Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

merge with main

Browse Source
This commit is contained in:
Lincoln Stein 2023-07-09 13:28:05 -04:00
commit 2f3190ad6c
23 changed files with 1062 additions and 209 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

189
LICENSE
View File

@ -1,21 +1,176 @@
MIT License
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
Copyright (c) 2022 InvokeAI Team
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
1. Definitions.
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.

20
README.md
View File

@ -3,8 +3,8 @@
![project hero](https://github.com/invoke-ai/InvokeAI/assets/31807370/1a917d94-e099-4fa1-a70f-7dd8d0691018)
# Invoke AI - Generative AI for Professional Creatives
## Image Generation for Stable Diffusion, Custom-Trained Models, and more.
Learn more about us and get started instantly at [invoke.ai](https://invoke.ai)
## Professional Creative Tools for Stable Diffusion, Custom-Trained Models, and more.
To learn more about Invoke AI, get started instantly, or implement our Business solutions, visit [invoke.ai](https://invoke.ai)
[![discord badge]][discord link]
@ -329,24 +329,24 @@ InvokeAI offers a locally hosted Web Server & React Frontend, with an industry l
The Unified Canvas is a fully integrated canvas implementation with support for all core generation capabilities, in/outpainting, brush tools, and more. This creative tool unlocks the capability for artists to create with AI as a creative collaborator, and can be used to augment AI-generated imagery, sketches, photography, renders, and more.
### *Advanced Prompt Syntax*
### *Node Architecture & Editor (Beta)*
Invoke AI's advanced prompt syntax allows for token weighting, cross-attention control, and prompt blending, allowing for fine-tuned tweaking of your invocations and exploration of the latent space.
Invoke AI's backend is built on a graph-based execution architecture. This allows for customizable generation pipelines to be developed by professional users looking to create specific workflows to support their production use-cases, and will be extended in the future with additional capabilities.
### *Command Line Interface*
### *Board & Gallery Management*
For users utilizing a terminal-based environment, or who want to take advantage of CLI features, InvokeAI offers an extensive and actively supported command-line interface that provides the full suite of generation functionality available in the tool.
Invoke AI provides an organized gallery system for easily storing, accessing, and remixing your content in the Invoke workspace. Images can be dragged/dropped onto any Image-base UI element in the application, and rich metadata within the Image allows for easy recall of key prompts or settings used in your workflow.
### Other features
- *Support for both ckpt and diffusers models*
- *SD 2.0, 2.1 support*
- *Upscaling & Face Restoration Tools*
- *Upscaling Tools*
- *Embedding Manager & Support*
- *Model Manager & Support*
- *Node-Based Architecture*
- *Node-Based Plug-&-Play UI (Beta)*
- *Boards & Gallery Management
- *SDXL Support* (Coming soon)
### Latest Changes
@ -359,7 +359,7 @@ Notes](https://github.com/invoke-ai/InvokeAI/releases) and the
Please check out our **[Q&A](https://invoke-ai.github.io/InvokeAI/help/TROUBLESHOOT/#faq)** to get solutions for common installation
problems and other issues.
## 🤝 Contributing
## Contributing
Anyone who wishes to contribute to this project, whether documentation, features, bug fixes, code
cleanup, testing, or code reviews, is very much encouraged to do so.
@ -378,7 +378,7 @@ to become part of our community.
Welcome to InvokeAI!
### 👥 Contributors
### Contributors
This fork is a combined effort of various people from across the world.
[Check out the list of all these amazing people](https://invoke-ai.github.io/InvokeAI/other/CONTRIBUTORS/). We thank them for

BIN
docs/assets/contributing/resize_invocation.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 7.1 KiB

BIN
docs/assets/contributing/resize_node_editor.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 17 KiB

519
docs/contributing/INVOCATIONS.md
View File

@ -1,8 +1,521 @@
# 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.
Features in InvokeAI are added in the form of modular node-like systems called
**Invocations**.
An Invocation is simply a single operation that takes in some inputs and gives
out some outputs. We can then chain multiple Invocations together to create more
complex functionality.
## Invocations Directory
InvokeAI Invocations can be found in the `invokeai/app/invocations` directory.
You can add your new functionality to one of the existing Invocations in this
directory or create a new file in this directory as per your needs.
**Note:** _All Invocations must be inside this directory for InvokeAI to
recognize them as valid Invocations._
## Creating A New Invocation
In order to understand the process of creating a new Invocation, let us actually
create one.
In our example, let us create an Invocation that will take in an image, resize
it and output the resized image.
The first set of things we need to do when creating a new Invocation are -
- Create a new class that derives from a predefined parent class called
`BaseInvocation`.
- The name of every Invocation must end with the word `Invocation` in order for
it to be recognized as an Invocation.
- Every Invocation must have a `docstring` that describes what this Invocation
does.
- Every Invocation must have a unique `type` field defined which becomes its
indentifier.
- Invocations are strictly typed. We make use of the native
[typing](https://docs.python.org/3/library/typing.html) library and the
installed [pydantic](https://pydantic-docs.helpmanual.io/) library for
validation.
So let us do that.
```python
from typing import Literal
from .baseinvocation import BaseInvocation
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
```
That's great.
Now we have setup the base of our new Invocation. Let us think about what inputs
our Invocation takes.
- We need an `image` that we are going to resize.
- We will need new `width` and `height` values to which we need to resize the
image to.
### **Inputs**
Every Invocation input is a pydantic `Field` and like everything else should be
strictly typed and defined.
So let us create these inputs for our Invocation. First up, the `image` input we
need. Generally, we can use standard variable types in Python but InvokeAI
already has a custom `ImageField` type that handles all the stuff that is needed
for image inputs.
But what is this `ImageField` ..? It is a special class type specifically
written to handle how images are dealt with in InvokeAI. We will cover how to
create your own custom field types later in this guide. For now, let's go ahead
and use it.
```python
from typing import Literal, Union
from pydantic import Field
from .baseinvocation import BaseInvocation
from ..models.image import ImageField
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
# Inputs
image: Union[ImageField, None] = Field(description="The input image", default=None)
```
Let us break down our input code.
```python
image: Union[ImageField, None] = Field(description="The input image", default=None)
```
| Part | Value | Description |
| --------- | ---------------------------------------------------- | -------------------------------------------------------------------------------------------------- |
| Name | `image` | The variable that will hold our image |
| Type Hint | `Union[ImageField, None]` | The types for our field. Indicates that the image can either be an `ImageField` type or `None` |
| Field | `Field(description="The input image", default=None)` | The image variable is a field which needs a description and a default value that we set to `None`. |
Great. Now let us create our other inputs for `width` and `height`
```python
from typing import Literal, Union
from pydantic import Field
from .baseinvocation import BaseInvocation
from ..models.image import ImageField
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
# Inputs
image: Union[ImageField, None] = Field(description="The input image", default=None)
width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
```
As you might have noticed, we added two new parameters to the field type for
`width` and `height` called `gt` and `le`. These basically stand for _greater
than or equal to_ and _less than or equal to_. There are various other param
types for field that you can find on the **pydantic** documentation.
**Note:** _Any time it is possible to define constraints for our field, we
should do it so the frontend has more information on how to parse this field._
Perfect. We now have our inputs. Let us do something with these.
### **Invoke Function**
The `invoke` function is where all the magic happens. This function provides you
the `context` parameter that is of the type `InvocationContext` which will give
you access to the current context of the generation and all the other services
that are provided by it by InvokeAI.
Let us create this function first.
```python
from typing import Literal, Union
from pydantic import Field
from .baseinvocation import BaseInvocation, InvocationContext
from ..models.image import ImageField
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
# Inputs
image: Union[ImageField, None] = Field(description="The input image", default=None)
width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
def invoke(self, context: InvocationContext):
pass
```
### **Outputs**
The output of our Invocation will be whatever is returned by this `invoke`
function. Like with our inputs, we need to strongly type and define our outputs
too.
What is our output going to be? Another image. Normally you'd have to create a
type for this but InvokeAI already offers you an `ImageOutput` type that handles
all the necessary info related to image outputs. So let us use that.
We will cover how to create your own output types later in this guide.
```python
from typing import Literal, Union
from pydantic import Field
from .baseinvocation import BaseInvocation, InvocationContext
from ..models.image import ImageField
from .image import ImageOutput
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
# Inputs
image: Union[ImageField, None] = Field(description="The input image", default=None)
width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
def invoke(self, context: InvocationContext) -> ImageOutput:
pass
```
Perfect. Now that we have our Invocation setup, let us do what we want to do.
- We will first load the image. Generally we do this using the `PIL` library but
we can use one of the services provided by InvokeAI to load the image.
- We will resize the image using `PIL` to our input data.
- We will output this image in the format we set above.
So let's do that.
```python
from typing import Literal, Union
from pydantic import Field
from .baseinvocation import BaseInvocation, InvocationContext
from ..models.image import ImageField, ResourceOrigin, ImageCategory
from .image import ImageOutput
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
# Inputs
image: Union[ImageField, None] = Field(description="The input image", default=None)
width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
def invoke(self, context: InvocationContext) -> ImageOutput:
# Load the image using InvokeAI's predefined Image Service.
image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
# Resizing the image
# Because we used the above service, we already have a PIL image. So we can simply resize.
resized_image = image.resize((self.width, self.height))
# Preparing the image for output using InvokeAI's predefined Image Service.
output_image = context.services.images.create(
image=resized_image,
image_origin=ResourceOrigin.INTERNAL,
image_category=ImageCategory.GENERAL,
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
)
# Returning the Image
return ImageOutput(
image=ImageField(
image_name=output_image.image_name,
image_origin=output_image.image_origin,
),
width=output_image.width,
height=output_image.height,
)
```
**Note:** Do not be overwhelmed by the `ImageOutput` process. InvokeAI has a
certain way that the images need to be dispatched in order to be stored and read
correctly. In 99% of the cases when dealing with an image output, you can simply
copy-paste the template above.
That's it. You made your own **Resize Invocation**.
## Result
Once you make your Invocation correctly, the rest of the process is fully
automated for you.
When you launch InvokeAI, you can go to `http://localhost:9090/docs` and see
your new Invocation show up there with all the relevant info.
![resize invocation](../assets/contributing/resize_invocation.png)
When you launch the frontend UI, you can go to the Node Editor tab and find your
new Invocation ready to be used.
![resize node editor](../assets/contributing/resize_node_editor.png)
# Advanced
## Custom Input Fields
Now that you know how to create your own Invocations, let us dive into slightly
more advanced topics.
While creating your own Invocations, you might run into a scenario where the
existing input types in InvokeAI do not meet your requirements. In such cases,
you can create your own input types.
Let us create one as an example. Let us say we want to create a color input
field that represents a color code. But before we start on that here are some
general good practices to keep in mind.
**Good Practices**
- There is no naming convention for input fields but we highly recommend that
you name it something appropriate like `ColorField`.
- It is not mandatory but it is heavily recommended to add a relevant
`docstring` to describe your input field.
- Keep your field in the same file as the Invocation that it is made for or in
another file where it is relevant.
All input types a class that derive from the `BaseModel` type from `pydantic`.
So let's create one.
```python
from pydantic import BaseModel
class ColorField(BaseModel):
'''A field that holds the rgba values of a color'''
pass
```
Perfect. Now let us create our custom inputs for our field. This is exactly
similar how you created input fields for your Invocation. All the same rules
apply. Let us create four fields representing the _red(r)_, _blue(b)_,
_green(g)_ and _alpha(a)_ channel of the color.
```python
class ColorField(BaseModel):
'''A field that holds the rgba values of a color'''
r: int = Field(ge=0, le=255, description="The red channel")
g: int = Field(ge=0, le=255, description="The green channel")
b: int = Field(ge=0, le=255, description="The blue channel")
a: int = Field(ge=0, le=255, description="The alpha channel")
```
That's it. We now have a new input field type that we can use in our Invocations
like this.
```python
color: ColorField = Field(default=ColorField(r=0, g=0, b=0, a=0), description='Background color of an image')
```
**Extra Config**
All input fields also take an additional `Config` class that you can use to do
various advanced things like setting required parameters and etc.
Let us do that for our _ColorField_ and enforce all the values because we did
not define any defaults for our fields.
```python
class ColorField(BaseModel):
'''A field that holds the rgba values of a color'''
r: int = Field(ge=0, le=255, description="The red channel")
g: int = Field(ge=0, le=255, description="The green channel")
b: int = Field(ge=0, le=255, description="The blue channel")
a: int = Field(ge=0, le=255, description="The alpha channel")
class Config:
schema_extra = {"required": ["r", "g", "b", "a"]}
```
Now it becomes mandatory for the user to supply all the values required by our
input field.
We will discuss the `Config` class in extra detail later in this guide and how
you can use it to make your Invocations more robust.
## Custom Output Types
Like with custom inputs, sometimes you might find yourself needing custom
outputs that InvokeAI does not provide. We can easily set one up.
Now that you are familiar with Invocations and Inputs, let us use that knowledge
to put together a custom output type for an Invocation that returns _width_,
_height_ and _background_color_ that we need to create a blank image.
- A custom output type is a class that derives from the parent class of
`BaseInvocationOutput`.
- It is not mandatory but we recommend using names ending with `Output` for
output types. So we'll call our class `BlankImageOutput`
- It is not mandatory but we highly recommend adding a `docstring` to describe
what your output type is for.
- Like Invocations, each output type should have a `type` variable that is
**unique**
Now that we know the basic rules for creating a new output type, let us go ahead
and make it.
```python
from typing import Literal
from pydantic import Field
from .baseinvocation import BaseInvocationOutput
class BlankImageOutput(BaseInvocationOutput):
'''Base output type for creating a blank image'''
type: Literal['blank_image_output'] = 'blank_image_output'
# Inputs
width: int = Field(description='Width of blank image')
height: int = Field(description='Height of blank image')
bg_color: ColorField = Field(description='Background color of blank image')
class Config:
schema_extra = {"required": ["type", "width", "height", "bg_color"]}
```
All set. We now have an output type that requires what we need to create a
blank_image. And if you noticed it, we even used the `Config` class to ensure
the fields are required.
## Custom Configuration
As you might have noticed when making inputs and outputs, we used a class called
`Config` from _pydantic_ to further customize them. Because our inputs and
outputs essentially inherit from _pydantic_'s `BaseModel` class, all
[configuration options](https://docs.pydantic.dev/latest/usage/schema/#schema-customization)
that are valid for _pydantic_ classes are also valid for our inputs and outputs.
You can do the same for your Invocations too but InvokeAI makes our life a
little bit easier on that end.
InvokeAI provides a custom configuration class called `InvocationConfig`
particularly for configuring Invocations. This is exactly the same as the raw
`Config` class from _pydantic_ with some extra stuff on top to help faciliate
parsing of the scheme in the frontend UI.
At the current moment, tihs `InvocationConfig` class is further improved with
the following features related the `ui`.
| Config Option | Field Type | Example |
| ------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- |
| type_hints | `Dict[str, Literal["integer", "float", "boolean", "string", "enum", "image", "latents", "model", "control"]]` | `type_hint: "model"` provides type hints related to the model like displaying a list of available models |
| tags | `List[str]` | `tags: ['resize', 'image']` will classify your invocation under the tags of resize and image. |
| title | `str` | `title: 'Resize Image` will rename your to this custom title rather than infer from the name of the Invocation class. |
So let us update your `ResizeInvocation` with some extra configuration and see
how that works.
```python
from typing import Literal, Union
from pydantic import Field
from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
from ..models.image import ImageField, ResourceOrigin, ImageCategory
from .image import ImageOutput
class ResizeInvocation(BaseInvocation):
'''Resizes an image'''
type: Literal['resize'] = 'resize'
# Inputs
image: Union[ImageField, None] = Field(description="The input image", default=None)
width: int = Field(default=512, ge=64, le=2048, description="Width of the new image")
height: int = Field(default=512, ge=64, le=2048, description="Height of the new image")
class Config(InvocationConfig):
schema_extra: {
ui: {
tags: ['resize', 'image'],
title: ['My Custom Resize']
}
}
def invoke(self, context: InvocationContext) -> ImageOutput:
# Load the image using InvokeAI's predefined Image Service.
image = context.services.images.get_pil_image(self.image.image_origin, self.image.image_name)
# Resizing the image
# Because we used the above service, we already have a PIL image. So we can simply resize.
resized_image = image.resize((self.width, self.height))
# Preparing the image for output using InvokeAI's predefined Image Service.
output_image = context.services.images.create(
image=resized_image,
image_origin=ResourceOrigin.INTERNAL,
image_category=ImageCategory.GENERAL,
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
)
# Returning the Image
return ImageOutput(
image=ImageField(
image_name=output_image.image_name,
image_origin=output_image.image_origin,
),
width=output_image.width,
height=output_image.height,
)
```
We now customized our code to let the frontend know that our Invocation falls
under `resize` and `image` categories. So when the user searches for these
particular words, our Invocation will show up too.
We also set a custom title for our Invocation. So instead of being called
`Resize`, it will be called `My Custom Resize`.
As simple as that.
As time goes by, InvokeAI will further improve and add more customizability for
Invocation configuration. We will have more documentation regarding this at a
later time.
# **[TODO]**
## Custom Components For Frontend
Every backend input type should have a corresponding frontend component so the
UI knows what to render when you use a particular field type.
If you are using existing field types, we already have components for those. So
you don't have to worry about creating anything new. But this might not always
be the case. Sometimes you might want to create new field types and have the
frontend UI deal with it in a different way.
This is where we venture into the world of React and Javascript and create our
own new components for our Invocations. Do not fear the world of JS. It's
actually pretty straightforward.
Let us create a new component for our custom color field we created above. When
we use a color field, let us say we want the UI to display a color picker for
the user to pick from rather than entering values. That is what we will build
now.
---
# OLD -- TO BE DELETED OR MOVED LATER
---
## Creating a new invocation

92
docs/features/CONCEPTS.md
View File

@ -1,9 +1,12 @@
---
title: Concepts Library
title: Concepts
---
# :material-library-shelves: The Hugging Face Concepts Library and Importing Textual Inversion files
With the advances in research, many new capabilities are available to customize the knowledge and understanding of novel concepts not originally contained in the base model.
## Using Textual Inversion Files
Textual inversion (TI) files are small models that customize the output of
@ -12,18 +15,16 @@ and artistic styles. They are also known as "embeds" in the machine learning
world.
Each TI file introduces one or more vocabulary terms to the SD model. These are
known in InvokeAI as "triggers." Triggers are often, but not always, denoted
using angle brackets as in "<trigger-phrase>". The two most common type of
known in InvokeAI as "triggers." Triggers are denoted using angle brackets
as in "<trigger-phrase>". The two most common type of
TI files that you'll encounter are `.pt` and `.bin` files, which are produced by
different TI training packages. InvokeAI supports both formats, but its
[built-in TI training system](TEXTUAL_INVERSION.md) produces `.pt`.
[built-in TI training system](TRAINING.md) produces `.pt`.
The [Hugging Face company](https://huggingface.co/sd-concepts-library) has
amassed a large ligrary of >800 community-contributed TI files covering a
broad range of subjects and styles. InvokeAI has built-in support for this
library which downloads and merges TI files automatically upon request. You can
also install your own or others' TI files by placing them in a designated
directory.
broad range of subjects and styles. You can also install your own or others' TI files
by placing them in the designated directory for the compatible model type
### An Example
@ -41,66 +42,43 @@ You can also combine styles and concepts:
| :--------------------------------------------------------: |
| ![](../assets/concepts/image5.png) |
</figure>
## Using a Hugging Face Concept
!!! warning "Authenticating to HuggingFace"
Some concepts require valid authentication to HuggingFace. Without it, they will not be downloaded
and will be silently ignored.
If you used an installer to install InvokeAI, you may have already set a HuggingFace token.
If you skipped this step, you can:
- run the InvokeAI configuration script again (if you used a manual installer): `invokeai-configure`
- set one of the `HUGGINGFACE_TOKEN` or `HUGGING_FACE_HUB_TOKEN` environment variables to contain your token
Finally, if you already used any HuggingFace library on your computer, you might already have a token
in your local cache. Check for a hidden `.huggingface` directory in your home folder. If it
contains a `token` file, then you are all set.
Hugging Face TI concepts are downloaded and installed automatically as you
require them. This requires your machine to be connected to the Internet. To
find out what each concept is for, you can browse the
[Hugging Face concepts library](https://huggingface.co/sd-concepts-library) and
look at examples of what each concept produces.
To load concepts, you will need to open the Web UI's configuration
dialogue and activate "Show Textual Inversions from HF Concepts
Library". This will then add a list of HF Concepts to the dropdown
"Add Textual Inversion" menu. Select the concept(s) of your choice and
they will be incorporated into the positive prompt. A few concepts are
designed for the negative prompt, in which case you can add them to
the negative prompt box by select the down arrow icon next to the
textual inversion menu.
There are nearly 1000 HF concepts, more than will fit into a menu. For
this reason we only show the most popular concepts (those which have
received 5 or more likes). If you wish to use a concept that is not on
the list, you may simply type its name surrounded by brackets. For
example, to load the concept named "xidiversity", add `<xidiversity>`
to the positive or negative prompt text.
## Installing your Own TI Files
You may install any number of `.pt` and `.bin` files simply by copying them into
the `embeddings` directory of the InvokeAI runtime directory (usually `invokeai`
in your home directory). You may create subdirectories in order to organize the
files in any way you wish. Be careful not to overwrite one file with another.
the `embedding` directory of the corresponding InvokeAI models directory (usually `invokeai`
in your home directory). For example, you can simply move a Stable Diffusion 1.5 embedding file to
the `sd-1/embedding` folder. Be careful not to overwrite one file with another.
For example, TI files generated by the Hugging Face toolkit share the named
`learned_embedding.bin`. You can use subdirectories to keep them distinct.
`learned_embedding.bin`. You can rename these, or use subdirectories to keep them distinct.
At startup time, InvokeAI will scan the `embeddings` directory and load any TI
files it finds there. At startup you will see a message similar to this one:
At startup time, InvokeAI will scan the various `embedding` directories and load any TI
files it finds there for compatible models. At startup you will see a message similar to this one:
```bash
>> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
```
To use these when generating, simply type the `<` key in your prompt to open the Textual Inversion WebUI and
select the embedding you'd like to use. This UI has type-ahead support, so you can easily find supported embeddings.
The terms you can use will appear in the "Add Textual Inversion"
dropdown menu above the HF Concepts.
## Using LoRAs
## Further Reading
LoRA files are models that customize the output of Stable Diffusion image generation.
Larger than embeddings, but much smaller than full models, they augment SD with improved
understanding of subjects and artistic styles.
Unlike TI files, LoRAs do not introduce novel vocabulary into the model's known tokens. Instead,
LoRAs augment the model's weights that are applied to generate imagery. LoRAs may be supplied
with a "trigger" word that they have been explicitly trained on, or may simply apply their
effect without being triggered.
LoRAs are typically stored in .safetensors files, which are the most secure way to store and transmit
these types of weights. You may install any number of `.safetensors` LoRA files simply by copying them into
the `lora` directory of the corresponding InvokeAI models directory (usually `invokeai`
in your home directory). For example, you can simply move a Stable Diffusion 1.5 LoRA file to
the `sd-1/lora` folder.
To use these when generating, open the LoRA menu item in the options panel, select the LoRAs you want to apply
and ensure that they have the appropriate weight recommended by the model provider. Typically, most LoRAs perform best at a weight of .75-1.
Please see [the repository](https://github.com/rinongal/textual_inversion) and
associated paper for details and limitations.

47
docs/features/PROMPTS.md
View File

@ -301,5 +301,48 @@ summoning up the concept of some sort of scifi creature? Let's find out.
Indeed, removing the word "hybrid" produces an image that is more like what we'd
expect.
In conclusion, prompt blending is great for exploring creative space,
but takes some trial and error to achieve the desired effect.
## Dynamic Prompts
Dynamic Prompts are a powerful feature designed to produce a variety of prompts based on user-defined options. Using a special syntax, you can construct a prompt with multiple possibilities, and the system will automatically generate a series of permutations based on your settings. This is extremely beneficial for ideation, exploring various scenarios, or testing different concepts swiftly and efficiently.
### Structure of a Dynamic Prompt
A Dynamic Prompt comprises of regular text, supplemented with alternatives enclosed within curly braces {} and separated by a vertical bar |. For example: {option1|option2|option3}. The system will then select one of the options to include in the final prompt. This flexible system allows for options to be placed throughout the text as needed.
Furthermore, Dynamic Prompts can designate multiple selections from a single group of options. This feature is triggered by prefixing the options with a numerical value followed by $$. For example, in {2$$option1|option2|option3}, the system will select two distinct options from the set.
### Creating Dynamic Prompts
To create a Dynamic Prompt, follow these steps:
Draft your sentence or phrase, identifying words or phrases with multiple possible options.
Encapsulate the different options within curly braces {}.
Within the braces, separate each option using a vertical bar |.
If you want to include multiple options from a single group, prefix with the desired number and $$.
For instance: A {house|apartment|lodge|cottage} in {summer|winter|autumn|spring} designed in {2$$style1|style2|style3}.
### How Dynamic Prompts Work
Once a Dynamic Prompt is configured, the system generates an array of combinations using the options provided. Each group of options in curly braces is treated independently, with the system selecting one option from each group. For a prefixed set (e.g., 2$$), the system will select two distinct options.
For example, the following prompts could be generated from the above Dynamic Prompt:
A house in summer designed in style1, style2
A lodge in autumn designed in style3, style1
A cottage in winter designed in style2, style3
And many more!
When the `Combinatorial` setting is on, Invoke will disable the "Images" selection, and generate every combination up until the setting for Max Prompts is reached.
When the `Combinatorial` setting is off, Invoke will randomly generate combinations up until the setting for Images has been reached.
### Tips and Tricks for Using Dynamic Prompts
Below are some useful strategies for creating Dynamic Prompts:
Utilize Dynamic Prompts to generate a wide spectrum of prompts, perfect for brainstorming and exploring diverse ideas.
Ensure that the options within a group are contextually relevant to the part of the sentence where they are used. For instance, group building types together, and seasons together.
Apply the 2$$ prefix when you want to incorporate more than one option from a single group. This becomes quite handy when mixing and matching different elements.
Experiment with different quantities for the prefix. For example, 3$$ will select three distinct options.
Be aware of coherence in your prompts. Although the system can generate all possible combinations, not all may semantically make sense. Therefore, carefully choose the options for each group.
Always review and fine-tune the generated prompts as needed. While Dynamic Prompts can help you generate a multitude of combinations, the final polishing and refining remain in your hands.

15
docs/features/TEXTUAL_INVERSION.md → docs/features/TRAINING.md
View File

@ -1,9 +1,10 @@
---
title: Textual-Inversion
title: Training
---
# :material-file-document: Textual Inversion
# :material-file-document: Training
# Textual Inversion Training
## **Personalizing Text-to-Image Generation**
You may personalize the generated images to provide your own styles or objects
@ -258,16 +259,6 @@ invokeai-ti \
--only_save_embeds
```
## Using Embeddings
After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings/<trigger word>/learned_embeds.bin`.
These will be automatically loaded when you start InvokeAI.
Add the trigger word, surrounded by angle brackets, to use that embedding. For example, if your trigger word was `terence`, use `<terence>` in prompts. This is the same syntax used by the HuggingFace concepts library.
**Note:** `.pt` embeddings do not require the angle brackets.
## Troubleshooting
### `Cannot load embedding for <trigger>. It was trained on a model with token dimension 1024, but the current model has token dimension 768`

9
invokeai/app/api_app.py
View File

@ -30,6 +30,8 @@ if app_config.version:
sys.exit(0)
import invokeai.frontend.web as web_dir
import mimetypes
from .api.dependencies import ApiDependencies
from .api.routers import sessions, models, images, boards, board_images, app_info
from .api.sockets import SocketIO
@ -39,7 +41,12 @@ from .invocations.baseinvocation import BaseInvocation
import torch
if torch.backends.mps.is_available():
import invokeai.backend.util.mps_fixes
# fix for windows mimetypes registry entries being borked
# see https://github.com/invoke-ai/InvokeAI/discussions/3684#discussioncomment-6391352
mimetypes.add_type('application/javascript', '.js')
mimetypes.add_type('text/css', '.css')
# Create the app
# TODO: create this all in a method so configuration/etc. can be passed in?
app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None)

1
invokeai/frontend/web/src/features/embedding/components/ParamEmbeddingPopover.tsx
View File

@ -115,6 +115,7 @@ const ParamEmbeddingPopover = (props: Props) => {
nothingFound="No matching Embeddings"
itemComponent={IAIMantineSelectItemWithTooltip}
disabled={data.length === 0}
onDropdownClose={onClose}
filter={(value, item: SelectItem) =>
item.label
?.toLowerCase()

13
invokeai/frontend/web/src/features/gallery/components/ImageGalleryGrid.tsx
View File

@ -57,6 +57,7 @@ const selector = createSelector(
images,
allImagesTotal,
isLoading,
isFetching,
categories,
selectedBoardId,
};
@ -82,8 +83,14 @@ const ImageGalleryGrid = () => {
},
});
const { images, isLoading, allImagesTotal, categories, selectedBoardId } =
useAppSelector(selector);
const {
images,
isLoading,
isFetching,
allImagesTotal,
categories,
selectedBoardId,
} = useAppSelector(selector);
const { selectedBoard } = useListAllBoardsQuery(undefined, {
selectFromResult: ({ data }) => ({
@ -176,7 +183,7 @@ const ImageGalleryGrid = () => {
<IAIButton
onClick={handleLoadMoreImages}
isDisabled={!areMoreAvailable}
isLoading={isLoading}
isLoading={isFetching}
loadingText="Loading"
flexShrink={0}
>

80
invokeai/frontend/web/src/features/gallery/components/NextPrevImageButtons.tsx
View File

@ -1,17 +1,18 @@
import { ChakraProps, Flex, Grid, IconButton } from '@chakra-ui/react';
import { ChakraProps, Flex, Grid, IconButton, Spinner } from '@chakra-ui/react';
import { createSelector } from '@reduxjs/toolkit';
import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import { clamp, isEqual } from 'lodash-es';
import { useCallback, useState } from 'react';
import { useTranslation } from 'react-i18next';
import { FaAngleLeft, FaAngleRight } from 'react-icons/fa';
import { stateSelector } from 'app/store/store';
import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import {
imageSelected,
selectFilteredImages,
selectImagesById,
} from 'features/gallery/store/gallerySlice';
import { clamp, isEqual } from 'lodash-es';
import { useCallback, useState } from 'react';
import { useHotkeys } from 'react-hotkeys-hook';
import { selectFilteredImages } from 'features/gallery/store/gallerySlice';
import { useTranslation } from 'react-i18next';
import { FaAngleDoubleRight, FaAngleLeft, FaAngleRight } from 'react-icons/fa';
import { receivedPageOfImages } from 'services/api/thunks/image';
const nextPrevButtonTriggerAreaStyles: ChakraProps['sx'] = {
height: '100%',
@ -26,6 +27,7 @@ const nextPrevButtonStyles: ChakraProps['sx'] = {
export const nextPrevImageButtonsSelector = createSelector(
[stateSelector, selectFilteredImages],
(state, filteredImages) => {
const { total, isFetching } = state.gallery;
const lastSelectedImage =
state.gallery.selection[state.gallery.selection.length - 1];
@ -63,6 +65,8 @@ export const nextPrevImageButtonsSelector = createSelector(
isOnFirstImage: currentImageIndex === 0,
isOnLastImage:
!isNaN(currentImageIndex) && currentImageIndex === imagesLength - 1,
areMoreImagesAvailable: total > imagesLength,
isFetching,
nextImage,
prevImage,
nextImageId,
@ -80,8 +84,14 @@ const NextPrevImageButtons = () => {
const dispatch = useAppDispatch();
const { t } = useTranslation();
const { isOnFirstImage, isOnLastImage, nextImageId, prevImageId } =
useAppSelector(nextPrevImageButtonsSelector);
const {
isOnFirstImage,
isOnLastImage,
nextImageId,
prevImageId,
areMoreImagesAvailable,
isFetching,
} = useAppSelector(nextPrevImageButtonsSelector);
const [shouldShowNextPrevButtons, setShouldShowNextPrevButtons] =
useState<boolean>(false);
@ -102,6 +112,14 @@ const NextPrevImageButtons = () => {
nextImageId && dispatch(imageSelected(nextImageId));
}, [dispatch, nextImageId]);
const handleLoadMoreImages = useCallback(() => {
dispatch(
receivedPageOfImages({
is_intermediate: false,
})
);
}, [dispatch]);
useHotkeys(
'left',
() => {
@ -113,9 +131,21 @@ const NextPrevImageButtons = () => {
useHotkeys(
'right',
() => {
handleNextImage();
if (isOnLastImage && areMoreImagesAvailable && !isFetching) {
handleLoadMoreImages();
return;
}
if (!isOnLastImage) {
handleNextImage();
}
},
[nextImageId]
[
nextImageId,
isOnLastImage,
areMoreImagesAvailable,
handleLoadMoreImages,
isFetching,
]
);
return (
@ -164,6 +194,34 @@ const NextPrevImageButtons = () => {
sx={nextPrevButtonStyles}
/>
)}
{shouldShowNextPrevButtons &&
isOnLastImage &&
areMoreImagesAvailable &&
!isFetching && (
<IconButton
aria-label={t('accessibility.loadMore')}
icon={<FaAngleDoubleRight size={64} />}
variant="unstyled"
onClick={handleLoadMoreImages}
boxSize={16}
sx={nextPrevButtonStyles}
/>
)}
{shouldShowNextPrevButtons &&
isOnLastImage &&
areMoreImagesAvailable &&
isFetching && (
<Flex
sx={{
w: 16,
h: 16,
alignItems: 'center',
justifyContent: 'center',
}}
>
<Spinner opacity={0.5} size="xl" />
</Flex>
)}
</Grid>
</Flex>
);

6
invokeai/frontend/web/src/features/nodes/components/AddNodeMenu.tsx
View File

@ -28,6 +28,12 @@ const selector = createSelector(
};
});
data.push({
label: 'Progress Image',
value: 'progress_image',
description: 'Displays the progress image in the Node Editor',
});
return { data };
},
defaultSelectorOptions

22
invokeai/frontend/web/src/features/nodes/components/Flow.tsx
View File

@ -1,14 +1,15 @@
import { RootState } from 'app/store/store';
import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import { useCallback } from 'react';
import {
Background,
OnConnect,
OnConnectEnd,
OnConnectStart,
OnEdgesChange,
OnNodesChange,
ReactFlow,
OnConnectStart,
OnConnectEnd,
} from 'reactflow';
import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import { RootState } from 'app/store/store';
import {
connectionEnded,
connectionMade,
@ -16,15 +17,18 @@ import {
edgesChanged,
nodesChanged,
} from '../store/nodesSlice';
import { useCallback } from 'react';
import { InvocationComponent } from './InvocationComponent';
import TopLeftPanel from './panels/TopLeftPanel';
import TopRightPanel from './panels/TopRightPanel';
import TopCenterPanel from './panels/TopCenterPanel';
import ProgressImageNode from './ProgressImageNode';
import BottomLeftPanel from './panels/BottomLeftPanel.tsx';
import MinimapPanel from './panels/MinimapPanel';
import TopCenterPanel from './panels/TopCenterPanel';
import TopLeftPanel from './panels/TopLeftPanel';
import TopRightPanel from './panels/TopRightPanel';
const nodeTypes = { invocation: InvocationComponent };
const nodeTypes = {
invocation: InvocationComponent,
progress_image: ProgressImageNode,
};
export const Flow = () => {
const dispatch = useAppDispatch();

19
invokeai/frontend/web/src/features/nodes/components/IAINode/IAINodeHeader.tsx
View File

@ -1,15 +1,15 @@
import { Flex, Heading, Tooltip, Icon } from '@chakra-ui/react';
import { InvocationTemplate } from 'features/nodes/types/types';
import { Flex, Heading, Icon, Tooltip } from '@chakra-ui/react';
import { memo } from 'react';
import { FaInfoCircle } from 'react-icons/fa';
interface IAINodeHeaderProps {
nodeId: string;
template: InvocationTemplate;
nodeId?: string;
title?: string;
description?: string;
}
const IAINodeHeader = (props: IAINodeHeaderProps) => {
const { nodeId, template } = props;
const { nodeId, title, description } = props;
return (
<Flex
sx={{
@ -31,15 +31,10 @@ const IAINodeHeader = (props: IAINodeHeaderProps) => {
_dark: { color: 'base.100' },
}}
>
{template.title}
{title}
</Heading>
</Tooltip>
<Tooltip
label={template.description}
placement="top"
hasArrow
shouldWrapChildren
>
<Tooltip label={description} placement="top" hasArrow shouldWrapChildren>
<Icon
sx={{
h: 'min-content',

82
invokeai/frontend/web/src/features/nodes/components/InvocationComponent.tsx
View File

@ -1,64 +1,16 @@
import { NodeProps } from 'reactflow';
import { Box, Flex, Icon, useToken } from '@chakra-ui/react';
import { Flex, Icon } from '@chakra-ui/react';
import { FaExclamationCircle } from 'react-icons/fa';
import { InvocationTemplate, InvocationValue } from '../types/types';
import { NodeProps } from 'reactflow';
import { InvocationValue } from '../types/types';
import { memo, PropsWithChildren, useMemo } from 'react';
import IAINodeOutputs from './IAINode/IAINodeOutputs';
import IAINodeInputs from './IAINode/IAINodeInputs';
import IAINodeHeader from './IAINode/IAINodeHeader';
import IAINodeResizer from './IAINode/IAINodeResizer';
import { RootState } from 'app/store/store';
import { AnyInvocationType } from 'services/events/types';
import { createSelector } from '@reduxjs/toolkit';
import { useAppSelector } from 'app/store/storeHooks';
import { NODE_MIN_WIDTH } from 'app/constants';
type InvocationComponentWrapperProps = PropsWithChildren & {
selected: boolean;
};
const InvocationComponentWrapper = (props: InvocationComponentWrapperProps) => {
const [nodeSelectedOutline, nodeShadow] = useToken('shadows', [
'nodeSelectedOutline',
'dark-lg',
]);
return (
<Box
sx={{
position: 'relative',
borderRadius: 'md',
minWidth: NODE_MIN_WIDTH,
shadow: props.selected
? `${nodeSelectedOutline}, ${nodeShadow}`
: `${nodeShadow}`,
}}
>
{props.children}
</Box>
);
};
const makeTemplateSelector = (type: AnyInvocationType) =>
createSelector(
[(state: RootState) => state.nodes],
(nodes) => {
const template = nodes.invocationTemplates[type];
if (!template) {
return;
}
return template;
},
{
memoizeOptions: {
resultEqualityCheck: (
a: InvocationTemplate | undefined,
b: InvocationTemplate | undefined
) => a !== undefined && b !== undefined && a.type === b.type,
},
}
);
import { memo, useMemo } from 'react';
import { makeTemplateSelector } from '../store/util/makeTemplateSelector';
import IAINodeHeader from './IAINode/IAINodeHeader';
import IAINodeInputs from './IAINode/IAINodeInputs';
import IAINodeOutputs from './IAINode/IAINodeOutputs';
import IAINodeResizer from './IAINode/IAINodeResizer';
import NodeWrapper from './NodeWrapper';
export const InvocationComponent = memo((props: NodeProps<InvocationValue>) => {
const { id: nodeId, data, selected } = props;
@ -70,7 +22,7 @@ export const InvocationComponent = memo((props: NodeProps<InvocationValue>) => {
if (!template) {
return (
<InvocationComponentWrapper selected={selected}>
<NodeWrapper selected={selected}>
<Flex sx={{ alignItems: 'center', justifyContent: 'center' }}>
<Icon
as={FaExclamationCircle}
@ -82,13 +34,17 @@ export const InvocationComponent = memo((props: NodeProps<InvocationValue>) => {
></Icon>
<IAINodeResizer />
</Flex>
</InvocationComponentWrapper>
</NodeWrapper>
);
}
return (
<InvocationComponentWrapper selected={selected}>
<IAINodeHeader nodeId={nodeId} template={template} />
<NodeWrapper selected={selected}>
<IAINodeHeader
nodeId={nodeId}
title={template.title}
description={template.description}
/>
<Flex
sx={{
flexDirection: 'column',
@ -102,7 +58,7 @@ export const InvocationComponent = memo((props: NodeProps<InvocationValue>) => {
<IAINodeInputs nodeId={nodeId} inputs={inputs} template={template} />
</Flex>
<IAINodeResizer />
</InvocationComponentWrapper>
</NodeWrapper>
);
});

32
invokeai/frontend/web/src/features/nodes/components/NodeWrapper.tsx Normal file
View File

@ -0,0 +1,32 @@
import { Box, useToken } from '@chakra-ui/react';
import { NODE_MIN_WIDTH } from 'app/constants';
import { PropsWithChildren } from 'react';
type NodeWrapperProps = PropsWithChildren & {
selected: boolean;
};
const NodeWrapper = (props: NodeWrapperProps) => {
const [nodeSelectedOutline, nodeShadow] = useToken('shadows', [
'nodeSelectedOutline',
'dark-lg',
]);
return (
<Box
sx={{
position: 'relative',
borderRadius: 'md',
minWidth: NODE_MIN_WIDTH,
shadow: props.selected
? `${nodeSelectedOutline}, ${nodeShadow}`
: `${nodeShadow}`,
}}
>
{props.children}
</Box>
);
};
export default NodeWrapper;

64
invokeai/frontend/web/src/features/nodes/components/ProgressImageNode.tsx Normal file
View File

@ -0,0 +1,64 @@
import { Flex, Image } from '@chakra-ui/react';
import { NodeProps } from 'reactflow';
import { InvocationValue } from '../types/types';
import { useAppSelector } from 'app/store/storeHooks';
import { IAINoContentFallback } from 'common/components/IAIImageFallback';
import { memo } from 'react';
import IAINodeHeader from './IAINode/IAINodeHeader';
import IAINodeResizer from './IAINode/IAINodeResizer';
import NodeWrapper from './NodeWrapper';
const ProgressImageNode = (props: NodeProps<InvocationValue>) => {
const progressImage = useAppSelector((state) => state.system.progressImage);
const { selected } = props;
return (
<NodeWrapper selected={selected}>
<IAINodeHeader
title="Progress Image"
description="Displays the progress image in the Node Editor"
/>
<Flex
sx={{
flexDirection: 'column',
borderBottomRadius: 'md',
p: 2,
bg: 'base.200',
_dark: { bg: 'base.800' },
}}
>
{progressImage ? (
<Image
src={progressImage.dataURL}
sx={{
w: 'full',
h: 'full',
objectFit: 'contain',
}}
/>
) : (
<Flex
sx={{
w: 'full',
h: 'full',
minW: 32,
minH: 32,
alignItems: 'center',
justifyContent: 'center',
}}
>
<IAINoContentFallback />
</Flex>
)}
</Flex>
<IAINodeResizer
maxHeight={progressImage?.height ?? 512}
maxWidth={progressImage?.width ?? 512}
/>
</NodeWrapper>
);
};
export default memo(ProgressImageNode);

2
invokeai/frontend/web/src/features/nodes/components/panels/TopCenterPanel.tsx
View File

@ -5,6 +5,7 @@ import { memo, useCallback } from 'react';
import { Panel } from 'reactflow';
import { receivedOpenAPISchema } from 'services/api/thunks/schema';
import NodeInvokeButton from '../ui/NodeInvokeButton';
import CancelButton from 'features/parameters/components/ProcessButtons/CancelButton';
const TopCenterPanel = () => {
const dispatch = useAppDispatch();
@ -17,6 +18,7 @@ const TopCenterPanel = () => {
<Panel position="top-center">
<HStack>
<NodeInvokeButton />
<CancelButton />
<IAIButton onClick={handleReloadSchema}>Reload Schema</IAIButton>
</HStack>
</Panel>

18
invokeai/frontend/web/src/features/nodes/hooks/useBuildInvocation.ts
View File

@ -24,7 +24,23 @@ export const useBuildInvocation = () => {
const flow = useReactFlow();
return useCallback(
(type: AnyInvocationType) => {
(type: AnyInvocationType | 'progress_image') => {
if (type === 'progress_image') {
const { x, y } = flow.project({
x: window.innerWidth / 2.5,
y: window.innerHeight / 8,
});
const node: Node = {
id: 'progress_image',
type: 'progress_image',
position: { x: x, y: y },
data: {},
};
return node;
}
const template = invocationTemplates[type];
if (template === undefined) {

24
invokeai/frontend/web/src/features/nodes/store/util/makeTemplateSelector.ts Normal file
View File

@ -0,0 +1,24 @@
import { createSelector } from '@reduxjs/toolkit';
import { RootState } from 'app/store/store';
import { InvocationTemplate } from 'features/nodes/types/types';
import { AnyInvocationType } from 'services/events/types';
export const makeTemplateSelector = (type: AnyInvocationType) =>
createSelector(
[(state: RootState) => state.nodes],
(nodes) => {
const template = nodes.invocationTemplates[type];
if (!template) {
return;
}
return template;
},
{
memoizeOptions: {
resultEqualityCheck: (
a: InvocationTemplate | undefined,
b: InvocationTemplate | undefined
) => a !== undefined && b !== undefined && a.type === b.type,
},
}
);

4
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildNodesGraph.ts
View File

@ -54,8 +54,10 @@ export const parseFieldValue = (field: InputFieldValue) => {
export const buildNodesGraph = (state: RootState): Graph => {
const { nodes, edges } = state.nodes;
const filteredNodes = nodes.filter((n) => n.type !== 'progress_image');
// Reduce the node editor nodes into invocation graph nodes
const parsedNodes = nodes.reduce<NonNullable<Graph['nodes']>>(
const parsedNodes = filteredNodes.reduce<NonNullable<Graph['nodes']>>(
(nodesAccumulator, node, nodeIndex) => {
const { id, data } = node;
const { type, inputs } = data;

13
invokeai/frontend/web/src/features/parameters/components/Parameters/Core/ParamModelandVAEandScheduler.tsx
View File

@ -10,20 +10,19 @@ const ParamModelandVAEandScheduler = () => {
return (
<Flex gap={3} w="full" flexWrap={isVaeEnabled ? 'wrap' : 'nowrap'}>
<Box w="full">
<ModelSelect />
</Box>
<Flex gap={3} w="full">
<Box w="full">
<ModelSelect />
</Box>
{isVaeEnabled && (
<Box w="full">
<VAESelect />
</Box>
)}
<Box w="full">
<ParamScheduler />
</Box>
</Flex>
<Box w="full">
<ParamScheduler />
</Box>
</Flex>
);
};