mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
c238a7f18b
Upgrade pydantic and fastapi to latest.
- pydantic~=2.4.2
- fastapi~=103.2
- fastapi-events~=0.9.1
**Big Changes**
There are a number of logic changes needed to support pydantic v2. Most changes are very simple, like using the new methods to serialized and deserialize models, but there are a few more complex changes.
**Invocations**
The biggest change relates to invocation creation, instantiation and validation.
Because pydantic v2 moves all validation logic into the rust pydantic-core, we may no longer directly stick our fingers into the validation pie.
Previously, we (ab)used models and fields to allow invocation fields to be optional at instantiation, but required when `invoke()` is called. We directly manipulated the fields and invocation models when calling `invoke()`.
With pydantic v2, this is much more involved. Changes to the python wrapper do not propagate down to the rust validation logic - you have to rebuild the model. This causes problem with concurrent access to the invocation classes and is not a free operation.
This logic has been totally refactored and we do not need to change the model any more. The details are in `baseinvocation.py`, in the `InputField` function and `BaseInvocation.invoke_internal()` method.
In the end, this implementation is cleaner.
**Invocation Fields**
In pydantic v2, you can no longer directly add or remove fields from a model.
Previously, we did this to add the `type` field to invocations.
**Invocation Decorators**
With pydantic v2, we instead use the imperative `create_model()` API to create a new model with the additional field. This is done in `baseinvocation.py` in the `invocation()` wrapper.
A similar technique is used for `invocation_output()`.
**Minor Changes**
There are a number of minor changes around the pydantic v2 models API.
**Protected `model_` Namespace**
All models' pydantic-provided methods and attributes are prefixed with `model_` and this is considered a protected namespace. This causes some conflict, because "model" means something to us, and we have a ton of pydantic models with attributes starting with "model_".
Forunately, there are no direct conflicts. However, in any pydantic model where we define an attribute or method that starts with "model_", we must tell set the protected namespaces to an empty tuple.
```py
class IPAdapterModelField(BaseModel):
model_name: str = Field(description="Name of the IP-Adapter model")
base_model: BaseModelType = Field(description="Base model")
model_config = ConfigDict(protected_namespaces=())
```
**Model Serialization**
Pydantic models no longer have `Model.dict()` or `Model.json()`.
Instead, we use `Model.model_dump()` or `Model.model_dump_json()`.
**Model Deserialization**
Pydantic models no longer have `Model.parse_obj()` or `Model.parse_raw()`, and there are no `parse_raw_as()` or `parse_obj_as()` functions.
Instead, you need to create a `TypeAdapter` object to parse python objects or JSON into a model.
```py
adapter_graph = TypeAdapter(Graph)
deserialized_graph_from_json = adapter_graph.validate_json(graph_json)
deserialized_graph_from_dict = adapter_graph.validate_python(graph_dict)
```
**Field Customisation**
Pydantic `Field`s no longer accept arbitrary args.
Now, you must put all additional arbitrary args in a `json_schema_extra` arg on the field.
**Schema Customisation**
FastAPI and pydantic schema generation now follows the OpenAPI version 3.1 spec.
This necessitates two changes:
- Our schema customization logic has been revised
- Schema parsing to build node templates has been revised
The specific aren't important, but this does present additional surface area for bugs.
**Performance Improvements**
Pydantic v2 is a full rewrite with a rust backend. This offers a substantial performance improvement (pydantic claims 5x to 50x depending on the task). We'll notice this the most during serialization and deserialization of sessions/graphs, which happens very very often - a couple times per node.
I haven't done any benchmarks, but anecdotally, graph execution is much faster. Also, very larges graphs - like with massive iterators - are much, much faster.
99 lines
3.1 KiB
Python
99 lines
3.1 KiB
Python
import os
|
|
import typing
|
|
from enum import Enum
|
|
from typing import Literal, Optional
|
|
|
|
import torch
|
|
|
|
from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus, build_ip_adapter
|
|
from invokeai.backend.model_management.models.base import (
|
|
BaseModelType,
|
|
InvalidModelException,
|
|
ModelBase,
|
|
ModelConfigBase,
|
|
ModelType,
|
|
SubModelType,
|
|
calc_model_size_by_fs,
|
|
classproperty,
|
|
)
|
|
|
|
|
|
class IPAdapterModelFormat(str, Enum):
|
|
# The custom IP-Adapter model format defined by InvokeAI.
|
|
InvokeAI = "invokeai"
|
|
|
|
|
|
class IPAdapterModel(ModelBase):
|
|
class InvokeAIConfig(ModelConfigBase):
|
|
model_format: Literal[IPAdapterModelFormat.InvokeAI]
|
|
|
|
def __init__(self, model_path: str, base_model: BaseModelType, model_type: ModelType):
|
|
assert model_type == ModelType.IPAdapter
|
|
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 IP-Adapter model at path '{path}'.")
|
|
|
|
if os.path.isdir(path):
|
|
model_file = os.path.join(path, "ip_adapter.bin")
|
|
image_encoder_config_file = os.path.join(path, "image_encoder.txt")
|
|
if os.path.exists(model_file) and os.path.exists(image_encoder_config_file):
|
|
return IPAdapterModelFormat.InvokeAI
|
|
|
|
raise InvalidModelException(f"Unexpected IP-Adapter 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 an IP-Adapter model.")
|
|
|
|
return self.model_size
|
|
|
|
def get_model(
|
|
self,
|
|
torch_dtype: torch.dtype,
|
|
child_type: Optional[SubModelType] = None,
|
|
) -> typing.Union[IPAdapter, IPAdapterPlus]:
|
|
if child_type is not None:
|
|
raise ValueError("There are no child models in an IP-Adapter model.")
|
|
|
|
model = build_ip_adapter(
|
|
ip_adapter_ckpt_path=os.path.join(self.model_path, "ip_adapter.bin"),
|
|
device=torch.device("cpu"),
|
|
dtype=torch_dtype,
|
|
)
|
|
|
|
self.model_size = model.calc_size()
|
|
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 == IPAdapterModelFormat.InvokeAI:
|
|
return model_path
|
|
else:
|
|
raise ValueError(f"Unsupported format: '{format}'.")
|
|
|
|
|
|
def get_ip_adapter_image_encoder_model_id(model_path: str):
|
|
"""Read the ID of the image encoder associated with the IP-Adapter at `model_path`."""
|
|
image_encoder_config_file = os.path.join(model_path, "image_encoder.txt")
|
|
|
|
with open(image_encoder_config_file, "r") as f:
|
|
image_encoder_model = f.readline().strip()
|
|
|
|
return image_encoder_model
|