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.
102 lines
3.4 KiB
Python
102 lines
3.4 KiB
Python
from os.path import exists
|
|
from typing import Optional, Union
|
|
|
|
import numpy as np
|
|
from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
|
|
from pydantic import field_validator
|
|
|
|
from invokeai.app.invocations.primitives import StringCollectionOutput
|
|
|
|
from .baseinvocation import BaseInvocation, InputField, InvocationContext, UIComponent, invocation
|
|
|
|
|
|
@invocation(
|
|
"dynamic_prompt",
|
|
title="Dynamic Prompt",
|
|
tags=["prompt", "collection"],
|
|
category="prompt",
|
|
version="1.0.0",
|
|
use_cache=False,
|
|
)
|
|
class DynamicPromptInvocation(BaseInvocation):
|
|
"""Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
|
|
|
|
prompt: str = InputField(
|
|
description="The prompt to parse with dynamicprompts",
|
|
ui_component=UIComponent.Textarea,
|
|
)
|
|
max_prompts: int = InputField(default=1, description="The number of prompts to generate")
|
|
combinatorial: bool = InputField(default=False, description="Whether to use the combinatorial generator")
|
|
|
|
def invoke(self, context: InvocationContext) -> StringCollectionOutput:
|
|
if self.combinatorial:
|
|
generator = CombinatorialPromptGenerator()
|
|
prompts = generator.generate(self.prompt, max_prompts=self.max_prompts)
|
|
else:
|
|
generator = RandomPromptGenerator()
|
|
prompts = generator.generate(self.prompt, num_images=self.max_prompts)
|
|
|
|
return StringCollectionOutput(collection=prompts)
|
|
|
|
|
|
@invocation(
|
|
"prompt_from_file",
|
|
title="Prompts from File",
|
|
tags=["prompt", "file"],
|
|
category="prompt",
|
|
version="1.0.0",
|
|
)
|
|
class PromptsFromFileInvocation(BaseInvocation):
|
|
"""Loads prompts from a text file"""
|
|
|
|
file_path: str = InputField(description="Path to prompt text file")
|
|
pre_prompt: Optional[str] = InputField(
|
|
default=None,
|
|
description="String to prepend to each prompt",
|
|
ui_component=UIComponent.Textarea,
|
|
)
|
|
post_prompt: Optional[str] = InputField(
|
|
default=None,
|
|
description="String to append to each prompt",
|
|
ui_component=UIComponent.Textarea,
|
|
)
|
|
start_line: int = InputField(default=1, ge=1, description="Line in the file to start start from")
|
|
max_prompts: int = InputField(default=1, ge=0, description="Max lines to read from file (0=all)")
|
|
|
|
@field_validator("file_path")
|
|
def file_path_exists(cls, v):
|
|
if not exists(v):
|
|
raise ValueError(FileNotFoundError)
|
|
return v
|
|
|
|
def promptsFromFile(
|
|
self,
|
|
file_path: str,
|
|
pre_prompt: Union[str, None],
|
|
post_prompt: Union[str, None],
|
|
start_line: int,
|
|
max_prompts: int,
|
|
):
|
|
prompts = []
|
|
start_line -= 1
|
|
end_line = start_line + max_prompts
|
|
if max_prompts <= 0:
|
|
end_line = np.iinfo(np.int32).max
|
|
with open(file_path) as f:
|
|
for i, line in enumerate(f):
|
|
if i >= start_line and i < end_line:
|
|
prompts.append((pre_prompt or "") + line.strip() + (post_prompt or ""))
|
|
if i >= end_line:
|
|
break
|
|
return prompts
|
|
|
|
def invoke(self, context: InvocationContext) -> StringCollectionOutput:
|
|
prompts = self.promptsFromFile(
|
|
self.file_path,
|
|
self.pre_prompt,
|
|
self.post_prompt,
|
|
self.start_line,
|
|
self.max_prompts,
|
|
)
|
|
return StringCollectionOutput(collection=prompts)
|