refactor(nodes): model identifiers

- All models are identified by a key and optionally a submodel type via new model `ModelField`. Previously, a few model types had their own class, but not all of them. This inconsistency just added complexity without any benefit.
- Update all invocation to use the new format.
- In the node API, models are loaded by key or an instance of `ModelField` as a convenience.
- Add an enriched model schema for metadata. It includes key, hash, name, base and type.
This commit is contained in:
psychedelicious
2024-03-06 19:37:15 +11:00
parent afd9ae7712
commit 528ac5dd25
15 changed files with 229 additions and 288 deletions

View File

@ -11,25 +11,17 @@ from invokeai.app.invocations.baseinvocation import (
invocation_output,
)
from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField
from invokeai.app.invocations.model import ModelField
from invokeai.app.invocations.primitives import ImageField
from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
from invokeai.app.services.shared.invocation_context import InvocationContext
from invokeai.backend.model_manager.config import BaseModelType, ModelType
# LS: Consider moving these two classes into model.py
class IPAdapterModelField(BaseModel):
key: str = Field(description="Key to the IP-Adapter model")
class CLIPVisionModelField(BaseModel):
key: str = Field(description="Key to the CLIP Vision image encoder model")
from invokeai.backend.model_manager.config import BaseModelType, IPAdapterConfig, ModelType
class IPAdapterField(BaseModel):
image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
ip_adapter_model: ModelField = Field(description="The IP-Adapter model to use.")
image_encoder_model: ModelField = Field(description="The name of the CLIP image encoder model.")
weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
begin_step_percent: float = Field(
default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
@ -62,7 +54,7 @@ class IPAdapterInvocation(BaseInvocation):
# Inputs
image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
ip_adapter_model: IPAdapterModelField = InputField(
ip_adapter_model: ModelField = InputField(
description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
)
@ -90,18 +82,18 @@ class IPAdapterInvocation(BaseInvocation):
def invoke(self, context: InvocationContext) -> IPAdapterOutput:
# Lookup the CLIP Vision encoder that is intended to be used with the IP-Adapter model.
ip_adapter_info = context.models.get_config(self.ip_adapter_model.key)
assert isinstance(ip_adapter_info, IPAdapterConfig)
image_encoder_model_id = ip_adapter_info.image_encoder_model_id
image_encoder_model_name = image_encoder_model_id.split("/")[-1].strip()
image_encoder_models = context.models.search_by_attrs(
name=image_encoder_model_name, base=BaseModelType.Any, type=ModelType.CLIPVision
)
assert len(image_encoder_models) == 1
image_encoder_model = CLIPVisionModelField(key=image_encoder_models[0].key)
return IPAdapterOutput(
ip_adapter=IPAdapterField(
image=self.image,
ip_adapter_model=self.ip_adapter_model,
image_encoder_model=image_encoder_model,
image_encoder_model=ModelField(key=image_encoder_models[0].key),
weight=self.weight,
begin_step_percent=self.begin_step_percent,
end_step_percent=self.end_step_percent,