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.
93 lines
3.8 KiB
Python
93 lines
3.8 KiB
Python
from invokeai.app.services.item_storage.item_storage_base import ItemStorageABC
|
|
|
|
from ...invocations.compel import CompelInvocation
|
|
from ...invocations.image import ImageNSFWBlurInvocation
|
|
from ...invocations.latent import DenoiseLatentsInvocation, LatentsToImageInvocation
|
|
from ...invocations.noise import NoiseInvocation
|
|
from ...invocations.primitives import IntegerInvocation
|
|
from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
|
|
|
|
default_text_to_image_graph_id = "539b2af5-2b4d-4d8c-8071-e54a3255fc74"
|
|
|
|
|
|
def create_text_to_image() -> LibraryGraph:
|
|
graph = Graph(
|
|
nodes={
|
|
"width": IntegerInvocation(id="width", value=512),
|
|
"height": IntegerInvocation(id="height", value=512),
|
|
"seed": IntegerInvocation(id="seed", value=-1),
|
|
"3": NoiseInvocation(id="3"),
|
|
"4": CompelInvocation(id="4"),
|
|
"5": CompelInvocation(id="5"),
|
|
"6": DenoiseLatentsInvocation(id="6"),
|
|
"7": LatentsToImageInvocation(id="7"),
|
|
"8": ImageNSFWBlurInvocation(id="8"),
|
|
},
|
|
edges=[
|
|
Edge(
|
|
source=EdgeConnection(node_id="width", field="value"),
|
|
destination=EdgeConnection(node_id="3", field="width"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="height", field="value"),
|
|
destination=EdgeConnection(node_id="3", field="height"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="seed", field="value"),
|
|
destination=EdgeConnection(node_id="3", field="seed"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="3", field="noise"),
|
|
destination=EdgeConnection(node_id="6", field="noise"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="6", field="latents"),
|
|
destination=EdgeConnection(node_id="7", field="latents"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="4", field="conditioning"),
|
|
destination=EdgeConnection(node_id="6", field="positive_conditioning"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="5", field="conditioning"),
|
|
destination=EdgeConnection(node_id="6", field="negative_conditioning"),
|
|
),
|
|
Edge(
|
|
source=EdgeConnection(node_id="7", field="image"),
|
|
destination=EdgeConnection(node_id="8", field="image"),
|
|
),
|
|
],
|
|
)
|
|
return LibraryGraph(
|
|
id=default_text_to_image_graph_id,
|
|
name="t2i",
|
|
description="Converts text to an image",
|
|
graph=graph,
|
|
exposed_inputs=[
|
|
ExposedNodeInput(node_path="4", field="prompt", alias="positive_prompt"),
|
|
ExposedNodeInput(node_path="5", field="prompt", alias="negative_prompt"),
|
|
ExposedNodeInput(node_path="width", field="value", alias="width"),
|
|
ExposedNodeInput(node_path="height", field="value", alias="height"),
|
|
ExposedNodeInput(node_path="seed", field="value", alias="seed"),
|
|
],
|
|
exposed_outputs=[ExposedNodeOutput(node_path="8", field="image", alias="image")],
|
|
)
|
|
|
|
|
|
def create_system_graphs(graph_library: ItemStorageABC[LibraryGraph]) -> list[LibraryGraph]:
|
|
"""Creates the default system graphs, or adds new versions if the old ones don't match"""
|
|
|
|
# TODO: Uncomment this when we are ready to fix this up to prevent breaking changes
|
|
graphs: list[LibraryGraph] = list()
|
|
|
|
text_to_image = graph_library.get(default_text_to_image_graph_id)
|
|
|
|
# TODO: Check if the graph is the same as the default one, and if not, update it
|
|
# if text_to_image is None:
|
|
text_to_image = create_text_to_image()
|
|
graph_library.set(text_to_image)
|
|
|
|
graphs.append(text_to_image)
|
|
|
|
return graphs
|