implement changes requested by @kyle0654 for PR #3221

- Add argparse groups to command-line switches.
- Do not let the `link` and `link_node` arguments leak into invocation objects.
- Remove `type` field from `LibraryGraph`

.github/CODEOWNERS

@@ -1,16 +1,16 @@
 # continuous integration
-/.github/workflows/ @mauwii @lstein @blessedcoolant
+/.github/workflows/  @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein @mauwii @tildebyte @blessedcoolant
-/mkdocs.yml @lstein @mauwii @blessedcoolant
+/docs/ @lstein  @tildebyte @blessedcoolant
+/mkdocs.yml @lstein  @blessedcoolant
 
 # nodes
 /invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
-/pyproject.toml @mauwii @lstein @blessedcoolant
-/docker/ @mauwii @lstein @blessedcoolant
+/pyproject.toml  @lstein @blessedcoolant
+/docker/  @lstein @blessedcoolant
 /scripts/ @ebr @lstein
 /installer/ @lstein @ebr
 /invokeai/assets @lstein @ebr
@@ -22,11 +22,11 @@
 /invokeai/backend @blessedcoolant @psychedelicious @lstein
 
 # generation, model management, postprocessing
-/invokeai/backend @keturn @damian0815 @lstein @blessedcoolant @jpphoto
+/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2
 
 # front ends
 /invokeai/frontend/CLI @lstein
-/invokeai/frontend/install @lstein @ebr @mauwii 
+/invokeai/frontend/install @lstein @ebr  
 /invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
 /invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
 /invokeai/frontend/web @psychedelicious @blessedcoolant

.github/stale.yaml

@@ -0,0 +1,19 @@
+# Number of days of inactivity before an issue becomes stale
+daysUntilStale: 28
+# Number of days of inactivity before a stale issue is closed
+daysUntilClose: 14
+# Issues with these labels will never be considered stale
+exemptLabels:
+  - pinned
+  - security
+# Label to use when marking an issue as stale
+staleLabel: stale
+# Comment to post when marking an issue as stale. Set to `false` to disable
+markComment: >
+  This issue has been automatically marked as stale because it has not had
+  recent activity. It will be closed if no further activity occurs. Please
+  update the ticket if this is still a problem on the latest release.
+# Comment to post when closing a stale issue. Set to `false` to disable
+closeComment: >
+  Due to inactivity, this issue has been automatically closed. If this is
+  still a problem on the latest release, please recreate the issue.

.github/workflows/build-container.yml

@@ -18,6 +18,7 @@ on:
 
 permissions:
   contents: write
+  packages: write
 
 jobs:
   docker:

.gitignore

@@ -9,6 +9,8 @@ models/ldm/stable-diffusion-v1/model.ckpt
 configs/models.user.yaml
 config/models.user.yml
 invokeai.init
+.version
+.last_model
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh

README.md

@@ -33,6 +33,8 @@
 
 </div>
 
+_**Note: The UI is not fully functional on `main`. If you need a stable UI based on `main`, use the `pre-nodes` tag while we [migrate to a new backend](https://github.com/invoke-ai/InvokeAI/discussions/3246).**_
+
 InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
 **Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
@@ -84,7 +86,7 @@ installing lots of models.
 
 6. Wait while the installer does its thing. After installing the software,
 the installer will launch a script that lets you configure InvokeAI and
-select a set of starting image generaiton models.
+select a set of starting image generation models.
 
 7. Find the folder that InvokeAI was installed into (it is not the
 same as the unpacked zip file directory!) The default location of this
@@ -148,6 +150,11 @@ not supported.
     pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
+    _For non-GPU systems:_
+    ```terminal
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
+    ``` 
+
     _For Macintoshes, either Intel or M1/M2:_
 
     ```sh

docs/contributing/INVOCATIONS.md

@@ -1,10 +1,18 @@
 # Invocations
 
-Invocations represent a single operation, its inputs, and its outputs. These operations and their outputs can be chained together to generate and modify images.
+Invocations represent a single operation, its inputs, and its outputs. These
+operations and their outputs can be chained together to generate and modify
+images.
 
 ## Creating a new invocation
 
-To create a new invocation, either find the appropriate module file in `/ldm/invoke/app/invocations` to add your invocation to, or create a new one in that folder. All invocations in that folder will be discovered and made available to the CLI and API automatically. Invocations make use of [typing](https://docs.python.org/3/library/typing.html) and [pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration into the CLI and API.
+To create a new invocation, either find the appropriate module file in
+`/ldm/invoke/app/invocations` to add your invocation to, or create a new one in
+that folder. All invocations in that folder will be discovered and made
+available to the CLI and API automatically. Invocations make use of
+[typing](https://docs.python.org/3/library/typing.html) and
+[pydantic](https://pydantic-docs.helpmanual.io/) for validation and integration
+into the CLI and API.
 
 An invocation looks like this:
 
@@ -41,34 +49,54 @@ class UpscaleInvocation(BaseInvocation):
 Each portion is important to implement correctly.
 
 ### Class definition and type
+
 ```py
 class UpscaleInvocation(BaseInvocation):
     """Upscales an image."""
     type: Literal['upscale'] = 'upscale'
 ```
-All invocations must derive from `BaseInvocation`. They should have a docstring that declares what they do in a single, short line. They should also have a `type` with a type hint that's `Literal["command_name"]`, where `command_name` is what the user will type on the CLI or use in the API to create this invocation. The `command_name` must be unique. The `type` must be assigned to the value of the literal in the type hint.
+
+All invocations must derive from `BaseInvocation`. They should have a docstring
+that declares what they do in a single, short line. They should also have a
+`type` with a type hint that's `Literal["command_name"]`, where `command_name`
+is what the user will type on the CLI or use in the API to create this
+invocation. The `command_name` must be unique. The `type` must be assigned to
+the value of the literal in the type hint.
 
 ### Inputs
+
 ```py
     # Inputs
     image: Union[ImageField,None] = Field(description="The input image")
     strength: float               = Field(default=0.75, gt=0, le=1, description="The strength")
     level: Literal[2,4]           = Field(default=2, description="The upscale level")
 ```
-Inputs consist of three parts: a name, a type hint, and a `Field` with default, description, and validation information. For example:
-| Part | Value | Description |
-| ---- | ----- | ----------- |
-| Name | `strength` | This field is referred to as `strength` |
-| Type Hint | `float` | This field must be of type `float` |
-| Field | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
 
-Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this field to be parsed with `None` as a value, which enables linking to previous invocations. All fields should either provide a default value or allow `None` as a value, so that they can be overwritten with a linked output from another invocation.
+Inputs consist of three parts: a name, a type hint, and a `Field` with default,
+description, and validation information. For example:
 
-The special type `ImageField` is also used here. All images are passed as `ImageField`, which protects them from pydantic validation errors (since images only ever come from links).
+| Part      | Value                                                         | Description                                                                                                               |
+| --------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |
+| Name      | `strength`                                                    | This field is referred to as `strength`                                                                                   |
+| Type Hint | `float`                                                       | This field must be of type `float`                                                                                        |
+| Field     | `Field(default=0.75, gt=0, le=1, description="The strength")` | The default value is `0.75`, the value must be in the range (0,1], and help text will show "The strength" for this field. |
 
-Finally, note that for all linking, the `type` of the linked fields must match. If the `name` also matches, then the field can be **automatically linked** to a previous invocation by name and matching.
+Notice that `image` has type `Union[ImageField,None]`. The `Union` allows this
+field to be parsed with `None` as a value, which enables linking to previous
+invocations. All fields should either provide a default value or allow `None` as
+a value, so that they can be overwritten with a linked output from another
+invocation.
+
+The special type `ImageField` is also used here. All images are passed as
+`ImageField`, which protects them from pydantic validation errors (since images
+only ever come from links).
+
+Finally, note that for all linking, the `type` of the linked fields must match.
+If the `name` also matches, then the field can be **automatically linked** to a
+previous invocation by name and matching.
 
 ### Invoke Function
+
 ```py
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(self.image.image_type, self.image.image_name)
@@ -88,13 +116,22 @@ Finally, note that for all linking, the `type` of the linked fields must match.
             image = ImageField(image_type = image_type, image_name = image_name)
         )
 ```
-The `invoke` function is the last portion of an invocation. It is provided an `InvocationContext` which contains services to perform work as well as a `session_id` for use as needed. It should return a class with output values that derives from `BaseInvocationOutput`.
 
-Before being called, the invocation will have all of its fields set from defaults, inputs, and finally links (overriding in that order).
+The `invoke` function is the last portion of an invocation. It is provided an
+`InvocationContext` which contains services to perform work as well as a
+`session_id` for use as needed. It should return a class with output values that
+derives from `BaseInvocationOutput`.
 
-Assume that this invocation may be running simultaneously with other invocations, may be running on another machine, or in other interesting scenarios. If you need functionality, please provide it as a service in the `InvocationServices` class, and make sure it can be overridden.
+Before being called, the invocation will have all of its fields set from
+defaults, inputs, and finally links (overriding in that order).
+
+Assume that this invocation may be running simultaneously with other
+invocations, may be running on another machine, or in other interesting
+scenarios. If you need functionality, please provide it as a service in the
+`InvocationServices` class, and make sure it can be overridden.
 
 ### Outputs
+
 ```py
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
@@ -102,4 +139,64 @@ class ImageOutput(BaseInvocationOutput):
 
     image: ImageField = Field(default=None, description="The output image")
 ```
-Output classes look like an invocation class without the invoke method. Prefer to use an existing output class if available, and prefer to name inputs the same as outputs when possible, to promote automatic invocation linking.
+
+Output classes look like an invocation class without the invoke method. Prefer
+to use an existing output class if available, and prefer to name inputs the same
+as outputs when possible, to promote automatic invocation linking.
+
+## Schema Generation
+
+Invocation, output and related classes are used to generate an OpenAPI schema.
+
+### Required Properties
+
+The schema generation treat all properties with default values as optional. This
+makes sense internally, but when when using these classes via the generated
+schema, we end up with e.g. the `ImageOutput` class having its `image` property
+marked as optional.
+
+We know that this property will always be present, so the additional logic
+needed to always check if the property exists adds a lot of extraneous cruft.
+
+To fix this, we can leverage `pydantic`'s
+[schema customisation](https://docs.pydantic.dev/usage/schema/#schema-customization)
+to mark properties that we know will always be present as required.
+
+Here's that `ImageOutput` class, without the needed schema customisation:
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    type: Literal["image"] = "image"
+    image:      ImageField = Field(default=None, description="The output image")
+```
+
+The generated OpenAPI schema, and all clients/types generated from it, will have
+the `type` and `image` properties marked as optional, even though we know they
+will always have a value by the time we can interact with them via the API.
+
+Here's the same class, but with the schema customisation added:
+
+```python
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    type: Literal["image"] = "image"
+    image:      ImageField = Field(default=None, description="The output image")
+
+    class Config:
+        schema_extra = {
+            'required': [
+                'type',
+                'image',
+            ]
+        }
+```
+
+The resultant schema (and any API client or types generated from it) will now
+have see `type` as string literal `"image"` and `image` as an `ImageField`
+object.
+
+See this `pydantic` issue for discussion on this solution:
+<https://github.com/pydantic/pydantic/discussions/4577>

docs/features/NSFW.md

@@ -32,7 +32,7 @@ turned on and off on the command line using `--nsfw_checker` and
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
 response is stored in the InvokeAI initialization file (usually
-`.invokeai` in your home directory). You can change the default at any
+`invokeai.init` in your home directory). You can change the default at any
 time by opening this file in a text editor and commenting or
 uncommenting the line `--nsfw_checker`.
 

docs/features/PROMPTS.md

@@ -268,7 +268,7 @@ model is so good at inpainting, a good substitute is to use the `clipseg` text
 masking option:
 
 ```bash
-invoke> a fluffy cat eating a hotdot
+invoke> a fluffy cat eating a hotdog
 Outputs:
 [1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
 invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat

docs/installation/050_INSTALLING_MODELS.md

@@ -50,7 +50,7 @@ subset that are currently installed are found in
 |stable-diffusion-1.5|runwayml/stable-diffusion-v1-5|Stable Diffusion version 1.5 diffusers model (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-v1-5 |
 |sd-inpainting-1.5|runwayml/stable-diffusion-inpainting|RunwayML SD 1.5 model optimized for inpainting, diffusers version (4.27 GB)|https://huggingface.co/runwayml/stable-diffusion-inpainting |
 |stable-diffusion-2.1|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.1 diffusers model, trained on 768 pixel images (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
-|sd-inpainting-2.0|stabilityai/stable-diffusion-2-1|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-1 |
+|sd-inpainting-2.0|stabilityai/stable-diffusion-2-inpainting|Stable Diffusion version 2.0 inpainting model (5.21 GB)|https://huggingface.co/stabilityai/stable-diffusion-2-inpainting |
 |analog-diffusion-1.0|wavymulder/Analog-Diffusion|An SD-1.5 model trained on diverse analog photographs (2.13 GB)|https://huggingface.co/wavymulder/Analog-Diffusion |
 |deliberate-1.0|XpucT/Deliberate|Versatile model that produces detailed images up to 768px (4.27 GB)|https://huggingface.co/XpucT/Deliberate |
 |d&d-diffusion-1.0|0xJustin/Dungeons-and-Diffusion|Dungeons & Dragons characters (2.13 GB)|https://huggingface.co/0xJustin/Dungeons-and-Diffusion |

installer/lib/installer.py

@@ -456,7 +456,7 @@ def get_torch_source() -> (Union[str, None],str):
     optional_modules = None
     if OS == "Linux":
         if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.2"
+            url = "https://download.pytorch.org/whl/rocm5.4.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 

invokeai/app/api/dependencies.py

@@ -3,10 +3,17 @@
 import os
 from argparse import Namespace
 
-from ...backend import Globals
+from invokeai.app.services.metadata import PngMetadataService, MetadataServiceBase
+
+from ..services.default_graphs import create_system_graphs
+
+from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+
+from ...backend.globals import Globals, copy_conf_to_globals
+from ..services.config import InvokeAIWebConfig
 from ..services.model_manager_initializer import get_model_manager
 from ..services.restoration_services import RestorationServices
-from ..services.graph import GraphExecutionState
+from ..services.graph import GraphExecutionState, LibraryGraph
 from ..services.image_storage import DiskImageStorage
 from ..services.invocation_queue import MemoryInvocationQueue
 from ..services.invocation_services import InvocationServices
@@ -39,11 +46,7 @@ class ApiDependencies:
 
     @staticmethod
     def initialize(config, event_handler_id: int):
-        Globals.try_patchmatch = config.patchmatch
-        Globals.always_use_cpu = config.always_use_cpu
-        Globals.internet_available = config.internet_available and check_internet()
-        Globals.disable_xformers = not config.xformers
-        Globals.ckpt_convert = config.ckpt_convert
+        copy_conf_to_globals(config)
 
         # TODO: Use a logger
         print(f">> Internet connectivity is {Globals.internet_available}")
@@ -54,7 +57,11 @@ class ApiDependencies:
             os.path.join(os.path.dirname(__file__), "../../../../outputs")
         )
 
-        images = DiskImageStorage(output_folder)
+        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents'))
+
+        metadata = PngMetadataService()
+
+        images = DiskImageStorage(f'{output_folder}/images', metadata_service=metadata)
 
         # TODO: build a file/path manager?
         db_location = os.path.join(output_folder, "invokeai.db")
@@ -62,15 +69,23 @@ class ApiDependencies:
         services = InvocationServices(
             model_manager=get_model_manager(config),
             events=events,
+            latents=latents,
             images=images,
+            metadata=metadata,
             queue=MemoryInvocationQueue(),
+            graph_library=SqliteItemStorage[LibraryGraph](
+                filename=db_location, table_name="graphs"
+            ),
             graph_execution_manager=SqliteItemStorage[GraphExecutionState](
                 filename=db_location, table_name="graph_executions"
             ),
             processor=DefaultInvocationProcessor(),
             restoration=RestorationServices(config),
+            configuration=config,
         )
 
+        create_system_graphs(services.graph_library)
+
         ApiDependencies.invoker = Invoker(services)
 
     @staticmethod

invokeai/app/api/events.py

@@ -45,7 +45,7 @@ class FastAPIEventService(EventServiceBase):
                 )
 
             except Empty:
-                await asyncio.sleep(0.001)
+                await asyncio.sleep(0.1)
                 pass
 
             except asyncio.CancelledError as e:

invokeai/app/api/models/images.py

@@ -0,0 +1,40 @@
+from typing import Optional
+from pydantic import BaseModel, Field
+
+from invokeai.app.models.image import ImageType
+from invokeai.app.services.metadata import InvokeAIMetadata
+
+
+class ImageResponseMetadata(BaseModel):
+    """An image's metadata. Used only in HTTP responses."""
+
+    created: int = Field(description="The creation timestamp of the image")
+    width: int = Field(description="The width of the image in pixels")
+    height: int = Field(description="The height of the image in pixels")
+    invokeai: Optional[InvokeAIMetadata] = Field(
+        description="The image's InvokeAI-specific metadata"
+    )
+
+
+class ImageResponse(BaseModel):
+    """The response type for images"""
+
+    image_type: ImageType = Field(description="The type of the image")
+    image_name: str = Field(description="The name of the image")
+    image_url: str = Field(description="The url of the image")
+    thumbnail_url: str = Field(description="The url of the image's thumbnail")
+    metadata: ImageResponseMetadata = Field(description="The image's metadata")
+
+
+class ProgressImage(BaseModel):
+    """The progress image sent intermittently during processing"""
+
+    width: int = Field(description="The effective width of the image in pixels")
+    height: int = Field(description="The effective height of the image in pixels")
+    dataURL: str = Field(description="The image data as a b64 data URL")
+
+
+class SavedImage(BaseModel):
+    image_name: str = Field(description="The name of the saved image")
+    thumbnail_name: str = Field(description="The name of the saved thumbnail")
+    created: int = Field(description="The created timestamp of the saved image")

invokeai/app/api/routers/images.py

@@ -1,11 +1,20 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
-
+import io
 from datetime import datetime, timezone
+import json
+import os
+from typing import Any
+import uuid
 
-from fastapi import Path, Request, UploadFile
+from fastapi import Body, HTTPException, Path, Query, Request, UploadFile
 from fastapi.responses import FileResponse, Response
 from fastapi.routing import APIRouter
 from PIL import Image
+from invokeai.app.api.models.images import (
+    ImageResponse,
+    ImageResponseMetadata,
+)
+from invokeai.app.services.item_storage import PaginatedResults
 
 from ...services.image_storage import ImageType
 from ..dependencies import ApiDependencies
@@ -17,40 +26,123 @@ images_router = APIRouter(prefix="/v1/images", tags=["images"])
 async def get_image(
     image_type: ImageType = Path(description="The type of image to get"),
     image_name: str = Path(description="The name of the image to get"),
-):
-    """Gets a result"""
-    # TODO: This is not really secure at all. At least make sure only output results are served
-    filename = ApiDependencies.invoker.services.images.get_path(image_type, image_name)
-    return FileResponse(filename)
+) -> FileResponse:
+    """Gets an image"""
+
+    path = ApiDependencies.invoker.services.images.get_path(
+        image_type=image_type, image_name=image_name
+    )
+
+    if ApiDependencies.invoker.services.images.validate_path(path):
+        return FileResponse(path)
+    else:
+        raise HTTPException(status_code=404)
+
+
+@images_router.delete("/{image_type}/{image_name}", operation_id="delete_image")
+async def delete_image(
+    image_type: ImageType = Path(description="The type of image to delete"),
+    image_name: str = Path(description="The name of the image to delete"),
+) -> None:
+    """Deletes an image and its thumbnail"""
+
+    ApiDependencies.invoker.services.images.delete(
+        image_type=image_type, image_name=image_name
+    )
+
+
+@images_router.get(
+    "/{thumbnail_type}/thumbnails/{thumbnail_name}", operation_id="get_thumbnail"
+)
+async def get_thumbnail(
+    thumbnail_type: ImageType = Path(description="The type of thumbnail to get"),
+    thumbnail_name: str = Path(description="The name of the thumbnail to get"),
+) -> FileResponse | Response:
+    """Gets a thumbnail"""
+
+    path = ApiDependencies.invoker.services.images.get_path(
+        image_type=thumbnail_type, image_name=thumbnail_name, is_thumbnail=True
+    )
+
+    if ApiDependencies.invoker.services.images.validate_path(path):
+        return FileResponse(path)
+    else:
+        raise HTTPException(status_code=404)
 
 
 @images_router.post(
     "/uploads/",
     operation_id="upload_image",
     responses={
-        201: {"description": "The image was uploaded successfully"},
-        404: {"description": "Session not found"},
+        201: {
+            "description": "The image was uploaded successfully",
+            "model": ImageResponse,
+        },
+        415: {"description": "Image upload failed"},
     },
+    status_code=201,
 )
-async def upload_image(file: UploadFile, request: Request):
+async def upload_image(
+    file: UploadFile, request: Request, response: Response
+) -> ImageResponse:
     if not file.content_type.startswith("image"):
-        return Response(status_code=415)
+        raise HTTPException(status_code=415, detail="Not an image")
 
     contents = await file.read()
+
     try:
-        im = Image.open(contents)
+        img = Image.open(io.BytesIO(contents))
     except:
         # Error opening the image
-        return Response(status_code=415)
+        raise HTTPException(status_code=415, detail="Failed to read image")
 
-    filename = f"{str(int(datetime.now(timezone.utc).timestamp()))}.png"
-    ApiDependencies.invoker.services.images.save(ImageType.UPLOAD, filename, im)
+    filename = f"{uuid.uuid4()}_{str(int(datetime.now(timezone.utc).timestamp()))}.png"
 
-    return Response(
-        status_code=201,
-        headers={
-            "Location": request.url_for(
-                "get_image", image_type=ImageType.UPLOAD, image_name=filename
-            )
-        },
+    saved_image = ApiDependencies.invoker.services.images.save(
+        ImageType.UPLOAD, filename, img
     )
+
+    invokeai_metadata = ApiDependencies.invoker.services.metadata.get_metadata(img)
+
+    image_url = ApiDependencies.invoker.services.images.get_uri(
+        ImageType.UPLOAD, saved_image.image_name
+    )
+
+    thumbnail_url = ApiDependencies.invoker.services.images.get_uri(
+        ImageType.UPLOAD, saved_image.image_name, True
+    )
+
+    res = ImageResponse(
+        image_type=ImageType.UPLOAD,
+        image_name=saved_image.image_name,
+        image_url=image_url,
+        thumbnail_url=thumbnail_url,
+        metadata=ImageResponseMetadata(
+            created=saved_image.created,
+            width=img.width,
+            height=img.height,
+            invokeai=invokeai_metadata,
+        ),
+    )
+
+    response.status_code = 201
+    response.headers["Location"] = image_url
+
+    return res
+
+
+@images_router.get(
+    "/",
+    operation_id="list_images",
+    responses={200: {"model": PaginatedResults[ImageResponse]}},
+)
+async def list_images(
+    image_type: ImageType = Query(
+        default=ImageType.RESULT, description="The type of images to get"
+    ),
+    page: int = Query(default=0, description="The page of images to get"),
+    per_page: int = Query(default=10, description="The number of images per page"),
+) -> PaginatedResults[ImageResponse]:
+    """Gets a list of images"""
+    result = ApiDependencies.invoker.services.images.list(image_type, page, per_page)
+    return result

invokeai/app/api/routers/models.py

@@ -0,0 +1,247 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
+
+import shutil
+import asyncio
+from typing import Annotated, Any, List, Literal, Optional, Union
+
+from fastapi.routing import APIRouter, HTTPException
+from pydantic import BaseModel, Field, parse_obj_as
+from pathlib import Path
+from ..dependencies import ApiDependencies
+
+models_router = APIRouter(prefix="/v1/models", tags=["models"])
+
+
+class VaeRepo(BaseModel):
+    repo_id: str = Field(description="The repo ID to use for this VAE")
+    path: Optional[str] = Field(description="The path to the VAE")
+    subfolder: Optional[str] = Field(description="The subfolder to use for this VAE")
+
+class ModelInfo(BaseModel):
+    description: Optional[str] = Field(description="A description of the model")
+    
+class CkptModelInfo(ModelInfo):
+    format: Literal['ckpt'] = 'ckpt'
+
+    config: str = Field(description="The path to the model config")
+    weights: str = Field(description="The path to the model weights")
+    vae: str = Field(description="The path to the model VAE")
+    width: Optional[int] = Field(description="The width of the model")
+    height: Optional[int] = Field(description="The height of the model")
+
+class DiffusersModelInfo(ModelInfo):
+    format: Literal['diffusers'] = 'diffusers'
+
+    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
+    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
+    path: Optional[str] = Field(description="The path to the model")
+
+class CreateModelRequest(BaseModel):
+    name: str = Field(description="The name of the model")
+    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
+
+class CreateModelResponse(BaseModel):
+    name: str = Field(description="The name of the new model")
+    info: Union[CkptModelInfo, DiffusersModelInfo] = Field(discriminator="format", description="The model info")
+    status: str = Field(description="The status of the API response")
+
+class ConversionRequest(BaseModel):
+    name: str = Field(description="The name of the new model")
+    info: CkptModelInfo = Field(description="The converted model info")
+    save_location: str = Field(description="The path to save the converted model weights")
+    
+
+class ConvertedModelResponse(BaseModel):
+    name: str = Field(description="The name of the new model")
+    info: DiffusersModelInfo = Field(description="The converted model info")
+
+class ModelsList(BaseModel):
+    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
+
+
+@models_router.get(
+    "/",
+    operation_id="list_models",
+    responses={200: {"model": ModelsList }},
+)
+async def list_models() -> ModelsList:
+    """Gets a list of models"""
+    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
+    models = parse_obj_as(ModelsList, { "models": models_raw })
+    return models
+
+
+@models_router.post(
+    "/",
+    operation_id="update_model",
+    responses={200: {"status": "success"}},
+)
+async def update_model(
+    model_request: CreateModelRequest
+) -> CreateModelResponse:
+    """ Add Model """
+    model_request_info = model_request.info
+    info_dict = model_request_info.dict()
+    model_response = CreateModelResponse(name=model_request.name, info=model_request.info, status="success")
+
+    ApiDependencies.invoker.services.model_manager.add_model(
+        model_name=model_request.name,
+        model_attributes=info_dict,
+        clobber=True,
+    )
+
+    return model_response
+
+
+@models_router.delete(
+    "/{model_name}",
+    operation_id="del_model",
+    responses={
+        204: {
+        "description": "Model deleted successfully"
+        }, 
+        404: {
+        "description": "Model not found"
+        }
+    },
+)
+async def delete_model(model_name: str) -> None:
+    """Delete Model"""
+    model_names = ApiDependencies.invoker.services.model_manager.model_names()
+    model_exists = model_name in model_names
+
+    # check if model exists
+    print(f">> Checking for model {model_name}...")
+           
+    if model_exists:
+        print(f">> Deleting Model: {model_name}")
+        ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
+        print(f">> Model Deleted: {model_name}")
+        raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
+    
+    else:
+        print(f">> Model not found")
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
+    
+
+            # @socketio.on("convertToDiffusers")
+        # def convert_to_diffusers(model_to_convert: dict):
+        #     try:
+        #         if model_info := self.generate.model_manager.model_info(
+        #             model_name=model_to_convert["model_name"]
+        #         ):
+        #             if "weights" in model_info:
+        #                 ckpt_path = Path(model_info["weights"])
+        #                 original_config_file = Path(model_info["config"])
+        #                 model_name = model_to_convert["model_name"]
+        #                 model_description = model_info["description"]
+        #             else:
+        #                 self.socketio.emit(
+        #                     "error", {"message": "Model is not a valid checkpoint file"}
+        #                 )
+        #         else:
+        #             self.socketio.emit(
+        #                 "error", {"message": "Could not retrieve model info."}
+        #             )
+
+        #         if not ckpt_path.is_absolute():
+        #             ckpt_path = Path(Globals.root, ckpt_path)
+
+        #         if original_config_file and not original_config_file.is_absolute():
+        #             original_config_file = Path(Globals.root, original_config_file)
+
+        #         diffusers_path = Path(
+        #             ckpt_path.parent.absolute(), f"{model_name}_diffusers"
+        #         )
+
+        #         if model_to_convert["save_location"] == "root":
+        #             diffusers_path = Path(
+        #                 global_converted_ckpts_dir(), f"{model_name}_diffusers"
+        #             )
+
+        #         if (
+        #             model_to_convert["save_location"] == "custom"
+        #             and model_to_convert["custom_location"] is not None
+        #         ):
+        #             diffusers_path = Path(
+        #                 model_to_convert["custom_location"], f"{model_name}_diffusers"
+        #             )
+
+        #         if diffusers_path.exists():
+        #             shutil.rmtree(diffusers_path)
+
+        #         self.generate.model_manager.convert_and_import(
+        #             ckpt_path,
+        #             diffusers_path,
+        #             model_name=model_name,
+        #             model_description=model_description,
+        #             vae=None,
+        #             original_config_file=original_config_file,
+        #             commit_to_conf=opt.conf,
+        #         )
+
+        #         new_model_list = self.generate.model_manager.list_models()
+        #         socketio.emit(
+        #             "modelConverted",
+        #             {
+        #                 "new_model_name": model_name,
+        #                 "model_list": new_model_list,
+        #                 "update": True,
+        #             },
+        #         )
+        #         print(f">> Model Converted: {model_name}")
+        #     except Exception as e:
+        #         self.handle_exceptions(e)
+
+        # @socketio.on("mergeDiffusersModels")
+        # def merge_diffusers_models(model_merge_info: dict):
+        #     try:
+        #         models_to_merge = model_merge_info["models_to_merge"]
+        #         model_ids_or_paths = [
+        #             self.generate.model_manager.model_name_or_path(x)
+        #             for x in models_to_merge
+        #         ]
+        #         merged_pipe = merge_diffusion_models(
+        #             model_ids_or_paths,
+        #             model_merge_info["alpha"],
+        #             model_merge_info["interp"],
+        #             model_merge_info["force"],
+        #         )
+
+        #         dump_path = global_models_dir() / "merged_models"
+        #         if model_merge_info["model_merge_save_path"] is not None:
+        #             dump_path = Path(model_merge_info["model_merge_save_path"])
+
+        #         os.makedirs(dump_path, exist_ok=True)
+        #         dump_path = dump_path / model_merge_info["merged_model_name"]
+        #         merged_pipe.save_pretrained(dump_path, safe_serialization=1)
+
+        #         merged_model_config = dict(
+        #             model_name=model_merge_info["merged_model_name"],
+        #             description=f'Merge of models {", ".join(models_to_merge)}',
+        #             commit_to_conf=opt.conf,
+        #         )
+
+        #         if vae := self.generate.model_manager.config[models_to_merge[0]].get(
+        #             "vae", None
+        #         ):
+        #             print(f">> Using configured VAE assigned to {models_to_merge[0]}")
+        #             merged_model_config.update(vae=vae)
+
+        #         self.generate.model_manager.import_diffuser_model(
+        #             dump_path, **merged_model_config
+        #         )
+        #         new_model_list = self.generate.model_manager.list_models()
+
+        #         socketio.emit(
+        #             "modelsMerged",
+        #             {
+        #                 "merged_models": models_to_merge,
+        #                 "merged_model_name": model_merge_info["merged_model_name"],
+        #                 "model_list": new_model_list,
+        #                 "update": True,
+        #             },
+        #         )
+        #         print(f">> Models Merged: {models_to_merge}")
+        #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
+        #     except Exception as e:

invokeai/app/api/routers/sessions.py

@@ -2,8 +2,7 @@
 
 from typing import Annotated, List, Optional, Union
 
-from fastapi import Body, Path, Query
-from fastapi.responses import Response
+from fastapi import Body, HTTPException, Path, Query, Response
 from fastapi.routing import APIRouter
 from pydantic.fields import Field
 
@@ -51,7 +50,7 @@ async def list_sessions(
     query: str = Query(default="", description="The query string to search for"),
 ) -> PaginatedResults[GraphExecutionState]:
     """Gets a list of sessions, optionally searching"""
-    if filter == "":
+    if query == "":
         result = ApiDependencies.invoker.services.graph_execution_manager.list(
             page, per_page
         )
@@ -76,7 +75,7 @@ async def get_session(
     """Gets a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
     else:
         return session
 
@@ -99,7 +98,7 @@ async def add_node(
     """Adds a node to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.add_node(node)
@@ -108,9 +107,9 @@ async def add_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session.id
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.put(
@@ -132,7 +131,7 @@ async def update_node(
     """Updates a node in the graph and removes all linked edges"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.update_node(node_path, node)
@@ -141,9 +140,9 @@ async def update_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.delete(
@@ -162,7 +161,7 @@ async def delete_node(
     """Deletes a node in the graph and removes all linked edges"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.delete_node(node_path)
@@ -171,9 +170,9 @@ async def delete_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.post(
@@ -192,7 +191,7 @@ async def add_edge(
     """Adds an edge to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.add_edge(edge)
@@ -201,9 +200,9 @@ async def add_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 # TODO: the edge being in the path here is really ugly, find a better solution
@@ -226,7 +225,7 @@ async def delete_edge(
     """Deletes an edge from the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         edge = Edge(
@@ -239,9 +238,9 @@ async def delete_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.put(
@@ -259,14 +258,14 @@ async def invoke_session(
     all: bool = Query(
         default=False, description="Whether or not to invoke all remaining invocations"
     ),
-) -> None:
+) -> Response:
     """Invokes a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     if session.is_complete():
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
     ApiDependencies.invoker.invoke(session, invoke_all=all)
     return Response(status_code=202)
@@ -281,7 +280,7 @@ async def invoke_session(
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),
-) -> None:
+) -> Response:
     """Invokes a session"""
     ApiDependencies.invoker.cancel(session_id)
     return Response(status_code=202)

invokeai/app/api_app.py

@@ -12,12 +12,11 @@ from fastapi_events.handlers.local import local_handler
 from fastapi_events.middleware import EventHandlerASGIMiddleware
 from pydantic.schema import schema
 
-from ..backend import Args
 from .api.dependencies import ApiDependencies
-from .api.routers import images, sessions
+from .api.routers import images, sessions, models
 from .api.sockets import SocketIO
-from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
+from .services.config import InvokeAIWebConfig
 
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
@@ -33,30 +32,15 @@ app.add_middleware(
     middleware_id=event_handler_id,
 )
 
-# Add CORS
-# TODO: use configuration for this
-origins = []
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
 socket_io = SocketIO(app)
 
-config = {}
-
+web_config = {}
 
 # Add startup event to load dependencies
 @app.on_event("startup")
 async def startup_event():
-    config = Args()
-    config.parse_args()
-
     ApiDependencies.initialize(
-        config=config, event_handler_id=event_handler_id
+        config=web_config, event_handler_id=event_handler_id
     )
 
 
@@ -76,6 +60,8 @@ app.include_router(sessions.session_router, prefix="/api")
 
 app.include_router(images.images_router, prefix="/api")
 
+app.include_router(models.models_router, prefix="/api")
+
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?
@@ -144,12 +130,21 @@ def overridden_redoc():
 
 
 def invoke_api():
+    # parse command-line settings, environment and the init file
+    # (this is a module global)
+    global web_config
+    web_config = InvokeAIWebConfig()
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=web_config.allow_origins,
+        allow_credentials=web_config.allow_credentials,
+        allow_methods=web_config.allow_methods,
+        allow_headers=web_config.allow_headers,
+    )
     # Start our own event loop for eventing usage
-    # TODO: determine if there's a better way to do this
     loop = asyncio.new_event_loop()
-    config = uvicorn.Config(app=app, host="0.0.0.0", port=9090, loop=loop)
+    config = uvicorn.Config(app=app, host=web_config.host, port=web_config.port, loop=loop)
     # Use access_log to turn off logging
-
     server = uvicorn.Server(config)
     loop.run_until_complete(server.serve())
 

invokeai/app/cli/commands.py

@@ -1,88 +1,97 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 
 from abc import ABC, abstractmethod
 import argparse
-from typing import Any, Callable, Iterable, Literal, get_args, get_origin, get_type_hints
-from pydantic import BaseModel, Field
+from typing import Any, Callable, Iterable, Literal, Union, get_args, get_type_hints
+from pydantic import Field
+import networkx as nx
+import matplotlib.pyplot as plt
 
+from ..invocations.baseinvocation import BaseInvocation
+from ..services.config import InvokeAISettings
 from ..invocations.image import ImageField
-from ..services.graph import GraphExecutionState
+from ..services.graph import GraphExecutionState, LibraryGraph, Edge
 from ..services.invoker import Invoker
 
-
 def add_parsers(
     subparsers,
     commands: list[type],
     command_field: str = "type",
     exclude_fields: list[str] = ["id", "type"],
-    add_arguments: Callable[[argparse.ArgumentParser], None]|None = None
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
     ):
     """Adds parsers for each command to the subparsers"""
 
     # Create subparsers for each command
     for command in commands:
-        hints = get_type_hints(command)
-        cmd_name = get_args(hints[command_field])[0]
-        command_parser = subparsers.add_parser(cmd_name, help=command.__doc__)
-
+        name = command.cmd_name()
+        command_parser = subparsers.add_parser(name, help=command.__doc__)
         if add_arguments is not None:
             add_arguments(command_parser)
+        command.add_parser_arguments(command_parser)
 
-        # Convert all fields to arguments
-        fields = command.__fields__ # type: ignore
-        for name, field in fields.items():
-            if name in exclude_fields:
-                continue
-
-            if get_origin(field.type_) == Literal:
-                allowed_values = get_args(field.type_)
-                allowed_types = set()
-                for val in allowed_values:
-                    allowed_types.add(type(val))
-                allowed_types_list = list(allowed_types)
-                field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
-
-                command_parser.add_argument(
-                    f"--{name}",
-                    dest=name,
-                    type=field_type,
-                    default=field.default,
-                    choices=allowed_values,
-                    help=field.field_info.description,
-                )
-            else:
-                command_parser.add_argument(
-                    f"--{name}",
-                    dest=name,
-                    type=field.type_,
-                    default=field.default,
-                    help=field.field_info.description,
-                )
+def add_graph_parsers(
+    subparsers,
+    graphs: list[LibraryGraph],
+    add_arguments: Union[Callable[[argparse.ArgumentParser], None], None] = None
+):
+    for graph in graphs:
+        command_parser = subparsers.add_parser(graph.name, help=graph.description)
+        
+        if add_arguments is not None:
+            graph.add_parser_arguments(command_parser)
 
+        # Add arguments for inputs
+        for exposed_input in graph.exposed_inputs:
+            node = graph.graph.get_node(exposed_input.node_path)
+            field = node.__fields__[exposed_input.field]
+            default_override = getattr(node, exposed_input.field)
+            graph.add_field_argument(command_parser, exposed_input.alias, field, default_override)
 
 class CliContext:
     invoker: Invoker
     session: GraphExecutionState
     parser: argparse.ArgumentParser
     defaults: dict[str, Any]
+    graph_nodes: dict[str, str]
+    nodes_added: list[str]
 
     def __init__(self, invoker: Invoker, session: GraphExecutionState, parser: argparse.ArgumentParser):
         self.invoker = invoker
         self.session = session
         self.parser = parser
         self.defaults = dict()
+        self.graph_nodes = dict()
+        self.nodes_added = list()
 
     def get_session(self):
         self.session = self.invoker.services.graph_execution_manager.get(self.session.id)
         return self.session
 
+    def reset(self):
+        self.session = self.invoker.create_execution_state()
+        self.graph_nodes = dict()
+        self.nodes_added = list()
+        # Leave defaults unchanged
+
+    def add_node(self, node: BaseInvocation):
+        self.get_session()
+        self.session.graph.add_node(node)
+        self.nodes_added.append(node.id)
+        self.invoker.services.graph_execution_manager.set(self.session)
+
+    def add_edge(self, edge: Edge):
+        self.get_session()
+        self.session.add_edge(edge)
+        self.invoker.services.graph_execution_manager.set(self.session)
+
 
 class ExitCli(Exception):
     """Exception to exit the CLI"""
     pass
 
 
-class BaseCommand(ABC, BaseModel):
+class BaseCommand(ABC, InvokeAISettings):
     """A CLI command"""
 
     # All commands must include a type name like this:
@@ -200,3 +209,39 @@ class SetDefaultCommand(BaseCommand):
                 del context.defaults[self.field]
         else:
             context.defaults[self.field] = self.value
+
+
+class DrawGraphCommand(BaseCommand):
+    """Debugs a graph"""
+    type: Literal['draw_graph'] = 'draw_graph'
+
+    def run(self, context: CliContext) -> None:
+        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
+        nxgraph = session.graph.nx_graph_flat()
+
+        # Draw the networkx graph
+        plt.figure(figsize=(20, 20))
+        pos = nx.spectral_layout(nxgraph)
+        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
+        nx.draw_networkx_edges(nxgraph, pos, width=2)
+        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
+        plt.axis("off")
+        plt.show()
+
+
+class DrawExecutionGraphCommand(BaseCommand):
+    """Debugs an execution graph"""
+    type: Literal['draw_xgraph'] = 'draw_xgraph'
+
+    def run(self, context: CliContext) -> None:
+        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
+        nxgraph = session.execution_graph.nx_graph_flat()
+
+        # Draw the networkx graph
+        plt.figure(figsize=(20, 20))
+        pos = nx.spectral_layout(nxgraph)
+        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
+        nx.draw_networkx_edges(nxgraph, pos, width=2)
+        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
+        plt.axis("off")
+        plt.show()

invokeai/app/cli/completer.py

@@ -10,9 +10,10 @@ import shlex
 from pathlib import Path
 from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
 
-from ...backend import ModelManager, Globals
+from ...backend import ModelManager
 from ..invocations.baseinvocation import BaseInvocation
 from .commands import BaseCommand
+from ..services.invocation_services import InvocationServices
 
 # singleton object, class variable
 completer = None
@@ -130,13 +131,13 @@ class Completer(object):
             readline.redisplay()
             self.linebuffer = None
     
-def set_autocompleter(model_manager: ModelManager) -> Completer:
+def set_autocompleter(services: InvocationServices) -> Completer:
     global completer
     
     if completer:
         return completer
     
-    completer = Completer(model_manager)
+    completer = Completer(services.model_manager)
 
     readline.set_completer(completer.complete)
     # pyreadline3 does not have a set_auto_history() method
@@ -152,7 +153,7 @@ def set_autocompleter(model_manager: ModelManager) -> Completer:
     readline.parse_and_bind("set skip-completed-text on")
     readline.parse_and_bind("set show-all-if-ambiguous on")
 
-    histfile = Path(Globals.root, ".invoke_history")
+    histfile = Path(services.configuration.root_dir / ".invoke_history")
     try:
         readline.read_history_file(histfile)
         readline.set_history_length(1000)

invokeai/app/cli_app.py

@@ -2,6 +2,7 @@
 
 import argparse
 import os
+import re
 import shlex
 import time
 from typing import (
@@ -12,22 +13,29 @@ from typing import (
 from pydantic import BaseModel
 from pydantic.fields import Field
 
-from ..backend import Args
-from .cli.commands import BaseCommand, CliContext, ExitCli, add_parsers, get_graph_execution_history
+from invokeai.app.services.metadata import PngMetadataService
+
+from .services.default_graphs import create_system_graphs
+
+from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
+
+from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, get_graph_execution_history
 from .cli.completer import set_autocompleter
 from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
 from .services.events import EventServiceBase
 from .services.model_manager_initializer import get_model_manager
 from .services.restoration_services import RestorationServices
-from .services.graph import Edge, EdgeConnection, GraphExecutionState
+from .services.graph import Edge, EdgeConnection, ExposedNodeInput, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
+from .services.default_graphs import default_text_to_image_graph_id
 from .services.image_storage import DiskImageStorage
 from .services.invocation_queue import MemoryInvocationQueue
 from .services.invocation_services import InvocationServices
 from .services.invoker import Invoker
 from .services.processor import DefaultInvocationProcessor
 from .services.sqlite import SqliteItemStorage
-
+from .services.config import InvokeAIAppConfig
+from ..backend.globals import copy_conf_to_globals   # temporary workaround for code depending on Globals
 
 class CliCommand(BaseModel):
     command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
@@ -44,7 +52,7 @@ def add_invocation_args(command_parser):
         "-l",
         action="append",
         nargs=3,
-        help="A link in the format 'dest_field source_node source_field'. source_node can be relative to history (e.g. -1)",
+        help="A link in the format 'source_node source_field dest_field'. source_node can be relative to history (e.g. -1)",
     )
 
     command_parser.add_argument(
@@ -55,7 +63,7 @@ def add_invocation_args(command_parser):
     )
 
 
-def get_command_parser() -> argparse.ArgumentParser:
+def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
     # Create invocation parser
     parser = argparse.ArgumentParser()
 
@@ -73,20 +81,72 @@ def get_command_parser() -> argparse.ArgumentParser:
     commands = BaseCommand.get_all_subclasses()
     add_parsers(subparsers, commands, exclude_fields=["type"])
 
+    # Create subparsers for exposed CLI graphs
+    # TODO: add a way to identify these graphs
+    text_to_image = services.graph_library.get(default_text_to_image_graph_id)
+    add_graph_parsers(subparsers, [text_to_image], add_arguments=add_invocation_args)
+
     return parser
 
 
+class NodeField():
+    alias: str
+    node_path: str
+    field: str
+    field_type: type
+
+    def __init__(self, alias: str, node_path: str, field: str, field_type: type):
+        self.alias = alias
+        self.node_path = node_path
+        self.field = field
+        self.field_type = field_type
+
+
+def fields_from_type_hints(hints: dict[str, type], node_path: str) -> dict[str,NodeField]:
+    return {k:NodeField(alias=k, node_path=node_path, field=k, field_type=v) for k, v in hints.items()}
+
+
+def get_node_input_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
+    """Gets the node field for the specified field alias"""
+    exposed_input = next(e for e in graph.exposed_inputs if e.alias == field_alias)
+    node_type = type(graph.graph.get_node(exposed_input.node_path))
+    return NodeField(alias=exposed_input.alias, node_path=f'{node_id}.{exposed_input.node_path}', field=exposed_input.field, field_type=get_type_hints(node_type)[exposed_input.field])
+
+
+def get_node_output_field(graph: LibraryGraph, field_alias: str, node_id: str) -> NodeField:
+    """Gets the node field for the specified field alias"""
+    exposed_output = next(e for e in graph.exposed_outputs if e.alias == field_alias)
+    node_type = type(graph.graph.get_node(exposed_output.node_path))
+    node_output_type = node_type.get_output_type()
+    return NodeField(alias=exposed_output.alias, node_path=f'{node_id}.{exposed_output.node_path}', field=exposed_output.field, field_type=get_type_hints(node_output_type)[exposed_output.field])
+
+
+def get_node_inputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
+    """Gets the inputs for the specified invocation from the context"""
+    node_type = type(invocation)
+    if node_type is not GraphInvocation:
+        return fields_from_type_hints(get_type_hints(node_type), invocation.id)
+    else:
+        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
+        return {e.alias: get_node_input_field(graph, e.alias, invocation.id) for e in graph.exposed_inputs}
+
+
+def get_node_outputs(invocation: BaseInvocation, context: CliContext) -> dict[str, NodeField]:
+    """Gets the outputs for the specified invocation from the context"""
+    node_type = type(invocation)
+    if node_type is not GraphInvocation:
+        return fields_from_type_hints(get_type_hints(node_type.get_output_type()), invocation.id)
+    else:
+        graph: LibraryGraph = context.invoker.services.graph_library.get(context.graph_nodes[invocation.id])
+        return {e.alias: get_node_output_field(graph, e.alias, invocation.id) for e in graph.exposed_outputs}
+
+
 def generate_matching_edges(
-    a: BaseInvocation, b: BaseInvocation
+    a: BaseInvocation, b: BaseInvocation, context: CliContext
 ) -> list[Edge]:
     """Generates all possible edges between two invocations"""
-    atype = type(a)
-    btype = type(b)
-
-    aoutputtype = atype.get_output_type()
-
-    afields = get_type_hints(aoutputtype)
-    bfields = get_type_hints(btype)
+    afields = get_node_outputs(a, context)
+    bfields = get_node_inputs(b, context)
 
     matching_fields = set(afields.keys()).intersection(bfields.keys())
 
@@ -94,12 +154,15 @@ def generate_matching_edges(
     invalid_fields = set(["type", "id"])
     matching_fields = matching_fields.difference(invalid_fields)
 
+    # Validate types
+    matching_fields = [f for f in matching_fields if are_connection_types_compatible(afields[f].field_type, bfields[f].field_type)]
+
     edges = [
         Edge(
-            source=EdgeConnection(node_id=a.id, field=field),
-            destination=EdgeConnection(node_id=b.id, field=field)
+            source=EdgeConnection(node_id=afields[alias].node_path, field=afields[alias].field),
+            destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field)
         )
-        for field in matching_fields
+        for alias in matching_fields
     ]
     return edges
 
@@ -127,21 +190,19 @@ def invoke_all(context: CliContext):
 
 
 def invoke_cli():
-    config = Args()
-    config.parse_args()
+    config = InvokeAIAppConfig()
+    copy_conf_to_globals(config)   # temporary workaround
     model_manager = get_model_manager(config)
 
     # This initializes the autocompleter and returns it.
     # Currently nothing is done with the returned Completer
     # object, but the object can be used to change autocompletion
     # behavior on the fly, if desired.
-    completer = set_autocompleter(model_manager)
 
     events = EventServiceBase()
 
-    output_folder = os.path.abspath(
-        os.path.join(os.path.dirname(__file__), "../../../outputs")
-    )
+    output_folder = config.output_path
+    metadata = PngMetadataService()
 
     # TODO: build a file/path manager?
     db_location = os.path.join(output_folder, "invokeai.db")
@@ -149,24 +210,37 @@ def invoke_cli():
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
-        images=DiskImageStorage(output_folder),
+        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
+        images=DiskImageStorage(f'{output_folder}/images', metadata_service=metadata),
+        metadata=metadata,
         queue=MemoryInvocationQueue(),
+        graph_library=SqliteItemStorage[LibraryGraph](
+            filename=db_location, table_name="graphs"
+        ),
         graph_execution_manager=SqliteItemStorage[GraphExecutionState](
             filename=db_location, table_name="graph_executions"
         ),
         processor=DefaultInvocationProcessor(),
         restoration=RestorationServices(config),
+        configuration=config,
     )
 
+    system_graphs = create_system_graphs(services.graph_library)
+    system_graph_names = set([g.name for g in system_graphs])
+
     invoker = Invoker(services)
     session: GraphExecutionState = invoker.create_execution_state()
-    parser = get_command_parser()
+    parser = get_command_parser(services)
+
+    re_negid = re.compile('^-[0-9]+$')
 
     # Uncomment to print out previous sessions at startup
     # print(services.session_manager.list())
 
     context = CliContext(invoker, session, parser)
 
+    set_autocompleter(services)
+
     while True:
         try:
             cmd_input = input("invoke> ")
@@ -176,11 +250,12 @@ def invoke_cli():
 
         try:
             # Refresh the state of the session
-            history = list(get_graph_execution_history(context.session))
+            #history = list(get_graph_execution_history(context.session))
+            history = list(reversed(context.nodes_added))
 
             # Split the command for piping
             cmds = cmd_input.split("|")
-            start_id = len(history)
+            start_id = len(context.nodes_added)
             current_id = start_id
             new_invocations = list()
             for cmd in cmds:
@@ -196,8 +271,33 @@ def invoke_cli():
                         args[field_name] = field_default
 
                 # Parse invocation
-                args["id"] = current_id
-                command = CliCommand(command=args)
+                command: CliCommand = None # type:ignore
+                system_graph: LibraryGraph|None = None
+                if args['type'] in system_graph_names:
+                    system_graph = next(filter(lambda g: g.name == args['type'], system_graphs))
+                    invocation = GraphInvocation(graph=system_graph.graph, id=str(current_id))
+                    for exposed_input in system_graph.exposed_inputs:
+                        if exposed_input.alias in args:
+                            node = invocation.graph.get_node(exposed_input.node_path)
+                            field = exposed_input.field
+                            setattr(node, field, args[exposed_input.alias])
+                    command = CliCommand(command = invocation)
+                    context.graph_nodes[invocation.id] = system_graph.id
+                else:
+                    if "id" in args:
+                        args["id"] = args["id"] or current_id
+                        
+                    # remove extraneous fields from initialization
+                    exclude = ['link','link_node']
+                    command_args = dict()
+                    for key,value in args.items():
+                        if key not in exclude:
+                            command_args[key]=value
+                            
+                    command = CliCommand(command=command_args)
+
+                if command is None:
+                    continue
 
                 # Run any CLI commands immediately
                 if isinstance(command.command, BaseCommand):
@@ -208,6 +308,7 @@ def invoke_cli():
                     command.command.run(context)
                     continue
 
+                # TODO: handle linking with library graphs
                 # Pipe previous command output (if there was a previous command)
                 edges: list[Edge] = list()
                 if len(history) > 0 or current_id != start_id:
@@ -220,16 +321,20 @@ def invoke_cli():
                         else context.session.graph.get_node(from_id)
                     )
                     matching_edges = generate_matching_edges(
-                        from_node, command.command
+                        from_node, command.command, context
                     )
                     edges.extend(matching_edges)
 
                 # Parse provided links
                 if "link_node" in args and args["link_node"]:
                     for link in args["link_node"]:
-                        link_node = context.session.graph.get_node(link)
+                        node_id = link
+                        if re_negid.match(node_id):
+                            node_id = str(current_id + int(node_id))
+
+                        link_node = context.session.graph.get_node(node_id)
                         matching_edges = generate_matching_edges(
-                            link_node, command.command
+                            link_node, command.command, context
                         )
                         matching_destinations = [e.destination for e in matching_edges]
                         edges = [e for e in edges if e.destination not in matching_destinations]
@@ -237,13 +342,20 @@ def invoke_cli():
 
                 if "link" in args and args["link"]:
                     for link in args["link"]:
-                        edges = [e for e in edges if e.destination.node_id != command.command.id and e.destination.field != link[2]]
+                        edges = [e for e in edges if e.destination.node_id != command.command.id or e.destination.field != link[2]]
+
+                        node_id = link[0]
+                        if re_negid.match(node_id):
+                            node_id = str(current_id + int(node_id))
+
+                        # TODO: handle missing input/output
+                        node_output = get_node_outputs(context.session.graph.get_node(node_id), context)[link[1]]
+                        node_input = get_node_inputs(command.command, context)[link[2]]
+
                         edges.append(
                             Edge(
-                                source=EdgeConnection(node_id=link[1], field=link[0]),
-                                destination=EdgeConnection(
-                                    node_id=command.command.id, field=link[2]
-                                )
+                                source=EdgeConnection(node_id=node_output.node_path, field=node_output.field),
+                                destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field)
                             )
                         )
 
@@ -252,10 +364,10 @@ def invoke_cli():
                 current_id = current_id + 1
 
                 # Add the node to the session
-                context.session.add_node(command.command)
+                context.add_node(command.command)
                 for edge in edges:
                     print(edge)
-                    context.session.add_edge(edge)
+                    context.add_edge(edge)
 
             # Execute all remaining nodes
             invoke_all(context)
@@ -267,7 +379,7 @@ def invoke_cli():
         except SessionError:
             # Start a new session
             print("Session error: creating a new session")
-            context.session = context.invoker.create_execution_state()
+            context.reset()
 
         except ExitCli:
             break

invokeai/app/invocations/baseinvocation.py

@@ -2,12 +2,12 @@
 
 from abc import ABC, abstractmethod
 from inspect import signature
-from typing import get_args, get_type_hints
+from typing import get_args, get_type_hints, Dict, List, Literal, TypedDict
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, BaseSettings, Field
 
 from ..services.invocation_services import InvocationServices
-
+from ..services.config import InvokeAISettings
 
 class InvocationContext:
     services: InvocationServices
@@ -36,7 +36,7 @@ class BaseInvocationOutput(BaseModel):
         return tuple(subclasses)
 
 
-class BaseInvocation(ABC, BaseModel):
+class BaseInvocation(ABC, InvokeAISettings):
     """A node to process inputs and produce outputs.
     May use dependency injection in __init__ to receive providers.
     """
@@ -76,3 +76,56 @@ class BaseInvocation(ABC, BaseModel):
     #fmt: off
     id: str = Field(description="The id of this node. Must be unique among all nodes.")
     #fmt: on
+
+
+# TODO: figure out a better way to provide these hints
+# TODO: when we can upgrade to python 3.11, we can use the`NotRequired` type instead of `total=False`
+class UIConfig(TypedDict, total=False):
+    type_hints: Dict[
+        str,
+        Literal[
+            "integer",
+            "float",
+            "boolean",
+            "string",
+            "enum",
+            "image",
+            "latents",
+            "model",
+        ],
+    ]
+    tags: List[str]
+    title: str
+
+class CustomisedSchemaExtra(TypedDict):
+    ui: UIConfig
+
+
+class InvocationConfig(BaseSettings.Config):
+    """Customizes pydantic's BaseSettings.Config class for use by Invocations.
+
+    Provide `schema_extra` a `ui` dict to add hints for generated UIs.
+
+    `tags`
+    - A list of strings, used to categorise invocations.
+
+    `type_hints`
+    - A dict of field types which override the types in the invocation definition.
+    - Each key should be the name of one of the invocation's fields.
+    - Each value should be one of the valid types:
+      - `integer`, `float`, `boolean`, `string`, `enum`, `image`, `latents`, `model`
+
+    ```python
+    class Config(InvocationConfig):
+      schema_extra = {
+          "ui": {
+              "tags": ["stable-diffusion", "image"],
+              "type_hints": {
+                  "initial_image": "image",
+              },
+          },
+      }
+    ```
+    """
+
+    schema_extra: CustomisedSchemaExtra

invokeai/app/invocations/collections.py

@@ -0,0 +1,64 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal, Optional
+
+import numpy as np
+import numpy.random
+from pydantic import Field
+
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationConfig,
+    InvocationContext,
+    BaseInvocationOutput,
+)
+
+
+class IntCollectionOutput(BaseInvocationOutput):
+    """A collection of integers"""
+
+    type: Literal["int_collection"] = "int_collection"
+
+    # Outputs
+    collection: list[int] = Field(default=[], description="The int collection")
+
+
+class RangeInvocation(BaseInvocation):
+    """Creates a range"""
+
+    type: Literal["range"] = "range"
+
+    # Inputs
+    start: int = Field(default=0, description="The start of the range")
+    stop: int = Field(default=10, description="The stop of the range")
+    step: int = Field(default=1, description="The step of the range")
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        return IntCollectionOutput(
+            collection=list(range(self.start, self.stop, self.step))
+        )
+
+
+class RandomRangeInvocation(BaseInvocation):
+    """Creates a collection of random numbers"""
+
+    type: Literal["random_range"] = "random_range"
+
+    # Inputs
+    low: int = Field(default=0, description="The inclusive low value")
+    high: int = Field(
+        default=np.iinfo(np.int32).max, description="The exclusive high value"
+    )
+    size: int = Field(default=1, description="The number of values to generate")
+    seed: Optional[int] = Field(
+        ge=0,
+        le=np.iinfo(np.int32).max,
+        description="The seed for the RNG",
+        default_factory=lambda: numpy.random.randint(0, np.iinfo(np.int32).max),
+    )
+
+    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
+        rng = np.random.default_rng(self.seed)
+        return IntCollectionOutput(
+            collection=list(rng.integers(low=self.low, high=self.high, size=self.size))
+        )

invokeai/app/invocations/cv.py

@@ -5,14 +5,26 @@ from typing import Literal
 import cv2 as cv
 import numpy
 from PIL import Image, ImageOps
-from pydantic import Field
+from pydantic import BaseModel, Field
 
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput
+from invokeai.app.models.image import ImageField, ImageType
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
 
 
-class CvInpaintInvocation(BaseInvocation):
+class CvInvocationConfig(BaseModel):
+    """Helper class to provide all OpenCV invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["cv", "image"],
+            },
+        }
+
+
+class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
     """Simple inpaint using opencv."""
     #fmt: off
     type: Literal["cv_inpaint"] = "cv_inpaint"
@@ -44,7 +56,14 @@ class CvInpaintInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, image_inpainted)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
+        
+        context.services.images.save(image_type, image_name, image_inpainted, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image_inpainted,
+        )

invokeai/app/invocations/generate.py

@@ -6,21 +6,36 @@ from typing import Literal, Optional, Union
 import numpy as np
 from torch import Tensor
 
-from pydantic import Field
+from pydantic import BaseModel, Field
 
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput
+from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.invocations.util.choose_model import choose_model
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
 from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
 from ...backend.stable_diffusion import PipelineIntermediateState
-from ..util.util import diffusers_step_callback_adapter, CanceledException
+from ..util.step_callback import stable_diffusion_step_callback
+
+SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
+
+
+class SDImageInvocation(BaseModel):
+    """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["stable-diffusion", "image"],
+                "type_hints": {
+                    "model": "model",
+                },
+            },
+        }
 
-SAMPLER_NAME_VALUES = Literal[
-    tuple(InvokeAIGenerator.schedulers())
-]
 
 # Text to image
-class TextToImageInvocation(BaseInvocation):
+class TextToImageInvocation(BaseInvocation, SDImageInvocation):
     """Generates an image using text2img."""
 
     type: Literal["txt2img"] = "txt2img"
@@ -34,7 +49,7 @@ class TextToImageInvocation(BaseInvocation):
     width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
     height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
     cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    sampler_name: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The sampler to use" )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
     seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
     model:       str = Field(default="", description="The model to use (currently ignored)")
     progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
@@ -42,35 +57,31 @@ class TextToImageInvocation(BaseInvocation):
 
     # TODO: pass this an emitter method or something? or a session for dispatching?
     def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
     ) -> None:
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-        
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # def step_callback(state: PipelineIntermediateState):
-        #     if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-        #         raise CanceledException
-        #     self.dispatch_progress(context, state.latents, state.step)
-
         # Handle invalid model parameter
-        # TODO: figure out if this can be done via a validator that uses the model_cache
-        # TODO: How to get the default model name now?
-        #       (right now uses whatever current model is set in model manager)
-        model= context.services.model_manager.get_model()
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
         outputs = Txt2Img(model).generate(
             prompt=self.prompt,
-            step_callback=partial(self.dispatch_progress, context),
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
             **self.dict(
                 exclude={"prompt"}
             ),  # Shorthand for passing all of the parameters above manually
@@ -86,9 +97,18 @@ class TextToImageInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, generate_output.image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(
+            image_type, image_name, generate_output.image, metadata
+        )
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=generate_output.image,
         )
 
 
@@ -108,20 +128,17 @@ class ImageToImageInvocation(TextToImageInvocation):
     )
 
     def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
@@ -134,18 +151,23 @@ class ImageToImageInvocation(TextToImageInvocation):
         mask = None
 
         # Handle invalid model parameter
-        # TODO: figure out if this can be done via a validator that uses the model_cache
-        # TODO: How to get the default model name now?
-        model = context.services.model_manager.get_model()
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
         outputs = Img2Img(model).generate(
-                prompt=self.prompt,
-                init_image=image,
-                init_mask=mask,
-                step_callback=partial(self.dispatch_progress, context),
-                **self.dict(
-                    exclude={"prompt", "image", "mask"}
-                ),  # Shorthand for passing all of the parameters above manually
-            )
+            prompt=self.prompt,
+            init_image=image,
+            init_mask=mask,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt", "image", "mask"}
+            ),  # Shorthand for passing all of the parameters above manually
+        )
 
         # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
         # each time it is called. We only need the first one.
@@ -160,11 +182,19 @@ class ImageToImageInvocation(TextToImageInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, result_image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
+        context.services.images.save(image_type, image_name, result_image, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=result_image,
+        )
+
+
 class InpaintInvocation(ImageToImageInvocation):
     """Generates an image using inpaint."""
 
@@ -180,20 +210,17 @@ class InpaintInvocation(ImageToImageInvocation):
     )
 
     def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
+        self,
+        context: InvocationContext,
+        source_node_id: str,
+        intermediate_state: PipelineIntermediateState,
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
@@ -210,18 +237,23 @@ class InpaintInvocation(ImageToImageInvocation):
         )
 
         # Handle invalid model parameter
-        # TODO: figure out if this can be done via a validator that uses the model_cache
-        # TODO: How to get the default model name now?
-        model = context.services.model_manager.get_model()
+        model = choose_model(context.services.model_manager, self.model)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(
+            context.graph_execution_state_id
+        )
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
         outputs = Inpaint(model).generate(
-                prompt=self.prompt,
-                init_img=image,
-                init_mask=mask,
-                step_callback=partial(self.dispatch_progress, context),
-                **self.dict(
-                    exclude={"prompt", "image", "mask"}
-                ),  # Shorthand for passing all of the parameters above manually
-            )
+            prompt=self.prompt,
+            init_img=image,
+            init_mask=mask,
+            step_callback=partial(self.dispatch_progress, context, source_node_id),
+            **self.dict(
+                exclude={"prompt", "image", "mask"}
+            ),  # Shorthand for passing all of the parameters above manually
+        )
 
         # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
         # each time it is called. We only need the first one.
@@ -236,7 +268,14 @@ class InpaintInvocation(ImageToImageInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, result_image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, result_image, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=result_image,
         )

invokeai/app/invocations/image.py

@@ -1,70 +1,97 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from datetime import datetime, timezone
 from typing import Literal, Optional
 
 import numpy
 from PIL import Image, ImageFilter, ImageOps
 from pydantic import BaseModel, Field
 
-from ..services.image_storage import ImageType
-from ..services.invocation_services import InvocationServices
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
+from ..models.image import ImageField, ImageType
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
 
 
-class ImageField(BaseModel):
-    """An image field used for passing image objects between invocations"""
+class PILInvocationConfig(BaseModel):
+    """Helper class to provide all PIL invocations with additional config"""
 
-    image_type: str = Field(
-        default=ImageType.RESULT, description="The type of the image"
-    )
-    image_name: Optional[str] = Field(default=None, description="The name of the image")
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["PIL", "image"],
+            },
+        }
 
 
 class ImageOutput(BaseInvocationOutput):
     """Base class for invocations that output an image"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["image"] = "image"
     image:      ImageField = Field(default=None, description="The output image")
-    #fmt: on
+    width:   Optional[int] = Field(default=None, description="The width of the image in pixels")
+    height:  Optional[int] = Field(default=None, description="The height of the image in pixels")
+    # fmt: on
 
     class Config:
         schema_extra = {
-            'required': [
-                'type',
-                'image',
-            ]
+            "required": ["type", "image", "width", "height", "mode"]
         }
 
+
+def build_image_output(
+    image_type: ImageType, image_name: str, image: Image.Image
+) -> ImageOutput:
+    """Builds an ImageOutput and its ImageField"""
+    image_field = ImageField(
+        image_name=image_name,
+        image_type=image_type,
+    )
+    return ImageOutput(
+        image=image_field,
+        width=image.width,
+        height=image.height,
+        mode=image.mode,
+    )
+
+
 class MaskOutput(BaseInvocationOutput):
     """Base class for invocations that output a mask"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["mask"] = "mask"
     mask:      ImageField = Field(default=None, description="The output mask")
-    #fmt: on
+    # fmt: on
 
     class Config:
         schema_extra = {
-            'required': [
-                'type',
-                'mask',
+            "required": [
+                "type",
+                "mask",
             ]
         }
 
-# TODO: this isn't really necessary anymore
+
 class LoadImageInvocation(BaseInvocation):
-    """Load an image from a filename and provide it as output."""
-    #fmt: off
+    """Load an image and provide it as output."""
+
+    # fmt: off
     type: Literal["load_image"] = "load_image"
 
     # Inputs
     image_type: ImageType = Field(description="The type of the image")
     image_name:       str = Field(description="The name of the image")
-    #fmt: on
-
+    # fmt: on
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        return ImageOutput(
-            image=ImageField(image_type=self.image_type, image_name=self.image_name)
+        image = context.services.images.get(self.image_type, self.image_name)
+
+        return build_image_output(
+            image_type=self.image_type,
+            image_name=self.image_name,
+            image=image,
         )
 
 
@@ -85,16 +112,17 @@ class ShowImageInvocation(BaseInvocation):
 
         # TODO: how to handle failure?
 
-        return ImageOutput(
-            image=ImageField(
-                image_type=self.image.image_type, image_name=self.image.image_name
-            )
+        return build_image_output(
+            image_type=self.image.image_type,
+            image_name=self.image.image_name,
+            image=image,
         )
 
 
-class CropImageInvocation(BaseInvocation):
+class CropImageInvocation(BaseInvocation, PILInvocationConfig):
     """Crops an image to a specified box. The box can be outside of the image."""
-    #fmt: off
+
+    # fmt: off
     type: Literal["crop"] = "crop"
 
     # Inputs
@@ -103,7 +131,7 @@ class CropImageInvocation(BaseInvocation):
     y:      int = Field(default=0, description="The top y coordinate of the crop rectangle")
     width:  int = Field(default=512, gt=0, description="The width of the crop rectangle")
     height: int = Field(default=512, gt=0, description="The height of the crop rectangle")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
@@ -119,15 +147,23 @@ class CropImageInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, image_crop)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+        
+        context.services.images.save(image_type, image_name, image_crop, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image_crop,
         )
 
 
-class PasteImageInvocation(BaseInvocation):
+class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
     """Pastes an image into another image."""
-    #fmt: off
+
+    # fmt: off
     type: Literal["paste"] = "paste"
 
     # Inputs
@@ -136,7 +172,7 @@ class PasteImageInvocation(BaseInvocation):
     mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
     x:                     int = Field(default=0, description="The left x coordinate at which to paste the image")
     y:                     int = Field(default=0, description="The top y coordinate at which to paste the image")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         base_image = context.services.images.get(
@@ -149,7 +185,7 @@ class PasteImageInvocation(BaseInvocation):
             None
             if self.mask is None
             else ImageOps.invert(
-                services.images.get(self.mask.image_type, self.mask.image_name)
+                context.services.images.get(self.mask.image_type, self.mask.image_name)
             )
         )
         # TODO: probably shouldn't invert mask here... should user be required to do it?
@@ -169,21 +205,29 @@ class PasteImageInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, new_image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+        
+        context.services.images.save(image_type, image_name, new_image, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=new_image,
         )
 
 
-class MaskFromAlphaInvocation(BaseInvocation):
+class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
     """Extracts the alpha channel of an image as a mask."""
-    #fmt: off
+
+    # fmt: off
     type: Literal["tomask"] = "tomask"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to create the mask from")
     invert:      bool = Field(default=False, description="Whether or not to invert the mask")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> MaskOutput:
         image = context.services.images.get(
@@ -198,22 +242,27 @@ class MaskFromAlphaInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, image_mask)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, image_mask, metadata)
         return MaskOutput(mask=ImageField(image_type=image_type, image_name=image_name))
 
 
-class BlurInvocation(BaseInvocation):
+class BlurInvocation(BaseInvocation, PILInvocationConfig):
     """Blurs an image"""
 
-    #fmt: off
+    # fmt: off
     type: Literal["blur"] = "blur"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to blur")
     radius:     float = Field(default=8.0, ge=0, description="The blur radius")
     blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
-    #fmt: on
-    
+    # fmt: on
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -230,22 +279,28 @@ class BlurInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, blur_image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, blur_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=blur_image
         )
 
 
-class LerpInvocation(BaseInvocation):
+class LerpInvocation(BaseInvocation, PILInvocationConfig):
     """Linear interpolation of all pixels of an image"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["lerp"] = "lerp"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
-    #fmt: on
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
@@ -261,23 +316,29 @@ class LerpInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, lerp_image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, lerp_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=lerp_image
         )
 
 
-class InverseLerpInvocation(BaseInvocation):
+class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
     """Inverse linear interpolation of all pixels of an image"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["ilerp"] = "ilerp"
 
     # Inputs
     image: ImageField = Field(default=None, description="The image to lerp")
     min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
     max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
-    #fmt: on
-    
+    # fmt: on
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -297,7 +358,12 @@ class InverseLerpInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, ilerp_image)
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, ilerp_image, metadata)
+        return build_image_output(
+            image_type=image_type, image_name=image_name, image=ilerp_image
         )

invokeai/app/invocations/latent.py

@@ -0,0 +1,433 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+import random
+from typing import Literal, Optional
+from pydantic import BaseModel, Field
+import torch
+
+from invokeai.app.invocations.util.choose_model import choose_model
+
+from invokeai.app.util.step_callback import stable_diffusion_step_callback
+
+from ...backend.model_management.model_manager import ModelManager
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
+from ...backend.image_util.seamless import configure_model_padding
+from ...backend.prompting.conditioning import get_uc_and_c_and_ec
+from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+import numpy as np
+from ..services.image_storage import ImageType
+from .baseinvocation import BaseInvocation, InvocationContext
+from .image import ImageField, ImageOutput, build_image_output
+from ...backend.stable_diffusion import PipelineIntermediateState
+from diffusers.schedulers import SchedulerMixin as Scheduler
+import diffusers
+from diffusers import DiffusionPipeline
+
+
+class LatentsField(BaseModel):
+    """A latents field used for passing latents between invocations"""
+
+    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
+
+    class Config:
+        schema_extra = {"required": ["latents_name"]}
+
+class LatentsOutput(BaseInvocationOutput):
+    """Base class for invocations that output latents"""
+    #fmt: off
+    type: Literal["latent_output"] = "latent_output"
+    latents: LatentsField            = Field(default=None, description="The output latents")
+    #fmt: on
+
+class NoiseOutput(BaseInvocationOutput):
+    """Invocation noise output"""
+    #fmt: off
+    type: Literal["noise_output"] = "noise_output"
+    noise: LatentsField            = Field(default=None, description="The output noise")
+    #fmt: on
+
+
+# TODO: this seems like a hack
+scheduler_map = dict(
+    ddim=diffusers.DDIMScheduler,
+    dpmpp_2=diffusers.DPMSolverMultistepScheduler,
+    k_dpm_2=diffusers.KDPM2DiscreteScheduler,
+    k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
+    k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
+    k_euler=diffusers.EulerDiscreteScheduler,
+    k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
+    k_heun=diffusers.HeunDiscreteScheduler,
+    k_lms=diffusers.LMSDiscreteScheduler,
+    plms=diffusers.PNDMScheduler,
+)
+
+
+SAMPLER_NAME_VALUES = Literal[
+    tuple(list(scheduler_map.keys()))
+]
+
+
+def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
+    scheduler_class = scheduler_map.get(scheduler_name,'ddim')
+    scheduler = scheduler_class.from_config(model.scheduler.config)
+    # hack copied over from generate.py
+    if not hasattr(scheduler, 'uses_inpainting_model'):
+        scheduler.uses_inpainting_model = lambda: False
+    return scheduler
+
+
+def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
+    # limit noise to only the diffusion image channels, not the mask channels
+    input_channels = min(latent_channels, 4)
+    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
+    generator = torch.Generator(device=use_device).manual_seed(seed)
+    x = torch.randn(
+        [
+            1,
+            input_channels,
+            height // downsampling_factor,
+            width //  downsampling_factor,
+        ],
+        dtype=torch_dtype(device),
+        device=use_device,
+        generator=generator,
+    ).to(device)
+    # if self.perlin > 0.0:
+    #     perlin_noise = self.get_perlin_noise(
+    #         width // self.downsampling_factor, height // self.downsampling_factor
+    #     )
+    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
+    return x
+
+
+def random_seed():
+    return random.randint(0, np.iinfo(np.uint32).max)
+
+
+class NoiseInvocation(BaseInvocation):
+    """Generates latent noise."""
+
+    type: Literal["noise"] = "noise"
+
+    # Inputs
+    seed:        int = Field(ge=0, le=np.iinfo(np.uint32).max, description="The seed to use", default_factory=random_seed)
+    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting noise", )
+    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting noise", )
+
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "noise"],
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> NoiseOutput:
+        device = torch.device(choose_torch_device())
+        noise = get_noise(self.width, self.height, device, self.seed)
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.set(name, noise)
+        return NoiseOutput(
+            noise=LatentsField(latents_name=name)
+        )
+
+
+# Text to image
+class TextToLatentsInvocation(BaseInvocation):
+    """Generates latents from a prompt."""
+
+    type: Literal["t2l"] = "t2l"
+
+    # Inputs
+    # TODO: consider making prompt optional to enable providing prompt through a link
+    # fmt: off
+    prompt: Optional[str] = Field(description="The prompt to generate an image from")
+    noise: Optional[LatentsField] = Field(description="The noise to use")
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
+    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    model:       str = Field(default="", description="The model to use (currently ignored)")
+    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
+    # fmt: on
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    # TODO: pass this an emitter method or something? or a session for dispatching?
+    def dispatch_progress(
+        self, context: InvocationContext, source_node_id: str, intermediate_state: PipelineIntermediateState
+    ) -> None:
+        stable_diffusion_step_callback(
+            context=context,
+            intermediate_state=intermediate_state,
+            node=self.dict(),
+            source_node_id=source_node_id,
+        )
+
+    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
+        model_info = choose_model(model_manager, self.model)
+        model_name = model_info['model_name']
+        model_hash = model_info['hash']
+        model: StableDiffusionGeneratorPipeline = model_info['model']
+        model.scheduler = get_scheduler(
+            model=model,
+            scheduler_name=self.scheduler
+        )
+
+        if isinstance(model, DiffusionPipeline):
+            for component in [model.unet, model.vae]:
+                configure_model_padding(component,
+                                        self.seamless,
+                                        self.seamless_axes
+                                        )
+        else:
+            configure_model_padding(model,
+                                    self.seamless,
+                                    self.seamless_axes
+                                    )
+
+        return model
+
+
+    def get_conditioning_data(self, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
+        uc, c, extra_conditioning_info = get_uc_and_c_and_ec(self.prompt, model=model)
+        conditioning_data = ConditioningData(
+            uc,
+            c,
+            self.cfg_scale,
+            extra_conditioning_info,
+            postprocessing_settings=PostprocessingSettings(
+                threshold=0.0,#threshold,
+                warmup=0.2,#warmup,
+                h_symmetry_time_pct=None,#h_symmetry_time_pct,
+                v_symmetry_time_pct=None#v_symmetry_time_pct,
+            ),
+        ).add_scheduler_args_if_applicable(model.scheduler, eta=None)#ddim_eta)
+        return conditioning_data
+
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        noise = context.services.latents.get(self.noise.latents_name)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, source_node_id, state)
+
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(model)
+
+        # TODO: Verify the noise is the right size
+
+        result_latents, result_attention_map_saver = model.latents_from_embeddings(
+            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
+            noise=noise,
+            num_inference_steps=self.steps,
+            conditioning_data=conditioning_data,
+            callback=step_callback
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.set(name, result_latents)
+        return LatentsOutput(
+            latents=LatentsField(latents_name=name)
+        )
+
+
+class LatentsToLatentsInvocation(TextToLatentsInvocation):
+    """Generates latents using latents as base image."""
+
+    type: Literal["l2l"] = "l2l"
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
+    strength: float = Field(default=0.5, description="The strength of the latents to use")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        noise = context.services.latents.get(self.noise.latents_name)
+        latent = context.services.latents.get(self.latents.latents_name)
+
+        # Get the source node id (we are invoking the prepared node)
+        graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
+        source_node_id = graph_execution_state.prepared_source_mapping[self.id]
+
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, source_node_id, state)
+
+        model = self.get_model(context.services.model_manager)
+        conditioning_data = self.get_conditioning_data(model)
+
+        # TODO: Verify the noise is the right size
+
+        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
+            latent, device=model.device, dtype=latent.dtype
+        )
+
+        timesteps, _ = model.get_img2img_timesteps(
+            self.steps,
+            self.strength,
+            device=model.device,
+        )
+
+        result_latents, result_attention_map_saver = model.latents_from_embeddings(
+            latents=initial_latents,
+            timesteps=timesteps,
+            noise=noise,
+            num_inference_steps=self.steps,
+            conditioning_data=conditioning_data,
+            callback=step_callback
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.set(name, result_latents)
+        return LatentsOutput(
+            latents=LatentsField(latents_name=name)
+        )
+
+
+# Latent to image
+class LatentsToImageInvocation(BaseInvocation):
+    """Generates an image from latents."""
+
+    type: Literal["l2i"] = "l2i"
+
+    # Inputs
+    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
+    model: str = Field(default="", description="The model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        # TODO: this only really needs the vae
+        model_info = choose_model(context.services.model_manager, self.model)
+        model: StableDiffusionGeneratorPipeline = model_info['model']
+
+        with torch.inference_mode():
+            np_image = model.decode_latents(latents)
+            image = model.numpy_to_pil(np_image)[0]
+
+            image_type = ImageType.RESULT
+            image_name = context.services.images.create_name(
+                context.graph_execution_state_id, self.id
+            )
+
+            metadata = context.services.metadata.build_metadata(
+                session_id=context.graph_execution_state_id, node=self
+            )
+
+            torch.cuda.empty_cache()
+
+            context.services.images.save(image_type, image_name, image, metadata)
+            return build_image_output(
+                image_type=image_type, image_name=image_name, image=image
+            )
+
+
+LATENTS_INTERPOLATION_MODE = Literal[
+    "nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"
+]
+
+
+class ResizeLatentsInvocation(BaseInvocation):
+    """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
+
+    type: Literal["lresize"] = "lresize"
+
+    # Inputs
+    latents: Optional[LatentsField]             = Field(description="The latents to resize")
+    width: int                                  = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
+    height: int                                 = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
+    mode: Optional[LATENTS_INTERPOLATION_MODE]  = Field(default="bilinear", description="The interpolation mode")
+    antialias: Optional[bool]                   = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        resized_latents = torch.nn.functional.interpolate(
+            latents,
+            size=(self.height // 8, self.width // 8),
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.set(name, resized_latents)
+        return LatentsOutput(latents=LatentsField(latents_name=name))
+
+
+class ScaleLatentsInvocation(BaseInvocation):
+    """Scales latents by a given factor."""
+
+    type: Literal["lscale"] = "lscale"
+
+    # Inputs
+    latents: Optional[LatentsField]             = Field(description="The latents to scale")
+    scale_factor: float                         = Field(gt=0, description="The factor by which to scale the latents")
+    mode: Optional[LATENTS_INTERPOLATION_MODE]  = Field(default="bilinear", description="The interpolation mode")
+    antialias: Optional[bool]                   = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        # resizing
+        resized_latents = torch.nn.functional.interpolate(
+            latents,
+            scale_factor=self.scale_factor,
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
+        )
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        torch.cuda.empty_cache()
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.set(name, resized_latents)
+        return LatentsOutput(latents=LatentsField(latents_name=name))

invokeai/app/invocations/math.py

@@ -0,0 +1,75 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+
+
+class MathInvocationConfig(BaseModel):
+    """Helper class to provide all math invocations with additional config"""
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["math"],
+            }
+        }
+
+
+class IntOutput(BaseInvocationOutput):
+    """An integer output"""
+    #fmt: off
+    type: Literal["int_output"] = "int_output"
+    a: int = Field(default=None, description="The output integer")
+    #fmt: on
+
+
+class AddInvocation(BaseInvocation, MathInvocationConfig):
+    """Adds two numbers"""
+    #fmt: off
+    type: Literal["add"] = "add"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a + self.b)
+
+
+class SubtractInvocation(BaseInvocation, MathInvocationConfig):
+    """Subtracts two numbers"""
+    #fmt: off
+    type: Literal["sub"] = "sub"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a - self.b)
+
+
+class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
+    """Multiplies two numbers"""
+    #fmt: off
+    type: Literal["mul"] = "mul"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a * self.b)
+
+
+class DivideInvocation(BaseInvocation, MathInvocationConfig):
+    """Divides two numbers"""
+    #fmt: off
+    type: Literal["div"] = "div"
+    a: int = Field(default=0, description="The first number")
+    b: int = Field(default=0, description="The second number")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=int(self.a / self.b))

invokeai/app/invocations/params.py

@@ -0,0 +1,18 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal
+from pydantic import Field
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
+from .math import IntOutput
+
+# Pass-through parameter nodes - used by subgraphs
+
+class ParamIntInvocation(BaseInvocation):
+    """An integer parameter"""
+    #fmt: off
+    type: Literal["param_int"] = "param_int"
+    a: int = Field(default=0, description="The integer value")
+    #fmt: on
+
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=self.a)

invokeai/app/invocations/reconstruct.py

@@ -1,12 +1,11 @@
-from datetime import datetime, timezone
 from typing import Literal, Union
 
 from pydantic import Field
 
-from ..services.image_storage import ImageType
-from ..services.invocation_services import InvocationServices
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput
+from invokeai.app.models.image import ImageField, ImageType
+
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
 
 class RestoreFaceInvocation(BaseInvocation):
     """Restores faces in an image."""
@@ -18,6 +17,14 @@ class RestoreFaceInvocation(BaseInvocation):
     strength:                float = Field(default=0.75, gt=0, le=1, description="The strength of the restoration"  )
     #fmt: on
     
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["restoration", "image"],
+            },
+        }
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -36,7 +43,14 @@ class RestoreFaceInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, results[0][0])
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
+
+        context.services.images.save(image_type, image_name, results[0][0], metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=results[0][0]
+        )

invokeai/app/invocations/upscale.py

@@ -1,14 +1,12 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from datetime import datetime, timezone
 from typing import Literal, Union
 
 from pydantic import Field
 
-from ..services.image_storage import ImageType
-from ..services.invocation_services import InvocationServices
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput
+from invokeai.app.models.image import ImageField, ImageType
+from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
+from .image import ImageOutput, build_image_output
 
 
 class UpscaleInvocation(BaseInvocation):
@@ -22,6 +20,15 @@ class UpscaleInvocation(BaseInvocation):
     level: Literal[2, 4] = Field(default=2, description="The upscale level")
     #fmt: on
 
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["upscaling", "image"],
+            },
+        }
+
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.services.images.get(
             self.image.image_type, self.image.image_name
@@ -40,7 +47,14 @@ class UpscaleInvocation(BaseInvocation):
         image_name = context.services.images.create_name(
             context.graph_execution_state_id, self.id
         )
-        context.services.images.save(image_type, image_name, results[0][0])
-        return ImageOutput(
-            image=ImageField(image_type=image_type, image_name=image_name)
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
+
+        context.services.images.save(image_type, image_name, results[0][0], metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=results[0][0]
+        )

invokeai/app/invocations/util/choose_model.py

@@ -0,0 +1,14 @@
+from invokeai.backend.model_management.model_manager import ModelManager
+
+
+def choose_model(model_manager: ModelManager, model_name: str):
+    """Returns the default model if the `model_name` not a valid model, else returns the selected model."""
+    if model_manager.valid_model(model_name):
+        model = model_manager.get_model(model_name)
+    else:
+        model = model_manager.get_model()
+        print(
+            f"* Warning: '{model_name}' is not a valid model name. Using default model \'{model['model_name']}\' instead."
+        )
+
+    return model

invokeai/app/models/exceptions.py

@@ -0,0 +1,3 @@
+class CanceledException(Exception):
+    """Execution canceled by user."""
+    pass

invokeai/app/models/image.py

@@ -0,0 +1,29 @@
+from enum import Enum
+from typing import Optional
+from pydantic import BaseModel, Field
+
+
+class ImageType(str, Enum):
+    RESULT = "results"
+    INTERMEDIATE = "intermediates"
+    UPLOAD = "uploads"
+
+
+def is_image_type(obj):
+    try:
+        ImageType(obj)
+    except ValueError:
+        return False
+    return True
+
+
+class ImageField(BaseModel):
+    """An image field used for passing image objects between invocations"""
+
+    image_type: ImageType = Field(
+        default=ImageType.RESULT, description="The type of the image"
+    )
+    image_name: Optional[str] = Field(default=None, description="The name of the image")
+
+    class Config:
+        schema_extra = {"required": ["image_type", "image_name"]}

invokeai/app/services/config.py

@@ -0,0 +1,379 @@
+# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein)
+
+'''Invokeai configuration system.
+
+Arguments and fields are taken from the pydantic definition of the
+model.  Defaults can be set by creating a yaml configuration file that
+has top-level keys corresponding to an invocation name, a command, or
+"globals" for global values such as `xformers_enabled`. Currently
+graphs cannot be configured this way, but their constituents can be.
+
+[file: invokeai.yaml]
+
+ globals:
+   nsfw_checker: False
+   max_loaded_models: 5
+ 
+ txt2img:
+   steps: 20
+   scheduler: k_heun
+   width: 768
+ 
+ img2img:
+   width: 1024
+   height: 1024
+
+The default name of the configuration file is `invokeai.yaml`, located
+in INVOKEAI_ROOT. You can use any OmegaConf dictionary by passing it
+to the config object at initialization time:
+
+ omegaconf = OmegaConf.load('/tmp/init.yaml')
+ conf = InvokeAIAppConfig(conf=omegaconf)
+
+By default, InvokeAIAppConfig will parse the contents of argv at
+initialization time. You may pass a list of strings in the optional
+`argv` argument to use instead of the system argv:
+
+ conf = InvokeAIAppConfig(arg=['--xformers_enabled'])
+
+It is also possible to set a value at initialization time. This value
+has highest priority.
+
+ conf = InvokeAIAppConfig(xformers_enabled=True)
+
+Any setting can be overwritten by setting an environment variable of
+form: "INVOKEAI_<command>_<value>", as in:
+
+  export INVOKEAI_txt2img_steps=30
+
+Order of precedence (from highest):
+   1) initialization options
+   2) command line options
+   3) environment variable options
+   4) config file options
+   5) pydantic defaults
+
+Typical usage:
+
+ from invokeai.app.services.config import InvokeAIAppConfig
+ from invokeai.invocations.generate import TextToImageInvocation
+
+ # get global configuration and print its nsfw_checker value
+ conf = InvokeAIAppConfig()
+ print(conf.nsfw_checker)
+
+ # get the text2image invocation and print its step value
+ text2image = TextToImageInvocation()
+ print(text2image.steps)
+
+Computed properties:
+
+The InvokeAIAppConfig object has a series of properties that
+resolve paths relative to the runtime root directory. They each return
+a Path object:
+
+ root_path          - path to InvokeAI root
+ output_path        - path to default outputs directory
+ model_conf_path    - path to models.yaml
+ conf               - alias for the above
+ embedding_path     - path to the embeddings directory
+ lora_path          - path to the LoRA directory
+ 
+
+'''
+import argparse
+import os
+import sys
+from argparse import ArgumentParser
+from omegaconf import OmegaConf, DictConfig
+from pathlib import Path
+from pydantic import BaseSettings, Field, parse_obj_as
+from typing import Any, ClassVar, Dict, List, Literal, Union, get_origin, get_type_hints, get_args
+
+INIT_FILE = Path('invokeai.yaml')
+LEGACY_INIT_FILE = Path('invokeai.init')
+
+class InvokeAISettings(BaseSettings):
+    '''
+    Runtime configuration settings in which default values are
+    read from an omegaconf .yaml file.
+    '''
+    initconf             : ClassVar[DictConfig] = None
+    argparse_groups      : ClassVar[Dict] = {}
+
+    def parse_args(self, argv: list=sys.argv[1:]):
+        parser = self.get_parser()
+        opt, _ = parser.parse_known_args(argv)
+        for name in self.__fields__:
+            if name not in self._excluded():
+                setattr(self, name, getattr(opt,name))
+
+    @classmethod
+    def add_parser_arguments(cls, parser):
+        env_prefix = cls.Config.env_prefix if hasattr(cls.Config,'env_prefix') else 'INVOKEAI_'
+        if 'type' in get_type_hints(cls):
+            default_settings_stanza = get_args(get_type_hints(cls)['type'])[0]
+        else:
+            default_settings_stanza = 'globals'
+        initconf = cls.initconf.get(default_settings_stanza) if cls.initconf and default_settings_stanza in cls.initconf else None
+
+        fields = cls.__fields__
+        cls.argparse_groups = {}
+        for name, field in fields.items():
+            if name not in cls._excluded():
+                env_name = env_prefix+f'{cls.cmd_name()}_{name}'
+                if initconf and name in initconf:
+                    field.default = initconf.get(name)
+                if env_name in os.environ:
+                    field.default = os.environ[env_name]
+                cls.add_field_argument(parser, name, field)
+
+
+    @classmethod
+    def cmd_name(self, command_field: str='type')->str:
+        hints = get_type_hints(self)
+        if command_field in hints:
+            return get_args(hints[command_field])[0]
+        else:
+            return 'globals'
+
+    @classmethod
+    def get_parser(cls)->ArgumentParser:
+        parser = ArgumentParser(
+            prog=cls.cmd_name(),
+            description=cls.__doc__,
+        )
+        cls.add_parser_arguments(parser)
+        return parser
+
+    @classmethod
+    def add_subparser(cls, parser: argparse.ArgumentParser):
+        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
+
+    @classmethod
+    def _excluded(self)->List[str]:
+        return ['type','initconf']
+    
+    class Config:
+        env_file_encoding = 'utf-8'
+        arbitrary_types_allowed = True
+        env_prefix = 'INVOKEAI_'
+        case_sensitive = True
+        @classmethod
+        def customise_sources(
+            cls,
+            init_settings,
+            env_settings,
+            file_secret_settings,
+        ):
+            return (
+                init_settings,
+                cls._omegaconf_settings_source,
+                env_settings,
+                file_secret_settings,
+            )
+
+        @classmethod
+        def _omegaconf_settings_source(cls, settings: BaseSettings) -> dict[str, Any]:
+            if initconf := InvokeAISettings.initconf:
+                return initconf.get(settings.cmd_name(),{})
+            else:
+                return {}
+
+    @classmethod
+    def add_field_argument(cls, command_parser, name: str, field, default_override = None):
+        default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+        if category := field.field_info.extra.get("category"):
+            if category not in cls.argparse_groups:
+                cls.argparse_groups[category] = command_parser.add_argument_group(category)
+            argparse_group = cls.argparse_groups[category]
+        else:
+            argparse_group = command_parser
+        
+        if get_origin(field.type_) == Literal:
+            allowed_values = get_args(field.type_)
+            allowed_types = set()
+            for val in allowed_values:
+                allowed_types.add(type(val))
+            allowed_types_list = list(allowed_types)
+            field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field_type,
+                default=default,
+                choices=allowed_values,
+                help=field.field_info.description,
+            )
+        else:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+def _find_root()->Path:
+    if os.environ.get("INVOKEAI_ROOT"):
+        root = Path(os.environ.get("INVOKEAI_ROOT")).resolve()
+    elif (
+            os.environ.get("VIRTUAL_ENV")
+            and (Path(os.environ.get("VIRTUAL_ENV"), "..", INIT_FILE).exists()
+                 or
+                 Path(os.environ.get("VIRTUAL_ENV"), "..", LEGACY_INIT_FILE).exists()
+                 )
+    ):
+        root = Path(os.environ.get("VIRTUAL_ENV"), "..").resolve()
+    else:
+        root = Path("~/invokeai").expanduser().resolve()
+    return root
+
+class InvokeAIAppConfig(InvokeAISettings):
+    '''
+    Application-wide settings.
+    '''
+    #fmt: off
+    type: Literal["globals"] = "globals"
+    root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
+    infile              : Path = Field(default=None, description='Path to a file of prompt commands to bulk generate from', category='Paths')
+    conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
+    model               : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
+    outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
+    embedding_dir       : Path = Field(default='embeddings', description='Path to InvokeAI textual inversion aembeddings directory', category='Paths')
+    lora_dir            : Path = Field(default='loras', description='Path to InvokeAI LoRA model directory', category='Paths')
+    autoconvert_dir     : Path = Field(default=None, description='Path to a directory of ckpt files to be converted into diffusers and imported on startup.', category='Paths')
+    gfpgan_model_dir    : Path = Field(default="./models/gfpgan/GFPGANv1.4.pth", description='Path to GFPGAN models directory.', category='Paths')
+    embeddings          : bool = Field(default=True, description='Load contents of embeddings directory', category='Models')
+    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
+    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
+    precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
+    max_loaded_models   : int = Field(default=2, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
+    free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
+    nsfw_checker        : bool = Field(default=True, description="Enable/disable the NSFW checker", category='Features')
+    restore             : bool = Field(default=True, description="Enable/disable face restoration code", category='Features')
+    esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
+    patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
+    internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
+    log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
+    #fmt: on
+
+    def __init__(self, conf: DictConfig = None, argv: List[str]=None, **kwargs):
+        '''
+        Initialize InvokeAIAppconfig.
+        :param conf: alternate Omegaconf dictionary object
+        :param argv: aternate sys.argv list
+        :param **kwargs: attributes to initialize with
+        '''
+        super().__init__(**kwargs)
+        
+        # Set the runtime root directory. We parse command-line switches here
+        # in order to pick up the --root_dir option.
+        self.parse_args(argv)
+        if not conf:
+            try:
+                conf = OmegaConf.load(self.root_dir / INIT_FILE)
+            except:
+                pass
+        InvokeAISettings.initconf = conf
+
+        # parse args again in order to pick up settings in configuration file
+        self.parse_args(argv)
+
+        # restore initialization values
+        hints = get_type_hints(self)
+        for k in kwargs:
+            setattr(self,k,parse_obj_as(hints[k],kwargs[k]))
+
+    @property
+    def root_path(self)->Path:
+        '''
+        Path to the runtime root directory
+        '''
+        if self.root:
+            return self.root.expanduser()
+        else:
+            return self.find_root()
+
+    @property
+    def root_dir(self)->Path:
+        '''
+        Alias for above.
+        '''
+        return self.root_path
+
+    def _resolve(self,partial_path:Path)->Path:
+        return (self.root_path / partial_path).resolve()
+
+    @property
+    def output_path(self)->Path:
+        '''
+        Path to defaults outputs directory.
+        '''
+        return self._resolve(self.outdir)
+
+    @property
+    def model_conf_path(self)->Path:
+        '''
+        Path to models configuration file.
+        '''
+        return self._resolve(self.conf_path)
+
+    @property
+    def conf(self)->Path:
+        '''
+        Path to models configuration file (alias for model_conf_path).
+        '''
+        return self.model_conf_path
+
+    @property
+    def embedding_path(self)->Path:
+        '''
+        Path to the textual inversion embeddings directory.
+        '''
+        return self._resolve(self.embedding_dir) if self.embedding_dir else None
+    
+    @property
+    def lora_path(self)->Path:
+        '''
+        Path to the LoRA models directory.
+        '''
+        return self._resolve(self.lora_dir) if self.lora_dir else None
+
+    @property
+    def autoconvert_path(self)->Path:
+        '''
+        Path to the directory containing models to be imported automatically at startup.
+        '''
+        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
+
+    @property
+    def gfpgan_model_path(self)->Path:
+        '''
+        Path to the GFPGAN model.
+        '''
+        return self._resolve(self.gfpgan_model_dir) if self.gfpgan_model_dir else None
+
+    @staticmethod
+    def find_root()->Path:
+        '''
+        Choose the runtime root directory when not specified on command line or
+        init file.
+        '''
+        return _find_root()
+
+class InvokeAIWebConfig(InvokeAIAppConfig):
+    '''
+    Web-specific settings
+    '''
+    #fmt: off
+    type               : Literal["web"] = "web"
+    allow_origins      : List = Field(default=[], description="Allowed CORS origins", category='Cross-Origin Resource Sharing')
+    allow_credentials  : bool = Field(default=True, description="Allow CORS credentials", category='Cross-Origin Resource Sharing')
+    allow_methods      : List = Field(default=["*"], description="Methods allowed for CORS", category='Cross-Origin Resource Sharing')
+    allow_headers      : List = Field(default=["*"], description="Headers allowed for CORS", category='Cross-Origin Resource Sharing')
+    host               : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
+    port               : int = Field(default=9090, description="Port to bind to", category='Web Server')
+    #fmt: on

invokeai/app/services/default_graphs.py

@@ -0,0 +1,56 @@
+from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
+from ..invocations.params import ParamIntInvocation
+from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
+from .item_storage import ItemStorageABC
+
+
+default_text_to_image_graph_id = '539b2af5-2b4d-4d8c-8071-e54a3255fc74'
+
+
+def create_text_to_image() -> LibraryGraph:
+    return LibraryGraph(
+        id=default_text_to_image_graph_id,
+        name='t2i',
+        description='Converts text to an image',
+        graph=Graph(
+            nodes={
+                'width': ParamIntInvocation(id='width', a=512),
+                'height': ParamIntInvocation(id='height', a=512),
+                '3': NoiseInvocation(id='3'),
+                '4': TextToLatentsInvocation(id='4'),
+                '5': LatentsToImageInvocation(id='5')
+            },
+            edges=[
+                Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='3', field='width')),
+                Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='3', field='height')),
+                Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='4', field='width')),
+                Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='4', field='height')),
+                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='4', field='noise')),
+                Edge(source=EdgeConnection(node_id='4', field='latents'), destination=EdgeConnection(node_id='5', field='latents')),
+            ]
+        ),
+        exposed_inputs=[
+            ExposedNodeInput(node_path='4', field='prompt', alias='prompt'),
+            ExposedNodeInput(node_path='width', field='a', alias='width'),
+            ExposedNodeInput(node_path='height', field='a', alias='height')
+        ],
+        exposed_outputs=[
+            ExposedNodeOutput(node_path='5', 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"""
+
+    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

invokeai/app/services/events.py

@@ -1,10 +1,9 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from typing import Any, Dict, TypedDict
+from typing import Any, Dict, TypedDict, Union
+from invokeai.app.api.models.images import ProgressImage
+from invokeai.app.util.misc import get_timestamp
 
-ProgressImage = TypedDict(
-    "ProgressImage", {"dataURL": str, "width": int, "height": int}
-)
 
 class EventServiceBase:
     session_event: str = "session_event"
@@ -14,7 +13,8 @@ class EventServiceBase:
     def dispatch(self, event_name: str, payload: Any) -> None:
         pass
 
-    def __emit_session_event(self, event_name: str, payload: Dict) -> None:
+    def __emit_session_event(self, event_name: str, payload: dict) -> None:
+        payload["timestamp"] = get_timestamp()
         self.dispatch(
             event_name=EventServiceBase.session_event,
             payload=dict(event=event_name, data=payload),
@@ -25,7 +25,8 @@ class EventServiceBase:
     def emit_generator_progress(
         self,
         graph_execution_state_id: str,
-        invocation_id: str,
+        node: dict,
+        source_node_id: str,
         progress_image: ProgressImage | None,
         step: int,
         total_steps: int,
@@ -35,48 +36,60 @@ class EventServiceBase:
             event_name="generator_progress",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation_id=invocation_id,
-                progress_image=progress_image,
+                node=node,
+                source_node_id=source_node_id,
+                progress_image=progress_image.dict() if progress_image is not None else None,
                 step=step,
                 total_steps=total_steps,
             ),
         )
 
     def emit_invocation_complete(
-        self, graph_execution_state_id: str, invocation_id: str, result: Dict
+        self,
+        graph_execution_state_id: str,
+        result: dict,
+        node: dict,
+        source_node_id: str,
     ) -> None:
         """Emitted when an invocation has completed"""
         self.__emit_session_event(
             event_name="invocation_complete",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation_id=invocation_id,
+                node=node,
+                source_node_id=source_node_id,
                 result=result,
             ),
         )
 
     def emit_invocation_error(
-        self, graph_execution_state_id: str, invocation_id: str, error: str
+        self,
+        graph_execution_state_id: str,
+        node: dict,
+        source_node_id: str,
+        error: str,
     ) -> None:
         """Emitted when an invocation has completed"""
         self.__emit_session_event(
             event_name="invocation_error",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation_id=invocation_id,
+                node=node,
+                source_node_id=source_node_id,
                 error=error,
             ),
         )
 
     def emit_invocation_started(
-        self, graph_execution_state_id: str, invocation_id: str
+        self, graph_execution_state_id: str, node: dict, source_node_id: str
     ) -> None:
         """Emitted when an invocation has started"""
         self.__emit_session_event(
             event_name="invocation_started",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation_id=invocation_id,
+                node=node,
+                source_node_id=source_node_id,
             ),
         )
 
@@ -84,5 +97,7 @@ class EventServiceBase:
         """Emitted when a session has completed all invocations"""
         self.__emit_session_event(
             event_name="graph_execution_state_complete",
-            payload=dict(graph_execution_state_id=graph_execution_state_id),
+            payload=dict(
+                graph_execution_state_id=graph_execution_state_id,
+            ),
         )

invokeai/app/services/graph.py

@@ -2,9 +2,7 @@
 
 import copy
 import itertools
-import traceback
 import uuid
-from types import NoneType
 from typing import (
     Annotated,
     Any,
@@ -15,9 +13,10 @@ from typing import (
     get_origin,
     get_type_hints,
 )
+NoneType = type(None)
 
 import networkx as nx
-from pydantic import BaseModel, validator
+from pydantic import BaseModel, root_validator, validator, Extra
 from pydantic.fields import Field
 
 from ..invocations import *
@@ -26,7 +25,7 @@ from ..invocations.baseinvocation import (
     BaseInvocationOutput,
     InvocationContext,
 )
-from .invocation_services import InvocationServices
+from .config import InvokeAISettings
 
 
 class EdgeConnection(BaseModel):
@@ -213,9 +212,10 @@ class CollectInvocation(BaseInvocation):
 InvocationsUnion = Union[BaseInvocation.get_invocations()]  # type: ignore
 InvocationOutputsUnion = Union[BaseInvocationOutput.get_all_subclasses_tuple()]  # type: ignore
 
+class Graph(InvokeAISettings):
+    id: str = Field(description="The id of this graph", default_factory=lambda: uuid.uuid4().__str__())
+    type: Literal["graph"] = "graph"
 
-class Graph(BaseModel):
-    id: str = Field(description="The id of this graph", default_factory=uuid.uuid4)
     # TODO: use a list (and never use dict in a BaseModel) because pydantic/fastapi hates me
     nodes: dict[str, Annotated[InvocationsUnion, Field(discriminator="type")]] = Field(
         description="The nodes in this graph", default_factory=dict
@@ -283,7 +283,8 @@ class Graph(BaseModel):
         :raises InvalidEdgeError: the provided edge is invalid.
         """
 
-        if self._is_edge_valid(edge) and edge not in self.edges:
+        self._validate_edge(edge)
+        if edge not in self.edges:
             self.edges.append(edge)
         else:
             raise InvalidEdgeError()
@@ -354,7 +355,7 @@ class Graph(BaseModel):
 
         return True
 
-    def _is_edge_valid(self, edge: Edge) -> bool:
+    def _validate_edge(self, edge: Edge):
         """Validates that a new edge doesn't create a cycle in the graph"""
 
         # Validate that the nodes exist (edges may contain node paths, so we can't just check for nodes directly)
@@ -362,54 +363,53 @@ class Graph(BaseModel):
             from_node = self.get_node(edge.source.node_id)
             to_node = self.get_node(edge.destination.node_id)
         except NodeNotFoundError:
-            return False
+            raise InvalidEdgeError("One or both nodes don't exist")
 
         # Validate that an edge to this node+field doesn't already exist
         input_edges = self._get_input_edges(edge.destination.node_id, edge.destination.field)
         if len(input_edges) > 0 and not isinstance(to_node, CollectInvocation):
-            return False
+            raise InvalidEdgeError(f'Edge to node {edge.destination.node_id} field {edge.destination.field} already exists')
 
         # Validate that no cycles would be created
         g = self.nx_graph_flat()
         g.add_edge(edge.source.node_id, edge.destination.node_id)
         if not nx.is_directed_acyclic_graph(g):
-            return False
+            raise InvalidEdgeError(f'Edge creates a cycle in the graph')
 
         # Validate that the field types are compatible
         if not are_connections_compatible(
             from_node, edge.source.field, to_node, edge.destination.field
         ):
-            return False
+            raise InvalidEdgeError(f'Fields are incompatible')
 
         # Validate if iterator output type matches iterator input type (if this edge results in both being set)
         if isinstance(to_node, IterateInvocation) and edge.destination.field == "collection":
             if not self._is_iterator_connection_valid(
                 edge.destination.node_id, new_input=edge.source
             ):
-                return False
+                raise InvalidEdgeError(f'Iterator input type does not match iterator output type')
 
         # Validate if iterator input type matches output type (if this edge results in both being set)
         if isinstance(from_node, IterateInvocation) and edge.source.field == "item":
             if not self._is_iterator_connection_valid(
                 edge.source.node_id, new_output=edge.destination
             ):
-                return False
+                raise InvalidEdgeError(f'Iterator output type does not match iterator input type')
 
         # Validate if collector input type matches output type (if this edge results in both being set)
         if isinstance(to_node, CollectInvocation) and edge.destination.field == "item":
             if not self._is_collector_connection_valid(
                 edge.destination.node_id, new_input=edge.source
             ):
-                return False
+                raise InvalidEdgeError(f'Collector output type does not match collector input type')
 
         # Validate if collector output type matches input type (if this edge results in both being set)
         if isinstance(from_node, CollectInvocation) and edge.source.field == "collection":
             if not self._is_collector_connection_valid(
                 edge.source.node_id, new_output=edge.destination
             ):
-                return False
+                raise InvalidEdgeError(f'Collector input type does not match collector output type')
 
-        return True
 
     def has_node(self, node_path: str) -> bool:
         """Determines whether or not a node exists in the graph."""
@@ -733,7 +733,7 @@ class Graph(BaseModel):
         for sgn in (
             gn for gn in self.nodes.values() if isinstance(gn, GraphInvocation)
         ):
-            sgn.graph.nx_graph_flat(g, self._get_node_path(sgn.id, prefix))
+            g = sgn.graph.nx_graph_flat(g, self._get_node_path(sgn.id, prefix))
 
         # TODO: figure out if iteration nodes need to be expanded
 
@@ -750,10 +750,8 @@ class Graph(BaseModel):
 class GraphExecutionState(BaseModel):
     """Tracks the state of a graph execution"""
 
-    id: str = Field(
-        description="The id of the execution state", default_factory=uuid.uuid4
-    )
-
+    id: str = Field(description="The id of the execution state", default_factory=lambda: uuid.uuid4().__str__())
+    
     # TODO: Store a reference to the graph instead of the actual graph?
     graph: Graph = Field(description="The graph being executed")
 
@@ -794,9 +792,6 @@ class GraphExecutionState(BaseModel):
         default_factory=dict,
     )
 
-    # Declare all fields as required; necessary for OpenAPI schema generation build.
-    # Technically only fields without a `default_factory` need to be listed here.
-    # See: https://github.com/pydantic/pydantic/discussions/4577
     class Config:
         schema_extra = {
             'required': [
@@ -812,7 +807,7 @@ class GraphExecutionState(BaseModel):
             ]
         }
 
-    def next(self) -> BaseInvocation | None:
+    def next(self) -> Union[BaseInvocation, None]:
         """Gets the next node ready to execute."""
 
         # TODO: enable multiple nodes to execute simultaneously by tracking currently executing nodes
@@ -861,7 +856,8 @@ class GraphExecutionState(BaseModel):
 
     def is_complete(self) -> bool:
         """Returns true if the graph is complete"""
-        return self.has_error() or all((k in self.executed for k in self.graph.nodes))
+        node_ids = set(self.graph.nx_graph_flat().nodes)
+        return self.has_error() or all((k in self.executed for k in node_ids))
 
     def has_error(self) -> bool:
         """Returns true if the graph has any errors"""
@@ -949,11 +945,11 @@ class GraphExecutionState(BaseModel):
 
     def _iterator_graph(self) -> nx.DiGraph:
         """Gets a DiGraph with edges to collectors removed so an ancestor search produces all active iterators for any node"""
-        g = self.graph.nx_graph()
+        g = self.graph.nx_graph_flat()
         collectors = (
             n
             for n in self.graph.nodes
-            if isinstance(self.graph.nodes[n], CollectInvocation)
+            if isinstance(self.graph.get_node(n), CollectInvocation)
         )
         for c in collectors:
             g.remove_edges_from(list(g.in_edges(c)))
@@ -965,7 +961,7 @@ class GraphExecutionState(BaseModel):
         iterators = [
             n
             for n in nx.ancestors(g, node_id)
-            if isinstance(self.graph.nodes[n], IterateInvocation)
+            if isinstance(self.graph.get_node(n), IterateInvocation)
         ]
         return iterators
 
@@ -1069,9 +1065,8 @@ class GraphExecutionState(BaseModel):
                 n
                 for n in prepared_nodes
                 if all(
-                    pit
+                    nx.has_path(execution_graph, pit[0], n)
                     for pit in parent_iterators
-                    if nx.has_path(execution_graph, pit[0], n)
                 )
             ),
             None,
@@ -1102,7 +1097,9 @@ class GraphExecutionState(BaseModel):
 
     # TODO: Add API for modifying underlying graph that checks if the change will be valid given the current execution state
     def _is_edge_valid(self, edge: Edge) -> bool:
-        if not self._is_edge_valid(edge):
+        try:
+            self.graph._validate_edge(edge)
+        except InvalidEdgeError:
             return False
 
         # Invalid if destination has already been prepared or executed
@@ -1148,4 +1145,55 @@ class GraphExecutionState(BaseModel):
         self.graph.delete_edge(edge)
 
 
+class ExposedNodeInput(BaseModel):
+    node_path: str = Field(description="The node path to the node with the input")
+    field: str = Field(description="The field name of the input")
+    alias: str = Field(description="The alias of the input")
+
+
+class ExposedNodeOutput(BaseModel):
+    node_path: str = Field(description="The node path to the node with the output")
+    field: str = Field(description="The field name of the output")
+    alias: str = Field(description="The alias of the output")
+
+class LibraryGraph(InvokeAISettings):
+    id: str = Field(description="The unique identifier for this library graph", default_factory=uuid.uuid4)
+    graph: Graph = Field(description="The graph")
+    name: str = Field(description="The name of the graph")
+    description: str = Field(description="The description of the graph")
+    exposed_inputs: list[ExposedNodeInput] = Field(description="The inputs exposed by this graph", default_factory=list)
+    exposed_outputs: list[ExposedNodeOutput] = Field(description="The outputs exposed by this graph", default_factory=list)
+
+    class Config:
+        extra='allow'
+
+    @validator('exposed_inputs', 'exposed_outputs')
+    def validate_exposed_aliases(cls, v):
+        if len(v) != len(set(i.alias for i in v)):
+            raise ValueError("Duplicate exposed alias")
+        return v
+
+    @root_validator
+    def validate_exposed_nodes(cls, values):
+        graph = values['graph']
+
+        # Validate exposed inputs
+        for exposed_input in values['exposed_inputs']:
+            if not graph.has_node(exposed_input.node_path):
+                raise ValueError(f"Exposed input node {exposed_input.node_path} does not exist")
+            node = graph.get_node(exposed_input.node_path)
+            if get_input_field(node, exposed_input.field) is None:
+                raise ValueError(f"Exposed input field {exposed_input.field} does not exist on node {exposed_input.node_path}")
+
+        # Validate exposed outputs
+        for exposed_output in values['exposed_outputs']:
+            if not graph.has_node(exposed_output.node_path):
+                raise ValueError(f"Exposed output node {exposed_output.node_path} does not exist")
+            node = graph.get_node(exposed_output.node_path)
+            if get_output_field(node, exposed_output.field) is None:
+                raise ValueError(f"Exposed output field {exposed_output.field} does not exist on node {exposed_output.node_path}")
+
+        return values
+
+
 GraphInvocation.update_forward_refs()

invokeai/app/services/image_storage.py

@@ -1,22 +1,29 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import datetime
 import os
+from glob import glob
 from abc import ABC, abstractmethod
-from enum import Enum
 from pathlib import Path
 from queue import Queue
-from typing import Dict
+from typing import Dict, List
 
 from PIL.Image import Image
-
-from invokeai.backend.image_util import PngWriter
-
-
-class ImageType(str, Enum):
-    RESULT = "results"
-    INTERMEDIATE = "intermediates"
-    UPLOAD = "uploads"
+import PIL.Image as PILImage
+from send2trash import send2trash
+from invokeai.app.api.models.images import (
+    ImageResponse,
+    ImageResponseMetadata,
+    SavedImage,
+)
+from invokeai.app.models.image import ImageType
+from invokeai.app.services.metadata import (
+    InvokeAIMetadata,
+    MetadataServiceBase,
+    build_invokeai_metadata_pnginfo,
+)
+from invokeai.app.services.item_storage import PaginatedResults
+from invokeai.app.util.misc import get_timestamp
+from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 
 
 class ImageStorageBase(ABC):
@@ -24,40 +31,74 @@ class ImageStorageBase(ABC):
 
     @abstractmethod
     def get(self, image_type: ImageType, image_name: str) -> Image:
+        """Retrieves an image as PIL Image."""
+        pass
+
+    @abstractmethod
+    def list(
+        self, image_type: ImageType, page: int = 0, per_page: int = 10
+    ) -> PaginatedResults[ImageResponse]:
+        """Gets a paginated list of images."""
         pass
 
     # TODO: make this a bit more flexible for e.g. cloud storage
     @abstractmethod
-    def get_path(self, image_type: ImageType, image_name: str) -> str:
+    def get_path(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        """Gets the internal path to an image or its thumbnail."""
+        pass
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    @abstractmethod
+    def get_uri(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        """Gets the external URI to an image or its thumbnail."""
+        pass
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    @abstractmethod
+    def validate_path(self, path: str) -> bool:
+        """Validates an image path."""
         pass
 
     @abstractmethod
-    def save(self, image_type: ImageType, image_name: str, image: Image) -> None:
+    def save(
+        self,
+        image_type: ImageType,
+        image_name: str,
+        image: Image,
+        metadata: InvokeAIMetadata | None = None,
+    ) -> SavedImage:
+        """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""
         pass
 
     @abstractmethod
     def delete(self, image_type: ImageType, image_name: str) -> None:
+        """Deletes an image and its thumbnail (if one exists)."""
         pass
 
     def create_name(self, context_id: str, node_id: str) -> str:
-        return f"{context_id}_{node_id}_{str(int(datetime.datetime.now(datetime.timezone.utc).timestamp()))}.png"
+        """Creates a unique contextual image filename."""
+        return f"{context_id}_{node_id}_{str(get_timestamp())}.png"
 
 
 class DiskImageStorage(ImageStorageBase):
     """Stores images on disk"""
 
     __output_folder: str
-    __pngWriter: PngWriter
     __cache_ids: Queue  # TODO: this is an incredibly naive cache
     __cache: Dict[str, Image]
     __max_cache_size: int
+    __metadata_service: MetadataServiceBase
 
-    def __init__(self, output_folder: str):
+    def __init__(self, output_folder: str, metadata_service: MetadataServiceBase):
         self.__output_folder = output_folder
-        self.__pngWriter = PngWriter(output_folder)
         self.__cache = dict()
         self.__cache_ids = Queue()
         self.__max_cache_size = 10  # TODO: get this from config
+        self.__metadata_service = metadata_service
 
         Path(output_folder).mkdir(parents=True, exist_ok=True)
 
@@ -66,6 +107,61 @@ class DiskImageStorage(ImageStorageBase):
             Path(os.path.join(output_folder, image_type)).mkdir(
                 parents=True, exist_ok=True
             )
+            Path(os.path.join(output_folder, image_type, "thumbnails")).mkdir(
+                parents=True, exist_ok=True
+            )
+
+    def list(
+        self, image_type: ImageType, page: int = 0, per_page: int = 10
+    ) -> PaginatedResults[ImageResponse]:
+        dir_path = os.path.join(self.__output_folder, image_type)
+        image_paths = glob(f"{dir_path}/*.png")
+        count = len(image_paths)
+
+        sorted_image_paths = sorted(
+            glob(f"{dir_path}/*.png"), key=os.path.getctime, reverse=True
+        )
+
+        page_of_image_paths = sorted_image_paths[
+            page * per_page : (page + 1) * per_page
+        ]
+
+        page_of_images: List[ImageResponse] = []
+
+        for path in page_of_image_paths:
+            filename = os.path.basename(path)
+            img = PILImage.open(path)
+
+            invokeai_metadata = self.__metadata_service.get_metadata(img)
+
+            page_of_images.append(
+                ImageResponse(
+                    image_type=image_type.value,
+                    image_name=filename,
+                    # TODO: DiskImageStorage should not be building URLs...?
+                    image_url=self.get_uri(image_type, filename),
+                    thumbnail_url=self.get_uri(image_type, filename, True),
+                    # TODO: Creation of this object should happen elsewhere (?), just making it fit here so it works
+                    metadata=ImageResponseMetadata(
+                        created=int(os.path.getctime(path)),
+                        width=img.width,
+                        height=img.height,
+                        invokeai=invokeai_metadata,
+                    ),
+                )
+            )
+
+        page_count_trunc = int(count / per_page)
+        page_count_mod = count % per_page
+        page_count = page_count_trunc if page_count_mod == 0 else page_count_trunc + 1
+
+        return PaginatedResults[ImageResponse](
+            items=page_of_images,
+            page=page,
+            pages=page_count,
+            per_page=per_page,
+            total=count,
+        )
 
     def get(self, image_type: ImageType, image_name: str) -> Image:
         image_path = self.get_path(image_type, image_name)
@@ -73,33 +169,97 @@ class DiskImageStorage(ImageStorageBase):
         if cache_item:
             return cache_item
 
-        image = Image.open(image_path)
+        image = PILImage.open(image_path)
         self.__set_cache(image_path, image)
         return image
 
     # TODO: make this a bit more flexible for e.g. cloud storage
-    def get_path(self, image_type: ImageType, image_name: str) -> str:
-        path = os.path.join(self.__output_folder, image_type, image_name)
-        return path
+    def get_path(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        # strip out any relative path shenanigans
+        basename = os.path.basename(image_name)
 
-    def save(self, image_type: ImageType, image_name: str, image: Image) -> None:
-        image_subpath = os.path.join(image_type, image_name)
-        self.__pngWriter.save_image_and_prompt_to_png(
-            image, "", image_subpath, None
-        )  # TODO: just pass full path to png writer
+        if is_thumbnail:
+            path = os.path.join(
+                self.__output_folder, image_type, "thumbnails", basename
+            )
+        else:
+            path = os.path.join(self.__output_folder, image_type, basename)
 
+        abspath = os.path.abspath(path)
+
+        return abspath
+
+    def get_uri(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        # strip out any relative path shenanigans
+        basename = os.path.basename(image_name)
+
+        if is_thumbnail:
+            thumbnail_basename = get_thumbnail_name(basename)
+            uri = f"api/v1/images/{image_type.value}/thumbnails/{thumbnail_basename}"
+        else:
+            uri = f"api/v1/images/{image_type.value}/{basename}"
+
+        return uri
+
+    def validate_path(self, path: str) -> bool:
+        try:
+            os.stat(path)
+            return True
+        except Exception:
+            return False
+
+    def save(
+        self,
+        image_type: ImageType,
+        image_name: str,
+        image: Image,
+        metadata: InvokeAIMetadata | None = None,
+    ) -> SavedImage:
         image_path = self.get_path(image_type, image_name)
+
+        # TODO: Reading the image and then saving it strips the metadata...
+        if metadata:
+            pnginfo = build_invokeai_metadata_pnginfo(metadata=metadata)
+            image.save(image_path, "PNG", pnginfo=pnginfo)
+        else:
+            image.save(image_path)  # this saved image has an empty info
+
+        thumbnail_name = get_thumbnail_name(image_name)
+        thumbnail_path = self.get_path(image_type, thumbnail_name, is_thumbnail=True)
+        thumbnail_image = make_thumbnail(image)
+        thumbnail_image.save(thumbnail_path)
+
         self.__set_cache(image_path, image)
+        self.__set_cache(thumbnail_path, thumbnail_image)
+
+        return SavedImage(
+            image_name=image_name,
+            thumbnail_name=thumbnail_name,
+            created=int(os.path.getctime(image_path)),
+        )
 
     def delete(self, image_type: ImageType, image_name: str) -> None:
-        image_path = self.get_path(image_type, image_name)
-        if os.path.exists(image_path):
-            os.remove(image_path)
+        basename = os.path.basename(image_name)
+        image_path = self.get_path(image_type, basename)
 
+        if os.path.exists(image_path):
+            send2trash(image_path)
         if image_path in self.__cache:
             del self.__cache[image_path]
 
-    def __get_cache(self, image_name: str) -> Image:
+        thumbnail_name = get_thumbnail_name(image_name)
+        thumbnail_path = self.get_path(image_type, thumbnail_name, True)
+
+        if os.path.exists(thumbnail_path):
+            send2trash(thumbnail_path)
+        if thumbnail_path in self.__cache:
+            del self.__cache[thumbnail_path]
+
+    def __get_cache(self, image_name: str) -> Image | None:
         return None if image_name not in self.__cache else self.__cache[image_name]
 
     def __set_cache(self, image_name: str, image: Image):

invokeai/app/services/invocation_queue.py

@@ -1,30 +1,17 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+import time
 from abc import ABC, abstractmethod
 from queue import Queue
-import time
+from typing import Union
+from pydantic import BaseModel, Field
 
 
-# TODO: make this serializable
-class InvocationQueueItem:
-    # session_id: str
-    graph_execution_state_id: str
-    invocation_id: str
-    invoke_all: bool
-    timestamp: float
-
-    def __init__(
-        self,
-        # session_id: str,
-        graph_execution_state_id: str,
-        invocation_id: str,
-        invoke_all: bool = False,
-    ):
-        # self.session_id = session_id
-        self.graph_execution_state_id = graph_execution_state_id
-        self.invocation_id = invocation_id
-        self.invoke_all = invoke_all
-        self.timestamp = time.time()
+class InvocationQueueItem(BaseModel):
+    graph_execution_state_id: str = Field(description="The ID of the graph execution state")
+    invocation_id: str = Field(description="The ID of the node being invoked")
+    invoke_all: bool = Field(default=False)
+    timestamp: float = Field(default_factory=time.time)
 
 
 class InvocationQueueABC(ABC):
@@ -35,7 +22,7 @@ class InvocationQueueABC(ABC):
         pass
 
     @abstractmethod
-    def put(self, item: InvocationQueueItem | None) -> None:
+    def put(self, item: Union[InvocationQueueItem, None]) -> None:
         pass
 
     @abstractmethod
@@ -70,7 +57,7 @@ class MemoryInvocationQueue(InvocationQueueABC):
 
         return item
 
-    def put(self, item: InvocationQueueItem | None) -> None:
+    def put(self, item: Union[InvocationQueueItem, None]) -> None:
         self.__queue.put(item)
 
     def cancel(self, graph_execution_state_id: str) -> None:

invokeai/app/services/invocation_services.py

@@ -1,22 +1,29 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+from invokeai.app.services.metadata import MetadataServiceBase
 from invokeai.backend import ModelManager
 
 from .events import EventServiceBase
+from .latent_storage import LatentsStorageBase
 from .image_storage import ImageStorageBase
 from .restoration_services import RestorationServices
 from .invocation_queue import InvocationQueueABC
 from .item_storage import ItemStorageABC
+from .config import InvokeAISettings
 
 class InvocationServices:
     """Services that can be used by invocations"""
 
     events: EventServiceBase
+    latents: LatentsStorageBase
     images: ImageStorageBase
+    metadata: MetadataServiceBase
     queue: InvocationQueueABC
     model_manager: ModelManager
     restoration: RestorationServices
+    configuration: InvokeAISettings
 
     # NOTE: we must forward-declare any types that include invocations, since invocations can use services
+    graph_library: ItemStorageABC["LibraryGraph"]
     graph_execution_manager: ItemStorageABC["GraphExecutionState"]
     processor: "InvocationProcessorABC"
 
@@ -24,16 +31,24 @@ class InvocationServices:
             self,
             model_manager: ModelManager,
             events: EventServiceBase,
+            latents: LatentsStorageBase,
             images: ImageStorageBase,
+            metadata: MetadataServiceBase,
             queue: InvocationQueueABC,
+            graph_library: ItemStorageABC["LibraryGraph"],
             graph_execution_manager: ItemStorageABC["GraphExecutionState"],
             processor: "InvocationProcessorABC",
             restoration: RestorationServices,
+            configuration: InvokeAISettings=None,
     ):
         self.model_manager = model_manager
         self.events = events
+        self.latents = latents
         self.images = images
+        self.metadata = metadata
         self.queue = queue
+        self.graph_library = graph_library
         self.graph_execution_manager = graph_execution_manager
         self.processor = processor
         self.restoration = restoration
+        self.configuration = configuration

invokeai/app/services/invoker.py

@@ -2,6 +2,7 @@
 
 from abc import ABC
 from threading import Event, Thread
+from typing import Union
 
 from ..invocations.baseinvocation import InvocationContext
 from .graph import Graph, GraphExecutionState
@@ -21,7 +22,7 @@ class Invoker:
 
     def invoke(
         self, graph_execution_state: GraphExecutionState, invoke_all: bool = False
-    ) -> str | None:
+    ) -> Union[str, None]:
         """Determines the next node to invoke and returns the id of the invoked node, or None if there are no nodes to execute"""
 
         # Get the next invocation
@@ -33,7 +34,6 @@ class Invoker:
         self.services.graph_execution_manager.set(graph_execution_state)
 
         # Queue the invocation
-        print(f"queueing item {invocation.id}")
         self.services.queue.put(
             InvocationQueueItem(
                 # session_id    = session.id,
@@ -45,7 +45,7 @@ class Invoker:
 
         return invocation.id
 
-    def create_execution_state(self, graph: Graph | None = None) -> GraphExecutionState:
+    def create_execution_state(self, graph: Union[Graph, None] = None) -> GraphExecutionState:
         """Creates a new execution state for the given graph"""
         new_state = GraphExecutionState(graph=Graph() if graph is None else graph)
         self.services.graph_execution_manager.set(new_state)

invokeai/app/services/latent_storage.py

@@ -0,0 +1,93 @@
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
+
+import os
+from abc import ABC, abstractmethod
+from pathlib import Path
+from queue import Queue
+from typing import Dict, Union
+
+import torch
+
+class LatentsStorageBase(ABC):
+    """Responsible for storing and retrieving latents."""
+
+    @abstractmethod
+    def get(self, name: str) -> torch.Tensor:
+        pass
+
+    @abstractmethod
+    def set(self, name: str, data: torch.Tensor) -> None:
+        pass
+
+    @abstractmethod
+    def delete(self, name: str) -> None:
+        pass
+
+
+class ForwardCacheLatentsStorage(LatentsStorageBase):
+    """Caches the latest N latents in memory, writing-thorugh to and reading from underlying storage"""
+    
+    __cache: Dict[str, torch.Tensor]
+    __cache_ids: Queue
+    __max_cache_size: int
+    __underlying_storage: LatentsStorageBase
+
+    def __init__(self, underlying_storage: LatentsStorageBase, max_cache_size: int = 20):
+        self.__underlying_storage = underlying_storage
+        self.__cache = dict()
+        self.__cache_ids = Queue()
+        self.__max_cache_size = max_cache_size
+
+    def get(self, name: str) -> torch.Tensor:
+        cache_item = self.__get_cache(name)
+        if cache_item is not None:
+            return cache_item
+
+        latent = self.__underlying_storage.get(name)
+        self.__set_cache(name, latent)
+        return latent
+
+    def set(self, name: str, data: torch.Tensor) -> None:
+        self.__underlying_storage.set(name, data)
+        self.__set_cache(name, data)
+
+    def delete(self, name: str) -> None:
+        self.__underlying_storage.delete(name)
+        if name in self.__cache:
+            del self.__cache[name]
+
+    def __get_cache(self, name: str) -> Union[torch.Tensor,None]:
+        return None if name not in self.__cache else self.__cache[name]
+
+    def __set_cache(self, name: str, data: torch.Tensor):
+        if not name in self.__cache:
+            self.__cache[name] = data
+            self.__cache_ids.put(name)
+            if self.__cache_ids.qsize() > self.__max_cache_size:
+                self.__cache.pop(self.__cache_ids.get())
+
+
+class DiskLatentsStorage(LatentsStorageBase):
+    """Stores latents in a folder on disk without caching"""
+
+    __output_folder: str
+
+    def __init__(self, output_folder: str):
+        self.__output_folder = output_folder
+        Path(output_folder).mkdir(parents=True, exist_ok=True)
+
+    def get(self, name: str) -> torch.Tensor:
+        latent_path = self.get_path(name)
+        return torch.load(latent_path)
+
+    def set(self, name: str, data: torch.Tensor) -> None:
+        latent_path = self.get_path(name)
+        torch.save(data, latent_path)
+
+    def delete(self, name: str) -> None:
+        latent_path = self.get_path(name)
+        os.remove(latent_path)
+
+    def get_path(self, name: str) -> str:
+        return os.path.join(self.__output_folder, name)
+    

invokeai/app/services/metadata.py

@@ -0,0 +1,96 @@
+import json
+from abc import ABC, abstractmethod
+from typing import Any, Dict, Optional, TypedDict
+from PIL import Image, PngImagePlugin
+from pydantic import BaseModel
+
+from invokeai.app.models.image import ImageType, is_image_type
+
+
+class MetadataImageField(TypedDict):
+    """Pydantic-less ImageField, used for metadata parsing."""
+
+    image_type: ImageType
+    image_name: str
+
+
+class MetadataLatentsField(TypedDict):
+    """Pydantic-less LatentsField, used for metadata parsing."""
+
+    latents_name: str
+
+
+# TODO: This is a placeholder for `InvocationsUnion` pending resolution of circular imports
+NodeMetadata = Dict[
+    str, str | int | float | bool | MetadataImageField | MetadataLatentsField
+]
+
+
+class InvokeAIMetadata(TypedDict, total=False):
+    """InvokeAI-specific metadata format."""
+
+    session_id: Optional[str]
+    node: Optional[NodeMetadata]
+
+
+def build_invokeai_metadata_pnginfo(
+    metadata: InvokeAIMetadata | None,
+) -> PngImagePlugin.PngInfo:
+    """Builds a PngInfo object with key `"invokeai"` and value `metadata`"""
+    pnginfo = PngImagePlugin.PngInfo()
+
+    if metadata is not None:
+        pnginfo.add_text("invokeai", json.dumps(metadata))
+
+    return pnginfo
+
+
+class MetadataServiceBase(ABC):
+    @abstractmethod
+    def get_metadata(self, image: Image.Image) -> InvokeAIMetadata | None:
+        """Gets the InvokeAI metadata from a PIL Image, skipping invalid values"""
+        pass
+
+    @abstractmethod
+    def build_metadata(
+        self, session_id: str, node: BaseModel
+    ) -> InvokeAIMetadata | None:
+        """Builds an InvokeAIMetadata object"""
+        pass
+
+
+class PngMetadataService(MetadataServiceBase):
+    """Handles loading and building metadata for images."""
+
+    # TODO: Use `InvocationsUnion` to **validate** metadata as representing a fully-functioning node
+    def _load_metadata(self, image: Image.Image) -> dict | None:
+        """Loads a specific info entry from a PIL Image."""
+
+        try:
+            info = image.info.get("invokeai")
+
+            if type(info) is not str:
+                return None
+
+            loaded_metadata = json.loads(info)
+
+            if type(loaded_metadata) is not dict:
+                return None
+
+            if len(loaded_metadata.items()) == 0:
+                return None
+
+            return loaded_metadata
+        except:
+            return None
+
+    def get_metadata(self, image: Image.Image) -> dict | None:
+        """Retrieves an image's metadata as a dict"""
+        loaded_metadata = self._load_metadata(image)
+
+        return loaded_metadata
+
+    def build_metadata(self, session_id: str, node: BaseModel) -> InvokeAIMetadata:
+        metadata = InvokeAIMetadata(session_id=session_id, node=node.dict())
+
+        return metadata

invokeai/app/services/model_manager_initializer.py

@@ -7,21 +7,20 @@ from omegaconf import OmegaConf
 from pathlib import Path
 
 import invokeai.version
+from .config import InvokeAISettings
 from ...backend import ModelManager
 from ...backend.util import choose_precision, choose_torch_device
-from ...backend import Globals
 
 # TODO: Replace with an abstract class base ModelManagerBase
-def get_model_manager(config: Args) -> ModelManager:
-    if not config.conf:
-        config_file = os.path.join(Globals.root, "configs", "models.yaml")
-        if not os.path.exists(config_file):
-            report_model_error(
-                config, FileNotFoundError(f"The file {config_file} could not be found.")
-            )
+def get_model_manager(config:InvokeAISettings) -> ModelManager:
+    model_config = config.model_conf_path
+    if not model_config.exists():
+        report_model_error(
+            config, FileNotFoundError(f"The file {model_config} could not be found.")
+        )
 
     print(f">> {invokeai.version.__app_name__}, version {invokeai.version.__version__}")
-    print(f'>> InvokeAI runtime directory is "{Globals.root}"')
+    print(f'>> InvokeAI runtime directory is "{config.root_dir}"')
 
     # these two lines prevent a horrible warning message from appearing
     # when the frozen CLIP tokenizer is imported
@@ -31,20 +30,7 @@ def get_model_manager(config: Args) -> ModelManager:
     import diffusers
 
     diffusers.logging.set_verbosity_error()
-
-    # normalize the config directory relative to root
-    if not os.path.isabs(config.conf):
-        config.conf = os.path.normpath(os.path.join(Globals.root, config.conf))
-
-    if config.embeddings:
-        if not os.path.isabs(config.embedding_path):
-            embedding_path = os.path.normpath(
-                os.path.join(Globals.root, config.embedding_path)
-            )
-        else:
-            embedding_path = config.embedding_path
-    else:
-        embedding_path = None
+    embedding_path = config.embedding_path
 
     # migrate legacy models
     ModelManager.migrate_models()
@@ -57,11 +43,11 @@ def get_model_manager(config: Args) -> ModelManager:
         else choose_precision(device)
         
         model_manager = ModelManager(
-            OmegaConf.load(config.conf),
+            OmegaConf.load(model_config),
             precision=precision,
             device_type=device,
             max_loaded_models=config.max_loaded_models,
-            embedding_path = Path(embedding_path),
+            embedding_path = embedding_path,
         )
     except (FileNotFoundError, TypeError, AssertionError) as e:
         report_model_error(config, e)
@@ -71,12 +57,10 @@ def get_model_manager(config: Args) -> ModelManager:
 
     # try to autoconvert new models
     # autoimport new .ckpt files
-    if path := config.autoconvert:
-        model_manager.autoconvert_weights(
-            conf_path=config.conf,
-            weights_directory=path,
+    if config.autoconvert_path:
+        model_manager.heuristic_import(
+            config.autoconvert_path,
         )
-
     return model_manager
 
 def report_model_error(opt: Namespace, e: Exception):

invokeai/app/services/processor.py

@@ -4,7 +4,7 @@ from threading import Event, Thread
 from ..invocations.baseinvocation import InvocationContext
 from .invocation_queue import InvocationQueueItem
 from .invoker import InvocationProcessorABC, Invoker
-from ..util.util import CanceledException
+from ..models.exceptions import CanceledException
 
 class DefaultInvocationProcessor(InvocationProcessorABC):
     __invoker_thread: Thread
@@ -43,10 +43,14 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     queue_item.invocation_id
                 )
 
+                # get the source node id to provide to clients (the prepared node id is not as useful)
+                source_node_id = graph_execution_state.prepared_source_mapping[invocation.id]
+
                 # Send starting event
                 self.__invoker.services.events.emit_invocation_started(
                     graph_execution_state_id=graph_execution_state.id,
-                    invocation_id=invocation.id,
+                    node=invocation.dict(),
+                    source_node_id=source_node_id
                 )
 
                 # Invoke
@@ -75,7 +79,8 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # Send complete event
                     self.__invoker.services.events.emit_invocation_complete(
                         graph_execution_state_id=graph_execution_state.id,
-                        invocation_id=invocation.id,
+                        node=invocation.dict(),
+                        source_node_id=source_node_id,
                         result=outputs.dict(),
                     )
 
@@ -99,7 +104,8 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # Send error event
                     self.__invoker.services.events.emit_invocation_error(
                         graph_execution_state_id=graph_execution_state.id,
-                        invocation_id=invocation.id,
+                        node=invocation.dict(),
+                        source_node_id=source_node_id,
                         error=error,
                     )
 

invokeai/app/services/sqlite.py

@@ -59,6 +59,7 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
                 f"""INSERT OR REPLACE INTO {self._table_name} (item) VALUES (?);""",
                 (item.json(),),
             )
+            self._conn.commit()
         finally:
             self._lock.release()
         self._on_changed(item)
@@ -84,6 +85,7 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
             self._cursor.execute(
                 f"""DELETE FROM {self._table_name} WHERE id = ?;""", (str(id),)
             )
+            self._conn.commit()
         finally:
             self._lock.release()
         self._on_deleted(id)

invokeai/app/util/misc.py

@@ -0,0 +1,5 @@
+import datetime
+
+
+def get_timestamp():
+    return int(datetime.datetime.now(datetime.timezone.utc).timestamp())

invokeai/app/util/step_callback.py

@@ -0,0 +1,55 @@
+from invokeai.app.api.models.images import ProgressImage
+from invokeai.app.models.exceptions import CanceledException
+from ..invocations.baseinvocation import InvocationContext
+from ...backend.util.util import image_to_dataURL
+from ...backend.generator.base import Generator
+from ...backend.stable_diffusion import PipelineIntermediateState
+
+
+def stable_diffusion_step_callback(
+    context: InvocationContext,
+    intermediate_state: PipelineIntermediateState,
+    node: dict,
+    source_node_id: str,
+):
+    if context.services.queue.is_canceled(context.graph_execution_state_id):
+        raise CanceledException
+
+    # Some schedulers report not only the noisy latents at the current timestep,
+    # but also their estimate so far of what the de-noised latents will be. Use
+    # that estimate if it is available.
+    if intermediate_state.predicted_original is not None:
+        sample = intermediate_state.predicted_original
+    else:
+        sample = intermediate_state.latents
+
+    # TODO: This does not seem to be needed any more?
+    # # txt2img provides a Tensor in the step_callback
+    # # img2img provides a PipelineIntermediateState
+    # if isinstance(sample, PipelineIntermediateState):
+    #     # this was an img2img
+    #     print('img2img')
+    #     latents = sample.latents
+    #     step = sample.step
+    # else:
+    #     print('txt2img')
+    #     latents = sample
+    #     step = intermediate_state.step
+
+    # TODO: only output a preview image when requested
+    image = Generator.sample_to_lowres_estimated_image(sample)
+
+    (width, height) = image.size
+    width *= 8
+    height *= 8
+
+    dataURL = image_to_dataURL(image, image_format="JPEG")
+
+    context.services.events.emit_generator_progress(
+        graph_execution_state_id=context.graph_execution_state_id,
+        node=node,
+        source_node_id=source_node_id,
+        progress_image=ProgressImage(width=width, height=height, dataURL=dataURL),
+        step=intermediate_state.step,
+        total_steps=node["steps"],
+    )

invokeai/app/util/thumbnails.py

@@ -0,0 +1,15 @@
+import os
+from PIL import Image
+
+
+def get_thumbnail_name(image_name: str) -> str:
+    """Formats given an image name, returns the appropriate thumbnail image name"""
+    thumbnail_name = os.path.splitext(image_name)[0] + ".webp"
+    return thumbnail_name
+
+
+def make_thumbnail(image: Image.Image, size: int = 256) -> Image.Image:
+    """Makes a thumbnail from a PIL Image"""
+    thumbnail = image.copy()
+    thumbnail.thumbnail(size=(size, size))
+    return thumbnail

invokeai/app/util/util.py

@@ -1,42 +0,0 @@
-import torch
-from PIL import Image
-from ..invocations.baseinvocation import InvocationContext
-from ...backend.util.util import image_to_dataURL
-from ...backend.generator.base import Generator
-from ...backend.stable_diffusion import PipelineIntermediateState
-
-class CanceledException(Exception):
-    pass
-
-def fast_latents_step_callback(sample: torch.Tensor, step: int, steps: int, id: str, context: InvocationContext, ):
-    # TODO: only output a preview image when requested
-    image = Generator.sample_to_lowres_estimated_image(sample)
-
-    (width, height) = image.size
-    width *= 8
-    height *= 8
-
-    dataURL = image_to_dataURL(image, image_format="JPEG")
-
-    context.services.events.emit_generator_progress(
-        context.graph_execution_state_id,
-        id,
-        {
-            "width": width,
-            "height": height,
-            "dataURL": dataURL
-        },
-        step,
-        steps,
-    )
-
-def diffusers_step_callback_adapter(*cb_args, **kwargs):
-    """
-    txt2img gives us a Tensor in the step_callbak, while img2img gives us a PipelineIntermediateState.
-    This adapter grabs the needed data and passes it along to the callback function.
-    """
-    if isinstance(cb_args[0], PipelineIntermediateState):
-        progress_state: PipelineIntermediateState = cb_args[0]
-        return fast_latents_step_callback(progress_state.latents, progress_state.step, **kwargs)
-    else:
-        return fast_latents_step_callback(*cb_args, **kwargs)

invokeai/backend/__init__.py

@@ -10,7 +10,7 @@ from .generator import (
     Img2Img,
     Inpaint
 )
-from .model_management import ModelManager
+from .model_management import ModelManager, SDModelComponent
 from .safety_checker import SafetyChecker
 from .args import Args
 from .globals import Globals

invokeai/backend/args.py

@@ -561,7 +561,7 @@ class Args(object):
             "--autoimport",
             default=None,
             type=str,
-            help="Check the indicated directory for .ckpt/.safetensors weights files at startup and import directly",
+            help="(DEPRECATED - NONFUNCTIONAL). Check the indicated directory for .ckpt/.safetensors weights files at startup and import directly",
         )
         model_group.add_argument(
             "--autoconvert",

invokeai/backend/config/model_install_backend.py

@@ -67,7 +67,6 @@ def install_requested_models(
     scan_directory: Path = None,
     external_models: List[str] = None,
     scan_at_startup: bool = False,
-    convert_to_diffusers: bool = False,
     precision: str = "float16",
     purge_deleted: bool = False,
     config_file_path: Path = None,
@@ -113,7 +112,6 @@ def install_requested_models(
             try:
                 model_manager.heuristic_import(
                     path_url_or_repo,
-                    convert=convert_to_diffusers,
                     commit_to_conf=config_file_path,
                 )
             except KeyboardInterrupt:
@@ -122,7 +120,7 @@ def install_requested_models(
                 pass
 
     if scan_at_startup and scan_directory.is_dir():
-        argument = "--autoconvert" if convert_to_diffusers else "--autoimport"
+        argument = "--autoconvert"
         initfile = Path(Globals.root, Globals.initfile)
         replacement = Path(Globals.root, f"{Globals.initfile}.new")
         directory = str(scan_directory).replace("\\", "/")

invokeai/backend/globals.py

@@ -16,6 +16,7 @@ import os.path as osp
 from argparse import Namespace
 from pathlib import Path
 from typing import Union
+from pydantic import BaseSettings
 
 Globals = Namespace()
 
@@ -120,3 +121,15 @@ def global_cache_dir(subdir: Union[str, Path] = "") -> Path:
         return Path(home, subdir)
     else:
         return Path(Globals.root, "models", subdir)
+
+def copy_conf_to_globals(conf: Union[dict,BaseSettings]):
+    '''
+    Given a dict or dict-like object, copy its keys and
+    values into the Globals Namespace. This is a transitional
+    workaround until we remove Globals entirely.
+    '''
+    if isinstance(conf,BaseSettings):
+        conf = conf.dict()
+    for key in conf.keys():
+        if key is not None:
+            setattr(Globals,key,conf[key])

invokeai/backend/model_management/__init__.py

@@ -5,5 +5,7 @@ from .convert_ckpt_to_diffusers import (
     convert_ckpt_to_diffusers,
     load_pipeline_from_original_stable_diffusion_ckpt,
 )
-from .model_manager import ModelManager
+from .model_manager import ModelManager,SDModelComponent
+
+
 

invokeai/backend/model_management/model_manager.py

@@ -1,4 +1,4 @@
-"""
+"""enum
 Manage a cache of Stable Diffusion model files for fast switching.
 They are moved between GPU and CPU as necessary. If CPU memory falls
 below a preset minimum, the least recently used model will be
@@ -15,7 +15,7 @@ import sys
 import textwrap
 import time
 import warnings
-from enum import Enum
+from enum import Enum, auto
 from pathlib import Path
 from shutil import move, rmtree
 from typing import Any, Optional, Union, Callable
@@ -24,8 +24,12 @@ import safetensors
 import safetensors.torch
 import torch
 import transformers
-from diffusers import AutoencoderKL
-from diffusers import logging as dlogging
+from diffusers import (
+    AutoencoderKL,
+    UNet2DConditionModel,
+    SchedulerMixin,
+    logging as dlogging,
+)    
 from huggingface_hub import scan_cache_dir
 from omegaconf import OmegaConf
 from omegaconf.dictconfig import DictConfig
@@ -33,37 +37,58 @@ from picklescan.scanner import scan_file_path
 
 from invokeai.backend.globals import Globals, global_cache_dir
 
-from ..stable_diffusion import StableDiffusionGeneratorPipeline
+from transformers import (
+    CLIPTextModel,
+    CLIPTokenizer,
+    CLIPFeatureExtractor,
+)
+from diffusers.pipelines.stable_diffusion.safety_checker import (
+    StableDiffusionSafetyChecker,
+    )
+from ..stable_diffusion import (
+    StableDiffusionGeneratorPipeline,
+)
 from ..util import CUDA_DEVICE, ask_user, download_with_resume
 
-class SDLegacyType(Enum):
-    V1 = 1
-    V1_INPAINT = 2
-    V2   = 3
-    V2_e = 4
-    V2_v = 5
-    UNKNOWN = 99
 
+class SDLegacyType(Enum):
+    V1 = auto()
+    V1_INPAINT = auto()
+    V2 = auto()
+    V2_e = auto()
+    V2_v = auto()
+    UNKNOWN = auto()
+
+class SDModelComponent(Enum):
+    vae="vae"
+    text_encoder="text_encoder"
+    tokenizer="tokenizer"
+    unet="unet"
+    scheduler="scheduler"
+    safety_checker="safety_checker"
+    feature_extractor="feature_extractor"
+    
 DEFAULT_MAX_MODELS = 2
 
 class ModelManager(object):
-    '''
+    """
     Model manager handles loading, caching, importing, deleting, converting, and editing models.
-    '''
+    """
+
     def __init__(
-            self,
-            config: OmegaConf|Path,
-            device_type: torch.device = CUDA_DEVICE,
-            precision: str = "float16",
-            max_loaded_models=DEFAULT_MAX_MODELS,
-            sequential_offload=False,
-            embedding_path: Path=None,
+        self,
+        config: OmegaConf | Path,
+        device_type: torch.device = CUDA_DEVICE,
+        precision: str = "float16",
+        max_loaded_models=DEFAULT_MAX_MODELS,
+        sequential_offload=False,
+        embedding_path: Path = None,
     ):
         """
         Initialize with the path to the models.yaml config file or
         an initialized OmegaConf dictionary. Optional parameters
         are the torch device type, precision, max_loaded_models,
-        and sequential_offload boolean. Note that the default device 
+        and sequential_offload boolean. Note that the default device
         type and precision are set up for a CUDA system running at half precision.
         """
         # prevent nasty-looking CLIP log message
@@ -87,15 +112,25 @@ class ModelManager(object):
         """
         return model_name in self.config
 
-    def get_model(self, model_name: str=None)->dict:
-        """
-        Given a model named identified in models.yaml, return
-        the model object. If in RAM will load into GPU VRAM.
-        If on disk, will load from there.
+    def get_model(self, model_name: str = None) -> dict:
+        """Given a model named identified in models.yaml, return a dict
+        containing the model object and some of its key features. If
+        in RAM will load into GPU VRAM.  If on disk, will load from
+        there.
+        The dict has the following keys:
+        'model': The StableDiffusionGeneratorPipeline object
+        'model_name': The name of the model in models.yaml
+        'width': The width of images trained by this model
+        'height': The height of images trained by this model
+        'hash': A unique hash of this model's files on disk.
         """
         if not model_name:
-            return self.get_model(self.current_model) if self.current_model else self.get_model(self.default_model())
-        
+            return (
+                self.get_model(self.current_model)
+                if self.current_model
+                else self.get_model(self.default_model())
+            )
+
         if not self.valid_model(model_name):
             print(
                 f'** "{model_name}" is not a known model name. Please check your models.yaml file'
@@ -135,6 +170,81 @@ class ModelManager(object):
             "hash": hash,
         }
 
+    def get_model_vae(self, model_name: str=None)->AutoencoderKL:
+        """Given a model name identified in models.yaml, load the model into
+        GPU if necessary and return its assigned VAE as an
+        AutoencoderKL object. If no model name is provided, return the
+        vae from the model currently in the GPU.
+        """
+        return self._get_sub_model(model_name, SDModelComponent.vae)
+                                   
+    def get_model_tokenizer(self, model_name: str=None)->CLIPTokenizer:
+        """Given a model name identified in models.yaml, load the model into
+        GPU if necessary and return its assigned CLIPTokenizer. If no
+        model name is provided, return the tokenizer from the model
+        currently in the GPU.
+        """
+        return self._get_sub_model(model_name, SDModelComponent.tokenizer)
+                                   
+    def get_model_unet(self, model_name: str=None)->UNet2DConditionModel:
+        """Given a model name identified in models.yaml, load the model into
+        GPU if necessary and return its assigned UNet2DConditionModel. If no model
+        name is provided, return the UNet from the model
+        currently in the GPU.  
+        """
+        return self._get_sub_model(model_name, SDModelComponent.unet)
+
+    def get_model_text_encoder(self, model_name: str=None)->CLIPTextModel:
+        """Given a model name identified in models.yaml, load the model into
+        GPU if necessary and return its assigned CLIPTextModel. If no
+        model name is provided, return the text encoder from the model
+        currently in the GPU.
+        """
+        return self._get_sub_model(model_name, SDModelComponent.text_encoder)
+
+    def get_model_feature_extractor(self, model_name: str=None)->CLIPFeatureExtractor:
+        """Given a model name identified in models.yaml, load the model into
+        GPU if necessary and return its assigned CLIPFeatureExtractor. If no
+        model name is provided, return the text encoder from the model
+        currently in the GPU.
+        """
+        return self._get_sub_model(model_name, SDModelComponent.feature_extractor)
+
+    def get_model_scheduler(self, model_name: str=None)->SchedulerMixin:
+        """Given a model name identified in models.yaml, load the model into
+        GPU if necessary and return its assigned scheduler. If no
+        model name is provided, return the text encoder from the model
+        currently in the GPU.
+        """
+        return self._get_sub_model(model_name, SDModelComponent.scheduler)
+    
+    def _get_sub_model(
+            self,
+            model_name: str=None,
+            model_part: SDModelComponent=SDModelComponent.vae,
+    ) -> Union[
+        AutoencoderKL,
+        CLIPTokenizer,
+        CLIPFeatureExtractor,
+        UNet2DConditionModel,
+        CLIPTextModel,
+        StableDiffusionSafetyChecker,
+    ]:
+        """Given a model name identified in models.yaml, and the part of the
+        model you wish to retrieve, return that part. Parts are in an Enum
+        class named SDModelComponent, and consist of:
+        SDModelComponent.vae
+        SDModelComponent.text_encoder
+        SDModelComponent.tokenizer
+        SDModelComponent.unet
+        SDModelComponent.scheduler
+        SDModelComponent.safety_checker
+        SDModelComponent.feature_extractor
+        """
+        model_dict = self.get_model(model_name)
+        model = model_dict["model"]
+        return getattr(model, model_part.value)
+
     def default_model(self) -> str | None:
         """
         Returns the name of the default model, or None
@@ -360,7 +470,7 @@ class ModelManager(object):
                 f"Unknown model format {model_name}: {model_format}"
             )
         self._add_embeddings_to_model(model)
-        
+
         # usage statistics
         toc = time.time()
         print(">> Model loaded in", "%4.2fs" % (toc - tic))
@@ -433,7 +543,7 @@ class ModelManager(object):
         width = pipeline.unet.config.sample_size * pipeline.vae_scale_factor
         height = width
         print(f"   | Default image dimensions = {width} x {height}")
-        
+
         return pipeline, width, height, model_hash
 
     def _load_ckpt_model(self, model_name, mconfig):
@@ -454,14 +564,18 @@ class ModelManager(object):
         from . import load_pipeline_from_original_stable_diffusion_ckpt
 
         try:
-            if self.list_models()[self.current_model]['status'] == 'active':
+            if self.list_models()[self.current_model]["status"] == "active":
                 self.offload_model(self.current_model)
         except Exception as e:
             pass
-        
+
         vae_path = None
         if vae:
-            vae_path = vae if os.path.isabs(vae) else os.path.normpath(os.path.join(Globals.root, vae))
+            vae_path = (
+                vae
+                if os.path.isabs(vae)
+                else os.path.normpath(os.path.join(Globals.root, vae))
+            )
         if self._has_cuda():
             torch.cuda.empty_cache()
         pipeline = load_pipeline_from_original_stable_diffusion_ckpt(
@@ -571,9 +685,7 @@ class ModelManager(object):
         models.yaml file.
         """
         model_name = model_name or Path(repo_or_path).stem
-        model_description = (
-            description or f"Imported diffusers model {model_name}"
-        )
+        model_description = description or f"Imported diffusers model {model_name}"
         new_config = dict(
             description=model_description,
             vae=vae,
@@ -602,7 +714,7 @@ class ModelManager(object):
         SDLegacyType.V2_v   (V2 using 'v_prediction' prediction type)
         SDLegacyType.UNKNOWN
         """
-        global_step = checkpoint.get('global_step')
+        global_step = checkpoint.get("global_step")
         state_dict = checkpoint.get("state_dict") or checkpoint
 
         try:
@@ -628,13 +740,13 @@ class ModelManager(object):
             return SDLegacyType.UNKNOWN
 
     def heuristic_import(
-            self,
-            path_url_or_repo: str,
-            model_name: str = None,
-            description: str = None,
-            model_config_file: Path = None,
-            commit_to_conf: Path = None,
-            config_file_callback: Callable[[Path], Path] = None,
+        self,
+        path_url_or_repo: str,
+        model_name: str = None,
+        description: str = None,
+        model_config_file: Path = None,
+        commit_to_conf: Path = None,
+        config_file_callback: Callable[[Path], Path] = None,
     ) -> str:
         """Accept a string which could be:
            - a HF diffusers repo_id
@@ -738,8 +850,8 @@ class ModelManager(object):
 
         # another round of heuristics to guess the correct config file.
         checkpoint = None
-        if model_path.suffix in [".ckpt",".pt"]:
-            self.scan_model(model_path,model_path)
+        if model_path.suffix in [".ckpt", ".pt"]:
+            self.scan_model(model_path, model_path)
             checkpoint = torch.load(model_path)
         else:
             checkpoint = safetensors.torch.load_file(model_path)
@@ -761,19 +873,16 @@ class ModelManager(object):
                 elif model_type == SDLegacyType.V1_INPAINT:
                     print("   | SD-v1 inpainting model detected")
                     model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v1-inpainting-inference.yaml"
+                        Globals.root,
+                        "configs/stable-diffusion/v1-inpainting-inference.yaml",
                     )
                 elif model_type == SDLegacyType.V2_v:
-                    print(
-                        "   | SD-v2-v model detected"
-                    )
+                    print("   | SD-v2-v model detected")
                     model_config_file = Path(
                         Globals.root, "configs/stable-diffusion/v2-inference-v.yaml"
                     )
                 elif model_type == SDLegacyType.V2_e:
-                    print(
-                        "   | SD-v2-e model detected"
-                    )
+                    print("   | SD-v2-e model detected")
                     model_config_file = Path(
                         Globals.root, "configs/stable-diffusion/v2-inference.yaml"
                     )
@@ -820,16 +929,16 @@ class ModelManager(object):
         return model_name
 
     def convert_and_import(
-            self,
-            ckpt_path: Path,
-            diffusers_path: Path,
-            model_name=None,
-            model_description=None,
-            vae:dict=None,
-            vae_path:Path=None,
-            original_config_file: Path = None,
-            commit_to_conf: Path = None,
-            scan_needed: bool=True,
+        self,
+        ckpt_path: Path,
+        diffusers_path: Path,
+        model_name=None,
+        model_description=None,
+        vae: dict = None,
+        vae_path: Path = None,
+        original_config_file: Path = None,
+        commit_to_conf: Path = None,
+        scan_needed: bool = True,
     ) -> str:
         """
         Convert a legacy ckpt weights file to diffuser model and import
@@ -857,10 +966,10 @@ class ModelManager(object):
         try:
             # By passing the specified VAE to the conversion function, the autoencoder
             # will be built into the model rather than tacked on afterward via the config file
-            vae_model=None
+            vae_model = None
             if vae:
-                vae_model=self._load_vae(vae)
-                vae_path=None
+                vae_model = self._load_vae(vae)
+                vae_path = None
             convert_ckpt_to_diffusers(
                 ckpt_path,
                 diffusers_path,
@@ -976,16 +1085,16 @@ class ModelManager(object):
         legacy_locations = [
             Path(
                 models_dir,
-                "CompVis/stable-diffusion-safety-checker/models--CompVis--stable-diffusion-safety-checker"
+                "CompVis/stable-diffusion-safety-checker/models--CompVis--stable-diffusion-safety-checker",
             ),
             Path(models_dir, "bert-base-uncased/models--bert-base-uncased"),
             Path(
                 models_dir,
-                "openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14"
+                "openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14",
             ),
         ]
-        legacy_locations.extend(list(global_cache_dir("diffusers").glob('*')))
-        
+        legacy_locations.extend(list(global_cache_dir("diffusers").glob("*")))
+
         legacy_layout = False
         for model in legacy_locations:
             legacy_layout = legacy_layout or model.exists()
@@ -1003,7 +1112,7 @@ class ModelManager(object):
 >> make adjustments, please press ctrl-C now to abort and relaunch InvokeAI when you are ready.
 >> Otherwise press <enter> to continue."""
         )
-        input('continue> ')
+        input("continue> ")
 
         # transformer files get moved into the hub directory
         if cls._is_huggingface_hub_directory_present():
@@ -1090,12 +1199,12 @@ class ModelManager(object):
             print(
                 f'>> Textual inversion triggers: {", ".join(sorted(model.textual_inversion_manager.get_all_trigger_strings()))}'
             )
-            
+
     def _has_cuda(self) -> bool:
         return self.device.type == "cuda"
 
     def _diffuser_sha256(
-        self, name_or_path: Union[str, Path], chunksize=4096
+        self, name_or_path: Union[str, Path], chunksize=16777216
     ) -> Union[str, bytes]:
         path = None
         if isinstance(name_or_path, Path):

invokeai/backend/stable_diffusion/concepts_lib.py

@@ -57,7 +57,7 @@ class HuggingFaceConceptsLibrary(object):
                 self.concept_list.extend(list(local_concepts_to_add))
                 return self.concept_list
             return self.concept_list
-        else:
+        elif Globals.internet_available is True:
             try:
                 models = self.hf_api.list_models(
                     filter=ModelFilter(model_name="sd-concepts-library/")
@@ -73,6 +73,8 @@ class HuggingFaceConceptsLibrary(object):
                     " ** You may load .bin and .pt file(s) manually using the --embedding_directory argument."
                 )
             return self.concept_list
+        else: 
+            return self.concept_list
 
     def get_concept_model_path(self, concept_name: str) -> str:
         """

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -445,8 +445,15 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
     @property
     def _submodels(self) -> Sequence[torch.nn.Module]:
         module_names, _, _ = self.extract_init_dict(dict(self.config))
-        values = [getattr(self, name) for name in module_names.keys()]
-        return [m for m in values if isinstance(m, torch.nn.Module)]
+        submodels = []
+        for name in module_names.keys():
+            if hasattr(self, name):
+                value = getattr(self, name)
+            else:
+                value = getattr(self.config, name)
+            if isinstance(value, torch.nn.Module):
+                submodels.append(value)
+        return submodels
 
     def image_from_embeddings(
         self,
@@ -544,7 +551,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             yield PipelineIntermediateState(
                 run_id=run_id,
                 step=-1,
-                timestep=self.scheduler.num_train_timesteps,
+                timestep=self.scheduler.config.num_train_timesteps,
                 latents=latents,
             )
 
@@ -915,7 +922,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
     @property
     def channels(self) -> int:
         """Compatible with DiffusionWrapper"""
-        return self.unet.in_channels
+        return self.unet.config.in_channels
 
     def decode_latents(self, latents):
         # Explicit call to get the vae loaded, since `decode` isn't the forward method.

invokeai/backend/stable_diffusion/diffusion/cross_attention_control.py

@@ -10,8 +10,7 @@ import diffusers
 import psutil
 import torch
 from compel.cross_attention_control import Arguments
-from diffusers.models.cross_attention import AttnProcessor
-from diffusers.models.unet_2d_condition import UNet2DConditionModel
+from diffusers.models.attention_processor import AttentionProcessor
 from torch import nn
 
 from ...util import torch_dtype
@@ -188,7 +187,7 @@ class Context:
 
 class InvokeAICrossAttentionMixin:
     """
-    Enable InvokeAI-flavoured CrossAttention calculation, which does aggressive low-memory slicing and calls
+    Enable InvokeAI-flavoured Attention calculation, which does aggressive low-memory slicing and calls
     through both to an attention_slice_wrangler and a slicing_strategy_getter for custom attention map wrangling
     and dymamic slicing strategy selection.
     """
@@ -209,7 +208,7 @@ class InvokeAICrossAttentionMixin:
         Set custom attention calculator to be called when attention is calculated
         :param wrangler: Callback, with args (module, suggested_attention_slice, dim, offset, slice_size),
         which returns either the suggested_attention_slice or an adjusted equivalent.
-            `module` is the current CrossAttention module for which the callback is being invoked.
+            `module` is the current Attention module for which the callback is being invoked.
             `suggested_attention_slice` is the default-calculated attention slice
             `dim` is -1 if the attenion map has not been sliced, or 0 or 1 for dimension-0 or dimension-1 slicing.
                 If `dim` is >= 0, `offset` and `slice_size` specify the slice start and length.
@@ -345,11 +344,11 @@ class InvokeAICrossAttentionMixin:
 def restore_default_cross_attention(
     model,
     is_running_diffusers: bool,
-    restore_attention_processor: Optional[AttnProcessor] = None,
+    restore_attention_processor: Optional[AttentionProcessor] = None,
 ):
     if is_running_diffusers:
         unet = model
-        unet.set_attn_processor(restore_attention_processor or CrossAttnProcessor())
+        unet.set_attn_processor(restore_attention_processor or AttnProcessor())
     else:
         remove_attention_function(model)
 
@@ -408,12 +407,9 @@ def override_cross_attention(model, context: Context, is_running_diffusers=False
 def get_cross_attention_modules(
     model, which: CrossAttentionType
 ) -> list[tuple[str, InvokeAICrossAttentionMixin]]:
-    from ldm.modules.attention import CrossAttention  # avoid circular import
 
     cross_attention_class: type = (
         InvokeAIDiffusersCrossAttention
-        if isinstance(model, UNet2DConditionModel)
-        else CrossAttention
     )
     which_attn = "attn1" if which is CrossAttentionType.SELF else "attn2"
     attention_module_tuples = [
@@ -428,10 +424,10 @@ def get_cross_attention_modules(
         print(
             f"Error! CrossAttentionControl found an unexpected number of {cross_attention_class} modules in the model "
             + f"(expected {expected_count}, found {cross_attention_modules_in_model_count}). Either monkey-patching failed "
-            + f"or some assumption has changed about the structure of the model itself. Please fix the monkey-patching, "
+            + "or some assumption has changed about the structure of the model itself. Please fix the monkey-patching, "
             + f"and/or update the {expected_count} above to an appropriate number, and/or find and inform someone who knows "
-            + f"what it means. This error is non-fatal, but it is likely that .swap() and attention map display will not "
-            + f"work properly until it is fixed."
+            + "what it means. This error is non-fatal, but it is likely that .swap() and attention map display will not "
+            + "work properly until it is fixed."
         )
     return attention_module_tuples
 
@@ -550,7 +546,7 @@ def get_mem_free_total(device):
 
 
 class InvokeAIDiffusersCrossAttention(
-    diffusers.models.attention.CrossAttention, InvokeAICrossAttentionMixin
+    diffusers.models.attention.Attention, InvokeAICrossAttentionMixin
 ):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -572,8 +568,8 @@ class InvokeAIDiffusersCrossAttention(
 """
 # base implementation
 
-class CrossAttnProcessor:
-    def __call__(self, attn: CrossAttention, hidden_states, encoder_hidden_states=None, attention_mask=None):
+class AttnProcessor:
+    def __call__(self, attn: Attention, hidden_states, encoder_hidden_states=None, attention_mask=None):
         batch_size, sequence_length, _ = hidden_states.shape
         attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length)
 
@@ -601,9 +597,9 @@ class CrossAttnProcessor:
 from dataclasses import dataclass, field
 
 import torch
-from diffusers.models.cross_attention import (
-    CrossAttention,
-    CrossAttnProcessor,
+from diffusers.models.attention_processor import (
+    Attention,
+    AttnProcessor,
     SlicedAttnProcessor,
 )
 
@@ -653,7 +649,7 @@ class SlicedSwapCrossAttnProcesser(SlicedAttnProcessor):
 
     def __call__(
         self,
-        attn: CrossAttention,
+        attn: Attention,
         hidden_states,
         encoder_hidden_states=None,
         attention_mask=None,

invokeai/backend/stable_diffusion/diffusion/shared_invokeai_diffusion.py

@@ -5,7 +5,7 @@ from typing import Any, Callable, Dict, Optional, Union
 
 import numpy as np
 import torch
-from diffusers.models.cross_attention import AttnProcessor
+from diffusers.models.attention_processor import AttentionProcessor
 from typing_extensions import TypeAlias
 
 from invokeai.backend.globals import Globals
@@ -101,7 +101,7 @@ class InvokeAIDiffuserComponent:
 
     def override_cross_attention(
         self, conditioning: ExtraConditioningInfo, step_count: int
-    ) -> Dict[str, AttnProcessor]:
+    ) -> Dict[str, AttentionProcessor]:
         """
         setup cross attention .swap control. for diffusers this replaces the attention processor, so
         the previous attention processor is returned so that the caller can restore it later.
@@ -118,7 +118,7 @@ class InvokeAIDiffuserComponent:
         )
 
     def restore_default_cross_attention(
-        self, restore_attention_processor: Optional["AttnProcessor"] = None
+        self, restore_attention_processor: Optional["AttentionProcessor"] = None
     ):
         self.conditioning = None
         self.cross_attention_control_context = None
@@ -262,7 +262,7 @@ class InvokeAIDiffuserComponent:
             # TODO remove when compvis codepath support is dropped
             if step_index is None and sigma is None:
                 raise ValueError(
-                    f"Either step_index or sigma is required when doing cross attention control, but both are None."
+                    "Either step_index or sigma is required when doing cross attention control, but both are None."
                 )
             percent_through = self.estimate_percent_through(step_index, sigma)
         return percent_through
@@ -599,7 +599,6 @@ class InvokeAIDiffuserComponent:
         )
 
         # below is fugly omg
-        num_actual_conditionings = len(c_or_weighted_c_list)
         conditionings = [uc] + [c for c, weight in weighted_cond_list]
         weights = [1] + [weight for c, weight in weighted_cond_list]
         chunk_count = ceil(len(conditionings) / 2)

invokeai/backend/stable_diffusion/textual_inversion_manager.py

@@ -1,16 +1,26 @@
-import os
 import traceback
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Optional, Union
+from typing import Optional, Union, List
 
+import safetensors.torch
 import torch
+
 from compel.embeddings_provider import BaseTextualInversionManager
 from picklescan.scanner import scan_file_path
 from transformers import CLIPTextModel, CLIPTokenizer
 
 from .concepts_lib import HuggingFaceConceptsLibrary
 
+@dataclass
+class EmbeddingInfo:
+    name: str
+    embedding: torch.Tensor
+    num_vectors_per_token: int
+    token_dim: int 
+    trained_steps: int = None
+    trained_model_name: str = None
+    trained_model_checksum: str = None
 
 @dataclass
 class TextualInversion:
@@ -72,66 +82,46 @@ class TextualInversionManager(BaseTextualInversionManager):
         if str(ckpt_path).endswith(".DS_Store"):
             return
 
-        try:
-            scan_result = scan_file_path(str(ckpt_path))
-            if scan_result.infected_files == 1:
+        embedding_list = self._parse_embedding(str(ckpt_path))
+        for embedding_info in embedding_list:
+            if (self.text_encoder.get_input_embeddings().weight.data[0].shape[0] != embedding_info.token_dim):
                 print(
-                    f"\n### Security Issues Found in Model: {scan_result.issues_count}"
+                    f"   ** Notice: {ckpt_path.parents[0].name}/{ckpt_path.name} was trained on a model with an incompatible token dimension: {self.text_encoder.get_input_embeddings().weight.data[0].shape[0]} vs {embedding_info.token_dim}."
                 )
-                print("### For your safety, InvokeAI will not load this embed.")
-                return
-        except Exception:
-            print(
-                f"### {ckpt_path.parents[0].name}/{ckpt_path.name} is damaged or corrupt."
-            )
-            return
+                continue
 
-        embedding_info = self._parse_embedding(str(ckpt_path))
-
-        if embedding_info is None:
-            # We've already put out an error message about the bad embedding in _parse_embedding, so just return.
-            return
-        elif (
-            self.text_encoder.get_input_embeddings().weight.data[0].shape[0]
-            != embedding_info["token_dim"]
-        ):
-            print(
-                f"** Notice: {ckpt_path.parents[0].name}/{ckpt_path.name} was trained on a model with an incompatible token dimension: {self.text_encoder.get_input_embeddings().weight.data[0].shape[0]} vs {embedding_info['token_dim']}."
-            )
-            return
-
-        # Resolve the situation in which an earlier embedding has claimed the same
-        # trigger string. We replace the trigger with '<source_file>', as we used to.
-        trigger_str = embedding_info["name"]
-        sourcefile = (
-            f"{ckpt_path.parent.name}/{ckpt_path.name}"
-            if ckpt_path.name == "learned_embeds.bin"
-            else ckpt_path.name
-        )
-
-        if trigger_str in self.trigger_to_sourcefile:
-            replacement_trigger_str = (
-                f"<{ckpt_path.parent.name}>"
+            # Resolve the situation in which an earlier embedding has claimed the same
+            # trigger string. We replace the trigger with '<source_file>', as we used to.
+            trigger_str = embedding_info.name
+            sourcefile = (
+                f"{ckpt_path.parent.name}/{ckpt_path.name}"
                 if ckpt_path.name == "learned_embeds.bin"
-                else f"<{ckpt_path.stem}>"
+                else ckpt_path.name
             )
-            print(
-                f">> {sourcefile}: Trigger token '{trigger_str}' is already claimed by '{self.trigger_to_sourcefile[trigger_str]}'. Trigger this concept with {replacement_trigger_str}"
-            )
-            trigger_str = replacement_trigger_str
 
-        try:
-            self._add_textual_inversion(
-                trigger_str,
-                embedding_info["embedding"],
-                defer_injecting_tokens=defer_injecting_tokens,
-            )
-            # remember which source file claims this trigger
-            self.trigger_to_sourcefile[trigger_str] = sourcefile
+            if trigger_str in self.trigger_to_sourcefile:
+                replacement_trigger_str = (
+                    f"<{ckpt_path.parent.name}>"
+                    if ckpt_path.name == "learned_embeds.bin"
+                    else f"<{ckpt_path.stem}>"
+                )
+                print(
+                    f">> {sourcefile}: Trigger token '{trigger_str}' is already claimed by '{self.trigger_to_sourcefile[trigger_str]}'. Trigger this concept with {replacement_trigger_str}"
+                )
+                trigger_str = replacement_trigger_str
 
-        except ValueError as e:
-            print(f'   | Ignoring incompatible embedding {embedding_info["name"]}')
-            print(f"   | The error was {str(e)}")
+            try:
+                self._add_textual_inversion(
+                    trigger_str,
+                    embedding_info.embedding,
+                    defer_injecting_tokens=defer_injecting_tokens,
+                )
+                # remember which source file claims this trigger
+                self.trigger_to_sourcefile[trigger_str] = sourcefile
+
+            except ValueError as e:
+                print(f'   | Ignoring incompatible embedding {embedding_info["name"]}')
+                print(f"   | The error was {str(e)}")
 
     def _add_textual_inversion(
         self, trigger_str, embedding, defer_injecting_tokens=False
@@ -309,111 +299,130 @@ class TextualInversionManager(BaseTextualInversionManager):
 
         return token_id
 
-    def _parse_embedding(self, embedding_file: str):
-        file_type = embedding_file.split(".")[-1]
-        if file_type == "pt":
-            return self._parse_embedding_pt(embedding_file)
-        elif file_type == "bin":
-            return self._parse_embedding_bin(embedding_file)
+
+    def _parse_embedding(self, embedding_file: str)->List[EmbeddingInfo]:
+        suffix = Path(embedding_file).suffix
+        try:
+            if suffix in [".pt",".ckpt",".bin"]:
+                scan_result = scan_file_path(embedding_file)
+                if scan_result.infected_files > 0:
+                    print(
+                        f"   ** Security Issues Found in Model: {scan_result.issues_count}"
+                    )
+                    print("   ** For your safety, InvokeAI will not load this embed.")
+                    return list()
+                ckpt = torch.load(embedding_file,map_location="cpu")
+            else:
+                ckpt = safetensors.torch.load_file(embedding_file)
+        except Exception as e:
+            print(f"   ** Notice: unrecognized embedding file format: {embedding_file}: {e}")
+            return list()
+        
+        # try to figure out what kind of embedding file it is and parse accordingly
+        keys = list(ckpt.keys())
+        if all(x in keys for x in ['string_to_token','string_to_param','name','step']):
+            return self._parse_embedding_v1(ckpt, embedding_file)     # example rem_rezero.pt
+        
+        elif all(x in keys for x in ['string_to_token','string_to_param']):
+            return self._parse_embedding_v2(ckpt, embedding_file)     # example midj-strong.pt
+        
+        elif 'emb_params' in keys:
+            return self._parse_embedding_v3(ckpt, embedding_file)     # example easynegative.safetensors
+        
         else:
-            print(f"** Notice: unrecognized embedding file format: {embedding_file}")
-            return None
+            return self._parse_embedding_v4(ckpt, embedding_file)     # usually a '.bin' file
 
-    def _parse_embedding_pt(self, embedding_file):
-        embedding_ckpt = torch.load(embedding_file, map_location="cpu")
-        embedding_info = {}
+    def _parse_embedding_v1(self, embedding_ckpt: dict, file_path: str)->List[EmbeddingInfo]:
+        basename = Path(file_path).stem
+        print(f'   | Loading v1 embedding file: {basename}')
 
-        # Check if valid embedding file
-        if "string_to_token" and "string_to_param" in embedding_ckpt:
-            # Catch variants that do not have the expected keys or values.
-            try:
-                embedding_info["name"] = embedding_ckpt["name"] or os.path.basename(
-                    os.path.splitext(embedding_file)[0]
-                )
+        embeddings = list()
+        token_counter = -1
+        for token,embedding in embedding_ckpt["string_to_param"].items():
+            if token_counter < 0:
+                trigger = embedding_ckpt["name"]
+            elif token_counter == 0:
+                trigger = f'<basename>'
+            else:
+                trigger = f'<{basename}-{int(token_counter:=token_counter)}>'
+            token_counter += 1
+            embedding_info = EmbeddingInfo(
+                name = trigger,
+                embedding = embedding,
+                num_vectors_per_token = embedding.size()[0],
+                token_dim = embedding.size()[1],
+                trained_steps = embedding_ckpt["step"],
+                trained_model_name = embedding_ckpt["sd_checkpoint_name"],
+                trained_model_checksum = embedding_ckpt["sd_checkpoint"]
+            )
+            embeddings.append(embedding_info)
+        return embeddings
 
-                # Check num of embeddings and warn user only the first will be used
-                embedding_info["num_of_embeddings"] = len(
-                    embedding_ckpt["string_to_token"]
-                )
-                if embedding_info["num_of_embeddings"] > 1:
-                    print(">> More than 1 embedding found. Will use the first one")
-
-                embedding = list(embedding_ckpt["string_to_param"].values())[0]
-            except (AttributeError, KeyError):
-                return self._handle_broken_pt_variants(embedding_ckpt, embedding_file)
-
-            embedding_info["embedding"] = embedding
-            embedding_info["num_vectors_per_token"] = embedding.size()[0]
-            embedding_info["token_dim"] = embedding.size()[1]
-
-            try:
-                embedding_info["trained_steps"] = embedding_ckpt["step"]
-                embedding_info["trained_model_name"] = embedding_ckpt[
-                    "sd_checkpoint_name"
-                ]
-                embedding_info["trained_model_checksum"] = embedding_ckpt[
-                    "sd_checkpoint"
-                ]
-            except AttributeError:
-                print(">> No Training Details Found. Passing ...")
-
-        # .pt files found at https://cyberes.github.io/stable-diffusion-textual-inversion-models/
-        # They are actually .bin files
-        elif len(embedding_ckpt.keys()) == 1:
-            embedding_info = self._parse_embedding_bin(embedding_file)
-
-        else:
-            print(">> Invalid embedding format")
-            embedding_info = None
-
-        return embedding_info
-
-    def _parse_embedding_bin(self, embedding_file):
-        embedding_ckpt = torch.load(embedding_file, map_location="cpu")
-        embedding_info = {}
-
-        if list(embedding_ckpt.keys()) == 0:
-            print(">> Invalid concepts file")
-            embedding_info = None
-        else:
-            for token in list(embedding_ckpt.keys()):
-                embedding_info["name"] = (
-                    token
-                    or f"<{os.path.basename(os.path.splitext(embedding_file)[0])}>"
-                )
-                embedding_info["embedding"] = embedding_ckpt[token]
-                embedding_info[
-                    "num_vectors_per_token"
-                ] = 1  # All Concepts seem to default to 1
-                embedding_info["token_dim"] = embedding_info["embedding"].size()[0]
-
-        return embedding_info
-
-    def _handle_broken_pt_variants(
-        self, embedding_ckpt: dict, embedding_file: str
-    ) -> dict:
+    def _parse_embedding_v2 (
+        self, embedding_ckpt: dict, file_path: str
+    ) -> List[EmbeddingInfo]:
         """
-        This handles the broken .pt file variants. We only know of one at present.
+        This handles embedding .pt file variant #2.
         """
-        embedding_info = {}
+        basename = Path(file_path).stem
+        print(f'   | Loading v2 embedding file: {basename}')
+        embeddings = list()
+        
         if isinstance(
             list(embedding_ckpt["string_to_token"].values())[0], torch.Tensor
         ):
-            for token in list(embedding_ckpt["string_to_token"].keys()):
-                embedding_info["name"] = (
-                    token
-                    if token != "*"
-                    else f"<{os.path.basename(os.path.splitext(embedding_file)[0])}>"
+            token_counter = 0
+            for token,embedding in embedding_ckpt["string_to_param"].items():
+                trigger = token if token != '*' \
+                    else f'<{basename}>' if token_counter == 0 \
+                         else f'<{basename}-{int(token_counter:=token_counter+1)}>'
+                embedding_info = EmbeddingInfo(
+                    name = trigger,
+                    embedding = embedding,
+                    num_vectors_per_token = embedding.size()[0],
+                    token_dim = embedding.size()[1],
                 )
-                embedding_info["embedding"] = embedding_ckpt[
-                    "string_to_param"
-                ].state_dict()[token]
-                embedding_info["num_vectors_per_token"] = embedding_info[
-                    "embedding"
-                ].shape[0]
-                embedding_info["token_dim"] = embedding_info["embedding"].size()[1]
+                embeddings.append(embedding_info)
         else:
-            print(">> Invalid embedding format")
-            embedding_info = None
+            print(f"   ** {basename}: Unrecognized embedding format")
 
-        return embedding_info
+        return embeddings
+
+    def _parse_embedding_v3(self, embedding_ckpt: dict, file_path: str)->List[EmbeddingInfo]:
+        """
+        Parse 'version 3' of the .pt textual inversion embedding files.
+        """
+        basename = Path(file_path).stem
+        print(f'   | Loading v3 embedding file: {basename}')
+        embedding = embedding_ckpt['emb_params']
+        embedding_info = EmbeddingInfo(
+            name = f'<{basename}>',
+            embedding = embedding,
+            num_vectors_per_token = embedding.size()[0],
+            token_dim = embedding.size()[1],
+        )
+        return [embedding_info]
+    
+    def _parse_embedding_v4(self, embedding_ckpt: dict, filepath: str)->List[EmbeddingInfo]:
+        """
+        Parse 'version 4' of the textual inversion embedding files. This one
+        is usually associated with .bin files trained by HuggingFace diffusers.
+        """
+        basename = Path(filepath).stem
+        short_path = Path(filepath).parents[0].name+'/'+Path(filepath).name
+        
+        print(f'   | Loading v4 embedding file: {short_path}')
+        
+        embeddings = list()
+        if list(embedding_ckpt.keys()) == 0:
+            print(f"   ** Invalid embeddings file: {short_path}")
+        else:
+            for token,embedding in embedding_ckpt.items():
+                embedding_info = EmbeddingInfo(
+                    name = token or f"<{basename}>",
+                    embedding = embedding,
+                    num_vectors_per_token = 1,  # All Concepts seem to default to 1
+                    token_dim = embedding.size()[0],
+                )
+                embeddings.append(embedding_info)
+        return embeddings

invokeai/frontend/CLI/CLI.py

@@ -158,14 +158,9 @@ def main():
         report_model_error(opt, e)
 
     # try to autoconvert new models
-    if path := opt.autoimport:
-        gen.model_manager.heuristic_import(
-            str(path), convert=False, commit_to_conf=opt.conf
-        )
-
     if path := opt.autoconvert:
         gen.model_manager.heuristic_import(
-            str(path), convert=True, commit_to_conf=opt.conf
+            str(path), commit_to_conf=opt.conf
         )
 
     # web server loops forever
@@ -581,6 +576,7 @@ def do_command(command: str, gen, opt: Args, completer) -> tuple:
 
     elif command.startswith("!replay"):
         file_path = command.replace("!replay", "", 1).strip()
+        file_path = os.path.join(opt.outdir, file_path)
         if infile is None and os.path.isfile(file_path):
             infile = open(file_path, "r", encoding="utf-8")
         completer.add_history(command)

invokeai/frontend/install/invokeai_update.py

@@ -1,10 +1,9 @@
-"""
+'''
 Minimalist updater script. Prompts user for the tag or branch to update to and runs
 pip install <path_to_git_source>.
-"""
+'''
 import os
 import platform
-
 import requests
 from rich import box, print
 from rich.console import Console, Group, group
@@ -16,8 +15,10 @@ from rich.text import Text
 
 from invokeai.version import __version__
 
-INVOKE_AI_SRC = "https://github.com/invoke-ai/InvokeAI/archive"
-INVOKE_AI_REL = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
+INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive"
+INVOKE_AI_TAG="https://github.com/invoke-ai/InvokeAI/archive/refs/tags"
+INVOKE_AI_BRANCH="https://github.com/invoke-ai/InvokeAI/archive/refs/heads"
+INVOKE_AI_REL="https://api.github.com/repos/invoke-ai/InvokeAI/releases"
 
 OS = platform.uname().system
 ARCH = platform.uname().machine
@@ -28,22 +29,22 @@ if OS == "Windows":
 else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
-
-def get_versions() -> dict:
+def get_versions()->dict:
     return requests.get(url=INVOKE_AI_REL).json()
 
-
 def welcome(versions: dict):
+    
     @group()
     def text():
-        yield f"InvokeAI Version: [bold yellow]{__version__}"
-        yield ""
-        yield "This script will update InvokeAI to the latest release, or to a development version of your choice."
-        yield ""
-        yield "[bold yellow]Options:"
-        yield f"""[1] Update to the latest official release ([italic]{versions[0]['tag_name']}[/italic])
+        yield f'InvokeAI Version: [bold yellow]{__version__}'
+        yield ''
+        yield 'This script will update InvokeAI to the latest release, or to a development version of your choice.'
+        yield ''
+        yield '[bold yellow]Options:'
+        yield f'''[1] Update to the latest official release ([italic]{versions[0]['tag_name']}[/italic])
 [2] Update to the bleeding-edge development version ([italic]main[/italic])
-[3] Manually enter the tag or branch name you wish to update"""
+[3] Manually enter the [bold]tag name[/bold] for the version you wish to update to
+[4] Manually enter the [bold]branch name[/bold] for the version you wish to update to'''        
 
     console.rule()
     print(
@@ -59,33 +60,41 @@ def welcome(versions: dict):
     )
     console.line()
 
-
 def main():
     versions = get_versions()
     welcome(versions)
 
     tag = None
-    choice = Prompt.ask("Choice:", choices=["1", "2", "3"], default="1")
+    branch = None
+    release = None
+    choice = Prompt.ask('Choice:',choices=['1','2','3','4'],default='1')
+    
+    if choice=='1':
+        release = versions[0]['tag_name']
+    elif choice=='2':
+        release = 'main'
+    elif choice=='3':
+        tag = Prompt.ask('Enter an InvokeAI tag name')
+    elif choice=='4':
+        branch = Prompt.ask('Enter an InvokeAI branch name')
 
-    if choice == "1":
-        tag = versions[0]["tag_name"]
-    elif choice == "2":
-        tag = "main"
-    elif choice == "3":
-        tag = Prompt.ask("Enter an InvokeAI tag or branch name")
-
-    print(f":crossed_fingers: Upgrading to [yellow]{tag}[/yellow]")
-    cmd = f"pip install {INVOKE_AI_SRC}/{tag}.zip --use-pep517"
-    print("")
-    print("")
-    if os.system(cmd) == 0:
-        print(f":heavy_check_mark: Upgrade successful")
+    print(f':crossed_fingers: Upgrading to [yellow]{tag if tag else release}[/yellow]')
+    if release:
+        cmd = f'pip install {INVOKE_AI_SRC}/{release}.zip --use-pep517 --upgrade'
+    elif tag:
+        cmd = f'pip install {INVOKE_AI_TAG}/{tag}.zip --use-pep517 --upgrade'
     else:
-        print(f":exclamation: [bold red]Upgrade failed[/red bold]")
-
-
+        cmd = f'pip install {INVOKE_AI_BRANCH}/{branch}.zip --use-pep517 --upgrade'
+    print('')
+    print('')
+    if os.system(cmd)==0:
+        print(f':heavy_check_mark: Upgrade successful')
+    else:
+        print(f':exclamation: [bold red]Upgrade failed[/red bold]')
+    
 if __name__ == "__main__":
     try:
         main()
     except KeyboardInterrupt:
         pass
+

invokeai/frontend/install/model_install.py

@@ -199,17 +199,6 @@ class addModelsForm(npyscreen.FormMultiPage):
             relx=4,
             scroll_exit=True,
         )
-        self.nextrely += 1
-        self.convert_models = self.add_widget_intelligent(
-            npyscreen.TitleSelectOne,
-            name="== CONVERT IMPORTED MODELS INTO DIFFUSERS==",
-            values=["Keep original format", "Convert to diffusers"],
-            value=0,
-            begin_entry_at=4,
-            max_height=4,
-            hidden=True,  # will appear when imported models box is edited
-            scroll_exit=True,
-        )
         self.cancel = self.add_widget_intelligent(
             npyscreen.ButtonPress,
             name="CANCEL",
@@ -244,8 +233,6 @@ class addModelsForm(npyscreen.FormMultiPage):
             self.show_directory_fields.addVisibleWhenSelected(i)
 
         self.show_directory_fields.when_value_edited = self._clear_scan_directory
-        self.import_model_paths.when_value_edited = self._show_hide_convert
-        self.autoload_directory.when_value_edited = self._show_hide_convert
 
     def resize(self):
         super().resize()
@@ -256,13 +243,6 @@ class addModelsForm(npyscreen.FormMultiPage):
         if not self.show_directory_fields.value:
             self.autoload_directory.value = ""
 
-    def _show_hide_convert(self):
-        model_paths = self.import_model_paths.value or ""
-        autoload_directory = self.autoload_directory.value or ""
-        self.convert_models.hidden = (
-            len(model_paths) == 0 and len(autoload_directory) == 0
-        )
-
     def _get_starter_model_labels(self) -> List[str]:
         window_width, window_height = get_terminal_size()
         label_width = 25
@@ -322,7 +302,6 @@ class addModelsForm(npyscreen.FormMultiPage):
         .scan_directory: Path to a directory of models to scan and import
         .autoscan_on_startup:  True if invokeai should scan and import at startup time
         .import_model_paths:   list of URLs, repo_ids and file paths to import
-        .convert_to_diffusers: if True, convert legacy checkpoints into diffusers
         """
         # we're using a global here rather than storing the result in the parentapp
         # due to some bug in npyscreen that is causing attributes to be lost
@@ -359,7 +338,6 @@ class addModelsForm(npyscreen.FormMultiPage):
 
         # URLs and the like
         selections.import_model_paths = self.import_model_paths.value.split()
-        selections.convert_to_diffusers = self.convert_models.value[0] == 1
 
 
 class AddModelApplication(npyscreen.NPSAppManaged):
@@ -372,7 +350,6 @@ class AddModelApplication(npyscreen.NPSAppManaged):
             scan_directory=None,
             autoscan_on_startup=None,
             import_model_paths=None,
-            convert_to_diffusers=None,
         )
 
     def onStart(self):
@@ -393,7 +370,6 @@ def process_and_execute(opt: Namespace, selections: Namespace):
     directory_to_scan = selections.scan_directory
     scan_at_startup = selections.autoscan_on_startup
     potential_models_to_install = selections.import_model_paths
-    convert_to_diffusers = selections.convert_to_diffusers
 
     install_requested_models(
         install_initial_models=models_to_install,
@@ -401,7 +377,6 @@ def process_and_execute(opt: Namespace, selections: Namespace):
         scan_directory=Path(directory_to_scan) if directory_to_scan else None,
         external_models=potential_models_to_install,
         scan_at_startup=scan_at_startup,
-        convert_to_diffusers=convert_to_diffusers,
         precision="float32"
         if opt.full_precision
         else choose_precision(torch.device(choose_torch_device())),

invokeai/frontend/web/.eslintignore

@@ -6,3 +6,5 @@ stats.html
 index.html
 .yarn/
 *.scss
+src/services/api/
+src/services/fixtures/*

invokeai/frontend/web/.prettierignore

@@ -3,4 +3,8 @@ dist/
 node_modules/
 patches/
 stats.html
+index.html
 .yarn/
+*.scss
+src/services/api/
+src/services/fixtures/*

invokeai/frontend/web/config/vite.app.config.ts

@@ -0,0 +1,40 @@
+import react from '@vitejs/plugin-react-swc';
+import { visualizer } from 'rollup-plugin-visualizer';
+import { PluginOption, UserConfig } from 'vite';
+import eslint from 'vite-plugin-eslint';
+import tsconfigPaths from 'vite-tsconfig-paths';
+
+export const appConfig: UserConfig = {
+  base: './',
+  plugins: [
+    react(),
+    eslint(),
+    tsconfigPaths(),
+    visualizer() as unknown as PluginOption,
+  ],
+  build: {
+    chunkSizeWarningLimit: 1500,
+  },
+  server: {
+    // Proxy HTTP requests to the flask server
+    proxy: {
+      // Proxy socket.io to the nodes socketio server
+      '/ws/socket.io': {
+        target: 'ws://127.0.0.1:9090',
+        ws: true,
+      },
+      // Proxy openapi schema definiton
+      '/openapi.json': {
+        target: 'http://127.0.0.1:9090/openapi.json',
+        rewrite: (path) => path.replace(/^\/openapi.json/, ''),
+        changeOrigin: true,
+      },
+      // proxy nodes api
+      '/api/v1': {
+        target: 'http://127.0.0.1:9090/api/v1',
+        rewrite: (path) => path.replace(/^\/api\/v1/, ''),
+        changeOrigin: true,
+      },
+    },
+  },
+};

invokeai/frontend/web/config/vite.package.config.ts

@@ -0,0 +1,47 @@
+import react from '@vitejs/plugin-react-swc';
+import path from 'path';
+import { visualizer } from 'rollup-plugin-visualizer';
+import { PluginOption, UserConfig } from 'vite';
+import dts from 'vite-plugin-dts';
+import eslint from 'vite-plugin-eslint';
+import tsconfigPaths from 'vite-tsconfig-paths';
+
+export const packageConfig: UserConfig = {
+  base: './',
+  plugins: [
+    react(),
+    eslint(),
+    tsconfigPaths(),
+    visualizer() as unknown as PluginOption,
+    dts({
+      insertTypesEntry: true,
+    }),
+  ],
+  build: {
+    chunkSizeWarningLimit: 1500,
+    lib: {
+      entry: path.resolve(__dirname, '../src/index.ts'),
+      name: 'InvokeAIUI',
+      fileName: (format) => `invoke-ai-ui.${format}.js`,
+    },
+    rollupOptions: {
+      external: ['react', 'react-dom', '@emotion/react'],
+      output: {
+        globals: {
+          react: 'React',
+          'react-dom': 'ReactDOM',
+        },
+      },
+    },
+  },
+  resolve: {
+    alias: {
+      app: path.resolve(__dirname, '../src/app'),
+      assets: path.resolve(__dirname, '../src/assets'),
+      common: path.resolve(__dirname, '../src/common'),
+      features: path.resolve(__dirname, '../src/features'),
+      services: path.resolve(__dirname, '../src/services'),
+      theme: path.resolve(__dirname, '../src/theme'),
+    },
+  },
+};

invokeai/frontend/web/dist/assets/ThemeLocaleProvider-7791bd91.js

@@ -1,4 +1,4 @@
-import{j as y,cN as Ie,r as _,cO as bt,q as Lr,cP as o,cQ as b,cR as v,cS as S,cT as Vr,cU as ut,cV as vt,cM as ft,cW as mt,n as gt,cX as ht,E as pt}from"./index-f7f41e1f.js";import{d as yt,i as St,T as xt,j as $t,h as kt}from"./storeHooks-eaf47ae3.js";var Or=`
+import{j as y,cO as Ie,r as _,cP as bt,q as Lr,cQ as o,cR as b,cS as v,cT as S,cU as Vr,cV as ut,cW as vt,cN as ft,cX as mt,n as gt,cY as ht,E as pt}from"./index-e53e8108.js";import{d as yt,i as St,T as xt,j as $t,h as kt}from"./storeHooks-5cde7d31.js";var Or=`
   :root {
     --chakra-vh: 100vh;
   }

invokeai/frontend/web/dist/index.html

@@ -12,7 +12,7 @@
         margin: 0;
       }
     </style>
-    <script type="module" crossorigin src="./assets/index-f7f41e1f.js"></script>
+    <script type="module" crossorigin src="./assets/index-e53e8108.js"></script>
     <link rel="stylesheet" href="./assets/index-5483945c.css">
   </head>
 

invokeai/frontend/web/dist/locales/ar.json

@@ -8,7 +8,6 @@
         "darkTheme": "داكن",
         "lightTheme": "فاتح",
         "greenTheme": "أخضر",
-        "text2img": "نص إلى صورة",
         "img2img": "صورة إلى صورة",
         "unifiedCanvas": "لوحة موحدة",
         "nodes": "عقد",

invokeai/frontend/web/dist/locales/de.json

@@ -7,7 +7,6 @@
         "darkTheme": "Dunkel",
         "lightTheme": "Hell",
         "greenTheme": "Grün",
-        "text2img": "Text zu Bild",
         "img2img": "Bild zu Bild",
         "nodes": "Knoten",
         "langGerman": "Deutsch",

invokeai/frontend/web/dist/locales/en.json

@@ -505,7 +505,9 @@
         "info": "Info",
         "deleteImage": "Delete Image",
         "initialImage": "Initial Image",
-        "showOptionsPanel": "Show Options Panel"
+        "showOptionsPanel": "Show Options Panel",
+        "hidePreview": "Hide Preview",
+        "showPreview": "Show Preview"
     },
     "settings": {
         "models": "Models",

invokeai/frontend/web/dist/locales/es.json

@@ -8,7 +8,6 @@
         "darkTheme": "Oscuro",
         "lightTheme": "Claro",
         "greenTheme": "Verde",
-        "text2img": "Texto a Imagen",
         "img2img": "Imagen a Imagen",
         "unifiedCanvas": "Lienzo Unificado",
         "nodes": "Nodos",
@@ -70,7 +69,11 @@
         "langHebrew": "Hebreo",
         "pinOptionsPanel": "Pin del panel de opciones",
         "loading": "Cargando",
-        "loadingInvokeAI": "Cargando invocar a la IA"
+        "loadingInvokeAI": "Cargando invocar a la IA",
+        "postprocessing": "Tratamiento posterior",
+        "txt2img": "De texto a imagen",
+        "accept": "Aceptar",
+        "cancel": "Cancelar"
     },
     "gallery": {
         "generations": "Generaciones",
@@ -404,7 +407,8 @@
         "none": "ninguno",
         "pickModelType": "Elige el tipo de modelo",
         "v2_768": "v2 (768px)",
-        "addDifference": "Añadir una diferencia"
+        "addDifference": "Añadir una diferencia",
+        "scanForModels": "Buscar modelos"
     },
     "parameters": {
         "images": "Imágenes",
@@ -574,7 +578,7 @@
         "autoSaveToGallery": "Guardar automáticamente en galería",
         "saveBoxRegionOnly": "Guardar solo región dentro de la caja",
         "limitStrokesToBox": "Limitar trazos a la caja",
-        "showCanvasDebugInfo": "Mostrar información de depuración de lienzo",
+        "showCanvasDebugInfo": "Mostrar la información adicional del lienzo",
         "clearCanvasHistory": "Limpiar historial de lienzo",
         "clearHistory": "Limpiar historial",
         "clearCanvasHistoryMessage": "Limpiar el historial de lienzo también restablece completamente el lienzo unificado. Esto incluye todo el historial de deshacer/rehacer, las imágenes en el área de preparación y la capa base del lienzo.",

invokeai/frontend/web/dist/locales/fr.json

@@ -8,7 +8,6 @@
         "darkTheme": "Sombre",
         "lightTheme": "Clair",
         "greenTheme": "Vert",
-        "text2img": "Texte en image",
         "img2img": "Image en image",
         "unifiedCanvas": "Canvas unifié",
         "nodes": "Nœuds",
@@ -47,7 +46,19 @@
         "statusLoadingModel": "Chargement du modèle",
         "statusModelChanged": "Modèle changé",
         "discordLabel": "Discord",
-        "githubLabel": "Github"
+        "githubLabel": "Github",
+        "accept": "Accepter",
+        "statusMergingModels": "Mélange des modèles",
+        "loadingInvokeAI": "Chargement de Invoke AI",
+        "cancel": "Annuler",
+        "langEnglish": "Anglais",
+        "statusConvertingModel": "Conversion du modèle",
+        "statusModelConverted": "Modèle converti",
+        "loading": "Chargement",
+        "pinOptionsPanel": "Épingler la page d'options",
+        "statusMergedModels": "Modèles mélangés",
+        "txt2img": "Texte vers image",
+        "postprocessing": "Post-Traitement"
     },
     "gallery": {
         "generations": "Générations",
@@ -518,5 +529,15 @@
         "betaDarkenOutside": "Assombrir à l'extérieur",
         "betaLimitToBox": "Limiter à la boîte",
         "betaPreserveMasked": "Conserver masqué"
+    },
+    "accessibility": {
+        "uploadImage": "Charger une image",
+        "reset": "Réinitialiser",
+        "nextImage": "Image suivante",
+        "previousImage": "Image précédente",
+        "useThisParameter": "Utiliser ce paramètre",
+        "zoomIn": "Zoom avant",
+        "zoomOut": "Zoom arrière",
+        "showOptionsPanel": "Montrer la page d'options"
     }
 }

invokeai/frontend/web/dist/locales/he.json

@@ -125,7 +125,6 @@
         "langSimplifiedChinese": "סינית",
         "langUkranian": "אוקראינית",
         "langSpanish": "ספרדית",
-        "text2img": "טקסט לתמונה",
         "img2img": "תמונה לתמונה",
         "unifiedCanvas": "קנבס מאוחד",
         "nodes": "צמתים",

invokeai/frontend/web/dist/locales/it.json

@@ -8,7 +8,6 @@
         "darkTheme": "Scuro",
         "lightTheme": "Chiaro",
         "greenTheme": "Verde",
-        "text2img": "Testo a Immagine",
         "img2img": "Immagine a Immagine",
         "unifiedCanvas": "Tela unificata",
         "nodes": "Nodi",
@@ -70,7 +69,11 @@
         "loading": "Caricamento in corso",
         "oceanTheme": "Oceano",
         "langHebrew": "Ebraico",
-        "loadingInvokeAI": "Caricamento Invoke AI"
+        "loadingInvokeAI": "Caricamento Invoke AI",
+        "postprocessing": "Post Elaborazione",
+        "txt2img": "Testo a Immagine",
+        "accept": "Accetta",
+        "cancel": "Annulla"
     },
     "gallery": {
         "generations": "Generazioni",
@@ -404,7 +407,8 @@
         "v2_768": "v2 (768px)",
         "none": "niente",
         "addDifference": "Aggiungi differenza",
-        "pickModelType": "Scegli il tipo di modello"
+        "pickModelType": "Scegli il tipo di modello",
+        "scanForModels": "Cerca modelli"
     },
     "parameters": {
         "images": "Immagini",
@@ -574,7 +578,7 @@
         "autoSaveToGallery": "Salvataggio automatico nella Galleria",
         "saveBoxRegionOnly": "Salva solo l'area di selezione",
         "limitStrokesToBox": "Limita i tratti all'area di selezione",
-        "showCanvasDebugInfo": "Mostra informazioni di debug della Tela",
+        "showCanvasDebugInfo": "Mostra ulteriori informazioni sulla Tela",
         "clearCanvasHistory": "Cancella cronologia Tela",
         "clearHistory": "Cancella la cronologia",
         "clearCanvasHistoryMessage": "La cancellazione della cronologia della tela lascia intatta la tela corrente, ma cancella in modo irreversibile la cronologia degli annullamenti e dei ripristini.",
@@ -612,7 +616,7 @@
         "copyMetadataJson": "Copia i metadati JSON",
         "exitViewer": "Esci dal visualizzatore",
         "zoomIn": "Zoom avanti",
-        "zoomOut": "Zoom Indietro",
+        "zoomOut": "Zoom indietro",
         "rotateCounterClockwise": "Ruotare in senso antiorario",
         "rotateClockwise": "Ruotare in senso orario",
         "flipHorizontally": "Capovolgi orizzontalmente",

invokeai/frontend/web/dist/locales/ko.json

@@ -11,7 +11,6 @@
         "langArabic": "العربية",
         "langEnglish": "English",
         "langDutch": "Nederlands",
-        "text2img": "텍스트->이미지",
         "unifiedCanvas": "통합 캔버스",
         "langFrench": "Français",
         "langGerman": "Deutsch",

invokeai/frontend/web/dist/locales/nl.json

@@ -8,7 +8,6 @@
         "darkTheme": "Donker",
         "lightTheme": "Licht",
         "greenTheme": "Groen",
-        "text2img": "Tekst naar afbeelding",
         "img2img": "Afbeelding naar afbeelding",
         "unifiedCanvas": "Centraal canvas",
         "nodes": "Knooppunten",

invokeai/frontend/web/dist/locales/pl.json

@@ -8,7 +8,6 @@
         "darkTheme": "Ciemny",
         "lightTheme": "Jasny",
         "greenTheme": "Zielony",
-        "text2img": "Tekst na obraz",
         "img2img": "Obraz na obraz",
         "unifiedCanvas": "Tryb uniwersalny",
         "nodes": "Węzły",

invokeai/frontend/web/dist/locales/pt.json

@@ -20,7 +20,6 @@
         "langSpanish": "Espanhol",
         "langRussian": "Русский",
         "langUkranian": "Украї́нська",
-        "text2img": "Texto para Imagem",
         "img2img": "Imagem para Imagem",
         "unifiedCanvas": "Tela Unificada",
         "nodes": "Nós",

invokeai/frontend/web/dist/locales/pt_BR.json

@@ -8,7 +8,6 @@
         "darkTheme": "Noite",
         "lightTheme": "Dia",
         "greenTheme": "Verde",
-        "text2img": "Texto Para Imagem",
         "img2img": "Imagem Para Imagem",
         "unifiedCanvas": "Tela Unificada",
         "nodes": "Nódulos",

invokeai/frontend/web/dist/locales/ru.json

@@ -8,7 +8,6 @@
         "darkTheme": "Темная",
         "lightTheme": "Светлая",
         "greenTheme": "Зеленая",
-        "text2img": "Изображение из текста (text2img)",
         "img2img": "Изображение в изображение (img2img)",
         "unifiedCanvas": "Универсальный холст",
         "nodes": "Ноды",

invokeai/frontend/web/dist/locales/uk.json

@@ -8,7 +8,6 @@
         "darkTheme": "Темна",
         "lightTheme": "Світла",
         "greenTheme": "Зелена",
-        "text2img": "Зображення із тексту (text2img)",
         "img2img": "Зображення із зображення (img2img)",
         "unifiedCanvas": "Універсальне полотно",
         "nodes": "Вузли",

invokeai/frontend/web/dist/locales/zh_CN.json

@@ -8,7 +8,6 @@
         "darkTheme": "暗色",
         "lightTheme": "亮色",
         "greenTheme": "绿色",
-        "text2img": "文字到图像",
         "img2img": "图像到图像",
         "unifiedCanvas": "统一画布",
         "nodes": "节点",

invokeai/frontend/web/dist/locales/zh_Hant.json

@@ -33,7 +33,6 @@
         "langBrPortuguese": "巴西葡萄牙語",
         "langRussian": "俄語",
         "langSpanish": "西班牙語",
-        "text2img": "文字到圖像",
         "unifiedCanvas": "統一畫布"
     }
 }

invokeai/frontend/web/docs/API_CLIENT.md

@@ -0,0 +1,87 @@
+# Generated axios API client
+
+- [Generated axios API client](#generated-axios-api-client)
+  - [Generation](#generation)
+    - [Generate the API client from the nodes web server](#generate-the-api-client-from-the-nodes-web-server)
+    - [Generate the API client from JSON](#generate-the-api-client-from-json)
+      - [Getting the JSON from the nodes web server](#getting-the-json-from-the-nodes-web-server)
+      - [Getting the JSON with a python script](#getting-the-json-with-a-python-script)
+      - [Generate the API client](#generate-the-api-client)
+  - [The generated client](#the-generated-client)
+  - [API client customisation](#api-client-customisation)
+
+This API client is generated by an [openapi code generator](https://github.com/ferdikoomen/openapi-typescript-codegen).
+
+All files in `invokeai/frontend/web/src/services/api/` are made by the generator.
+
+## Generation
+
+The axios client may be generated by from the OpenAPI schema from the nodes web server, or from JSON.
+
+### Generate the API client from the nodes web server
+
+We need to start the nodes web server, which serves the OpenAPI schema to the generator.
+
+1. Start the nodes web server.
+
+```bash
+# from the repo root
+python scripts/invoke-new.py --web
+```
+
+2. Generate the API client.
+
+```bash
+# from invokeai/frontend/web/
+yarn api:web
+```
+
+### Generate the API client from JSON
+
+The JSON can be acquired from the nodes web server, or with a python script.
+
+#### Getting the JSON from the nodes web server
+
+Start the nodes web server as described above, then download the file.
+
+```bash
+# from invokeai/frontend/web/
+curl http://localhost:9090/openapi.json -o openapi.json
+```
+
+#### Getting the JSON with a python script
+
+Run this python script from the repo root, so it can access the nodes server modules.
+
+The script will output `openapi.json` in the repo root. Then we need to move it to `invokeai/frontend/web/`.
+
+```bash
+# from the repo root
+python invokeai/app/util/generate_openapi_json.py
+mv invokeai/app/util/openapi.json invokeai/frontend/web/services/fixtures/
+```
+
+#### Generate the API client
+
+Now we can generate the API client from the JSON.
+
+```bash
+# from invokeai/frontend/web/
+yarn api:file
+```
+
+## The generated client
+
+The client will be written to `invokeai/frontend/web/services/api/`:
+
+- `axios` client
+- TS types
+- An easily parseable schema, which we can use to generate UI
+
+## API client customisation
+
+The generator has a default `request.ts` file that implements a base `axios` client. The generated client uses this base client.
+
+One shortcoming of this is base client is it does not provide response headers unless the response body is empty. To fix this, we provide our own lightly-patched `request.ts`.
+
+To access the headers, call `getHeaders(response)` on any response from the generated api client. This function is exported from `invokeai/frontend/web/src/services/util/getHeaders.ts`.

invokeai/frontend/web/docs/EVENTS.md

@@ -0,0 +1,21 @@
+# Events
+
+Events via `socket.io`
+
+## `actions.ts`
+
+Redux actions for all socket events. Payloads all include a timestamp, and optionally some other data.
+
+Any reducer (or middleware) can respond to the actions.
+
+## `middleware.ts`
+
+Redux middleware for events.
+
+Handles dispatching the event actions. Only put logic here if it can't really go anywhere else.
+
+For example, on connect we want to load images to the gallery if it's not populated. This requires dispatching a thunk, so we need to directly dispatch this in the middleware.
+
+## `types.ts`
+
+Hand-written types for the socket events. Cannot generate these from the server, but fortunately they are few and simple.

invokeai/frontend/web/docs/NODE_EDITOR.md

@@ -0,0 +1,17 @@
+# Node Editor Design
+
+WIP
+
+nodes
+
+everything in `src/features/nodes/`
+
+have a look at `state.nodes.invocation`
+
+- on socket connect, if no schema saved, fetch `localhost:9090/openapi.json`, save JSON to `state.nodes.schema`
+- on fulfilled schema fetch, `parseSchema()` the schema. this outputs a `Record<string, Invocation>` which is saved to `state.nodes.invocations` - `Invocation` is like a template for the node
+- when you add a node, the the `Invocation` template is passed to `InvocationComponent.tsx` to build the UI component for that node
+- inputs/outputs have field types - and each field type gets an `FieldComponent` which includes a dispatcher to write state changes to redux `nodesSlice`
+- `reactflow` sends changes to nodes/edges to redux
+- to invoke, `buildNodesGraph()` state, then send this
+- changed onClick Invoke button actions to build the schema, then when schema builds it dispatches the actual network request to create the session - see `session.ts`

invokeai/frontend/web/docs/PACKAGE_SCRIPTS.md

@@ -0,0 +1,29 @@
+# Package Scripts
+
+WIP walkthrough of `package.json` scripts.
+
+## `theme` & `theme:watch`
+
+These run the Chakra CLI to generate types for the theme, or watch for code change and re-generate the types.
+
+The CLI essentially monkeypatches Chakra's files in `node_modules`.
+
+## `postinstall`
+
+The `postinstall` script patches a few packages and runs the Chakra CLI to generate types for the theme.
+
+### Patch `@chakra-ui/cli`
+
+See: <https://github.com/chakra-ui/chakra-ui/issues/7394>
+
+### Patch `redux-persist`
+
+We want to persist the canvas state to `localStorage` but many canvas operations change data very quickly, so we need to debounce the writes to `localStorage`.
+
+`redux-persist` is unfortunately unmaintained. The repo's current code is nonfunctional, but the last release's code depends on a package that was removed from `npm` for being malware, so we cannot just fork it.
+
+So, we have to patch it directly. Perhaps a better way would be to write a debounced storage adapter, but I couldn't figure out how to do that.
+
+### Patch `redux-deep-persist`
+
+This package makes blacklisting and whitelisting persist configs very simple, but we have to patch it to match `redux-persist` for the types to work.

invokeai/frontend/web/docs/README.md

@@ -1,10 +1,16 @@
 # InvokeAI Web UI
 
+- [InvokeAI Web UI](#invokeai-web-ui)
+  - [Stack](#stack)
+  - [Contributing](#contributing)
+    - [Dev Environment](#dev-environment)
+    - [Production builds](#production-builds)
+
 The UI is a fairly straightforward Typescript React app. The only really fancy stuff is the Unified Canvas.
 
 Code in `invokeai/frontend/web/` if you want to have a look.
 
-## Details
+## Stack
 
 State management is Redux via [Redux Toolkit](https://github.com/reduxjs/redux-toolkit). Communication with server is a mix of HTTP and [socket.io](https://github.com/socketio/socket.io-client) (with a custom redux middleware to help).
 
@@ -32,7 +38,7 @@ Start everything in dev mode:
 
 1. Start the dev server: `yarn dev`
 2. Start the InvokeAI UI per usual: `invokeai --web`
-3. Point your browser to the dev server address e.g. `http://localhost:5173/`
+3. Point your browser to the dev server address e.g. <http://localhost:5173/>
 
 ### Production builds
 

invokeai/frontend/web/index.d.ts

@@ -1,78 +0,0 @@
-import React, { PropsWithChildren } from 'react';
-import { IAIPopoverProps } from '../web/src/common/components/IAIPopover';
-import { IAIIconButtonProps } from '../web/src/common/components/IAIIconButton';
-
-export {};
-
-declare module 'redux-socket.io-middleware';
-
-declare global {
-  /* eslint-disable @typescript-eslint/no-explicit-any */
-  interface Array<T> {
-    /**
-     * Returns the value of the last element in the array where predicate is true, and undefined
-     * otherwise.
-     * @param predicate findLast calls predicate once for each element of the array, in descending
-     * order, until it finds one where predicate returns true. If such an element is found, findLast
-     * immediately returns that element value. Otherwise, findLast returns undefined.
-     * @param thisArg If provided, it will be used as the this value for each invocation of
-     * predicate. If it is not provided, undefined is used instead.
-     */
-    findLast<S extends T>(
-      predicate: (value: T, index: number, array: T[]) => value is S,
-      thisArg?: any
-    ): S | undefined;
-    findLast(
-      predicate: (value: T, index: number, array: T[]) => unknown,
-      thisArg?: any
-    ): T | undefined;
-
-    /**
-     * Returns the index of the last element in the array where predicate is true, and -1
-     * otherwise.
-     * @param predicate findLastIndex calls predicate once for each element of the array, in descending
-     * order, until it finds one where predicate returns true. If such an element is found,
-     * findLastIndex immediately returns that element index. Otherwise, findLastIndex returns -1.
-     * @param thisArg If provided, it will be used as the this value for each invocation of
-     * predicate. If it is not provided, undefined is used instead.
-     */
-    findLastIndex(
-      predicate: (value: T, index: number, array: T[]) => unknown,
-      thisArg?: any
-    ): number;
-  }
-  /* eslint-enable @typescript-eslint/no-explicit-any */
-}
-
-declare module '@invoke-ai/invoke-ai-ui' {
-  declare class ThemeChanger extends React.Component<ThemeChangerProps> {
-    public constructor(props: ThemeChangerProps);
-  }
-
-  declare class InvokeAiLogoComponent extends React.Component<InvokeAILogoComponentProps> {
-    public constructor(props: InvokeAILogoComponentProps);
-  }
-
-  declare class IAIPopover extends React.Component<IAIPopoverProps> {
-    public constructor(props: IAIPopoverProps);
-  }
-
-  declare class IAIIconButton extends React.Component<IAIIconButtonProps> {
-    public constructor(props: IAIIconButtonProps);
-  }
-
-  declare class SettingsModal extends React.Component<SettingsModalProps> {
-    public constructor(props: SettingsModalProps);
-  }
-}
-
-declare function Invoke(props: PropsWithChildren): JSX.Element;
-
-export {
-  ThemeChanger,
-  InvokeAiLogoComponent,
-  IAIPopover,
-  IAIIconButton,
-  SettingsModal,
-};
-export = Invoke;

invokeai/frontend/web/package.json

@@ -1,11 +1,31 @@
 {
-  "name": "invoke-ai-ui",
+  "name": "@invoke-ai/invoke-ai-ui",
   "private": true,
   "version": "0.0.1",
+  "publishConfig": {
+    "access": "restricted",
+    "registry": "https://npm.pkg.github.com"
+  },
+  "main": "./dist/invoke-ai-ui.umd.js",
+  "module": "./dist/invoke-ai-ui.es.js",
+  "exports": {
+    ".": {
+      "import": "./dist/invoke-ai-ui.es.js",
+      "require": "./dist/invoke-ai-ui.umd.js"
+    }
+  },
+  "types": "./dist/index.d.ts",
+  "files": [
+    "dist"
+  ],
   "scripts": {
     "prepare": "cd ../../../ && husky install invokeai/frontend/web/.husky",
     "dev": "concurrently \"vite dev\" \"yarn run theme:watch\"",
+    "dev:nodes": "concurrently \"vite dev --mode nodes\" \"yarn run theme:watch\"",
+    "dev:host": "concurrently \"vite dev --host\" \"yarn run theme:watch\"",
     "build": "yarn run lint && vite build",
+    "api:web": "openapi -i http://localhost:9090/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --exportSchemas true --indent 2 --request src/services/fixtures/request.ts",
+    "api:file": "openapi -i src/services/fixtures/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --exportSchemas true --indent 2 --request src/services/fixtures/request.ts",
     "preview": "vite preview",
     "lint:madge": "madge --circular src/main.tsx",
     "lint:eslint": "eslint --max-warnings=0 .",
@@ -36,70 +56,93 @@
   },
   "dependencies": {
     "@chakra-ui/anatomy": "^2.1.1",
-    "@chakra-ui/cli": "^2.3.0",
-    "@chakra-ui/icons": "^2.0.17",
-    "@chakra-ui/react": "^2.5.1",
-    "@chakra-ui/styled-system": "^2.6.1",
+    "@chakra-ui/icons": "^2.0.19",
+    "@chakra-ui/react": "^2.6.0",
+    "@chakra-ui/styled-system": "^2.9.0",
     "@chakra-ui/theme-tools": "^2.0.16",
+    "@dagrejs/graphlib": "^2.1.12",
     "@emotion/react": "^11.10.6",
     "@emotion/styled": "^11.10.6",
-    "@reduxjs/toolkit": "^1.9.2",
+    "@fontsource/inter": "^4.5.15",
+    "@reduxjs/toolkit": "^1.9.5",
+    "@roarr/browser-log-writer": "^1.1.5",
     "chakra-ui-contextmenu": "^1.0.5",
     "dateformat": "^5.0.3",
     "formik": "^2.2.9",
-    "framer-motion": "^9.0.4",
-    "i18next": "^22.4.10",
+    "framer-motion": "^10.12.4",
+    "fuse.js": "^6.6.2",
+    "i18next": "^22.4.15",
     "i18next-browser-languagedetector": "^7.0.1",
-    "i18next-http-backend": "^2.1.1",
-    "konva": "^8.4.2",
-    "lodash": "^4.17.21",
-    "patch-package": "^6.5.1",
+    "i18next-http-backend": "^2.2.0",
+    "konva": "^9.0.1",
+    "lodash-es": "^4.17.21",
+    "patch-package": "^7.0.0",
     "re-resizable": "^6.9.9",
     "react": "^18.2.0",
     "react-colorful": "^5.6.1",
     "react-dom": "^18.2.0",
     "react-dropzone": "^14.2.3",
-    "react-hotkeys-hook": "4.3.5",
-    "react-i18next": "^12.1.5",
+    "react-hotkeys-hook": "4.4.0",
+    "react-i18next": "^12.2.2",
     "react-icons": "^4.7.1",
-    "react-konva": "^18.2.4",
-    "react-konva-utils": "^0.3.2",
+    "react-konva": "^18.2.7",
+    "react-konva-utils": "^1.0.4",
     "react-redux": "^8.0.5",
+    "react-rnd": "^10.4.1",
     "react-transition-group": "^4.4.5",
-    "react-zoom-pan-pinch": "^2.6.1",
+    "react-use": "^17.4.0",
+    "react-zoom-pan-pinch": "^3.0.7",
+    "reactflow": "^11.7.0",
     "redux-deep-persist": "^1.0.7",
+    "redux-dynamic-middlewares": "^2.2.0",
     "redux-persist": "^6.0.0",
+    "roarr": "^7.15.0",
+    "serialize-error": "^11.0.0",
     "socket.io-client": "^4.6.0",
     "use-image": "^1.1.0",
     "uuid": "^9.0.0"
   },
+  "peerDependencies": {
+    "@chakra-ui/cli": "^2.4.0",
+    "react": "^18.2.0",
+    "react-dom": "^18.2.0",
+    "ts-toolbelt": "^9.6.0"
+  },
   "devDependencies": {
-    "@fontsource/inter": "^4.5.15",
+    "@chakra-ui/cli": "^2.4.0",
     "@types/dateformat": "^5.0.0",
-    "@types/react": "^18.0.28",
-    "@types/react-dom": "^18.0.11",
+    "@types/lodash-es": "^4.14.194",
+    "@types/node": "^18.16.2",
+    "@types/react": "^18.2.0",
+    "@types/react-dom": "^18.2.1",
     "@types/react-transition-group": "^4.4.5",
     "@types/uuid": "^9.0.0",
-    "@typescript-eslint/eslint-plugin": "^5.52.0",
-    "@typescript-eslint/parser": "^5.52.0",
-    "@vitejs/plugin-react-swc": "^3.2.0",
+    "@typescript-eslint/eslint-plugin": "^5.59.1",
+    "@typescript-eslint/parser": "^5.59.1",
+    "@vitejs/plugin-react-swc": "^3.3.0",
+    "axios": "^1.4.0",
     "babel-plugin-transform-imports": "^2.0.0",
-    "concurrently": "^7.6.0",
-    "eslint": "^8.34.0",
-    "eslint-config-prettier": "^8.6.0",
+    "concurrently": "^8.0.1",
+    "eslint": "^8.39.0",
+    "eslint-config-prettier": "^8.8.0",
     "eslint-plugin-prettier": "^4.2.1",
     "eslint-plugin-react": "^7.32.2",
     "eslint-plugin-react-hooks": "^4.6.0",
+    "form-data": "^4.0.0",
     "husky": "^8.0.3",
-    "lint-staged": "^13.1.2",
+    "lint-staged": "^13.2.2",
     "madge": "^6.0.0",
+    "openapi-types": "^12.1.0",
+    "openapi-typescript-codegen": "^0.24.0",
     "postinstall-postinstall": "^2.1.0",
-    "prettier": "^2.8.4",
+    "prettier": "^2.8.8",
     "rollup-plugin-visualizer": "^5.9.0",
-    "terser": "^5.16.4",
-    "vite": "^4.1.2",
+    "terser": "^5.17.1",
+    "ts-toolbelt": "^9.6.0",
+    "vite": "^4.3.3",
+    "vite-plugin-dts": "^2.3.0",
     "vite-plugin-eslint": "^1.8.1",
-    "vite-tsconfig-paths": "^4.0.5",
+    "vite-tsconfig-paths": "^4.2.0",
     "yarn": "^1.22.19"
   }
 }