start=mask_start,
mask_end=mask_end,
)
operation = SynchronousOperation(
endpoint=ApiEndpoint(
path="/proxy/stability/v2beta/audio/stable-audio-2/inpaint",
method=HttpMethod.POST,
request_model=StabilityAudioInpaintRequest,
response_model=StabilityAudioResponse,
),
request=payload,
content_type="multipart/form-data",
files={"audio": audio_input_to_mp3(audio)},
auth_kwargs={
"auth_token": cls.hidden.auth_token_comfy_org,
"comfy_api_key": cls.hidden.api_key_comfy_org,
},
)
response_api = await operation.execute()
if not response_api.audio:
raise ValueError("No audio file was received in response.")
return comfy_io.NodeOutput(audio_bytes_to_audio_input(base64.b64decode(response_api.audio)))
class StabilityExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[comfy_io.ComfyNode]]:
return [
StabilityStableImageUltraNode,
StabilityStableImageSD_3_5Node,
StabilityUpscaleConservativeNode,
StabilityUpscaleCreativeNode,
StabilityUpscaleFastNode,
StabilityTextToAudio,
StabilityAudioToAudio,
StabilityAudioInpaint,
]
async def comfy_entrypoint() -> StabilityExtension:
return StabilityExtension()
|