Add CLIPVisionModel to model management.

invokeai/backend/model_management/models/__init__.py

@@ -18,6 +18,7 @@ from .base import (  # noqa: F401
     SilenceWarnings,
     SubModelType,
 )
+from .clip_vision import CLIPVisionModel
 from .controlnet import ControlNetModel  # TODO:
 from .ip_adapter import IPAdapterModel
 from .lora import LoRAModel
@@ -36,6 +37,7 @@ MODEL_CLASSES = {
         ModelType.ControlNet: ControlNetModel,
         ModelType.TextualInversion: TextualInversionModel,
         ModelType.IPAdapter: IPAdapterModel,
+        ModelType.CLIPVision: CLIPVisionModel,
     },
     BaseModelType.StableDiffusion2: {
         ModelType.ONNX: ONNXStableDiffusion2Model,
@@ -45,6 +47,7 @@ MODEL_CLASSES = {
         ModelType.ControlNet: ControlNetModel,
         ModelType.TextualInversion: TextualInversionModel,
         ModelType.IPAdapter: IPAdapterModel,
+        ModelType.CLIPVision: CLIPVisionModel,
     },
     BaseModelType.StableDiffusionXL: {
         ModelType.Main: StableDiffusionXLModel,
@@ -55,6 +58,7 @@ MODEL_CLASSES = {
         ModelType.TextualInversion: TextualInversionModel,
         ModelType.ONNX: ONNXStableDiffusion2Model,
         ModelType.IPAdapter: IPAdapterModel,
+        ModelType.CLIPVision: CLIPVisionModel,
     },
     BaseModelType.StableDiffusionXLRefiner: {
         ModelType.Main: StableDiffusionXLModel,
@@ -65,6 +69,7 @@ MODEL_CLASSES = {
         ModelType.TextualInversion: TextualInversionModel,
         ModelType.ONNX: ONNXStableDiffusion2Model,
         ModelType.IPAdapter: IPAdapterModel,
+        ModelType.CLIPVision: CLIPVisionModel,
     },
     # BaseModelType.Kandinsky2_1: {
     #    ModelType.Main: Kandinsky2_1Model,

invokeai/backend/model_management/models/base.py

@@ -62,6 +62,7 @@ class ModelType(str, Enum):
     ControlNet = "controlnet"  # used by model_probe
     TextualInversion = "embedding"
     IPAdapter = "ip_adapter"
+    CLIPVision = "clip_vision"
 
 
 class SubModelType(str, Enum):

invokeai/backend/model_management/models/clip_vision.py

@@ -0,0 +1,82 @@
+import os
+from enum import Enum
+from typing import Literal, Optional
+
+import torch
+from transformers import CLIPVisionModelWithProjection
+
+from invokeai.backend.model_management.models.base import (
+    BaseModelType,
+    InvalidModelException,
+    ModelBase,
+    ModelConfigBase,
+    ModelType,
+    SubModelType,
+    calc_model_size_by_data,
+    calc_model_size_by_fs,
+    classproperty,
+)
+
+
+class CLIPVisionModelFormat(str, Enum):
+    Diffusers = "diffusers"
+
+
+class CLIPVisionModel(ModelBase):
+    class DiffusersConfig(ModelConfigBase):
+        model_format: Literal[CLIPVisionModelFormat.Diffusers]
+
+    def __init__(self, model_path: str, base_model: BaseModelType, model_type: ModelType):
+        assert model_type == ModelType.CLIPVision
+        super().__init__(model_path, base_model, model_type)
+
+        self.model_size = calc_model_size_by_fs(self.model_path)
+
+    @classmethod
+    def detect_format(cls, path: str) -> str:
+        if not os.path.exists(path):
+            raise ModuleNotFoundError(f"No CLIP Vision model at path '{path}'.")
+
+        if os.path.isdir(path) and os.path.exists(os.path.join(path, "config.json")):
+            return CLIPVisionModelFormat.Diffusers
+
+        raise InvalidModelException(f"Unexpected CLIP Vision model format: {path}")
+
+    @classproperty
+    def save_to_config(cls) -> bool:
+        return True
+
+    def get_size(self, child_type: Optional[SubModelType] = None) -> int:
+        if child_type is not None:
+            raise ValueError("There are no child models in a CLIP Vision model.")
+
+        return self.model_size
+
+    def get_model(
+        self,
+        torch_dtype: Optional[torch.dtype],
+        child_type: Optional[SubModelType] = None,
+    ) -> CLIPVisionModelWithProjection:
+        if child_type is not None:
+            raise ValueError("There are no child models in a CLIP Vision model.")
+
+        model = CLIPVisionModelWithProjection.from_pretrained(self._image_encoder_path, torch_dtype=torch_dtype)
+
+        # Calculate a more accurate model size.
+        self.model_size = calc_model_size_by_data(model)
+
+        return model
+
+    @classmethod
+    def convert_if_required(
+        cls,
+        model_path: str,
+        output_path: str,
+        config: ModelConfigBase,
+        base_model: BaseModelType,
+    ) -> str:
+        format = cls.detect_format(model_path)
+        if format == CLIPVisionModelFormat.Diffusers:
+            return model_path
+        else:
+            raise ValueError(f"Unsupported format: '{format}'.")