[pull] master from Comfy-Org:master

comfy/sd1_clip.py

@@ -466,7 +466,7 @@ def load_embed(embedding_name, embedding_directory, embedding_size, embed_key=No
     return embed_out
 
 class SDTokenizer:
-    def __init__(self, tokenizer_path=None, max_length=77, pad_with_end=True, embedding_directory=None, embedding_size=768, embedding_key='clip_l', tokenizer_class=CLIPTokenizer, has_start_token=True, has_end_token=True, pad_to_max_length=True, min_length=None, pad_token=None, end_token=None, min_padding=None, pad_left=False, disable_weights=False, tokenizer_data={}, tokenizer_args={}):
+    def __init__(self, tokenizer_path=None, max_length=77, pad_with_end=True, embedding_directory=None, embedding_size=768, embedding_key='clip_l', tokenizer_class=CLIPTokenizer, has_start_token=True, has_end_token=True, pad_to_max_length=True, min_length=None, pad_token=None, end_token=None, start_token=None, min_padding=None, pad_left=False, disable_weights=False, tokenizer_data={}, tokenizer_args={}):
         if tokenizer_path is None:
             tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "sd1_tokenizer")
         self.tokenizer = tokenizer_class.from_pretrained(tokenizer_path, **tokenizer_args)
@@ -479,16 +479,23 @@ def __init__(self, tokenizer_path=None, max_length=77, pad_with_end=True, embedd
         empty = self.tokenizer('')["input_ids"]
         self.tokenizer_adds_end_token = has_end_token
         if has_start_token:
-            self.tokens_start = 1
-            self.start_token = empty[0]
+            if len(empty) > 0:
+                self.tokens_start = 1
+                self.start_token = empty[0]
+            else:
+                self.tokens_start = 0
+                self.start_token = start_token
+                if start_token is None:
+                    logging.warning("WARNING: There's something wrong with your tokenizers.'")
+
             if end_token is not None:
                 self.end_token = end_token
             else:
                 if has_end_token:
                     self.end_token = empty[1]
         else:
             self.tokens_start = 0
-            self.start_token = None
+            self.start_token = start_token
             if end_token is not None:
                 self.end_token = end_token
             else:

comfy/text_encoders/flux.py

@@ -118,7 +118,7 @@ def from_pretrained(path, **kwargs):
 class Mistral3Tokenizer(sd1_clip.SDTokenizer):
     def __init__(self, embedding_directory=None, tokenizer_data={}):
         self.tekken_data = tokenizer_data.get("tekken_model", None)
-        super().__init__("", pad_with_end=False, embedding_size=5120, embedding_key='mistral3_24b', tokenizer_class=MistralTokenizerClass, has_end_token=False, pad_to_max_length=False, pad_token=11, max_length=99999999, min_length=1, pad_left=True, tokenizer_args=load_mistral_tokenizer(self.tekken_data), tokenizer_data=tokenizer_data)
+        super().__init__("", pad_with_end=False, embedding_size=5120, embedding_key='mistral3_24b', tokenizer_class=MistralTokenizerClass, has_end_token=False, pad_to_max_length=False, pad_token=11, start_token=1, max_length=99999999, min_length=1, pad_left=True, tokenizer_args=load_mistral_tokenizer(self.tekken_data), tokenizer_data=tokenizer_data)
 
     def state_dict(self):
         return {"tekken_model": self.tekken_data}

comfy_api_nodes/apis/bytedance.py

@@ -13,17 +13,6 @@ class Text2ImageTaskCreationRequest(BaseModel):
     watermark: bool | None = Field(False)
 
 
-class Image2ImageTaskCreationRequest(BaseModel):
-    model: str = Field(...)
-    prompt: str = Field(...)
-    response_format: str | None = Field("url")
-    image: str = Field(..., description="Base64 encoded string or image URL")
-    size: str | None = Field("adaptive")
-    seed: int | None = Field(..., ge=0, le=2147483647)
-    guidance_scale: float | None = Field(..., ge=1.0, le=10.0)
-    watermark: bool | None = Field(False)
-
-
 class Seedream4Options(BaseModel):
     max_images: int = Field(15)
 

comfy_api_nodes/apis/magnific.py

@@ -0,0 +1,122 @@
+from typing import TypedDict
+
+from pydantic import AliasChoices, BaseModel, Field, model_validator
+
+
+class InputPortraitMode(TypedDict):
+    portrait_mode: str
+    portrait_style: str
+    portrait_beautifier: str
+
+
+class InputAdvancedSettings(TypedDict):
+    advanced_settings: str
+    whites: int
+    blacks: int
+    brightness: int
+    contrast: int
+    saturation: int
+    engine: str
+    transfer_light_a: str
+    transfer_light_b: str
+    fixed_generation: bool
+
+
+class InputSkinEnhancerMode(TypedDict):
+    mode: str
+    skin_detail: int
+    optimized_for: str
+
+
+class ImageUpscalerCreativeRequest(BaseModel):
+    image: str = Field(...)
+    scale_factor: str = Field(...)
+    optimized_for: str = Field(...)
+    prompt: str | None = Field(None)
+    creativity: int = Field(...)
+    hdr: int = Field(...)
+    resemblance: int = Field(...)
+    fractality: int = Field(...)
+    engine: str = Field(...)
+
+
+class ImageUpscalerPrecisionV2Request(BaseModel):
+    image: str = Field(...)
+    sharpen: int = Field(...)
+    smart_grain: int = Field(...)
+    ultra_detail: int = Field(...)
+    flavor: str = Field(...)
+    scale_factor: int = Field(...)
+
+
+class ImageRelightAdvancedSettingsRequest(BaseModel):
+    whites: int = Field(...)
+    blacks: int = Field(...)
+    brightness: int = Field(...)
+    contrast: int = Field(...)
+    saturation: int = Field(...)
+    engine: str = Field(...)
+    transfer_light_a: str = Field(...)
+    transfer_light_b: str = Field(...)
+    fixed_generation: bool = Field(...)
+
+
+class ImageRelightRequest(BaseModel):
+    image: str = Field(...)
+    prompt: str | None = Field(None)
+    transfer_light_from_reference_image: str | None = Field(None)
+    light_transfer_strength: int = Field(...)
+    interpolate_from_original: bool = Field(...)
+    change_background: bool = Field(...)
+    style: str = Field(...)
+    preserve_details: bool = Field(...)
+    advanced_settings: ImageRelightAdvancedSettingsRequest | None = Field(...)
+
+
+class ImageStyleTransferRequest(BaseModel):
+    image: str = Field(...)
+    reference_image: str = Field(...)
+    prompt: str | None = Field(None)
+    style_strength: int = Field(...)
+    structure_strength: int = Field(...)
+    is_portrait: bool = Field(...)
+    portrait_style: str | None = Field(...)
+    portrait_beautifier: str | None = Field(...)
+    flavor: str = Field(...)
+    engine: str = Field(...)
+    fixed_generation: bool = Field(...)
+
+
+class ImageSkinEnhancerCreativeRequest(BaseModel):
+    image: str = Field(...)
+    sharpen: int = Field(...)
+    smart_grain: int = Field(...)
+
+
+class ImageSkinEnhancerFaithfulRequest(BaseModel):
+    image: str = Field(...)
+    sharpen: int = Field(...)
+    smart_grain: int = Field(...)
+    skin_detail: int = Field(...)
+
+
+class ImageSkinEnhancerFlexibleRequest(BaseModel):
+    image: str = Field(...)
+    sharpen: int = Field(...)
+    smart_grain: int = Field(...)
+    optimized_for: str = Field(...)
+
+
+class TaskResponse(BaseModel):
+    """Unified response model that handles both wrapped and unwrapped API responses."""
+
+    task_id: str = Field(...)
+    status: str = Field(validation_alias=AliasChoices("status", "task_status"))
+    generated: list[str] | None = Field(None)
+
+    @model_validator(mode="before")
+    @classmethod
+    def unwrap_data(cls, values: dict) -> dict:
+        if "data" in values and isinstance(values["data"], dict):
+            return values["data"]
+        return values

comfy_api_nodes/nodes_bytedance.py

@@ -9,7 +9,6 @@
     RECOMMENDED_PRESETS,
     RECOMMENDED_PRESETS_SEEDREAM_4,
     VIDEO_TASKS_EXECUTION_TIME,
-    Image2ImageTaskCreationRequest,
     Image2VideoTaskCreationRequest,
     ImageTaskCreationResponse,
     Seedream4Options,
@@ -174,99 +173,6 @@ async def execute(
         return IO.NodeOutput(await download_url_to_image_tensor(get_image_url_from_response(response)))
 
 
-class ByteDanceImageEditNode(IO.ComfyNode):
-
-    @classmethod
-    def define_schema(cls):
-        return IO.Schema(
-            node_id="ByteDanceImageEditNode",
-            display_name="ByteDance Image Edit",
-            category="api node/image/ByteDance",
-            description="Edit images using ByteDance models via api based on prompt",
-            inputs=[
-                IO.Combo.Input("model", options=["seededit-3-0-i2i-250628"]),
-                IO.Image.Input(
-                    "image",
-                    tooltip="The base image to edit",
-                ),
-                IO.String.Input(
-                    "prompt",
-                    multiline=True,
-                    default="",
-                    tooltip="Instruction to edit image",
-                ),
-                IO.Int.Input(
-                    "seed",
-                    default=0,
-                    min=0,
-                    max=2147483647,
-                    step=1,
-                    display_mode=IO.NumberDisplay.number,
-                    control_after_generate=True,
-                    tooltip="Seed to use for generation",
-                    optional=True,
-                ),
-                IO.Float.Input(
-                    "guidance_scale",
-                    default=5.5,
-                    min=1.0,
-                    max=10.0,
-                    step=0.01,
-                    display_mode=IO.NumberDisplay.number,
-                    tooltip="Higher value makes the image follow the prompt more closely",
-                    optional=True,
-                ),
-                IO.Boolean.Input(
-                    "watermark",
-                    default=False,
-                    tooltip='Whether to add an "AI generated" watermark to the image',
-                    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,
-            is_deprecated=True,
-        )
-
-    @classmethod
-    async def execute(
-        cls,
-        model: str,
-        image: Input.Image,
-        prompt: str,
-        seed: int,
-        guidance_scale: float,
-        watermark: bool,
-    ) -> IO.NodeOutput:
-        validate_string(prompt, strip_whitespace=True, min_length=1)
-        if get_number_of_images(image) != 1:
-            raise ValueError("Exactly one input image is required.")
-        validate_image_aspect_ratio(image, (1, 3), (3, 1))
-        source_url = (await upload_images_to_comfyapi(cls, image, max_images=1, mime_type="image/png"))[0]
-        payload = Image2ImageTaskCreationRequest(
-            model=model,
-            prompt=prompt,
-            image=source_url,
-            seed=seed,
-            guidance_scale=guidance_scale,
-            watermark=watermark,
-        )
-        response = await sync_op(
-            cls,
-            ApiEndpoint(path=BYTEPLUS_IMAGE_ENDPOINT, method="POST"),
-            data=payload,
-            response_model=ImageTaskCreationResponse,
-        )
-        return IO.NodeOutput(await download_url_to_image_tensor(get_image_url_from_response(response)))
-
-
 class ByteDanceSeedreamNode(IO.ComfyNode):
 
     @classmethod
@@ -1101,7 +1007,6 @@ class ByteDanceExtension(ComfyExtension):
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
         return [
             ByteDanceImageNode,
-            ByteDanceImageEditNode,
             ByteDanceSeedreamNode,
             ByteDanceTextToVideoNode,
             ByteDanceImageToVideoNode,