feat: clip model

__init__.py

@@ -2,6 +2,7 @@ from .src.nodes import (
     NODE_CLASS_MAPPINGS,
     NODE_DISPLAY_NAME_MAPPINGS,
     ComfyUIAutoencoderDTO,
+    ComfyUIClipDTO,
     ComfyUIPipelineDTO,
 )
 
@@ -10,4 +11,5 @@ __all__ = [
     "NODE_DISPLAY_NAME_MAPPINGS",
     "ComfyUIPipelineDTO",
     "ComfyUIAutoencoderDTO",
+    "ComfyUIClipDTO",
 ]

src/domain/model/__init__.py

@@ -1,7 +1,9 @@
 from ._autoencoder import Autoencoder
+from ._clip import Clip
 from ._pipeline import Pipeline
 
 __all__ = [
     "Pipeline",
     "Autoencoder",
+    "Clip",
 ]

src/domain/model/_clip.py

@@ -0,0 +1,10 @@
+from dataclasses import dataclass
+
+from transformers import CLIPTextModel, CLIPTokenizer
+
+
+@dataclass
+class Clip:
+    tokenizer: CLIPTokenizer
+    text_encoder: CLIPTextModel
+    path: str

src/nodes/__init__.py

@@ -1,7 +1,7 @@
 from ..di import Container
 from ._diffusers_pipeline_loader import DiffusersPipelineLoader
 from ._diffusers_vae_loader import DiffusersVaeLoader
-from .dto import ComfyUIAutoencoderDTO, ComfyUIPipelineDTO
+from .dto import ComfyUIAutoencoderDTO, ComfyUIClipDTO, ComfyUIPipelineDTO
 
 container = Container()
 container.wire(modules=[__name__])
@@ -20,4 +20,5 @@ __all__ = [
     "NODE_DISPLAY_NAME_MAPPINGS",
     "ComfyUIPipelineDTO",
     "ComfyUIAutoencoderDTO",
+    "ComfyUIClipDTO",
 ]

src/nodes/dto/__init__.py

@@ -1,4 +1,5 @@
 from ._autoencoder_dto import ComfyUIAutoencoderDTO
+from ._clip import ComfyUIClipDTO
 from ._pipeline_dto import ComfyUIPipelineDTO
 
-__all__ = ["ComfyUIPipelineDTO", "ComfyUIAutoencoderDTO"]
+__all__ = ["ComfyUIPipelineDTO", "ComfyUIAutoencoderDTO", "ComfyUIClipDTO"]

src/nodes/dto/_clip.py

@@ -0,0 +1,60 @@
+from dataclasses import dataclass
+from typing import ClassVar
+
+from transformers import CLIPTextModel, CLIPTokenizer
+
+from ...domain.model import Clip
+
+
+@dataclass
+class ComfyUIClipDTO:
+    """Data Transfer Object for CLIP (Tokenizer and Text Encoder) in ComfyUI.
+
+    This DTO is designed to be used across different custom nodes.
+    Other node developers can import and use this type for CLIP operations.
+
+    Attributes:
+        tokenizer: CLIPTokenizer instance from transformers library
+        text_encoder: CLIPTextModel instance from transformers library
+        path: Path to the loaded model directory
+
+    Class Attributes:
+        COMFY_TYPE: Type name used in ComfyUI's RETURN_TYPES and INPUT_TYPES
+
+    Example:
+        ```python
+        from your_node_package.nodes.dto import ComfyUIClipDTO
+
+        class YourCustomNode:
+            @classmethod
+            def INPUT_TYPES(cls):
+                return {"required": {"clip": (ComfyUIClipDTO.COMFY_TYPE,)}}
+
+            RETURN_TYPES = (ComfyUIClipDTO.COMFY_TYPE,)
+
+            def execute(self, clip: ComfyUIClipDTO):
+                # Use the tokenizer and text encoder
+                tokens = clip.tokenizer(prompt, return_tensors="pt")
+                embeddings = clip.text_encoder(**tokens)
+                return (embeddings,)
+        ```
+    """
+
+    # ClassVar to avoid being treated as a dataclass field
+    COMFY_TYPE: ClassVar[str] = "DIFFUSERS_CLIP"
+
+    tokenizer: CLIPTokenizer
+    text_encoder: CLIPTextModel
+    path: str
+
+    @classmethod
+    def from_domain(cls, clip: Clip) -> "ComfyUIClipDTO":
+        """Create DTO from domain model.
+
+        Args:
+            clip: Clip from domain layer
+
+        Returns:
+            ComfyUIClipDTO instance
+        """
+        return cls(tokenizer=clip.tokenizer, text_encoder=clip.text_encoder, path=clip.path)