chore(openapi): sync shared API contract from cloud@77c7755

Signed-off-by: bigcat88 <bigcat88@icloud.com>

comfy_api/latest/_io.py

@@ -891,14 +891,6 @@ class Tracks(ComfyTypeIO):
         track_visibility: torch.Tensor
     Type = TrackDict
 
-@comfytype(io_type="DICT")
-class Dict(ComfyTypeIO):
-    Type = dict
-
-@comfytype(io_type="ARRAY")
-class Array(ComfyTypeIO):
-    Type = list
-
 @comfytype(io_type="COMFY_MULTITYPED_V3")
 class MultiType:
     Type = Any
@@ -1287,19 +1279,6 @@ class Color(ComfyTypeIO):
       def as_dict(self):
           return super().as_dict()
 
-
-@comfytype(io_type="COLORS")
-class Colors(ComfyTypeIO):
-    Type = list[Color.Type]
-
-    class Input(WidgetInput):
-        def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
-                     socketless: bool=True, default: list[str]=None, advanced: bool=None):
-            super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced)
-            if default is None:
-                self.default = []
-
-
 @comfytype(io_type="BOUNDING_BOX")
 class BoundingBox(ComfyTypeIO):
     class BoundingBoxDict(TypedDict):
@@ -1347,20 +1326,6 @@ class Curve(ComfyTypeIO):
             return d
 
 
-@comfytype(io_type="BOUNDING_BOXES")
-class BoundingBoxes(ComfyTypeIO):
-    class BoundingBoxWithMetadata(BoundingBox.BoundingBoxDict):
-        metadata: dict
-    Type = list[BoundingBoxWithMetadata]
-
-    class Input(WidgetInput):
-        def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
-                     socketless: bool=True, default: list[dict]=None, advanced: bool=None):
-            super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced)
-            if default is None:
-                self.default = []
-
-
 @comfytype(io_type="HISTOGRAM")
 class Histogram(ComfyTypeIO):
     """A histogram represented as a list of bin counts."""
@@ -2411,8 +2376,6 @@ __all__ = [
     "AnyType",
     "MultiType",
     "Tracks",
-    "Dict",
-    "Array",
     "Color",
     # Dynamic Types
     "MatchType",
@@ -2431,8 +2394,6 @@ __all__ = [
     "PriceBadgeDepends",
     "PriceBadge",
     "BoundingBox",
-    "BoundingBoxes",
-    "Colors",
     "Curve",
     "Histogram",
     "Range",

comfy_api_nodes/apis/bytedance.py

@@ -163,15 +163,27 @@ class SeedanceVirtualLibraryCreateAssetRequest(BaseModel):
     asset_type: str | None = Field(None, description="BytePlus asset type. Defaults to Image server-side when omitted.")
 
 
-# Dollars per 1K tokens, keyed by (model_id, has_video_input).
+# Dollars per 1K tokens, keyed by (model_id, has_video_input, resolution).
 SEEDANCE2_PRICE_PER_1K_TOKENS = {
-    ("dreamina-seedance-2-0-260128", False): 0.007,
-    ("dreamina-seedance-2-0-260128", True): 0.0043,
-    ("dreamina-seedance-2-0-fast-260128", False): 0.0056,
-    ("dreamina-seedance-2-0-fast-260128", True): 0.0033,
+    ("dreamina-seedance-2-0-260128", False, "480p"): 0.007,
+    ("dreamina-seedance-2-0-260128", True, "480p"): 0.0043,
+    ("dreamina-seedance-2-0-260128", False, "720p"): 0.007,
+    ("dreamina-seedance-2-0-260128", True, "720p"): 0.0043,
+    ("dreamina-seedance-2-0-260128", False, "1080p"): 0.0077,
+    ("dreamina-seedance-2-0-260128", True, "1080p"): 0.0047,
+    ("dreamina-seedance-2-0-260128", False, "4k"): 0.004,
+    ("dreamina-seedance-2-0-260128", True, "4k"): 0.0024,
+    ("dreamina-seedance-2-0-fast-260128", False, "480p"): 0.0056,
+    ("dreamina-seedance-2-0-fast-260128", True, "480p"): 0.0033,
+    ("dreamina-seedance-2-0-fast-260128", False, "720p"): 0.0056,
+    ("dreamina-seedance-2-0-fast-260128", True, "720p"): 0.0033,
 }
 
 
+def seedance2_price_per_1k_tokens(model_id: str, has_video_input: bool, resolution: str) -> float | None:
+    return SEEDANCE2_PRICE_PER_1K_TOKENS.get((model_id, has_video_input, resolution))
+
+
 RECOMMENDED_PRESETS = [
     ("1024x1024 (1:1)", 1024, 1024),
     ("864x1152 (3:4)", 864, 1152),

comfy_api_nodes/nodes_bytedance.py

@@ -15,7 +15,6 @@ from comfy_api_nodes.apis.bytedance import (
     RECOMMENDED_PRESETS_SEEDREAM_4_0,
     RECOMMENDED_PRESETS_SEEDREAM_4_5,
     RECOMMENDED_PRESETS_SEEDREAM_5_LITE,
-    SEEDANCE2_PRICE_PER_1K_TOKENS,
     SEEDANCE2_REF_VIDEO_PIXEL_LIMITS,
     VIDEO_TASKS_EXECUTION_TIME,
     GetAssetResponse,
@@ -40,6 +39,7 @@ from comfy_api_nodes.apis.bytedance import (
     TaskVideoContentUrl,
     Text2ImageTaskCreationRequest,
     Text2VideoTaskCreationRequest,
+    seedance2_price_per_1k_tokens,
 )
 from comfy_api_nodes.util import (
     ApiEndpoint,
@@ -141,7 +141,7 @@ SEEDANCE2_RATIO_WH = {
     "9:16": (9, 16),
     "21:9": (21, 9),
 }
-SEEDANCE2_RES_SHORT_SIDE = {"480p": 480, "720p": 720, "1080p": 1080}
+SEEDANCE2_RES_SHORT_SIDE = {"480p": 480, "720p": 720, "1080p": 1080, "4k": 2160}
 
 
 def _seedance2_target_dims(resolution: str, ratio: str, image: torch.Tensor) -> tuple[int, int]:
@@ -377,9 +377,9 @@ async def _seedance_virtual_library_upload_video_asset(
     return f"asset://{create_resp.asset_id}"
 
 
-def _seedance2_price_extractor(model_id: str, has_video_input: bool):
+def _seedance2_price_extractor(model_id: str, has_video_input: bool, resolution: str):
     """Returns a price_extractor closure for Seedance 2.0 poll_op."""
-    rate = SEEDANCE2_PRICE_PER_1K_TOKENS.get((model_id, has_video_input))
+    rate = seedance2_price_per_1k_tokens(model_id, has_video_input, resolution)
     if rate is None:
         return None
 
@@ -1621,7 +1621,7 @@ class ByteDance2TextToVideoNode(IO.ComfyNode):
                 IO.DynamicCombo.Input(
                     "model",
                     options=[
-                        IO.DynamicCombo.Option("Seedance 2.0", _seedance2_text_inputs(["480p", "720p", "1080p"])),
+                        IO.DynamicCombo.Option("Seedance 2.0", _seedance2_text_inputs(["480p", "720p", "1080p", "4k"])),
                         IO.DynamicCombo.Option("Seedance 2.0 Fast", _seedance2_text_inputs(["480p", "720p"])),
                     ],
                     tooltip="Seedance 2.0 for maximum quality; Seedance 2.0 Fast for speed optimization.",
@@ -1660,11 +1660,15 @@ class ByteDance2TextToVideoNode(IO.ComfyNode):
                   $rate480 := 10044;
                   $rate720 := 21600;
                   $rate1080 := 48800;
+                  $rate4k := 195200;
                   $m := widgets.model;
-                  $pricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001;
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $rate := $res = "1080p" ? $rate1080 :
+                  $pricePer1K := $res = "4k"    ? 0.00572 :
+                                 $res = "1080p" ? 0.011011 :
+                                 $contains($m, "fast") ? 0.008008 : 0.01001;
+                  $rate := $res = "4k"    ? $rate4k :
+                           $res = "1080p" ? $rate1080 :
                            $res = "720p"  ? $rate720 :
                                             $rate480;
                   $cost := $dur * $rate * $pricePer1K / 1000;
@@ -1703,7 +1707,7 @@ class ByteDance2TextToVideoNode(IO.ComfyNode):
             ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"),
             response_model=TaskStatusResponse,
             status_extractor=lambda r: r.status,
-            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False),
+            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False, resolution=model["resolution"]),
             poll_interval=9,
         )
         return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))
@@ -1724,7 +1728,7 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
                     options=[
                         IO.DynamicCombo.Option(
                             "Seedance 2.0",
-                            _seedance2_text_inputs(["480p", "720p", "1080p"], default_ratio="adaptive"),
+                            _seedance2_text_inputs(["480p", "720p", "1080p", "4k"], default_ratio="adaptive"),
                         ),
                         IO.DynamicCombo.Option(
                             "Seedance 2.0 Fast",
@@ -1791,11 +1795,15 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
                   $rate480 := 10044;
                   $rate720 := 21600;
                   $rate1080 := 48800;
+                  $rate4k := 195200;
                   $m := widgets.model;
-                  $pricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001;
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $rate := $res = "1080p" ? $rate1080 :
+                  $pricePer1K := $res = "4k"    ? 0.00572 :
+                                 $res = "1080p" ? 0.011011 :
+                                 $contains($m, "fast") ? 0.008008 : 0.01001;
+                  $rate := $res = "4k"    ? $rate4k :
+                           $res = "1080p" ? $rate1080 :
                            $res = "720p"  ? $rate720 :
                                             $rate480;
                   $cost := $dur * $rate * $pricePer1K / 1000;
@@ -1913,7 +1921,7 @@ class ByteDance2FirstLastFrameNode(IO.ComfyNode):
             ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"),
             response_model=TaskStatusResponse,
             status_extractor=lambda r: r.status,
-            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False),
+            price_extractor=_seedance2_price_extractor(model_id, has_video_input=False, resolution=model["resolution"]),
             poll_interval=9,
         )
         return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))
@@ -2010,7 +2018,7 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
                     options=[
                         IO.DynamicCombo.Option(
                             "Seedance 2.0",
-                            _seedance2_reference_inputs(["480p", "720p", "1080p"], default_ratio="adaptive"),
+                            _seedance2_reference_inputs(["480p", "720p", "1080p", "4k"], default_ratio="adaptive"),
                         ),
                         IO.DynamicCombo.Option(
                             "Seedance 2.0 Fast",
@@ -2056,13 +2064,19 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
                   $rate480 := 10044;
                   $rate720 := 21600;
                   $rate1080 := 48800;
+                  $rate4k := 195200;
                   $m := widgets.model;
                   $hasVideo := $lookup(inputGroups, "model.reference_videos") > 0;
-                  $noVideoPricePer1K := $contains($m, "fast") ? 0.008008 : 0.01001;
-                  $videoPricePer1K := $contains($m, "fast") ? 0.004719 : 0.006149;
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $rate := $res = "1080p" ? $rate1080 :
+                  $noVideoPricePer1K := $res = "4k"    ? 0.00572 :
+                                        $res = "1080p" ? 0.011011 :
+                                        $contains($m, "fast") ? 0.008008 : 0.01001;
+                  $videoPricePer1K := $res = "4k"    ? 0.003432 :
+                                      $res = "1080p" ? 0.006721 :
+                                      $contains($m, "fast") ? 0.004719 : 0.006149;
+                  $rate := $res = "4k"    ? $rate4k :
+                           $res = "1080p" ? $rate1080 :
                            $res = "720p"  ? $rate720 :
                                             $rate480;
                   $noVideoCost := $dur * $rate * $noVideoPricePer1K / 1000;
@@ -2258,7 +2272,9 @@ class ByteDance2ReferenceNode(IO.ComfyNode):
             ApiEndpoint(path=f"{BYTEPLUS_SEEDANCE2_TASK_STATUS_ENDPOINT}/{initial_response.id}"),
             response_model=TaskStatusResponse,
             status_extractor=lambda r: r.status,
-            price_extractor=_seedance2_price_extractor(model_id, has_video_input=has_video_input),
+            price_extractor=_seedance2_price_extractor(
+                model_id, has_video_input=has_video_input, resolution=model["resolution"]
+            ),
             poll_interval=9,
         )
         return IO.NodeOutput(await download_url_to_video_output(response.content.video_url))

comfy_api_nodes/nodes_grok.py

@@ -30,7 +30,7 @@ from comfy_api_nodes.util import (
 
 
 _GROK_VIDEO_MODEL_API_IDS = {
-    "grok-imagine-video-1.5": "grok-imagine-video-1.5-preview",
+    "grok-imagine-video-1.5": "grok-imagine-video-1.5",
 }
 
 
@@ -521,8 +521,8 @@ class GrokVideoNode(IO.ComfyNode):
                 ),
                 IO.Combo.Input(
                     "resolution",
-                    options=["480p", "720p"],
-                    tooltip="The resolution of the output video.",
+                    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",
@@ -570,11 +570,12 @@ class GrokVideoNode(IO.ComfyNode):
                 (
                   $is15 := $contains(widgets.model, "1.5");
                   $rate := $is15
-                    ? (widgets.resolution = "720p" ? 0.2002 : 0.1144)
+                    ? (widgets.resolution = "1080p" ? 0.25 : (widgets.resolution = "720p" ? 0.14 : 0.08))
                     : (widgets.resolution = "720p" ? 0.07 : 0.05);
-                  $imgCost := $is15 ? 0.0143 : 0.002;
+                  $imgCost := $is15 ? 0.01 : 0.002;
                   $base := $rate * widgets.duration;
-                  {"type":"usd","usd": inputs.image.connected ? $base + $imgCost : $base}
+                  $total := inputs.image.connected ? $base + $imgCost : $base;
+                  {"type":"usd","usd": $is15 ? $total * 1.43 : $total}
                 )
                 """,
             ),
@@ -593,6 +594,8 @@ class GrokVideoNode(IO.ComfyNode):
     ) -> IO.NodeOutput:
         if image is None and model == "grok-imagine-video-1.5":
             raise ValueError(f"The '{model}' model requires an input image; connect one to the 'image' input.")
+        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:

comfy_api_nodes/nodes_wan.py

@@ -48,10 +48,13 @@ from comfy_api_nodes.util import (
     upload_image_to_comfyapi,
     upload_video_to_comfyapi,
     validate_audio_duration,
+    validate_image_aspect_ratio,
+    validate_image_dimensions,
     validate_string,
     validate_video_duration,
 )
 
+
 RES_IN_PARENS = re.compile(r"\((\d+)\s*[x×]\s*(\d+)\)")
 
 
@@ -1657,6 +1660,44 @@ class HappyHorseTextToVideoApi(IO.ComfyNode):
                 IO.DynamicCombo.Input(
                     "model",
                     options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.1-t2v",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Prompt describing the elements and visual features. "
+                                    "Supports English and Chinese.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Combo.Input(
+                                    "ratio",
+                                    options=[
+                                        "16:9",
+                                        "9:16",
+                                        "1:1",
+                                        "4:3",
+                                        "3:4",
+                                        "21:9",
+                                        "9:21",
+                                        "5:4",
+                                        "4:5",
+                                    ],
+                                ),
+                                IO.Int.Input(
+                                    "duration",
+                                    default=5,
+                                    min=3,
+                                    max=15,
+                                    step=1,
+                                    display_mode=IO.NumberDisplay.number,
+                                ),
+                            ],
+                        ),
                         IO.DynamicCombo.Option(
                             "happyhorse-1.0-t2v",
                             [
@@ -1719,7 +1760,9 @@ class HappyHorseTextToVideoApi(IO.ComfyNode):
                 (
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $ppsTable := $contains(widgets.model, "1.1")
+                    ? { "720p": 0.2002, "1080p": 0.2574 }
+                    : { "720p": 0.14, "1080p": 0.24 };
                   $pps := $lookup($ppsTable, $res);
                   { "type": "usd", "usd": $pps * $dur }
                 )
@@ -1781,6 +1824,30 @@ class HappyHorseImageToVideoApi(IO.ComfyNode):
                 IO.DynamicCombo.Input(
                     "model",
                     options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.1-i2v",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Prompt describing the elements and visual features. "
+                                    "Supports English and Chinese.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Int.Input(
+                                    "duration",
+                                    default=5,
+                                    min=3,
+                                    max=15,
+                                    step=1,
+                                    display_mode=IO.NumberDisplay.number,
+                                ),
+                            ],
+                        ),
                         IO.DynamicCombo.Option(
                             "happyhorse-1.0-i2v",
                             [
@@ -1843,7 +1910,9 @@ class HappyHorseImageToVideoApi(IO.ComfyNode):
                 (
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $ppsTable := $contains(widgets.model, "1.1")
+                    ? { "720p": 0.2002, "1080p": 0.2574 }
+                    : { "720p": 0.14, "1080p": 0.24 };
                   $pps := $lookup($ppsTable, $res);
                   { "type": "usd", "usd": $pps * $dur }
                 )
@@ -1859,6 +1928,8 @@ class HappyHorseImageToVideoApi(IO.ComfyNode):
         seed: int,
         watermark: bool,
     ):
+        validate_image_dimensions(first_frame, min_width=300, min_height=300)
+        validate_image_aspect_ratio(first_frame, (1, 2.5), (2.5, 1), strict=False)
         media = [
             Wan27MediaItem(
                 type="first_frame",
@@ -2053,6 +2124,62 @@ class HappyHorseReferenceVideoApi(IO.ComfyNode):
                 IO.DynamicCombo.Input(
                     "model",
                     options=[
+                        IO.DynamicCombo.Option(
+                            "happyhorse-1.1-r2v",
+                            [
+                                IO.String.Input(
+                                    "prompt",
+                                    multiline=True,
+                                    default="",
+                                    tooltip="Prompt describing the video. Use identifiers such as 'character1' and "
+                                    "'character2' to refer to the reference characters.",
+                                ),
+                                IO.Combo.Input(
+                                    "resolution",
+                                    options=["720P", "1080P"],
+                                ),
+                                IO.Combo.Input(
+                                    "ratio",
+                                    options=[
+                                        "16:9",
+                                        "9:16",
+                                        "1:1",
+                                        "4:3",
+                                        "3:4",
+                                        "21:9",
+                                        "9:21",
+                                        "5:4",
+                                        "4:5",
+                                    ],
+                                ),
+                                IO.Int.Input(
+                                    "duration",
+                                    default=5,
+                                    min=3,
+                                    max=15,
+                                    step=1,
+                                    display_mode=IO.NumberDisplay.number,
+                                ),
+                                IO.Autogrow.Input(
+                                    "reference_images",
+                                    template=IO.Autogrow.TemplateNames(
+                                        IO.Image.Input("reference_image"),
+                                        names=[
+                                            "image1",
+                                            "image2",
+                                            "image3",
+                                            "image4",
+                                            "image5",
+                                            "image6",
+                                            "image7",
+                                            "image8",
+                                            "image9",
+                                        ],
+                                        min=1,
+                                    ),
+                                ),
+                            ],
+                        ),
                         IO.DynamicCombo.Option(
                             "happyhorse-1.0-r2v",
                             [
@@ -2133,7 +2260,9 @@ class HappyHorseReferenceVideoApi(IO.ComfyNode):
                 (
                   $res := $lookup(widgets, "model.resolution");
                   $dur := $lookup(widgets, "model.duration");
-                  $ppsTable := { "720p": 0.14, "1080p": 0.24 };
+                  $ppsTable := $contains(widgets.model, "1.1")
+                    ? { "720p": 0.2002, "1080p": 0.2574 }
+                    : { "720p": 0.14, "1080p": 0.24 };
                   $pps := $lookup($ppsTable, $res);
                   { "type": "usd", "usd": $pps * $dur }
                 )
@@ -2149,8 +2278,11 @@ class HappyHorseReferenceVideoApi(IO.ComfyNode):
         watermark: bool,
     ):
         validate_string(model["prompt"], strip_whitespace=False, min_length=1)
-        media = []
         reference_images = model.get("reference_images", {})
+        for key in reference_images:
+            validate_image_dimensions(reference_images[key], min_width=400, min_height=400)
+            validate_image_aspect_ratio(reference_images[key], (1, 2.5), (2.5, 1), strict=False)
+        media = []
         for key in reference_images:
             media.append(
                 Wan27MediaItem(
@@ -2159,7 +2291,7 @@ class HappyHorseReferenceVideoApi(IO.ComfyNode):
                 )
             )
         if not media:
-            raise ValueError("At least one reference reference image must be provided.")
+            raise ValueError("At least one reference image must be provided.")
 
         initial_response = await sync_op(
             cls,

comfy_extras/color_util.py

@@ -1,23 +0,0 @@
-def hex_to_rgb(value: str) -> tuple[int, int, int]:
-    h = value.lstrip("#")
-    if len(h) != 6:
-        return (255, 255, 255)
-    try:
-        return (int(h[0:2], 16), int(h[2:4], 16), int(h[4:6], 16))
-    except ValueError:
-        return (255, 255, 255)
-
-
-def readable_color(rgb: tuple[int, int, int]) -> tuple[int, int, int]:
-    r, g, b = rgb
-    lum = 0.299 * r + 0.587 * g + 0.114 * b
-    if lum >= 130:
-        return (r, g, b)
-    t = (130 - lum) / (255 - lum)
-    return (round(r + (255 - r) * t), round(g + (255 - g) * t), round(b + (255 - b) * t))
-
-
-def normalize_palette(colors) -> list[str]:
-    if isinstance(colors, dict):
-        colors = colors.values()
-    return [c.upper() for c in colors if isinstance(c, str) and c]

comfy_extras/nodes_bounding_boxes.py

@@ -1,253 +0,0 @@
-import numpy as np
-import torch
-from PIL import Image, ImageDraw, ImageEnhance, ImageFont
-from typing_extensions import override
-
-from comfy_api.latest import ComfyExtension, io
-from comfy_extras.color_util import hex_to_rgb, normalize_palette, readable_color
-
-_PREVIEW_LONG_EDGE = 1024
-_PREVIEW_DIM = 0.25
-
-
-def pixels_to_fractions(box: dict, width: int, height: int) -> dict:
-    w = width or 1
-    h = height or 1
-    return {
-        "x": box.get("x", 0) / w,
-        "y": box.get("y", 0) / h,
-        "w": box.get("width", 0) / w,
-        "h": box.get("height", 0) / h,
-    }
-
-
-def fractions_to_pixels(box: dict, width: int, height: int) -> dict:
-    x, y = box.get("x", 0.0), box.get("y", 0.0)
-    w, h = box.get("w", 0.0), box.get("h", 0.0)
-    if w < 0:
-        x, w = x + w, -w
-    if h < 0:
-        y, h = y + h, -h
-    return {
-        "x": round(x * width),
-        "y": round(y * height),
-        "width": round(w * width),
-        "height": round(h * height),
-    }
-
-
-def fractions_to_bbox_frame(boxes: list, width: int, height: int) -> list:
-    pixels = [
-        fractions_to_pixels(box, width, height)
-        for box in boxes
-        if isinstance(box, dict)
-    ]
-    return [pixels] if pixels else []
-
-
-def _font(size: int):
-    try:
-        return ImageFont.load_default(size)
-    except Exception:
-        return ImageFont.load_default()
-
-
-def _wrap(draw, text: str, font, max_w: float) -> list[str]:
-    lines = []
-    for para in text.split("\n"):
-        line = ""
-        for word in para.split():
-            test = word if not line else line + " " + word
-            if line and draw.textlength(test, font=font) > max_w:
-                lines.append(line)
-                line = word
-            else:
-                line = test
-        lines.append(line)
-    return lines
-
-
-def _bg_from_image(image) -> Image.Image | None:
-    if image is None:
-        return None
-    try:
-        arr = (image[0].detach().cpu().numpy() * 255).clip(0, 255).astype(np.uint8)
-        return Image.fromarray(arr)
-    except Exception:
-        return None
-
-
-def render_preview(regions, width, height, bg=None):
-    if bg is not None:
-        iw, ih = bg.size
-        long_edge = max(iw, ih) or 1
-        scale = min(1.0, _PREVIEW_LONG_EDGE / long_edge)
-        rw, rh = max(1, round(iw * scale)), max(1, round(ih * scale))
-        base = bg.convert("RGB").resize((rw, rh), Image.LANCZOS)
-        base = ImageEnhance.Brightness(base).enhance(_PREVIEW_DIM)
-        img = base.convert("RGBA")
-    else:
-        long_edge = max(width, height) or 1
-        scale = min(1.0, _PREVIEW_LONG_EDGE / long_edge)
-        rw, rh = max(1, round(width * scale)), max(1, round(height * scale))
-        grey = round(_PREVIEW_DIM * 128)
-        img = Image.new("RGBA", (rw, rh), (grey, grey, grey, 255))
-
-    overlay = Image.new("RGBA", (rw, rh), (0, 0, 0, 0))
-    draw = ImageDraw.Draw(overlay)
-    fs = max(10, round(rh / 64))
-    font = _font(fs)
-    tag_font = _font(max(9, fs - 2))
-    line_h = fs + 2
-
-    for i, region in enumerate(regions):
-        if not isinstance(region, dict):
-            continue
-        palette = [c for c in (region.get("palette") or []) if c]
-        r, g, b = hex_to_rgb(palette[0]) if palette else (140, 140, 140)
-        x1 = max(0, min(rw, round(region.get("x", 0) * rw)))
-        y1 = max(0, min(rh, round(region.get("y", 0) * rh)))
-        x2 = max(0, min(rw, round((region.get("x", 0) + region.get("w", 0)) * rw)))
-        y2 = max(0, min(rh, round((region.get("y", 0) + region.get("h", 0)) * rh)))
-        if x2 < x1:
-            x1, x2 = x2, x1
-        if y2 < y1:
-            y1, y2 = y2, y1
-
-        draw.rectangle([x1, y1, x2, y2], outline=(r, g, b, 255), width=2)
-
-        swatches = palette[:5]
-        if swatches and (x2 - x1) > 2:
-            sh = max(5, fs // 2)
-            seg = (x2 - x1) / len(swatches)
-            for p, hexc in enumerate(swatches):
-                sx = x1 + round(p * seg)
-                draw.rectangle([sx, y1, x1 + round((p + 1) * seg), y1 + sh], fill=hex_to_rgb(hexc))
-
-        etype = "text" if region.get("type") == "text" else "obj"
-        tag = str(i + 1).zfill(2)
-        tw = draw.textlength(tag, font=tag_font)
-        draw.rectangle([x1, y1, x1 + tw + 6, y1 + fs + 2], fill=(r, g, b, 255))
-        tag_fill = (0, 0, 0, 255) if (0.299 * r + 0.587 * g + 0.114 * b) > 140 else (255, 255, 255, 255)
-        draw.text((x1 + 3, y1 + 1), tag, fill=tag_fill, font=tag_font)
-
-        body = region.get("desc", "") or ""
-        if etype == "text" and region.get("text"):
-            body = '"%s"%s' % (region["text"], " — " + body if body else "")
-        if body and (x2 - x1) > 8:
-            ty = y1 + fs + 5
-            for line in _wrap(draw, body, font, x2 - x1 - 8):
-                if ty > y2:
-                    break
-                draw.text((x1 + 4, ty), line, fill=readable_color((r, g, b)) + (255,), font=font)
-                ty += line_h
-
-    composed = Image.alpha_composite(img, overlay).convert("RGB")
-    arr = np.asarray(composed, dtype=np.float32) / 255.0
-    return torch.from_numpy(arr).unsqueeze(0)
-
-
-def boxes_to_regions(boxes, width: int, height: int) -> list:
-    regions: list = []
-    if not isinstance(boxes, list):
-        return regions
-    for box in boxes:
-        if not isinstance(box, dict):
-            continue
-        meta = box.get("metadata")
-        meta = meta if isinstance(meta, dict) else {}
-        regions.append({
-            **pixels_to_fractions(box, width, height),
-            "type": meta.get("type", "obj"),
-            "text": meta.get("text", ""),
-            "desc": meta.get("desc", ""),
-            "palette": meta.get("palette", []),
-        })
-    return regions
-
-
-def _norm_bbox(region: dict) -> list[int]:
-    def grid(value: float) -> int:
-        return max(0, min(1000, round(value * 1000)))
-
-    x, y = region.get("x", 0.0), region.get("y", 0.0)
-    w, h = region.get("w", 0.0), region.get("h", 0.0)
-    ymin, xmin, ymax, xmax = grid(y), grid(x), grid(y + h), grid(x + w)
-    if ymin > ymax:
-        ymin, ymax = ymax, ymin
-    if xmin > xmax:
-        xmin, xmax = xmax, xmin
-    return [ymin, xmin, ymax, xmax]
-
-
-def build_elements(regions: list) -> list:
-    elements = []
-    for region in regions:
-        if not isinstance(region, dict):
-            continue
-        etype = "text" if region.get("type") == "text" else "obj"
-        element = {"type": etype}
-        element["bbox"] = _norm_bbox(region)
-        if etype == "text":
-            element["text"] = region.get("text", "")
-        element["desc"] = region.get("desc", "")
-        palette = normalize_palette(region.get("palette", []))
-        if palette:
-            element["color_palette"] = palette[:5]
-        elements.append(element)
-    return elements
-
-
-class CreateBoundingBoxes(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        editor_state = io.BoundingBoxes.Input(
-            "editor_state",
-            socketless=False,
-            tooltip="Draw bounding boxes and set each box type, text, description, color palette. Start with background element first and foreground last.",
-        )
-        return io.Schema(
-            node_id="CreateBoundingBoxes",
-            display_name="Create Bounding Boxes",
-            category="utilities",
-            description="Draw bounding boxes in a canvas. Outputs Ideogram prompt elements, pixel-space bounding boxes, and a preview image.",
-            inputs=[
-                io.Image.Input(
-                    "background",
-                    optional=True,
-                    tooltip="Optional image used as background in the canvas and preview.",
-                ),
-                io.Int.Input("width", default=1024, min=64, max=16384, step=16,
-                             tooltip="Width of the canvas and the pixel grid for the bounding boxes."),
-                io.Int.Input("height", default=1024, min=64, max=16384, step=16,
-                             tooltip="Height of the canvas and the pixel grid for the bounding boxes."),
-                editor_state,
-            ],
-            outputs=[
-                io.Image.Output(display_name="preview"),
-                io.BoundingBox.Output(display_name="bboxes"),
-                io.Array.Output(display_name="elements"),
-            ],
-            is_experimental=True,
-        )
-
-    @classmethod
-    def execute(cls, width, height, editor_state=None, background=None) -> io.NodeOutput:
-        regions = boxes_to_regions(editor_state, width, height)
-        preview = render_preview(regions, width, height, _bg_from_image(background))
-        return io.NodeOutput(
-            preview,
-            fractions_to_bbox_frame(regions, width, height),
-            build_elements(regions),
-            ui={"dims": [width, height]},
-        )
-
-
-class BoundingBoxesExtension(ComfyExtension):
-    @override
-    async def get_node_list(self) -> list[type[io.ComfyNode]]:
-        return [CreateBoundingBoxes]
-
-
-async def comfy_entrypoint() -> BoundingBoxesExtension:
-    return BoundingBoxesExtension()

comfy_extras/nodes_color.py

@@ -1,6 +1,5 @@
 from typing_extensions import override
 from comfy_api.latest import ComfyExtension, io
-from comfy_extras.color_util import hex_to_rgb
 
 
 class ColorToRGBInt(io.ComfyNode):
@@ -25,11 +24,9 @@ class ColorToRGBInt(io.ComfyNode):
         # expect format #RRGGBB
         if len(color) != 7 or color[0] != "#":
             raise ValueError("Color must be in format #RRGGBB")
-        try:
-            int(color[1:], 16)
-        except ValueError:
-            raise ValueError("Color must be in format #RRGGBB") from None
-        r, g, b = hex_to_rgb(color)
+        r = int(color[1:3], 16)
+        g = int(color[3:5], 16)
+        b = int(color[5:7], 16)
 
         rgb_int = r * 256 * 256 + g * 256 + b
         return io.NodeOutput(rgb_int, color)

comfy_extras/nodes_json_prompt.py

@@ -1,77 +0,0 @@
-from typing_extensions import override
-
-from comfy_api.latest import ComfyExtension, io
-from comfy_extras.color_util import normalize_palette
-
-
-class BuildJsonPromptIdeogram(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        color_palette = io.Colors.Input(
-            "color_palette",
-            socketless=False,
-            tooltip="Hex color codes that steer the image's dominant colors. Up to 16 entries.",
-        )
-        return io.Schema(
-            node_id="BuildJsonPromptIdeogram",
-            display_name="Build JSON Prompt (Ideogram)",
-            category="text",
-            description="Build a JSON prompt for the Ideogram 4 model.",
-            inputs=[
-                io.Array.Input("element", tooltip="Prompt elements from the node Create Bounding Boxes."),
-                io.String.Input("high_level_description", multiline=True, default="",
-                                tooltip="Optional description of the image in one or two sentences. Strongly recommended."),
-                io.String.Input("background", multiline=True, default="",
-                                tooltip="Mandatory description of the image background or environment."),
-                io.DynamicCombo.Input("style", options=[
-                    io.DynamicCombo.Option("none", []),
-                    io.DynamicCombo.Option("photo", [io.String.Input("photo", default="", tooltip="Camera or lens details for photographic outputs (e.g. 35mm, f/1.4, bokeh).")]),
-                    io.DynamicCombo.Option("art_style", [io.String.Input("art_style", default="", tooltip="Art style description (e.g. flat vector illustration, bold outlines).")]),
-                ]),
-                io.String.Input("aesthetics", default="", tooltip="Mandatory aesthetic keywords (e.g. moody, cinematic, desaturated)."),
-                io.String.Input("lighting", default="", tooltip="Mandatory lighting description (e.g. golden hour, rim light, dramatic shadows)."),
-                io.String.Input("medium", default="", tooltip="Mandatory medium type (e.g. photograph, illustration, 3d_render, painting, graphic_design). When style = photo, set to photograph."),
-                color_palette,
-            ],
-            outputs=[io.Dict.Output(display_name="prompt")],
-            is_experimental=True,
-        )
-
-    @classmethod
-    def execute(cls, element, style, high_level_description="", background="",
-                aesthetics="", lighting="", medium="", color_palette=None) -> io.NodeOutput:
-        elements = element if isinstance(element, list) else []
-        kind = style.get("style", "none") if isinstance(style, dict) else "none"
-        photo = style.get("photo", "") if isinstance(style, dict) else ""
-        art_style = style.get("art_style", "") if isinstance(style, dict) else ""
-        palette = normalize_palette(color_palette or [])
-
-        caption: dict = {}
-        if high_level_description.strip():
-            caption["high_level_description"] = high_level_description
-        if kind != "none":
-            style_desc: dict = {"aesthetics": aesthetics, "lighting": lighting}
-            if kind == "photo":
-                style_desc["photo"] = photo
-                style_desc["medium"] = medium
-            else:
-                style_desc["medium"] = medium
-                style_desc["art_style"] = art_style
-            if palette:
-                style_desc["color_palette"] = palette
-            caption["style_description"] = style_desc
-        caption["compositional_deconstruction"] = {
-            "background": background,
-            "elements": elements,
-        }
-        return io.NodeOutput(caption)
-
-
-class JsonPromptExtension(ComfyExtension):
-    @override
-    async def get_node_list(self) -> list[type[io.ComfyNode]]:
-        return [BuildJsonPromptIdeogram]
-
-
-async def comfy_entrypoint() -> JsonPromptExtension:
-    return JsonPromptExtension()

comfy_extras/nodes_string.py

@@ -440,57 +440,6 @@ class JsonExtractString(io.ComfyNode):
         except (json.JSONDecodeError, TypeError):
             return io.NodeOutput("")
 
-
-def _dump_json(value, indent):
-    return json.dumps(value, ensure_ascii=False, indent=indent or None)
-
-
-class ConvertDictionaryToString(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="ConvertDictionaryToString",
-            display_name="Convert Dictionary to String",
-            category="text",
-            search_aliases=["json", "dict to json", "stringify", "serialize", "dict to string"],
-            inputs=[
-                io.Dict.Input("dictionary"),
-                io.Int.Input("indent", default=2, min=0, max=8,
-                             tooltip="Spaces per indent level. 0 produces compact single-line string."),
-            ],
-            outputs=[
-                io.String.Output(),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, dictionary, indent=2):
-        return io.NodeOutput(_dump_json(dictionary, indent))
-
-
-class ConvertArrayToString(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="ConvertArrayToString",
-            display_name="Convert Array to String",
-            category="text",
-            search_aliases=["json", "list to json", "stringify", "serialize", "list to string", "array to json"],
-            inputs=[
-                io.Array.Input("array"),
-                io.Int.Input("indent", default=2, min=0, max=8,
-                             tooltip="Spaces per indent level. 0 produces compact single-line string."),
-            ],
-            outputs=[
-                io.String.Output(),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, array, indent=2):
-        return io.NodeOutput(_dump_json(array, indent))
-
-
 class StringExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[io.ComfyNode]]:
@@ -508,8 +457,6 @@ class StringExtension(ComfyExtension):
             RegexExtract,
             RegexReplace,
             JsonExtractString,
-            ConvertDictionaryToString,
-            ConvertArrayToString,
         ]
 
 async def comfy_entrypoint() -> StringExtension:

nodes.py

@@ -2374,8 +2374,6 @@ async def init_builtin_extra_nodes():
         "nodes_images.py",
         "nodes_video_model.py",
         "nodes_ideogram4.py",
-        "nodes_bounding_boxes.py",
-        "nodes_json_prompt.py",
         "nodes_train.py",
         "nodes_dataset.py",
         "nodes_sag.py",

openapi.yaml

@@ -1692,6 +1692,12 @@ paths:
                             schema:
                                 $ref: '#/components/schemas/ErrorResponse'
                     description: Unsupported media type
+                "422":
+                    content:
+                        application/json:
+                            schema:
+                                $ref: '#/components/schemas/ErrorResponse'
+                    description: Validation error (e.g., disallowed model_type tag)
                 "500":
                     content:
                         application/json:
@@ -2137,6 +2143,12 @@ paths:
                             schema:
                                 $ref: '#/components/schemas/ErrorResponse'
                     description: Source asset with given hash not found
+                "422":
+                    content:
+                        application/json:
+                            schema:
+                                $ref: '#/components/schemas/ErrorResponse'
+                    description: Validation error (e.g., disallowed model_type tag)
                 "500":
                     content:
                         application/json:
@@ -2357,6 +2369,10 @@ paths:
             description: |
                 Returns a list of model folders available in the system.
                 This is an experimental endpoint that replaces the legacy /models endpoint.
+                Each folder's name is the identifier to pass to /api/experiment/models/{folder}.
+                Once the model_type migration is active the names are model_type folder_names
+                (e.g. `ultralytics_bbox`); a folder with no folder_name mapping is returned by
+                its directory path.
             operationId: getModelFolders
             responses:
                 "200":

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.45.19
-comfyui-workflow-templates==0.10.3
+comfyui-workflow-templates==0.10.2
 comfyui-embedded-docs==0.5.5
 torch
 torchsde