File size: 42,298 Bytes
5de606a | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 | import re
import torch
from typing_extensions import override
from comfy_api.latest import IO, ComfyExtension, Input
from comfy_api_nodes.apis.grok import (
ImageEditRequest,
ImageGenerationRequest,
ImageGenerationResponse,
InputUrlObject,
VideoEditRequest,
VideoExtensionRequest,
VideoGenerationRequest,
VideoGenerationResponse,
VideoStatusResponse,
VoiceReferenceObject,
)
from comfy_api_nodes.util import (
ApiEndpoint,
download_url_to_image_tensor,
download_url_to_video_output,
get_fs_object_size,
get_number_of_images,
poll_op,
sync_op,
tensor_to_base64_string,
upload_images_to_comfyapi,
upload_video_to_comfyapi,
validate_string,
validate_video_duration,
)
_GROK_VIDEO_MODEL_API_IDS = {
"grok-imagine-video-1.5": "grok-imagine-video-1.5",
}
_GROK_VOICE_OPTIONS = [
"none",
"ara",
"eve",
"leo",
"rex",
"sal",
"carina",
"zagan",
"helix",
"orion",
"luna",
"iris",
"altair",
"zenith",
"perseus",
"helios",
"lux",
"kepler",
"rigel",
"cosmo",
"celeste",
"ursa",
"sirius",
"lumen",
"castor",
"naksh",
"atlas",
]
_GROK_REF_TAG_RE = re.compile(r"(?<!\w)@(image|audio)(?P<idx>\d*)(?!\w)", re.IGNORECASE | re.ASCII)
def _normalize_grok_reference_prompt(prompt: str, total_images: int, voices: list[str]) -> str:
"""Rewrite @Image1/@Audio1 style references (1-based, shared partner-node syntax)
into Grok's native <IMAGE_0>/<AUDIO_0> tags; an unnumbered @image/@audio means the first one.
Native tags pass through untouched. @ImageN refers to the Nth reference image overall, in
input order — a batched input contributes one number per image. @AudioN refers to the
'voice_N' widget; the API only accepts compact arrays, so voices are remapped to array
positions and 'none' slots between selected voices are harmless. Substitution repeats until
stable so adjacent tags like '@Image1@Image2' all resolve."""
audio_indices: dict[int, int] = {}
for slot, voice in enumerate(voices, start=1):
if voice != "none":
audio_indices[slot] = len(audio_indices)
def repl(match: re.Match) -> str:
kind = match.group(1).lower()
idx = int(match.group("idx") or 1)
if kind == "image":
if not 1 <= idx <= total_images:
raise ValueError(
f"The prompt references @Image{idx}, but only {total_images} "
f"reference images are connected (a batched input counts once per image)."
)
return f"<IMAGE_{idx - 1}>"
if idx not in audio_indices:
if 1 <= idx <= len(voices):
raise ValueError(f"The prompt references @Audio{idx}, but 'voice_{idx}' is set to 'none'.")
raise ValueError(f"The prompt references @Audio{idx}, but only voices 1..{len(voices)} exist.")
return f"<AUDIO_{audio_indices[idx]}>"
prev = None
while prev != prompt:
prev = prompt
prompt = _GROK_REF_TAG_RE.sub(repl, prompt)
return prompt
def _extract_grok_price(response) -> float | None:
if response.usage and response.usage.cost_in_usd_ticks is not None:
return response.usage.cost_in_usd_ticks / 10_000_000_000
return None
def _extract_grok_video_price(response) -> float | None:
price = _extract_grok_price(response)
if price is not None:
return price * 1.43
return None
class GrokImageNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokImageNode",
display_name="Grok Image",
category="partner/image/Grok",
description="Generate images using Grok based on a text prompt",
inputs=[
IO.Combo.Input(
"model",
options=[
"grok-imagine-image-quality",
"grok-imagine-image-pro",
"grok-imagine-image",
],
),
IO.String.Input(
"prompt",
multiline=True,
tooltip="The text prompt used to generate the image",
),
IO.Combo.Input(
"aspect_ratio",
options=[
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"9:16",
"16:9",
"9:19.5",
"19.5:9",
"9:20",
"20:9",
"1:2",
"2:1",
],
),
IO.Int.Input(
"number_of_images",
default=1,
min=1,
max=10,
step=1,
tooltip="Number of images to generate",
display_mode=IO.NumberDisplay.number,
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
IO.Combo.Input("resolution", options=["1K", "2K"], optional=True),
],
outputs=[
IO.Image.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["model", "number_of_images", "resolution"]),
expr="""
(
$rate := widgets.model = "grok-imagine-image-quality"
? (widgets.resolution = "1k" ? 0.05 : 0.07)
: ($contains(widgets.model, "pro") ? 0.07 : 0.02);
{"type":"usd","usd": $rate * widgets.number_of_images}
)
""",
),
)
@classmethod
async def execute(
cls,
model: str,
prompt: str,
aspect_ratio: str,
number_of_images: int,
seed: int,
resolution: str = "1K",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/images/generations", method="POST"),
data=ImageGenerationRequest(
model=model,
prompt=prompt,
aspect_ratio=aspect_ratio,
n=number_of_images,
seed=seed,
resolution=resolution.lower(),
),
response_model=ImageGenerationResponse,
)
if len(response.data) == 1:
return IO.NodeOutput(await download_url_to_image_tensor(response.data[0].url))
return IO.NodeOutput(
torch.cat(
[await download_url_to_image_tensor(i) for i in [str(d.url) for d in response.data if d.url]],
)
)
_GROK_IMAGE_EDIT_ASPECT_RATIO_OPTIONS = [
"auto",
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"9:16",
"16:9",
"9:19.5",
"19.5:9",
"9:20",
"20:9",
"1:2",
"2:1",
]
def _grok_image_edit_model_inputs(*, max_ref_images: int, with_aspect_ratio: bool):
inputs = [
IO.Autogrow.Input(
"images",
template=IO.Autogrow.TemplateNames(
IO.Image.Input("image"),
names=[f"image_{i}" for i in range(1, max_ref_images + 1)],
min=1,
),
tooltip=(
"Reference image to edit."
if max_ref_images == 1
else f"Reference image(s) to edit. Up to {max_ref_images} images."
),
),
IO.Combo.Input("resolution", options=["1K", "2K"]),
IO.Int.Input(
"number_of_images",
default=1,
min=1,
max=10,
step=1,
tooltip="Number of edited images to generate",
display_mode=IO.NumberDisplay.number,
),
]
if with_aspect_ratio:
inputs.append(
IO.Combo.Input(
"aspect_ratio",
options=_GROK_IMAGE_EDIT_ASPECT_RATIO_OPTIONS,
tooltip="Only allowed when multiple images are connected.",
)
)
return inputs
class GrokImageEditNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokImageEditNode",
display_name="Grok Image Edit",
category="partner/image/Grok",
description="Modify an existing image based on a text prompt",
inputs=[
IO.Combo.Input(
"model",
options=[
"grok-imagine-image-quality",
"grok-imagine-image-pro",
"grok-imagine-image",
],
),
IO.Image.Input("image", display_name="images"),
IO.String.Input(
"prompt",
multiline=True,
tooltip="The text prompt used to generate the image",
),
IO.Combo.Input("resolution", options=["1K", "2K"]),
IO.Int.Input(
"number_of_images",
default=1,
min=1,
max=10,
step=1,
tooltip="Number of edited images to generate",
display_mode=IO.NumberDisplay.number,
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
IO.Combo.Input(
"aspect_ratio",
options=[
"auto",
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"9:16",
"16:9",
"9:19.5",
"19.5:9",
"9:20",
"20:9",
"1:2",
"2:1",
],
optional=True,
tooltip="Only allowed when multiple images are connected to the image input.",
),
],
outputs=[
IO.Image.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["model", "number_of_images", "resolution"]),
expr="""
(
$isQualityModel := widgets.model = "grok-imagine-image-quality";
$isPro := $contains(widgets.model, "pro");
$rate := $isQualityModel
? (widgets.resolution = "1k" ? 0.05 : 0.07)
: ($isPro ? 0.07 : 0.02);
$base := $isQualityModel ? 0.01 : 0.002;
$output := $rate * widgets.number_of_images;
$isPro
? {"type":"usd","usd": $base + $output}
: {"type":"range_usd","min_usd": $base + $output, "max_usd": 3 * $base + $output}
)
""",
),
is_deprecated=True,
)
@classmethod
async def execute(
cls,
model: str,
image: Input.Image,
prompt: str,
resolution: str,
number_of_images: int,
seed: int,
aspect_ratio: str = "auto",
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
if model == "grok-imagine-image-pro":
if get_number_of_images(image) > 1:
raise ValueError("The pro model supports only 1 input image.")
elif get_number_of_images(image) > 3:
raise ValueError("A maximum of 3 input images is supported.")
if aspect_ratio != "auto" and get_number_of_images(image) == 1:
raise ValueError(
"Custom aspect ratio is only allowed when multiple images are connected to the image input."
)
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/images/edits", method="POST"),
data=ImageEditRequest(
model=model,
images=[InputUrlObject(url=f"data:image/png;base64,{tensor_to_base64_string(i)}") for i in image],
prompt=prompt,
resolution=resolution.lower(),
n=number_of_images,
seed=seed,
aspect_ratio=None if aspect_ratio == "auto" else aspect_ratio,
),
response_model=ImageGenerationResponse,
)
if len(response.data) == 1:
return IO.NodeOutput(await download_url_to_image_tensor(response.data[0].url))
return IO.NodeOutput(
torch.cat(
[await download_url_to_image_tensor(i) for i in [str(d.url) for d in response.data if d.url]],
)
)
class GrokImageEditNodeV2(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokImageEditNodeV2",
display_name="Grok Image Edit",
category="partner/image/Grok",
description="Modify an existing image based on a text prompt",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
default="",
tooltip="The text prompt used to generate the image",
),
IO.DynamicCombo.Input(
"model",
options=[
IO.DynamicCombo.Option(
"grok-imagine-image-quality",
_grok_image_edit_model_inputs(max_ref_images=3, with_aspect_ratio=True),
),
IO.DynamicCombo.Option(
"grok-imagine-image-pro",
_grok_image_edit_model_inputs(max_ref_images=1, with_aspect_ratio=False),
),
IO.DynamicCombo.Option(
"grok-imagine-image",
_grok_image_edit_model_inputs(max_ref_images=3, with_aspect_ratio=True),
),
],
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
],
outputs=[
IO.Image.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(
widgets=["model", "model.resolution", "model.number_of_images"],
),
expr="""
(
$isQualityModel := widgets.model = "grok-imagine-image-quality";
$isPro := $contains(widgets.model, "pro");
$res := $lookup(widgets, "model.resolution");
$n := $lookup(widgets, "model.number_of_images");
$rate := $isQualityModel
? ($res = "1k" ? 0.05 : 0.07)
: ($isPro ? 0.07 : 0.02);
$base := $isQualityModel ? 0.01 : 0.002;
$output := $rate * $n;
$isPro
? {"type":"usd","usd": $base + $output}
: {"type":"range_usd","min_usd": $base + $output, "max_usd": 3 * $base + $output}
)
""",
),
)
@classmethod
async def execute(
cls,
prompt: str,
model: dict,
seed: int,
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
model_id = model["model"]
resolution = model["resolution"]
number_of_images = model["number_of_images"]
images_dict = model.get("images") or {}
aspect_ratio = model.get("aspect_ratio", "auto")
image_tensors: list[Input.Image] = [t for t in images_dict.values() if t is not None]
n_images = sum(get_number_of_images(t) for t in image_tensors)
if n_images < 1:
raise ValueError("At least one image is required for editing.")
if model_id == "grok-imagine-image-pro" and n_images > 1:
raise ValueError("The pro model supports only 1 input image.")
if model_id != "grok-imagine-image-pro" and n_images > 3:
raise ValueError("A maximum of 3 input images is supported.")
if aspect_ratio != "auto" and n_images == 1:
raise ValueError(
"Custom aspect ratio is only allowed when multiple images are connected to the image input."
)
flat_tensors: list[torch.Tensor] = []
for tensor in image_tensors:
if len(tensor.shape) == 4:
flat_tensors.extend(tensor[i] for i in range(tensor.shape[0]))
else:
flat_tensors.append(tensor)
response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/images/edits", method="POST"),
data=ImageEditRequest(
model=model_id,
images=[
InputUrlObject(url=f"data:image/png;base64,{tensor_to_base64_string(i)}") for i in flat_tensors
],
prompt=prompt,
resolution=resolution.lower(),
n=number_of_images,
seed=seed,
aspect_ratio=None if aspect_ratio == "auto" else aspect_ratio,
),
response_model=ImageGenerationResponse,
)
if len(response.data) == 1:
return IO.NodeOutput(await download_url_to_image_tensor(response.data[0].url))
return IO.NodeOutput(
torch.cat(
[await download_url_to_image_tensor(i) for i in [str(d.url) for d in response.data if d.url]],
)
)
class GrokVideoNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokVideoNode",
display_name="Grok Video",
category="partner/video/Grok",
description="Generate video from a prompt or an image",
inputs=[
IO.Combo.Input(
"model",
options=["grok-imagine-video", "grok-imagine-video-1.5"],
tooltip="The model to use for video generation.",
),
IO.String.Input(
"prompt",
multiline=True,
tooltip="Text description of the desired video. "
"Optional for grok-imagine-video-1.5 when an input image is provided.",
),
IO.Combo.Input(
"resolution",
options=["480p", "720p", "1080p"],
tooltip="The resolution of the output video. 1080p is only available for grok-imagine-video-1.5.",
),
IO.Combo.Input(
"aspect_ratio",
options=["auto", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16"],
tooltip="The aspect ratio of the output video.",
),
IO.Int.Input(
"duration",
default=6,
min=1,
max=15,
step=1,
tooltip="The duration of the output video in seconds.",
display_mode=IO.NumberDisplay.slider,
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
IO.Image.Input(
"image",
optional=True,
tooltip="Optional starting image. If omitted, the video is generated from the text prompt alone.",
),
],
outputs=[
IO.Video.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["model", "duration", "resolution"], inputs=["image"]),
expr="""
(
$is15 := $contains(widgets.model, "1.5");
$rate := $is15
? (widgets.resolution = "1080p" ? 0.25 : (widgets.resolution = "720p" ? 0.14 : 0.08))
: (widgets.resolution = "720p" ? 0.07 : 0.05);
$imgCost := $is15 ? 0.01 : 0.002;
$base := $rate * widgets.duration;
$total := inputs.image.connected ? $base + $imgCost : $base;
{"type":"usd","usd": $is15 ? $total * 1.43 : $total}
)
""",
),
)
@classmethod
async def execute(
cls,
model: str,
prompt: str,
resolution: str,
aspect_ratio: str,
duration: int,
seed: int,
image: Input.Image | None = None,
) -> IO.NodeOutput:
if resolution == "1080p" and model != "grok-imagine-video-1.5":
raise ValueError(f"1080p resolution is only available for grok-imagine-video-1.5, not '{model}'.")
image_url = None
if image is not None:
if get_number_of_images(image) != 1:
raise ValueError("Only one input image is supported.")
image_url = InputUrlObject(url=f"data:image/png;base64,{tensor_to_base64_string(image)}")
if image is None or model != "grok-imagine-video-1.5":
validate_string(prompt, strip_whitespace=True, min_length=1)
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/videos/generations", method="POST"),
data=VideoGenerationRequest(
model=_GROK_VIDEO_MODEL_API_IDS.get(model, model),
image=image_url,
prompt=prompt,
resolution=resolution,
duration=duration,
aspect_ratio=None if aspect_ratio == "auto" else aspect_ratio,
seed=seed,
),
response_model=VideoGenerationResponse,
)
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/xai/v1/videos/{initial_response.request_id}"),
status_extractor=lambda r: r.status if r.status is not None else "complete",
response_model=VideoStatusResponse,
price_extractor=_extract_grok_video_price if model == "grok-imagine-video-1.5" else _extract_grok_price,
)
return IO.NodeOutput(await download_url_to_video_output(response.video.url))
class GrokVideoEditNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokVideoEditNode",
display_name="Grok Video Edit",
category="partner/video/Grok",
description="Edit an existing video based on a text prompt.",
inputs=[
IO.Combo.Input("model", options=["grok-imagine-video"]),
IO.String.Input(
"prompt",
multiline=True,
tooltip="Text description of the desired video.",
),
IO.Video.Input("video", tooltip="Maximum supported duration is 8.7 seconds and 50MB file size."),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
],
outputs=[
IO.Video.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
expr="""{"type":"usd","usd": 0.06, "format": {"suffix": "/sec", "approximate": true}}""",
),
)
@classmethod
async def execute(
cls,
model: str,
prompt: str,
video: Input.Video,
seed: int,
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
validate_video_duration(video, min_duration=1, max_duration=8.7)
video_stream = video.get_stream_source()
video_size = get_fs_object_size(video_stream)
if video_size > 50 * 1024 * 1024:
raise ValueError(f"Video size ({video_size / 1024 / 1024:.1f}MB) exceeds 50MB limit.")
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/videos/edits", method="POST"),
data=VideoEditRequest(
model=model,
video=InputUrlObject(url=await upload_video_to_comfyapi(cls, video)),
prompt=prompt,
seed=seed,
),
response_model=VideoGenerationResponse,
)
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/xai/v1/videos/{initial_response.request_id}"),
status_extractor=lambda r: r.status if r.status is not None else "complete",
response_model=VideoStatusResponse,
price_extractor=_extract_grok_price,
)
return IO.NodeOutput(await download_url_to_video_output(response.video.url))
class GrokVideoReferenceNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokVideoReferenceNode",
display_name="Grok Reference-to-Video",
category="partner/video/Grok",
description="Generate video guided by reference images, with optional preset voice references.",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
tooltip="Text description of the desired video.",
),
IO.DynamicCombo.Input(
"model",
options=[
IO.DynamicCombo.Option(
"grok-imagine-video-1.5",
[
IO.Autogrow.Input(
"reference_images",
template=IO.Autogrow.TemplateNames(
IO.Image.Input("image"),
names=[f"reference_{i}" for i in range(1, 8)],
min=1,
),
tooltip="Up to 7 reference images to guide the video generation. "
"Refer to them in the prompt as @Image1 ... @Image7, numbered "
"in input order; a batched input counts once per image.",
),
IO.Combo.Input(
"voice_1",
options=_GROK_VOICE_OPTIONS,
tooltip="Optional preset voice reference; refer to it in the prompt as @Audio1. "
"The API supports only these preset voices, not custom audio.",
),
IO.Combo.Input(
"voice_2",
options=_GROK_VOICE_OPTIONS,
tooltip="Optional second voice reference; @Audio2 in the prompt.",
),
IO.Combo.Input(
"voice_3",
options=_GROK_VOICE_OPTIONS,
tooltip="Optional third voice reference; @Audio3 in the prompt.",
),
IO.Combo.Input(
"resolution",
options=["480p", "720p"],
tooltip="The resolution of the output video.",
),
IO.Combo.Input(
"aspect_ratio",
options=["16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16"],
tooltip="The aspect ratio of the output video.",
),
IO.Int.Input(
"duration",
default=6,
min=1,
max=15,
step=1,
tooltip="The duration of the output video in seconds.",
display_mode=IO.NumberDisplay.slider,
),
],
),
IO.DynamicCombo.Option(
"grok-imagine-video",
[
IO.Autogrow.Input(
"reference_images",
template=IO.Autogrow.TemplatePrefix(
IO.Image.Input("image"),
prefix="reference_",
min=1,
max=7,
),
tooltip="Up to 7 reference images to guide the video generation.",
),
IO.Combo.Input(
"resolution",
options=["480p", "720p"],
tooltip="The resolution of the output video.",
),
IO.Combo.Input(
"aspect_ratio",
options=["16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16"],
tooltip="The aspect ratio of the output video.",
),
IO.Int.Input(
"duration",
default=6,
min=2,
max=10,
step=1,
tooltip="The duration of the output video in seconds.",
display_mode=IO.NumberDisplay.slider,
),
],
),
],
tooltip="The model to use for video generation.",
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
],
outputs=[
IO.Video.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(
widgets=["model", "model.duration", "model.resolution"],
input_groups=["model.reference_images"],
),
expr="""
(
$is15 := $contains(widgets.model, "1.5");
$res := $lookup(widgets, "model.resolution");
$dur := $lookup(widgets, "model.duration");
$refs := $lookup(inputGroups, "model.reference_images");
$rate := $is15
? ($res = "720p" ? 0.14 : 0.08)
: ($res = "720p" ? 0.07 : 0.05);
$imgCost := $is15 ? 0.01 : 0.002;
$price := ($rate * $dur + $imgCost * $refs) * 1.43;
{"type":"usd","usd": $price}
)
""",
),
)
@classmethod
async def execute(
cls,
prompt: str,
model: dict,
seed: int,
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
total_images = sum(get_number_of_images(t) for t in model["reference_images"].values())
if total_images > 7:
raise ValueError(f"A maximum of 7 reference images is supported; {total_images} are connected.")
reference_audios = None
if model["model"] == "grok-imagine-video-1.5":
voices = [model.get(f"voice_{i}", "none") for i in range(1, 4)]
reference_audios = [VoiceReferenceObject(voice_id=v) for v in voices if v != "none"] or None
prompt = _normalize_grok_reference_prompt(prompt, total_images=total_images, voices=voices)
ref_image_urls = await upload_images_to_comfyapi(
cls,
list(model["reference_images"].values()),
mime_type="image/png",
wait_label="Uploading base images",
max_images=7,
)
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/videos/generations", method="POST"),
data=VideoGenerationRequest(
model=_GROK_VIDEO_MODEL_API_IDS.get(model["model"], model["model"]),
reference_images=[InputUrlObject(url=i) for i in ref_image_urls],
reference_audios=reference_audios,
prompt=prompt,
resolution=model["resolution"],
duration=model["duration"],
aspect_ratio=model["aspect_ratio"],
seed=seed,
),
response_model=VideoGenerationResponse,
)
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/xai/v1/videos/{initial_response.request_id}"),
status_extractor=lambda r: r.status if r.status is not None else "complete",
response_model=VideoStatusResponse,
price_extractor=_extract_grok_video_price,
)
return IO.NodeOutput(await download_url_to_video_output(response.video.url))
class GrokVideoExtendNode(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="GrokVideoExtendNode",
display_name="Grok Video Extend",
category="partner/video/Grok",
description="Extend an existing video with a seamless continuation based on a text prompt.",
inputs=[
IO.String.Input(
"prompt",
multiline=True,
tooltip="Text description of what should happen next in the video.",
),
IO.Video.Input("video", tooltip="Source video to extend. MP4 format, 2-15 seconds."),
IO.DynamicCombo.Input(
"model",
options=[
IO.DynamicCombo.Option(
"grok-imagine-video",
[
IO.Int.Input(
"duration",
default=8,
min=2,
max=10,
step=1,
tooltip="Length of the extension in seconds.",
display_mode=IO.NumberDisplay.slider,
),
],
),
],
tooltip="The model to use for video extension.",
),
IO.Int.Input(
"seed",
default=0,
min=0,
max=2147483647,
step=1,
display_mode=IO.NumberDisplay.number,
control_after_generate=True,
tooltip="Seed to determine if node should re-run; "
"actual results are nondeterministic regardless of seed.",
),
],
outputs=[
IO.Video.Output(),
],
hidden=[
IO.Hidden.auth_token_comfy_org,
IO.Hidden.api_key_comfy_org,
IO.Hidden.unique_id,
],
is_api_node=True,
price_badge=IO.PriceBadge(
depends_on=IO.PriceBadgeDepends(widgets=["model.duration"]),
expr="""
(
$dur := $lookup(widgets, "model.duration");
{
"type": "range_usd",
"min_usd": (0.02 + 0.05 * $dur) * 1.43,
"max_usd": (0.15 + 0.05 * $dur) * 1.43
}
)
""",
),
)
@classmethod
async def execute(
cls,
prompt: str,
video: Input.Video,
model: dict,
seed: int,
) -> IO.NodeOutput:
validate_string(prompt, strip_whitespace=True, min_length=1)
validate_video_duration(video, min_duration=2, max_duration=15)
video_size = get_fs_object_size(video.get_stream_source())
if video_size > 50 * 1024 * 1024:
raise ValueError(f"Video size ({video_size / 1024 / 1024:.1f}MB) exceeds 50MB limit.")
initial_response = await sync_op(
cls,
ApiEndpoint(path="/proxy/xai/v1/videos/extensions", method="POST"),
data=VideoExtensionRequest(
prompt=prompt,
video=InputUrlObject(url=await upload_video_to_comfyapi(cls, video)),
duration=model["duration"],
),
response_model=VideoGenerationResponse,
)
response = await poll_op(
cls,
ApiEndpoint(path=f"/proxy/xai/v1/videos/{initial_response.request_id}"),
status_extractor=lambda r: r.status if r.status is not None else "complete",
response_model=VideoStatusResponse,
price_extractor=_extract_grok_video_price,
)
return IO.NodeOutput(await download_url_to_video_output(response.video.url))
class GrokExtension(ComfyExtension):
@override
async def get_node_list(self) -> list[type[IO.ComfyNode]]:
return [
GrokImageNode,
GrokImageEditNode,
GrokImageEditNodeV2,
GrokVideoNode,
GrokVideoReferenceNode,
GrokVideoEditNode,
GrokVideoExtendNode,
]
async def comfy_entrypoint() -> GrokExtension:
return GrokExtension()
|