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 branch 'main' into patch-1

Browse Source
This commit is contained in:
Millun Atluri 2023-11-07 10:17:46 +11:00 committed by GitHub
commit a07336a020
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
267 changed files with 16167 additions and 11801 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitattributes vendored
View File

@ -2,3 +2,4 @@
# Only affects text files and ignores other file types.
# For more info see: https://www.aleksandrhovhannisyan.com/blog/crlf-vs-lf-normalizing-line-endings-in-git/
* text=auto
docker/** text eol=lf

2
.github/workflows/pypi-release.yml vendored
View File

@ -28,7 +28,7 @@ jobs:
run: twine check dist/*
- name: check PyPI versions
if: github.ref == 'refs/heads/main' || github.ref == 'refs/heads/v2.3' || github.ref == 'refs/heads/v3.3.0post1'
if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release/')
run: |
pip install --upgrade requests
python -c "\

12
.gitignore vendored
View File

@ -1,8 +1,5 @@
.idea/
# ignore the Anaconda/Miniconda installer used while building Docker image
anaconda.sh
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
@ -136,12 +133,10 @@ celerybeat.pid
# Environments
.env
.venv
.venv*
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
@ -186,11 +181,6 @@ cython_debug/
.scratch/
.vscode/
# ignore environment.yml and requirements.txt
# these are links to the real files in environments-and-requirements
environment.yml
requirements.txt
# source installer files
installer/*zip
installer/install.bat

2
README.md
View File

@ -123,7 +123,7 @@ and go to http://localhost:9090.
### Command-Line Installation (for developers and users familiar with Terminals)
You must have Python 3.9 through 3.11 installed on your machine. Earlier or
You must have Python 3.10 through 3.11 installed on your machine. Earlier or
later versions are not supported.
Node.js also needs to be installed along with yarn (can be installed with
the command `npm install -g yarn` if needed)

12
docker/.env.sample
View File

@ -1,13 +1,15 @@
## Make a copy of this file named `.env` and fill in the values below.
## Any environment variables supported by InvokeAI can be specified here.
## Any environment variables supported by InvokeAI can be specified here,
## in addition to the examples below.
# INVOKEAI_ROOT is the path to a path on the local filesystem where InvokeAI will store data.
# Outputs will also be stored here by default.
# This **must** be an absolute path.
INVOKEAI_ROOT=
HUGGINGFACE_TOKEN=
# Get this value from your HuggingFace account settings page.
# HUGGING_FACE_HUB_TOKEN=
## optional variables specific to the docker setup
# GPU_DRIVER=cuda
# CONTAINER_UID=1000
## optional variables specific to the docker setup.
# GPU_DRIVER=cuda # or rocm
# CONTAINER_UID=1000

23
docker/Dockerfile
View File

@ -2,7 +2,7 @@
## Builder stage
FROM library/ubuntu:22.04 AS builder
FROM library/ubuntu:23.04 AS builder
ARG DEBIAN_FRONTEND=noninteractive
RUN rm -f /etc/apt/apt.conf.d/docker-clean; echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache
@ -10,7 +10,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,target=/var/lib/apt,sharing=locked \
apt update && apt-get install -y \
git \
python3.10-venv \
python3-venv \
python3-pip \
build-essential
@ -18,8 +18,8 @@ ENV INVOKEAI_SRC=/opt/invokeai
ENV VIRTUAL_ENV=/opt/venv/invokeai
ENV PATH="$VIRTUAL_ENV/bin:$PATH"
ARG TORCH_VERSION=2.0.1
ARG TORCHVISION_VERSION=0.15.2
ARG TORCH_VERSION=2.1.0
ARG TORCHVISION_VERSION=0.16
ARG GPU_DRIVER=cuda
ARG TARGETPLATFORM="linux/amd64"
# unused but available
@ -35,9 +35,9 @@ RUN --mount=type=cache,target=/root/.cache/pip \
if [ "$TARGETPLATFORM" = "linux/arm64" ] || [ "$GPU_DRIVER" = "cpu" ]; then \
extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cpu"; \
elif [ "$GPU_DRIVER" = "rocm" ]; then \
extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/rocm5.4.2"; \
extra_index_url_arg="--index-url https://download.pytorch.org/whl/rocm5.6"; \
else \
extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu118"; \
extra_index_url_arg="--extra-index-url https://download.pytorch.org/whl/cu121"; \
fi &&\
pip install $extra_index_url_arg \
torch==$TORCH_VERSION \
@ -70,7 +70,7 @@ RUN --mount=type=cache,target=/usr/lib/node_modules \
#### Runtime stage ---------------------------------------
FROM library/ubuntu:22.04 AS runtime
FROM library/ubuntu:23.04 AS runtime
ARG DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
@ -85,6 +85,7 @@ RUN apt update && apt install -y --no-install-recommends \
iotop \
bzip2 \
gosu \
magic-wormhole \
libglib2.0-0 \
libgl1-mesa-glx \
python3-venv \
@ -94,10 +95,6 @@ RUN apt update && apt install -y --no-install-recommends \
libstdc++-10-dev &&\
apt-get clean && apt-get autoclean
# globally add magic-wormhole
# for ease of transferring data to and from the container
# when running in sandboxed cloud environments; e.g. Runpod etc.
RUN pip install magic-wormhole
ENV INVOKEAI_SRC=/opt/invokeai
ENV VIRTUAL_ENV=/opt/venv/invokeai
@ -120,9 +117,7 @@ WORKDIR ${INVOKEAI_SRC}
RUN cd /usr/lib/$(uname -p)-linux-gnu/pkgconfig/ && ln -sf opencv4.pc opencv.pc
RUN python3 -c "from patchmatch import patch_match"
# Create unprivileged user and make the local dir
RUN useradd --create-home --shell /bin/bash -u 1000 --comment "container local user" invoke
RUN mkdir -p ${INVOKEAI_ROOT} && chown -R invoke:invoke ${INVOKEAI_ROOT}
RUN mkdir -p ${INVOKEAI_ROOT} && chown -R 1000:1000 ${INVOKEAI_ROOT}
COPY docker/docker-entrypoint.sh ./
ENTRYPOINT ["/opt/invokeai/docker-entrypoint.sh"]

19
docker/README.md
View File

@ -5,7 +5,7 @@ All commands are to be run from the `docker` directory: `cd docker`
#### Linux
1. Ensure builkit is enabled in the Docker daemon settings (`/etc/docker/daemon.json`)
2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://www.digitalocean.com/community/tutorials/how-to-install-and-use-docker-compose-on-ubuntu-22-04).
2. Install the `docker compose` plugin using your package manager, or follow a [tutorial](https://docs.docker.com/compose/install/linux/#install-using-the-repository).
- The deprecated `docker-compose` (hyphenated) CLI continues to work for now.
3. Ensure docker daemon is able to access the GPU.
- You may need to install [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
@ -20,7 +20,6 @@ This is done via Docker Desktop preferences
## Quickstart
1. Make a copy of `env.sample` and name it `.env` (`cp env.sample .env` (Mac/Linux) or `copy example.env .env` (Windows)). Make changes as necessary. Set `INVOKEAI_ROOT` to an absolute path to:
a. the desired location of the InvokeAI runtime directory, or
b. an existing, v3.0.0 compatible runtime directory.
@ -42,20 +41,22 @@ The Docker daemon on the system must be already set up to use the GPU. In case o
Check the `.env.sample` file. It contains some environment variables for running in Docker. Copy it, name it `.env`, and fill it in with your own values. Next time you run `docker compose up`, your custom values will be used.
You can also set these values in `docker compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
You can also set these values in `docker-compose.yml` directly, but `.env` will help avoid conflicts when code is updated.
Example (most values are optional):
Example (values are optional, but setting `INVOKEAI_ROOT` is highly recommended):
```
```bash
INVOKEAI_ROOT=/Volumes/WorkDrive/invokeai
HUGGINGFACE_TOKEN=the_actual_token
CONTAINER_UID=1000
GPU_DRIVER=cuda
```
Any environment variables supported by InvokeAI can be set here - please see the [Configuration docs](https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/) for further detail.
## Even Moar Customizing!
See the `docker compose.yaml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
See the `docker-compose.yml` file. The `command` instruction can be uncommented and used to run arbitrary startup commands. Some examples below.
### Reconfigure the runtime directory
@ -63,7 +64,7 @@ Can be used to download additional models from the supported model list
In conjunction with `INVOKEAI_ROOT` can be also used to initialize a runtime directory
```
```yaml
command:
- invokeai-configure
- --yes
@ -71,7 +72,7 @@ command:
Or install models:
```
```yaml
command:
- invokeai-model-install
```
```

4
docker/build.sh
View File

@ -5,7 +5,7 @@ build_args=""
[[ -f ".env" ]] && build_args=$(awk '$1 ~ /\=[^$]/ {print "--build-arg " $0 " "}' .env)
echo "docker-compose build args:"
echo "docker compose build args:"
echo $build_args
docker-compose build $build_args
docker compose build $build_args

4
docker/docker-compose.yml
View File

@ -15,6 +15,10 @@ services:
- driver: nvidia
count: 1
capabilities: [gpu]
# For AMD support, comment out the deploy section above and uncomment the devices section below:
#devices:
# - /dev/kfd:/dev/kfd
# - /dev/dri:/dev/dri
build:
context: ..
dockerfile: docker/Dockerfile

2
docker/docker-entrypoint.sh
View File

@ -19,7 +19,7 @@ set -e -o pipefail
# Default UID: 1000 chosen due to popularity on Linux systems. Possibly 501 on MacOS.
USER_ID=${CONTAINER_UID:-1000}
USER=invoke
USER=ubuntu
usermod -u ${USER_ID} ${USER} 1>/dev/null
configure() {

7
docker/run.sh
View File

@ -1,8 +1,11 @@
#!/usr/bin/env bash
set -e
# This script is provided for backwards compatibility with the old docker setup.
# it doesn't do much aside from wrapping the usual docker compose CLI.
SCRIPTDIR=$(dirname "${BASH_SOURCE[0]}")
cd "$SCRIPTDIR" || exit 1
docker-compose up --build -d
docker-compose logs -f
docker compose up -d
docker compose logs -f

4
docs/CHANGELOG.md
View File

@ -488,7 +488,7 @@ sections describe what's new for InvokeAI.
- A choice of installer scripts that automate installation and configuration.
See
[Installation](installation/index.md).
[Installation](installation/INSTALLATION.md).
- A streamlined manual installation process that works for both Conda and
PIP-only installs. See
[Manual Installation](installation/020_INSTALL_MANUAL.md).
@ -657,7 +657,7 @@ sections describe what's new for InvokeAI.
## v1.13 <small>(3 September 2022)</small>
- Support image variations (see [VARIATIONS](features/VARIATIONS.md)
- Support image variations (see [VARIATIONS](deprecated/VARIATIONS.md)
([Kevin Gibbons](https://github.com/bakkot) and many contributors and
reviewers)
- Supports a Google Colab notebook for a standalone server running on Google

0
CODE_OF_CONDUCT.md → docs/CODE_OF_CONDUCT.md
View File

2
docs/contributing/contribution_guides/development.md
View File

@ -45,5 +45,5 @@ For backend related work, please reach out to **@blessedcoolant**, **@lstein**,
## **What does the Code of Conduct mean for me?**
Our [Code of Conduct](CODE_OF_CONDUCT.md) means that you are responsible for treating everyone on the project with respect and courtesy regardless of their identity. If you are the victim of any inappropriate behavior or comments as described in our Code of Conduct, we are here for you and will do the best to ensure that the abuser is reprimanded appropriately, per our code.
Our [Code of Conduct](../../CODE_OF_CONDUCT.md) means that you are responsible for treating everyone on the project with respect and courtesy regardless of their identity. If you are the victim of any inappropriate behavior or comments as described in our Code of Conduct, we are here for you and will do the best to ensure that the abuser is reprimanded appropriately, per our code.

4
docs/deprecated/CLI.md
View File

@ -211,8 +211,8 @@ Here are the invoke> command that apply to txt2img:
| `--facetool <name>` | `-ft <name>` | `-ft gfpgan` | Select face restoration algorithm to use: gfpgan, codeformer |
| `--codeformer_fidelity` | `-cf <float>` | `0.75` | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality |
| `--save_original` | `-save_orig` | `False` | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
| `--variation <float>` | `-v<float>` | `0.0` | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
| `--with_variations <pattern>` | | `None` | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this. |
| `--variation <float>` | `-v<float>` | `0.0` | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](VARIATIONS.md). |
| `--with_variations <pattern>` | | `None` | Combine two or more variations. See [Variations](VARIATIONS.md) for now to use this. |
| `--save_intermediates <n>` | | `None` | Save the image from every nth step into an "intermediates" folder inside the output directory |
| `--h_symmetry_time_pct <float>` | | `None` | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.) |
| `--v_symmetry_time_pct <float>` | | `None` | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.) |

0
docs/other/TRANSLATION.md → docs/deprecated/TRANSLATION.md
View File

2
docs/features/VARIATIONS.md → docs/deprecated/VARIATIONS.md
View File

@ -126,6 +126,6 @@ amounts of image-to-image variation even when the seed is fixed and the
`-v` argument is very low. Others are more deterministic. Feel free to
experiment until you find the combination that you like.
Also be aware of the [Perlin Noise](OTHER.md#thresholding-and-perlin-noise-initialization-options)
Also be aware of the [Perlin Noise](../features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
feature, which provides another way of introducing variability into your
image generation requests.

5
docs/features/CONCEPTS.md
View File

@ -28,8 +28,9 @@ by placing them in the designated directory for the compatible model type
### An Example
Here are a few examples to illustrate how it works. All these images were
generated using the command-line client and the Stable Diffusion 1.5 model:
Here are a few examples to illustrate how it works. All these images
were generated using the legacy command-line client and the Stable
Diffusion 1.5 model:
| Japanese gardener | Japanese gardener &lt;ghibli-face&gt; | Japanese gardener &lt;hoi4-leaders&gt; | Japanese gardener &lt;cartoona-animals&gt; |
| :--------------------------------: | :-----------------------------------: | :------------------------------------: | :----------------------------------------: |

2
docs/features/CONFIGURATION.md
View File

@ -82,7 +82,7 @@ format of YAML files can be found
[here](https://circleci.com/blog/what-is-yaml-a-beginner-s-guide/).
You can fix a broken `invokeai.yaml` by deleting it and running the
configuration script again -- option [7] in the launcher, "Re-run the
configuration script again -- option [6] in the launcher, "Re-run the
configure script".
#### Reading Environment Variables

71
docs/features/CONTROLNET.md
View File

@ -17,9 +17,6 @@ image generation, providing you with a way to direct the network
towards generating images that better fit your desired style or
outcome.
#### How it works
ControlNet works by analyzing an input image, pre-processing that
image to identify relevant information that can be interpreted by each
specific ControlNet model, and then inserting that control information
@ -27,35 +24,21 @@ into the generation process. This can be used to adjust the style,
composition, or other aspects of the image to better achieve a
specific result.
#### Models
#### Installation
InvokeAI provides access to a series of ControlNet models that provide
different effects or styles in your generated images. Currently
InvokeAI only supports "diffuser" style ControlNet models. These are
folders that contain the files `config.json` and/or
`diffusion_pytorch_model.safetensors` and
`diffusion_pytorch_model.fp16.safetensors`. The name of the folder is
the name of the model.
different effects or styles in your generated images.
***InvokeAI does not currently support checkpoint-format
ControlNets. These come in the form of a single file with the
extension `.safetensors`.***
To install ControlNet Models:
Diffuser-style ControlNet models are available at HuggingFace
(http://huggingface.co) and accessed via their repo IDs (identifiers
in the format "author/modelname"). The easiest way to install them is
1. The easiest way to install them is
to use the InvokeAI model installer application. Use the
`invoke.sh`/`invoke.bat` launcher to select item [5] and then navigate
`invoke.sh`/`invoke.bat` launcher to select item [4] and then navigate
to the CONTROLNETS section. Select the models you wish to install and
press "APPLY CHANGES". You may also enter additional HuggingFace
repo_ids in the "Additional models" textbox:
repo_ids in the "Additional models" textbox.
2. Using the "Add Model" function of the model manager, enter the HuggingFace Repo ID of the ControlNet. The ID is in the format "author/repoName"
![Model Installer -
Controlnetl](../assets/installing-models/model-installer-controlnet.png){:width="640px"}
Command-line users can launch the model installer using the command
`invokeai-model-install`.
_Be aware that some ControlNet models require additional code
functionality in order to work properly, so just installing a
@ -63,6 +46,17 @@ third-party ControlNet model may not have the desired effect._ Please
read and follow the documentation for installing a third party model
not currently included among InvokeAI's default list.
Currently InvokeAI **only** supports 🤗 Diffusers-format ControlNet models. These are
folders that contain the files `config.json` and/or
`diffusion_pytorch_model.safetensors` and
`diffusion_pytorch_model.fp16.safetensors`. The name of the folder is
the name of the model.
🤗 Diffusers-format ControlNet models are available at HuggingFace
(http://huggingface.co) and accessed via their repo IDs (identifiers
in the format "author/modelname").
#### ControlNet Models
The models currently supported include:
**Canny**:
@ -133,6 +127,29 @@ Start/End - 0 represents the start of the generation, 1 represents the end. The
Additionally, each ControlNet section can be expanded in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in when you Invoke.
## T2I-Adapter
[T2I-Adapter](https://github.com/TencentARC/T2I-Adapter) is a tool similar to ControlNet that allows for control over the generation process by providing control information during the generation process. T2I-Adapter models tend to be smaller and more efficient than ControlNets.
##### Installation
To install T2I-Adapter Models:
1. The easiest way to install models is
to use the InvokeAI model installer application. Use the
`invoke.sh`/`invoke.bat` launcher to select item [5] and then navigate
to the T2I-Adapters section. Select the models you wish to install and
press "APPLY CHANGES". You may also enter additional HuggingFace
repo_ids in the "Additional models" textbox.
2. Using the "Add Model" function of the model manager, enter the HuggingFace Repo ID of the T2I-Adapter. The ID is in the format "author/repoName"
#### Usage
Each T2I Adapter has two settings that are applied.
Weight - Strength of the model applied to the generation for the section, defined by start/end.
Start/End - 0 represents the start of the generation, 1 represents the end. The Start/end setting controls what steps during the generation process have the ControlNet applied.
Additionally, each section can be expanded with the "Show Advanced" button in order to manipulate settings for the image pre-processor that adjusts your uploaded image before using it in during the generation process.
## IP-Adapter
@ -140,13 +157,13 @@ Additionally, each ControlNet section can be expanded in order to manipulate set
![IP-Adapter + T2I](https://github.com/tencent-ailab/IP-Adapter/raw/main/assets/demo/ip_adpter_plus_multi.jpg)
![IP-Adapter + IMG2IMG](https://github.com/tencent-ailab/IP-Adapter/blob/main/assets/demo/image-to-image.jpg)
![IP-Adapter + IMG2IMG](https://raw.githubusercontent.com/tencent-ailab/IP-Adapter/main/assets/demo/image-to-image.jpg)
#### Installation
There are several ways to install IP-Adapter models with an existing InvokeAI installation:
1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [5] to download models.
2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](www.models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.
1. Through the command line interface launched from the invoke.sh / invoke.bat scripts, option [4] to download models.
2. Through the Model Manager UI with models from the *Tools* section of [www.models.invoke.ai](https://www.models.invoke.ai). To do this, copy the repo ID from the desired model page, and paste it in the Add Model field of the model manager. **Note** Both the IP-Adapter and the Image Encoder must be installed for IP-Adapter to work. For example, the [SD 1.5 IP-Adapter](https://models.invoke.ai/InvokeAI/ip_adapter_plus_sd15) and [SD1.5 Image Encoder](https://models.invoke.ai/InvokeAI/ip_adapter_sd_image_encoder) must be installed to use IP-Adapter with SD1.5 based models.
3. **Advanced -- Not recommended ** Manually downloading the IP-Adapter and Image Encoder files - Image Encoder folders shouid be placed in the `models\any\clip_vision` folders. IP Adapter Model folders should be placed in the relevant `ip-adapter` folder of relevant base model folder of Invoke root directory. For example, for the SDXL IP-Adapter, files should be added to the `model/sdxl/ip_adapter/` folder.
#### Using IP-Adapter

7
docs/features/MODEL_MERGING.md
View File

@ -16,9 +16,10 @@ Model Merging can be be done by navigating to the Model Manager and clicking the
display all the diffusers-style models that InvokeAI knows about.
If you do not see the model you are looking for, then it is probably
a legacy checkpoint model and needs to be converted using the
`invoke` command-line client and its `!optimize` command. You
must select at least two models to merge. The third can be left at
"None" if you desire.
"Convert" option in the Web-based Model Manager tab.
You must select at least two models to merge. The third can be left
at "None" if you desire.
* Alpha: This is the ratio to use when combining models. It ranges
from 0 to 1. The higher the value, the more weight is given to the

10
docs/features/UTILITIES.md
View File

@ -8,7 +8,7 @@ title: Command-line Utilities
InvokeAI comes with several scripts that are accessible via the
command line. To access these commands, start the "developer's
console" from the launcher (`invoke.bat` menu item [8]). Users who are
console" from the launcher (`invoke.bat` menu item [7]). Users who are
familiar with Python can alternatively activate InvokeAI's virtual
environment (typically, but not necessarily `invokeai/.venv`).
@ -34,7 +34,7 @@ invokeai-web --ram 7
## **invokeai-merge**
This is the model merge script, the same as launcher option [4]. Call
This is the model merge script, the same as launcher option [3]. Call
it with the `--gui` command-line argument to start the interactive
console-based GUI. Alternatively, you can run it non-interactively
using command-line arguments as illustrated in the example below which
@ -48,7 +48,7 @@ invokeai-merge --force --base-model sd-1 --models stable-diffusion-1.5 inkdiffus
## **invokeai-ti**
This is the textual inversion training script that is run by launcher
option [3]. Call it with `--gui` to run the interactive console-based
option [2]. Call it with `--gui` to run the interactive console-based
front end. It can also be run non-interactively. It has about a
zillion arguments, but a typical training session can be launched
with:
@ -68,7 +68,7 @@ in Windows).
## **invokeai-install**
This is the console-based model install script that is run by launcher
option [5]. If called without arguments, it will launch the
option [4]. If called without arguments, it will launch the
interactive console-based interface. It can also be used
non-interactively to list, add and remove models as shown by these
examples:
@ -148,7 +148,7 @@ launch the web server against it with `invokeai-web --root InvokeAI-New`.
## **invokeai-update**
This is the interactive console-based script that is run by launcher
menu item [9] to update to a new version of InvokeAI. It takes no
menu item [8] to update to a new version of InvokeAI. It takes no
command-line arguments.
## **invokeai-metadata**

2
docs/features/index.md
View File

@ -28,7 +28,7 @@ Learn how to install and use ControlNet models for fine control over
image output.
### * [Image-to-Image Guide](IMG2IMG.md)
Use a seed image to build new creations in the CLI.
Use a seed image to build new creations.
## Model Management

4
docs/help/gettingStartedWithAI.md
View File

@ -57,7 +57,9 @@ Prompts provide the models directions on what to generate. As a general rule of
Models are the magic that power InvokeAI. These files represent the output of training a machine on understanding massive amounts of images - providing them with the capability to generate new images using just a text description of what you’d like to see. (Like Stable Diffusion!)
Invoke offers a simple way to download several different models upon installation, but many more can be discovered online, including at ****. Each model can produce a unique style of output, based on the images it was trained on - Try out different models to see which best fits your creative vision!
Invoke offers a simple way to download several different models upon installation, but many more can be discovered online, including at https://models.invoke.ai
Each model can produce a unique style of output, based on the images it was trained on - Try out different models to see which best fits your creative vision!
- *Models that contain “inpainting” in the name are designed for use with the inpainting feature of the Unified Canvas*

7
docs/index.md
View File

@ -143,7 +143,6 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.
<!-- seperator -->
### Prompt Engineering
- [Prompt Syntax](features/PROMPTS.md)
- [Generating Variations](features/VARIATIONS.md)
### InvokeAI Configuration
- [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md)
@ -166,10 +165,8 @@ still a work in progress, but coming soon.
### Command-Line Interface Retired
The original "invokeai" command-line interface has been retired. The
`invokeai` command will now launch a new command-line client that can
be used by developers to create and test nodes. It is not intended to
be used for routine image generation or manipulation.
All "invokeai" command-line interfaces have been retired as of version
3.4.
To launch the Web GUI from the command-line, use the command
`invokeai-web` rather than the traditional `invokeai --web`.

4
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -40,7 +40,7 @@ experimental versions later.
this, open up a command-line window ("Terminal" on Linux and
Macintosh, "Command" or "Powershell" on Windows) and type `python
--version`. If Python is installed, it will print out the version
number. If it is version `3.9.*`, `3.10.*` or `3.11.*` you meet
number. If it is version `3.10.*` or `3.11.*` you meet
requirements.
!!! warning "What to do if you have an unsupported version"
@ -48,7 +48,7 @@ experimental versions later.
Go to [Python Downloads](https://www.python.org/downloads/)
and download the appropriate installer package for your
platform. We recommend [Version
3.10.9](https://www.python.org/downloads/release/python-3109/),
3.10.12](https://www.python.org/downloads/release/python-3109/),
which has been extensively tested with InvokeAI.
_Please select your platform in the section below for platform-specific

4
docs/installation/020_INSTALL_MANUAL.md
View File

@ -32,7 +32,7 @@ gaming):
* **Python**
version 3.9 through 3.11
version 3.10 through 3.11
* **CUDA Tools**
@ -65,7 +65,7 @@ gaming):
To install InvokeAI with virtual environments and the PIP package
manager, please follow these steps:
1. Please make sure you are using Python 3.9 through 3.11. The rest of the install
1. Please make sure you are using Python 3.10 through 3.11. The rest of the install
procedure depends on this and will not work with other versions:
```bash

265
docs/installation/040_INSTALL_DOCKER.md
View File

@ -4,30 +4,31 @@ title: Installing with Docker
# :fontawesome-brands-docker: Docker
!!! warning "For most users"
!!! warning "macOS and AMD GPU Users"
We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md)
We highly recommend to Install InvokeAI locally using [these instructions](INSTALLATION.md),
because Docker containers can not access the GPU on macOS.
!!! tip "For developers"
!!! warning "AMD GPU Users"
For container-related development tasks or for enabling easy
deployment to other environments (on-premises or cloud), follow these
instructions.
Container support for AMD GPUs has been reported to work by the community, but has not received
extensive testing. Please make sure to set the `GPU_DRIVER=rocm` environment variable (see below), and
use the `build.sh` script to build the image for this to take effect at build time.
For general use, install locally to leverage your machine's GPU.
!!! tip "Linux and Windows Users"
For optimal performance, configure your Docker daemon to access your machine's GPU.
Docker Desktop on Windows [includes GPU support](https://www.docker.com/blog/wsl-2-gpu-support-for-docker-desktop-on-nvidia-gpus/).
Linux users should install and configure the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html)
## Why containers?
They provide a flexible, reliable way to build and deploy InvokeAI. You'll also
use a Docker volume to store the largest model files and image outputs as a
first step in decoupling storage and compute. Future enhancements can do this
for other assets. See [Processes](https://12factor.net/processes) under the
Twelve-Factor App methodology for details on why running applications in such a
stateless fashion is important.
They provide a flexible, reliable way to build and deploy InvokeAI.
See [Processes](https://12factor.net/processes) under the Twelve-Factor App
methodology for details on why running applications in such a stateless fashion is important.
You can specify the target platform when building the image and running the
container. You'll also need to specify the InvokeAI requirements file that
matches the container's OS and the architecture it will run on.
The container is configured for CUDA by default, but can be built to support AMD GPUs
by setting the `GPU_DRIVER=rocm` environment variable at Docker image build time.
Developers on Apple silicon (M1/M2): You
[can't access your GPU cores from Docker containers](https://github.com/pytorch/pytorch/issues/81224)
@ -36,6 +37,16 @@ development purposes it's fine. Once you're done with development tasks on your
laptop you can build for the target platform and architecture and deploy to
another environment with NVIDIA GPUs on-premises or in the cloud.
## TL;DR
This assumes properly configured Docker on Linux or Windows/WSL2. Read on for detailed customization options.
```bash
# docker compose commands should be run from the `docker` directory
cd docker
docker compose up
```
## Installation in a Linux container (desktop)
### Prerequisites
@ -58,222 +69,44 @@ a token and copy it, since you will need in for the next step.
### Setup
Set the fork you want to use and other variables.
Set up your environmnent variables. In the `docker` directory, make a copy of `env.sample` and name it `.env`. Make changes as necessary.
!!! tip
Any environment variables supported by InvokeAI can be set here - please see the [CONFIGURATION](../features/CONFIGURATION.md) for further detail.
I preffer to save my env vars
in the repository root in a `.env` (or `.envrc`) file to automatically re-apply
them when I come back.
The build- and run- scripts contain default values for almost everything,
besides the [Hugging Face Token](https://huggingface.co/settings/tokens) you
created in the last step.
Some Suggestions of variables you may want to change besides the Token:
At a minimum, you might want to set the `INVOKEAI_ROOT` environment variable
to point to the location where you wish to store your InvokeAI models, configuration, and outputs.
<figure markdown>
| Environment-Variable <img width="220" align="right"/> | Default value <img width="360" align="right"/> | Description |
| ----------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `HUGGING_FACE_HUB_TOKEN` | No default, but **required**! | This is the only **required** variable, without it you can't download the huggingface models |
| `REPOSITORY_NAME` | The Basename of the Repo folder | This name will used as the container repository/image name |
| `VOLUMENAME` | `${REPOSITORY_NAME,,}_data` | Name of the Docker Volume where model files will be stored |
| `ARCH` | arch of the build machine | Can be changed if you want to build the image for another arch |
| `CONTAINER_REGISTRY` | ghcr.io | Name of the Container Registry to use for the full tag |
| `CONTAINER_REPOSITORY` | `$(whoami)/${REPOSITORY_NAME}` | Name of the Container Repository |
| `CONTAINER_FLAVOR` | `cuda` | The flavor of the image to built, available options are `cuda`, `rocm` and `cpu`. If you choose `rocm` or `cpu`, the extra-index-url will be selected automatically, unless you set one yourself. |
| `CONTAINER_TAG` | `${INVOKEAI_BRANCH##*/}-${CONTAINER_FLAVOR}` | The Container Repository / Tag which will be used |
| `INVOKE_DOCKERFILE` | `Dockerfile` | The Dockerfile which should be built, handy for development |
| `PIP_EXTRA_INDEX_URL` | | If you want to use a custom pip-extra-index-url |
| `INVOKEAI_ROOT` | `~/invokeai` | **Required** - the location of your InvokeAI root directory. It will be created if it does not exist.
| `HUGGING_FACE_HUB_TOKEN` | | InvokeAI will work without it, but some of the integrations with HuggingFace (like downloading from models from private repositories) may not work|
| `GPU_DRIVER` | `cuda` | Optionally change this to `rocm` to build the image for AMD GPUs. NOTE: Use the `build.sh` script to build the image for this to take effect.
</figure>
#### Build the Image
I provided a build script, which is located next to the Dockerfile in
`docker/build.sh`. It can be executed from repository root like this:
Use the standard `docker compose build` command from within the `docker` directory.
```bash
./docker/build.sh
```
The build Script not only builds the container, but also creates the docker
volume if not existing yet.
If using an AMD GPU:
a: set the `GPU_DRIVER=rocm` environment variable in `docker-compose.yml` and continue using `docker compose build` as usual, or
b: set `GPU_DRIVER=rocm` in the `.env` file and use the `build.sh` script, provided for convenience
#### Run the Container
After the build process is done, you can run the container via the provided
`docker/run.sh` script
Use the standard `docker compose up` command, and generally the `docker compose` [CLI](https://docs.docker.com/compose/reference/) as usual.
```bash
./docker/run.sh
```
Once the container starts up (and configures the InvokeAI root directory if this is a new installation), you can access InvokeAI at [http://localhost:9090](http://localhost:9090)
When used without arguments, the container will start the webserver and provide
you the link to open it. But if you want to use some other parameters you can
also do so.
## Troubleshooting / FAQ
!!! example "run script example"
```bash
./docker/run.sh "banana sushi" -Ak_lms -S42 -s10
```
This would generate the legendary "banana sushi" with Seed 42, k_lms Sampler and 10 steps.
Find out more about available CLI-Parameters at [features/CLI.md](../../features/CLI/#arguments)
---
## Running the container on your GPU
If you have an Nvidia GPU, you can enable InvokeAI to run on the GPU by running
the container with an extra environment variable to enable GPU usage and have
the process run much faster:
```bash
GPU_FLAGS=all ./docker/run.sh
```
This passes the `--gpus all` to docker and uses the GPU.
If you don't have a GPU (or your host is not yet setup to use it) you will see a
message like this:
`docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]].`
You can use the full set of GPU combinations documented here:
https://docs.docker.com/config/containers/resource_constraints/#gpu
For example, use `GPU_FLAGS=device=GPU-3a23c669-1f69-c64e-cf85-44e9b07e7a2a` to
choose a specific device identified by a UUID.
---
!!! warning "Deprecated"
From here on you will find the the previous Docker-Docs, which will still
provide some usefull informations.
## Usage (time to have fun)
### Startup
If you're on a **Linux container** the `invoke` script is **automatically
started** and the output dir set to the Docker volume you created earlier.
If you're **directly on macOS follow these startup instructions**. With the
Conda environment activated (`conda activate ldm`), run the interactive
interface that combines the functionality of the original scripts `txt2img` and
`img2img`: Use the more accurate but VRAM-intensive full precision math because
half-precision requires autocast and won't work. By default the images are saved
in `outputs/img-samples/`.
```Shell
python3 scripts/invoke.py --full_precision
```
You'll get the script's prompt. You can see available options or quit.
```Shell
invoke> -h
invoke> q
```
### Text to Image
For quick (but bad) image results test with 5 steps (default 50) and 1 sample
image. This will let you know that everything is set up correctly. Then increase
steps to 100 or more for good (but slower) results. The prompt can be in quotes
or not.
```Shell
invoke> The hulk fighting with sheldon cooper -s5 -n1
invoke> "woman closeup highly detailed" -s 150
# Reuse previous seed and apply face restoration
invoke> "woman closeup highly detailed" --steps 150 --seed -1 -G 0.75
```
You'll need to experiment to see if face restoration is making it better or
worse for your specific prompt.
If you're on a container the output is set to the Docker volume. You can copy it
wherever you want. You can download it from the Docker Desktop app, Volumes,
my-vol, data. Or you can copy it from your Mac terminal. Keep in mind
`docker cp` can't expand `*.png` so you'll need to specify the image file name.
On your host Mac (you can use the name of any container that mounted the
volume):
```Shell
docker cp dummy:/data/000001.928403745.png /Users/<your-user>/Pictures
```
### Image to Image
You can also do text-guided image-to-image translation. For example, turning a
sketch into a detailed drawing.
`strength` is a value between 0.0 and 1.0 that controls the amount of noise that
is added to the input image. Values that approach 1.0 allow for lots of
variations but will also produce images that are not semantically consistent
with the input. 0.0 preserves image exactly, 1.0 replaces it completely.
Make sure your input image size dimensions are multiples of 64 e.g. 512x512.
Otherwise you'll get `Error: product of dimension sizes > 2**31'`. If you still
get the error
[try a different size](https://support.apple.com/guide/preview/resize-rotate-or-flip-an-image-prvw2015/mac#:~:text=image's%20file%20size-,In%20the%20Preview%20app%20on%20your%20Mac%2C%20open%20the%20file,is%20shown%20at%20the%20bottom.)
like 512x256.
If you're on a Docker container, copy your input image into the Docker volume
```Shell
docker cp /Users/<your-user>/Pictures/sketch-mountains-input.jpg dummy:/data/
```
Try it out generating an image (or more). The `invoke` script needs absolute
paths to find the image so don't use `~`.
If you're on your Mac
```Shell
invoke> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.75 --steps 100 -n4
```
If you're on a Linux container on your Mac
```Shell
invoke> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75 --steps 50 -n1
```
### Web Interface
You can use the `invoke` script with a graphical web interface. Start the web
server with:
```Shell
python3 scripts/invoke.py --full_precision --web
```
If it's running on your Mac point your Mac web browser to
<http://127.0.0.1:9090>
Press Control-C at the command line to stop the web server.
### Notes
Some text you can add at the end of the prompt to make it very pretty:
```Shell
cinematic photo, highly detailed, cinematic lighting, ultra-detailed, ultrarealistic, photorealism, Octane Rendering, cyberpunk lights, Hyper Detail, 8K, HD, Unreal Engine, V-Ray, full hd, cyberpunk, abstract, 3d octane render + 4k UHD + immense detail + dramatic lighting + well lit + black, purple, blue, pink, cerulean, teal, metallic colours, + fine details, ultra photoreal, photographic, concept art, cinematic composition, rule of thirds, mysterious, eerie, photorealism, breathtaking detailed, painting art deco pattern, by hsiao, ron cheng, john james audubon, bizarre compositions, exquisite detail, extremely moody lighting, painted by greg rutkowski makoto shinkai takashi takeuchi studio ghibli, akihiko yoshida
```
The original scripts should work as well.
```Shell
python3 scripts/orig_scripts/txt2img.py --help
python3 scripts/orig_scripts/txt2img.py --ddim_steps 100 --n_iter 1 --n_samples 1 --plms --prompt "new born baby kitten. Hyper Detail, Octane Rendering, Unreal Engine, V-Ray"
python3 scripts/orig_scripts/txt2img.py --ddim_steps 5 --n_iter 1 --n_samples 1 --plms --prompt "ocean" # or --klms
```
- Q: I am running on Windows under WSL2, and am seeing a "no such file or directory" error.
- A: Your `docker-entrypoint.sh` file likely has Windows (CRLF) as opposed to Unix (LF) line endings,
and you may have cloned this repository before the issue was fixed. To solve this, please change
the line endings in the `docker-entrypoint.sh` file to `LF`. You can do this in VSCode
(`Ctrl+P` and search for "line endings"), or by using the `dos2unix` utility in WSL.
Finally, you may delete `docker-entrypoint.sh` followed by `git pull; git checkout docker/docker-entrypoint.sh`
to reset the file to its most recent version.
For more information on this issue, please see the [Docker Desktop documentation](https://docs.docker.com/desktop/troubleshoot/topics/#avoid-unexpected-syntax-errors-use-unix-style-line-endings-for-files-in-containers)

2
docs/installation/050_INSTALLING_MODELS.md
View File

@ -84,7 +84,7 @@ InvokeAI root directory's `autoimport` folder.
### Installation via `invokeai-model-install`
From the `invoke` launcher, choose option [5] "Download and install
From the `invoke` launcher, choose option [4] "Download and install
models." This will launch the same script that prompted you to select
models at install time. You can use this to add models that you
skipped the first time around. It is all right to specify a model that

3
docs/installation/060_INSTALL_PATCHMATCH.md
View File

@ -59,8 +59,7 @@ Prior to installing PyPatchMatch, you need to take the following steps:
`from patchmatch import patch_match`: It should look like the following:
```py
Python 3.9.5 (default, Nov 23 2021, 15:27:38)
[GCC 9.3.0] on linux
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from patchmatch import patch_match
Compiling and loading c extensions from "/home/lstein/Projects/InvokeAI/.invokeai-env/src/pypatchmatch/patchmatch".

4
docs/installation/deprecated_documentation/INSTALL_LINUX.md
View File

@ -79,7 +79,7 @@ title: Manual Installation, Linux
and obtaining an access token for downloading. It will then download and
install the weights files for you.
Please look [here](../INSTALL_MANUAL.md) for a manual process for doing
Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing
the same thing.
7. Start generating images!
@ -112,7 +112,7 @@ title: Manual Installation, Linux
To use an alternative model you may invoke the `!switch` command in
the CLI, or pass `--model <model_name>` during `invoke.py` launch for
either the CLI or the Web UI. See [Command Line
Client](../../features/CLI.md#model-selection-and-importation). The
Client](../../deprecated/CLI.md#model-selection-and-importation). The
model names are defined in `configs/models.yaml`.
8. Subsequently, to relaunch the script, be sure to run "conda activate

2
docs/installation/deprecated_documentation/INSTALL_MAC.md
View File

@ -150,7 +150,7 @@ will do our best to help.
To use an alternative model you may invoke the `!switch` command in
the CLI, or pass `--model <model_name>` during `invoke.py` launch for
either the CLI or the Web UI. See [Command Line
Client](../../features/CLI.md#model-selection-and-importation). The
Client](../../deprecated/CLI.md#model-selection-and-importation). The
model names are defined in `configs/models.yaml`.
---

2
docs/installation/deprecated_documentation/INSTALL_SOURCE.md
View File

@ -128,7 +128,7 @@ python scripts/invoke.py --web --max_load_models=3 \
```
These options are described in detail in the
[Command-Line Interface](../../features/CLI.md) documentation.
[Command-Line Interface](../../deprecated/CLI.md) documentation.
## Troubleshooting

4
docs/installation/deprecated_documentation/INSTALL_WINDOWS.md
View File

@ -75,7 +75,7 @@ Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehan
obtaining an access token for downloading. It will then download and install the
weights files for you.
Please look [here](../INSTALL_MANUAL.md) for a manual process for doing the
Please look [here](../020_INSTALL_MANUAL.md) for a manual process for doing the
same thing.
8. Start generating images!
@ -108,7 +108,7 @@ Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehan
To use an alternative model you may invoke the `!switch` command in
the CLI, or pass `--model <model_name>` during `invoke.py` launch for
either the CLI or the Web UI. See [Command Line
Client](../../features/CLI.md#model-selection-and-importation). The
Client](../../deprecated/CLI.md#model-selection-and-importation). The
model names are defined in `configs/models.yaml`.
9. Subsequently, to relaunch the script, first activate the Anaconda

391
docs/nodes/communityNodes.md
View File

@ -4,32 +4,58 @@ These are nodes that have been developed by the community, for the community. If
If you'd like to submit a node for the community, please refer to the [node creation overview](contributingNodes.md).
To download a node, simply download the `.py` node file from the link and add it to the `invokeai/app/invocations` folder in your Invoke AI install location. If you used the automated installation, this can be found inside the `.venv` folder. Along with the node, an example node graph should be provided to help you get started with the node.
To use a node, add the node to the `nodes` folder found in your InvokeAI install location.
The suggested method is to use `git clone` to clone the repository the node is found in. This allows for easy updates of the node in the future.
If you'd prefer, you can also just download the `.py` file from the linked repository and add it to the `nodes` folder.
To use a community workflow, download the the `.json` node graph file and load it into Invoke AI via the **Load Workflow** button in the Workflow Editor.
--------------------------------
- Community Nodes
+ [Average Images](#average-images)
+ [Depth Map from Wavefront OBJ](#depth-map-from-wavefront-obj)
+ [Film Grain](#film-grain)
+ [Generative Grammar-Based Prompt Nodes](#generative-grammar-based-prompt-nodes)
+ [GPT2RandomPromptMaker](#gpt2randompromptmaker)
+ [Grid to Gif](#grid-to-gif)
+ [Halftone](#halftone)
+ [Ideal Size](#ideal-size)
+ [Image and Mask Composition Pack](#image-and-mask-composition-pack)
+ [Image to Character Art Image Nodes](#image-to-character-art-image-nodes)
+ [Image Picker](#image-picker)
+ [Load Video Frame](#load-video-frame)
+ [Make 3D](#make-3d)
+ [Oobabooga](#oobabooga)
+ [Prompt Tools](#prompt-tools)
+ [Retroize](#retroize)
+ [Size Stepper Nodes](#size-stepper-nodes)
+ [Text font to Image](#text-font-to-image)
+ [Thresholding](#thresholding)
+ [XY Image to Grid and Images to Grids nodes](#xy-image-to-grid-and-images-to-grids-nodes)
- [Example Node Template](#example-node-template)
- [Disclaimer](#disclaimer)
- [Help](#help)
--------------------------------
### Make 3D
### Average Images
**Description:** Create compelling 3D stereo images from 2D originals.
**Description:** This node takes in a collection of images of the same size and averages them as output. It converts everything to RGB mode first.
**Node Link:** [https://gitlab.com/srcrr/shift3d/-/raw/main/make3d.py](https://gitlab.com/srcrr/shift3d)
**Example Node Graph:** https://gitlab.com/srcrr/shift3d/-/raw/main/example-workflow.json?ref_type=heads&inline=false
**Output Examples**
![Painting of a cozy delapidated house](https://gitlab.com/srcrr/shift3d/-/raw/main/example-1.png){: style="height:512px;width:512px"}
![Photo of cute puppies](https://gitlab.com/srcrr/shift3d/-/raw/main/example-2.png){: style="height:512px;width:512px"}
**Node Link:** https://github.com/JPPhoto/average-images-node
--------------------------------
### Ideal Size
### Depth Map from Wavefront OBJ
**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
**Node Link:** https://github.com/JPPhoto/ideal-size-node
To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
**Node Link:** https://github.com/dwringer/depth-from-obj-node
**Example Usage:**
</br><img src="https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg" width="500" />
--------------------------------
### Film Grain
@ -39,68 +65,19 @@ To use a community workflow, download the the `.json` node graph file and load i
**Node Link:** https://github.com/JPPhoto/film-grain-node
--------------------------------
### Image Picker
### Generative Grammar-Based Prompt Nodes
**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no nonterminal terms remain in the string.
**Node Link:** https://github.com/JPPhoto/image-picker-node
This includes 3 Nodes:
- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
--------------------------------
### Thresholding
**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
**Description:** This node generates masks for highlights, midtones, and shadows given an input image. You can optionally specify a blur for the lookup table used in making those masks from the source image.
**Node Link:** https://github.com/JPPhoto/thresholding-node
**Examples**
Input:
![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/c88ada13-fb3d-484c-a4fe-947b44712632){: style="height:512px;width:512px"}
Highlights/Midtones/Shadows:
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/727021c1-36ff-4ec8-90c8-105e00de986d" style="width: 30%" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0b721bfc-f051-404e-b905-2f16b824ddfe" style="width: 30%" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/04c1297f-1c88-42b6-a7df-dd090b976286" style="width: 30%" />
Highlights/Midtones/Shadows (with LUT blur enabled):
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/19aa718a-70c1-4668-8169-d68f4bd13771" style="width: 30%" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0a440e43-697f-4d17-82ee-f287467df0a5" style="width: 30%" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0701fd0f-2ca7-4fe2-8613-2b52547bafce" style="width: 30%" />
--------------------------------
### Halftone
**Description**: Halftone converts the source image to grayscale and then performs halftoning. CMYK Halftone converts the image to CMYK and applies a per-channel halftoning to make the source image look like a magazine or newspaper. For both nodes, you can specify angles and halftone dot spacing.
**Node Link:** https://github.com/JPPhoto/halftone-node
**Example**
Input:
![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/fd5efb9f-4355-4409-a1c2-c1ca99e0cab4){: style="height:512px;width:512px"}
Halftone Output:
![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/7e606f29-e68f-4d46-b3d5-97f799a4ec2f){: style="height:512px;width:512px"}
CMYK Halftone Output:
![image](https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea){: style="height:512px;width:512px"}
--------------------------------
### Retroize
**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
**Retroize Output Examples**
![image](https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974)
**Example Usage:**
</br><img src="https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg" width="500" />
--------------------------------
### GPT2RandomPromptMaker
@ -113,76 +90,49 @@ CMYK Halftone Output:
Generated Prompt: An enchanted weapon will be usable by any character regardless of their alignment.
![9acf5aef-7254-40dd-95b3-8eac431dfab0 (1)](https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c)
<img src="https://github.com/mickr777/InvokeAI/assets/115216705/8496ba09-bcdd-4ff7-8076-ff213b6a1e4c" width="200" />
--------------------------------
### Load Video Frame
### Grid to Gif
**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
**Description:** One node that turns a grid image into an image collection, one node that turns an image collection into a gif.
**Node Link:** https://github.com/helix4u/load_video_frame
**Node Link:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/GridToGif.py
**Example Node Graph:** https://github.com/helix4u/load_video_frame/blob/main/Example_Workflow.json
**Example Node Graph:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/Grid%20to%20Gif%20Example%20Workflow.json
**Output Example:**
**Output Examples**
![Example animation](https://github.com/helix4u/load_video_frame/blob/main/testmp4_embed_converted.gif)
[Full mp4 of Example Output test.mp4](https://github.com/helix4u/load_video_frame/blob/main/test.mp4)
<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/input.png" width="300" />
<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/output.gif" width="300" />
--------------------------------
### Halftone
### Oobabooga
**Description**: Halftone converts the source image to grayscale and then performs halftoning. CMYK Halftone converts the image to CMYK and applies a per-channel halftoning to make the source image look like a magazine or newspaper. For both nodes, you can specify angles and halftone dot spacing.
**Description:** asks a local LLM running in Oobabooga's Text-Generation-Webui to write a prompt based on the user input.
**Node Link:** https://github.com/JPPhoto/halftone-node
**Link:** https://github.com/sammyf/oobabooga-node
**Example**
Input:
**Example:**
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/fd5efb9f-4355-4409-a1c2-c1ca99e0cab4" width="300" />
"describe a new mystical creature in its natural environment"
Halftone Output:
*can return*
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/7e606f29-e68f-4d46-b3d5-97f799a4ec2f" width="300" />
"The mystical creature I am describing to you is called the "Glimmerwing". It is a majestic, iridescent being that inhabits the depths of the most enchanted forests and glimmering lakes. Its body is covered in shimmering scales that reflect every color of the rainbow, and it has delicate, translucent wings that sparkle like diamonds in the sunlight. The Glimmerwing's home is a crystal-clear lake, surrounded by towering trees with leaves that shimmer like jewels. In this serene environment, the Glimmerwing spends its days swimming gracefully through the water, chasing schools of glittering fish and playing with the gentle ripples of the lake's surface.
As the sun sets, the Glimmerwing perches on a branch of one of the trees, spreading its wings to catch the last rays of light. The creature's scales glow softly, casting a rainbow of colors across the forest floor. The Glimmerwing sings a haunting melody, its voice echoing through the stillness of the night air. Its song is said to have the power to heal the sick and bring peace to troubled souls. Those who are lucky enough to hear the Glimmerwing's song are forever changed by its beauty and grace."
CMYK Halftone Output:
![glimmerwing_small](https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed)
**Requirement**
a Text-Generation-Webui instance (might work remotely too, but I never tried it) and obviously InvokeAI 3.x
**Note**
This node works best with SDXL models, especially as the style can be described independantly of the LLM's output.
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c59c578f-db8e-4d66-8c66-2851752d75ea" width="300" />
--------------------------------
### Depth Map from Wavefront OBJ
### Ideal Size
**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
**Description:** This node calculates an ideal image size for a first pass of a multi-pass upscaling. The aim is to avoid duplication that results from choosing a size larger than the model is capable of.
To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
**Node Link:** https://github.com/dwringer/depth-from-obj-node
**Example Usage:**
![depth from obj usage graph](https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg)
--------------------------------
### Generative Grammar-Based Prompt Nodes
**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no more nonterminal terms remain in the string.
This includes 3 Nodes:
- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
**Example Usage:**
![lookups usage example graph](https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg)
**Node Link:** https://github.com/JPPhoto/ideal-size-node
--------------------------------
### Image and Mask Composition Pack
@ -208,45 +158,84 @@ This includes 15 Nodes:
- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
**Node Link:** https://github.com/dwringer/composition-nodes
**Nodes and Output Examples:**
![composition nodes usage graph](https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_pack_overview.jpg)
</br><img src="https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_pack_overview.jpg" width="500" />
--------------------------------
### Size Stepper Nodes
### Image to Character Art Image Nodes
**Description:** This is a set of nodes for calculating the necessary size increments for doing upscaling workflows. Use the *Final Size & Orientation* node to enter your full size dimensions and orientation (portrait/landscape/random), then plug that and your initial generation dimensions into the *Ideal Size Stepper* and get 1, 2, or 3 intermediate pairs of dimensions for upscaling. Note this does not output the initial size or full size dimensions: the 1, 2, or 3 outputs of this node are only the intermediate sizes.
**Description:** Group of nodes to convert an input image into ascii/unicode art Image
A third node is included, *Random Switch (Integers)*, which is just a generic version of Final Size with no orientation selection.
**Node Link:** https://github.com/dwringer/size-stepper-nodes
**Example Usage:**
![size stepper usage graph](https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg)
--------------------------------
### Text font to Image
**Description:** text font to text image node for InvokeAI, download a font to use (or if in font cache uses it from there), the text is always resized to the image size, but can control that with padding, optional 2nd line
**Node Link:** https://github.com/mickr777/textfontimage
**Node Link:** https://github.com/mickr777/imagetoasciiimage
**Output Examples**
![a3609d48-d9b7-41f0-b280-063d857986fb](https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36)
Results after using the depth controlnet
![9133eabb-bcda-4326-831e-1b641228b178](https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a)
![4f9a3fa8-9be9-4236-8a3e-fcec66decd2a](https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc)
![babd69c4-9d60-4a55-a834-5e8397f62610](https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89)
<img src="https://user-images.githubusercontent.com/115216705/271817646-8e061fcc-9a2c-4fa9-bcc7-c0f7b01e9056.png" width="300" /><img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/3c4990eb-2f42-46b9-90f9-0088b939dc6a" width="300" /></br>
<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/fee7f800-a4a8-41e2-a66b-c66e4343307e" width="300" />
<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/1d9c1003-a45f-45c2-aac7-46470bb89330" width="300" />
--------------------------------
### Image Picker
**Description:** This InvokeAI node takes in a collection of images and randomly chooses one. This can be useful when you have a number of poses to choose from for a ControlNet node, or a number of input images for another purpose.
**Node Link:** https://github.com/JPPhoto/image-picker-node
--------------------------------
### Load Video Frame
**Description:** This is a video frame image provider + indexer/video creation nodes for hooking up to iterators and ranges and ControlNets and such for invokeAI node experimentation. Think animation + ControlNet outputs.
**Node Link:** https://github.com/helix4u/load_video_frame
**Output Example:**
<img src="https://raw.githubusercontent.com/helix4u/load_video_frame/main/_git_assets/testmp4_embed_converted.gif" width="500" />
--------------------------------
### Make 3D
**Description:** Create compelling 3D stereo images from 2D originals.
**Node Link:** [https://gitlab.com/srcrr/shift3d/-/raw/main/make3d.py](https://gitlab.com/srcrr/shift3d)
**Example Node Graph:** https://gitlab.com/srcrr/shift3d/-/raw/main/example-workflow.json?ref_type=heads&inline=false
**Output Examples**
<img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-1.png" width="300" />
<img src="https://gitlab.com/srcrr/shift3d/-/raw/main/example-2.png" width="300" />
--------------------------------
### Oobabooga
**Description:** asks a local LLM running in Oobabooga's Text-Generation-Webui to write a prompt based on the user input.
**Link:** https://github.com/sammyf/oobabooga-node
**Example:**
"describe a new mystical creature in its natural environment"
*can return*
"The mystical creature I am describing to you is called the "Glimmerwing". It is a majestic, iridescent being that inhabits the depths of the most enchanted forests and glimmering lakes. Its body is covered in shimmering scales that reflect every color of the rainbow, and it has delicate, translucent wings that sparkle like diamonds in the sunlight. The Glimmerwing's home is a crystal-clear lake, surrounded by towering trees with leaves that shimmer like jewels. In this serene environment, the Glimmerwing spends its days swimming gracefully through the water, chasing schools of glittering fish and playing with the gentle ripples of the lake's surface.
As the sun sets, the Glimmerwing perches on a branch of one of the trees, spreading its wings to catch the last rays of light. The creature's scales glow softly, casting a rainbow of colors across the forest floor. The Glimmerwing sings a haunting melody, its voice echoing through the stillness of the night air. Its song is said to have the power to heal the sick and bring peace to troubled souls. Those who are lucky enough to hear the Glimmerwing's song are forever changed by its beauty and grace."
<img src="https://github.com/sammyf/oobabooga-node/assets/42468608/cecdd820-93dd-4c35-abbf-607e001fb2ed" width="300" />
**Requirement**
a Text-Generation-Webui instance (might work remotely too, but I never tried it) and obviously InvokeAI 3.x
**Note**
This node works best with SDXL models, especially as the style can be described independently of the LLM's output.
--------------------------------
### Prompt Tools
**Description:** A set of InvokeAI nodes that add general prompt manipulation tools. These where written to accompany the PromptsFromFile node and other prompt generation nodes.
**Description:** A set of InvokeAI nodes that add general prompt manipulation tools. These were written to accompany the PromptsFromFile node and other prompt generation nodes.
1. PromptJoin - Joins to prompts into one.
2. PromptReplace - performs a search and replace on a prompt. With the option of using regex.
@ -263,62 +252,94 @@ See full docs here: https://github.com/skunkworxdark/Prompt-tools-nodes/edit/mai
**Node Link:** https://github.com/skunkworxdark/Prompt-tools-nodes
--------------------------------
### Retroize
**Description:** Retroize is a collection of nodes for InvokeAI to "Retroize" images. Any image can be given a fresh coat of retro paint with these nodes, either from your gallery or from within the graph itself. It includes nodes to pixelize, quantize, palettize, and ditherize images; as well as to retrieve palettes from existing images.
**Node Link:** https://github.com/Ar7ific1al/invokeai-retroizeinode/
**Retroize Output Examples**
<img src="https://github.com/Ar7ific1al/InvokeAI_nodes_retroize/assets/2306586/de8b4fa6-324c-4c2d-b36c-297600c73974" width="500" />
--------------------------------
### Size Stepper Nodes
**Description:** This is a set of nodes for calculating the necessary size increments for doing upscaling workflows. Use the *Final Size & Orientation* node to enter your full size dimensions and orientation (portrait/landscape/random), then plug that and your initial generation dimensions into the *Ideal Size Stepper* and get 1, 2, or 3 intermediate pairs of dimensions for upscaling. Note this does not output the initial size or full size dimensions: the 1, 2, or 3 outputs of this node are only the intermediate sizes.
A third node is included, *Random Switch (Integers)*, which is just a generic version of Final Size with no orientation selection.
**Node Link:** https://github.com/dwringer/size-stepper-nodes
**Example Usage:**
</br><img src="https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg" width="500" />
--------------------------------
### Text font to Image
**Description:** text font to text image node for InvokeAI, download a font to use (or if in font cache uses it from there), the text is always resized to the image size, but can control that with padding, optional 2nd line
**Node Link:** https://github.com/mickr777/textfontimage
**Output Examples**
<img src="https://github.com/mickr777/InvokeAI/assets/115216705/c21b0af3-d9c6-4c16-9152-846a23effd36" width="300" />
Results after using the depth controlnet
<img src="https://github.com/mickr777/InvokeAI/assets/115216705/915f1a53-968e-43eb-aa61-07cd8f1a733a" width="300" />
<img src="https://github.com/mickr777/InvokeAI/assets/115216705/821ef89e-8a60-44f5-b94e-471a9d8690cc" width="300" />
<img src="https://github.com/mickr777/InvokeAI/assets/115216705/2befcb6d-49f4-4bfd-b5fc-1fee19274f89" width="300" />
--------------------------------
### Thresholding
**Description:** This node generates masks for highlights, midtones, and shadows given an input image. You can optionally specify a blur for the lookup table used in making those masks from the source image.
**Node Link:** https://github.com/JPPhoto/thresholding-node
**Examples**
Input:
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/c88ada13-fb3d-484c-a4fe-947b44712632" width="300" />
Highlights/Midtones/Shadows:
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/727021c1-36ff-4ec8-90c8-105e00de986d" width="300" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0b721bfc-f051-404e-b905-2f16b824ddfe" width="300" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/04c1297f-1c88-42b6-a7df-dd090b976286" width="300" />
Highlights/Midtones/Shadows (with LUT blur enabled):
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/19aa718a-70c1-4668-8169-d68f4bd13771" width="300" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0a440e43-697f-4d17-82ee-f287467df0a5" width="300" />
<img src="https://github.com/invoke-ai/InvokeAI/assets/34005131/0701fd0f-2ca7-4fe2-8613-2b52547bafce" width="300" />
--------------------------------
### XY Image to Grid and Images to Grids nodes
**Description:** Image to grid nodes and supporting tools.
1. "Images To Grids" node - Takes a collection of images and creates a grid(s) of images. If there are more images than the size of a single grid then mutilple grids will be created until it runs out of images.
2. "XYImage To Grid" node - Converts a collection of XYImages into a labeled Grid of images. The XYImages collection has to be built using the supporoting nodes. See example node setups for more details.
1. "Images To Grids" node - Takes a collection of images and creates a grid(s) of images. If there are more images than the size of a single grid then multiple grids will be created until it runs out of images.
2. "XYImage To Grid" node - Converts a collection of XYImages into a labeled Grid of images. The XYImages collection has to be built using the supporting nodes. See example node setups for more details.
See full docs here: https://github.com/skunkworxdark/XYGrid_nodes/edit/main/README.md
**Node Link:** https://github.com/skunkworxdark/XYGrid_nodes
--------------------------------
### Image to Character Art Image Node's
**Description:** Group of nodes to convert an input image into ascii/unicode art Image
**Node Link:** https://github.com/mickr777/imagetoasciiimage
**Output Examples**
<img src="https://github.com/invoke-ai/InvokeAI/assets/115216705/8e061fcc-9a2c-4fa9-bcc7-c0f7b01e9056" width="300" />
<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/3c4990eb-2f42-46b9-90f9-0088b939dc6a" width="300" /></br>
<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/fee7f800-a4a8-41e2-a66b-c66e4343307e" width="300" />
<img src="https://github.com/mickr777/imagetoasciiimage/assets/115216705/1d9c1003-a45f-45c2-aac7-46470bb89330" width="300" />
--------------------------------
### Grid to Gif
**Description:** One node that turns a grid image into an image colletion, one node that turns an image collection into a gif
**Node Link:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/GridToGif.py
**Example Node Graph:** https://github.com/mildmisery/invokeai-GridToGifNode/blob/main/Grid%20to%20Gif%20Example%20Workflow.json
**Output Examples**
<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/input.png" width="300" />
<img src="https://raw.githubusercontent.com/mildmisery/invokeai-GridToGifNode/main/output.gif" width="300" />
--------------------------------
### Example Node Template
**Description:** This node allows you to do super cool things with InvokeAI.
**Node Link:** https://github.com/invoke-ai/InvokeAI/fake_node.py
**Node Link:** https://github.com/invoke-ai/InvokeAI/blob/main/invokeai/app/invocations/prompt.py
**Example Node Graph:** https://github.com/invoke-ai/InvokeAI/fake_node_graph.json
**Example Workflow:** https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/Prompt_from_File.json
**Output Examples**
![Example Image](https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png){: style="height:115px;width:240px"}
</br><img src="https://invoke-ai.github.io/InvokeAI/assets/invoke_ai_banner.png" width="500" />
## Disclaimer

2
docs/nodes/contributingNodes.md
View File

@ -4,7 +4,7 @@ To learn about the specifics of creating a new node, please visit our [Node crea
Once you’ve created a node and confirmed that it behaves as expected locally, follow these steps:
- Make sure the node is contained in a new Python (.py) file. Preferrably, the node is in a repo with a README detaling the nodes usage & examples to help others more easily use your node.
- Make sure the node is contained in a new Python (.py) file. Preferably, the node is in a repo with a README detailing the nodes usage & examples to help others more easily use your node. Including the tag "invokeai-node" in your repository's README can also help other users find it more easily.
- Submit a pull request with a link to your node(s) repo in GitHub against the `main` branch to add the node to the [Community Nodes](communityNodes.md) list
- Make sure you are following the template below and have provided all relevant details about the node and what it does. Example output images and workflows are very helpful for other users looking to use your node.
- A maintainer will review the pull request and node. If the node is aligned with the direction of the project, you may be asked for permission to include it in the core project.

12
docs/nodes/exampleWorkflows.md
View File

@ -2,13 +2,17 @@
We've curated some example workflows for you to get started with Workflows in InvokeAI
To use them, right click on your desired workflow, press "Download Linked File". You can then use the "Load Workflow" functionality in InvokeAI to load the workflow and start generating images!
To use them, right click on your desired workflow, follow the link to GitHub and click the "⬇" button to download the raw file. You can then use the "Load Workflow" functionality in InvokeAI to load the workflow and start generating images!
If you're interested in finding more workflows, checkout the [#share-your-workflows](https://discord.com/channels/1020123559063990373/1130291608097661000) channel in the InvokeAI Discord.
* [SD1.5 / SD2 Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/Text_to_Image.json)
* [SDXL Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json)
* [SDXL (with Refiner) Text to Image](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/SDXL_Text_to_Image.json)
* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json)
* [SDXL Text to Image](https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/SDXL_Text_to_Image.json)
* [SDXL Text to Image with Refiner](https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/SDXL_w_Refiner_Text_to_Image.json)
* [Multi ControlNet (Canny & Depth)](https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/Multi_ControlNet_Canny_and_Depth.json)
* [Tiled Upscaling with ControlNet](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/ESRGAN_img2img_upscale_w_Canny_ControlNet.json)
* [Prompt From File](https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/Prompt_from_File.json)
* [Face Detailer with IP-Adapter & ControlNet](https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/Face_Detailer_with_IP-Adapter_and_Canny.json.json)
* [FaceMask](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceMask.json)
* [FaceOff with 2x Face Scaling](https://github.com/invoke-ai/InvokeAI/blob/main/docs/workflows/FaceOff_FaceScale2x.json)
* [QR Code Monster](https://github.com/invoke-ai/InvokeAI/blob/docs/main/docs/workflows/QR_Code_Monster.json)

1382
docs/workflows/ESRGAN_img2img_upscale w_Canny_ControlNet.json → docs/workflows/ESRGAN_img2img_upscale_w_Canny_ControlNet.json
View File

File diff suppressed because it is too large Load Diff

822
docs/workflows/FaceMask.json
View File

File diff suppressed because it is too large Load Diff

1356
docs/workflows/FaceOff_FaceScale2x.json
View File

File diff suppressed because it is too large Load Diff

2032
docs/workflows/Face_Detailer_with_IP-Adapter_and_Canny.json Normal file
View File

File diff suppressed because it is too large Load Diff

985
docs/workflows/Multi_ControlNet_Canny_and_Depth.json Normal file
View File

@ -0,0 +1,985 @@
{
"name": "Multi ControlNet (Canny & Depth)",
"author": "Millu",
"description": "A sample workflow using canny & depth ControlNets to guide the generation process. ",
"version": "0.1.0",
"contact": "millun@invoke.ai",
"tags": "ControlNet, canny, depth",
"notes": "",
"exposedFields": [
{
"nodeId": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"fieldName": "model"
},
{
"nodeId": "7ce68934-3419-42d4-ac70-82cfc9397306",
"fieldName": "prompt"
},
{
"nodeId": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
"fieldName": "prompt"
},
{
"nodeId": "c4b23e64-7986-40c4-9cad-46327b12e204",
"fieldName": "image"
},
{
"nodeId": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
"fieldName": "image"
}
],
"meta": {
"version": "1.0.0"
},
"nodes": [
{
"id": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
"type": "invocation",
"data": {
"id": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
"type": "image",
"inputs": {
"image": {
"id": "189c8adf-68cc-4774-a729-49da89f6fdf1",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": "Depth Input Image"
}
},
"outputs": {
"image": {
"id": "1a31cacd-9d19-4f32-b558-c5e4aa39ce73",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "12f298fd-1d11-4cca-9426-01240f7ec7cf",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "c47dabcb-44e8-40c9-992d-81dca59f598e",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 225,
"position": {
"x": 3617.163483500202,
"y": 40.5529847930888
}
},
{
"id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
"type": "invocation",
"data": {
"id": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
"type": "controlnet",
"inputs": {
"image": {
"id": "4e0a3172-d3c2-4005-a84c-fa12a404f8a0",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": ""
},
"control_model": {
"id": "8cb2d998-4086-430a-8b13-94cbc81e3ca3",
"name": "control_model",
"type": "ControlNetModelField",
"fieldKind": "input",
"label": "",
"value": {
"model_name": "sd-controlnet-depth",
"base_model": "sd-1"
}
},
"control_weight": {
"id": "5e32bd8a-9dc8-42d8-9bcc-c2b0460c0b0f",
"name": "control_weight",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 1
},
"begin_step_percent": {
"id": "c258a276-352a-416c-8358-152f11005c0c",
"name": "begin_step_percent",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"end_step_percent": {
"id": "43001125-0d70-4f87-8e79-da6603ad6c33",
"name": "end_step_percent",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"control_mode": {
"id": "d2f14561-9443-4374-9270-e2f05007944e",
"name": "control_mode",
"type": "enum",
"fieldKind": "input",
"label": "",
"value": "balanced"
},
"resize_mode": {
"id": "727ee7d3-8bf6-4c7d-8b8a-43546b3b59cd",
"name": "resize_mode",
"type": "enum",
"fieldKind": "input",
"label": "",
"value": "just_resize"
}
},
"outputs": {
"control": {
"id": "b034aa0f-4d0d-46e4-b5e3-e25a9588d087",
"name": "control",
"type": "ControlField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 508,
"position": {
"x": 4477.604342844504,
"y": -49.39005411272677
}
},
{
"id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
"type": "invocation",
"data": {
"id": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
"type": "compel",
"inputs": {
"prompt": {
"id": "7c2c4771-2161-4d77-aced-ff8c4b3f1c15",
"name": "prompt",
"type": "string",
"fieldKind": "input",
"label": "Negative Prompt",
"value": ""
},
"clip": {
"id": "06d59e91-9cca-411d-bf05-86b099b3e8f7",
"name": "clip",
"type": "ClipField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"conditioning": {
"id": "858bc33c-134c-4bf6-8855-f943e1d26f14",
"name": "conditioning",
"type": "ConditioningField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 261,
"position": {
"x": 4444.706437017514,
"y": -924.0715320874991
}
},
{
"id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"type": "invocation",
"data": {
"id": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"type": "main_model_loader",
"inputs": {
"model": {
"id": "f4a915a5-593e-4b6d-9198-c78eb5cefaed",
"name": "model",
"type": "MainModelField",
"fieldKind": "input",
"label": "",
"value": {
"model_name": "stable-diffusion-v1-5",
"base_model": "sd-1",
"model_type": "main"
}
}
},
"outputs": {
"unet": {
"id": "ee24fb16-da38-4c66-9fbc-e8f296ed40d2",
"name": "unet",
"type": "UNetField",
"fieldKind": "output"
},
"clip": {
"id": "f3fb0524-8803-41c1-86db-a61a13ee6a33",
"name": "clip",
"type": "ClipField",
"fieldKind": "output"
},
"vae": {
"id": "5c4878a8-b40f-44ab-b146-1c1f42c860b3",
"name": "vae",
"type": "VaeField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 226,
"position": {
"x": 3837.096149678291,
"y": -1050.015351148365
}
},
{
"id": "7ce68934-3419-42d4-ac70-82cfc9397306",
"type": "invocation",
"data": {
"id": "7ce68934-3419-42d4-ac70-82cfc9397306",
"type": "compel",
"inputs": {
"prompt": {
"id": "7c2c4771-2161-4d77-aced-ff8c4b3f1c15",
"name": "prompt",
"type": "string",
"fieldKind": "input",
"label": "Positive Prompt",
"value": ""
},
"clip": {
"id": "06d59e91-9cca-411d-bf05-86b099b3e8f7",
"name": "clip",
"type": "ClipField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"conditioning": {
"id": "858bc33c-134c-4bf6-8855-f943e1d26f14",
"name": "conditioning",
"type": "ConditioningField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 261,
"position": {
"x": 4449.356038911986,
"y": -1201.659695420063
}
},
{
"id": "d204d184-f209-4fae-a0a1-d152800844e1",
"type": "invocation",
"data": {
"id": "d204d184-f209-4fae-a0a1-d152800844e1",
"type": "controlnet",
"inputs": {
"image": {
"id": "4e0a3172-d3c2-4005-a84c-fa12a404f8a0",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": ""
},
"control_model": {
"id": "8cb2d998-4086-430a-8b13-94cbc81e3ca3",
"name": "control_model",
"type": "ControlNetModelField",
"fieldKind": "input",
"label": "",
"value": {
"model_name": "sd-controlnet-canny",
"base_model": "sd-1"
}
},
"control_weight": {
"id": "5e32bd8a-9dc8-42d8-9bcc-c2b0460c0b0f",
"name": "control_weight",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 1
},
"begin_step_percent": {
"id": "c258a276-352a-416c-8358-152f11005c0c",
"name": "begin_step_percent",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"end_step_percent": {
"id": "43001125-0d70-4f87-8e79-da6603ad6c33",
"name": "end_step_percent",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"control_mode": {
"id": "d2f14561-9443-4374-9270-e2f05007944e",
"name": "control_mode",
"type": "enum",
"fieldKind": "input",
"label": "",
"value": "balanced"
},
"resize_mode": {
"id": "727ee7d3-8bf6-4c7d-8b8a-43546b3b59cd",
"name": "resize_mode",
"type": "enum",
"fieldKind": "input",
"label": "",
"value": "just_resize"
}
},
"outputs": {
"control": {
"id": "b034aa0f-4d0d-46e4-b5e3-e25a9588d087",
"name": "control",
"type": "ControlField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 508,
"position": {
"x": 4479.68542130465,
"y": -618.4221638099414
}
},
{
"id": "c4b23e64-7986-40c4-9cad-46327b12e204",
"type": "invocation",
"data": {
"id": "c4b23e64-7986-40c4-9cad-46327b12e204",
"type": "image",
"inputs": {
"image": {
"id": "189c8adf-68cc-4774-a729-49da89f6fdf1",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": "Canny Input Image"
}
},
"outputs": {
"image": {
"id": "1a31cacd-9d19-4f32-b558-c5e4aa39ce73",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "12f298fd-1d11-4cca-9426-01240f7ec7cf",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "c47dabcb-44e8-40c9-992d-81dca59f598e",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 225,
"position": {
"x": 3593.7474460420153,
"y": -538.1200472386865
}
},
{
"id": "ca4d5059-8bfb-447f-b415-da0faba5a143",
"type": "invocation",
"data": {
"id": "ca4d5059-8bfb-447f-b415-da0faba5a143",
"type": "collect",
"inputs": {
"item": {
"id": "b16ae602-8708-4b1b-8d4f-9e0808d429ab",
"name": "item",
"type": "CollectionItem",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"collection": {
"id": "d8987dd8-dec8-4d94-816a-3e356af29884",
"name": "collection",
"type": "Collection",
"fieldKind": "output"
}
},
"label": "ControlNet Collection",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 104,
"position": {
"x": 4866.191497139488,
"y": -299.0538619537037
}
},
{
"id": "018b1214-c2af-43a7-9910-fb687c6726d7",
"type": "invocation",
"data": {
"id": "018b1214-c2af-43a7-9910-fb687c6726d7",
"type": "midas_depth_image_processor",
"inputs": {
"metadata": {
"id": "77f91980-c696-4a18-a9ea-6e2fc329a747",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"image": {
"id": "50710a20-2af5-424d-9d17-aa08167829c6",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": ""
},
"a_mult": {
"id": "f3b26f9d-2498-415e-9c01-197a8d06c0a5",
"name": "a_mult",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 2
},
"bg_th": {
"id": "4b1eb3ae-9d4a-47d6-b0ed-da62501e007f",
"name": "bg_th",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0.1
}
},
"outputs": {
"image": {
"id": "b4ed637c-c4a0-4fdd-a24e-36d6412e4ccf",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "6bf9b609-d72c-4239-99bd-390a73cc3a9c",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "3e8aef09-cf44-4e3e-a490-d3c9e7b23119",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 339,
"position": {
"x": 4054.229311491893,
"y": -31.611411056365725
}
},
{
"id": "c826ba5e-9676-4475-b260-07b85e88753c",
"type": "invocation",
"data": {
"id": "c826ba5e-9676-4475-b260-07b85e88753c",
"type": "canny_image_processor",
"inputs": {
"metadata": {
"id": "08331ea6-99df-4e61-a919-204d9bfa8fb2",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"image": {
"id": "33a37284-06ac-459c-ba93-1655e4f69b2d",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": ""
},
"low_threshold": {
"id": "21ec18a3-50c5-4ba1-9642-f921744d594f",
"name": "low_threshold",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 100
},
"high_threshold": {
"id": "ebeab271-a5ff-4c88-acfd-1d0271ab6ed4",
"name": "high_threshold",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 200
}
},
"outputs": {
"image": {
"id": "c0caadbf-883f-4cb4-a62d-626b9c81fc4e",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "df225843-8098-49c0-99d1-3b0b6600559f",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "e4abe0de-aa16-41f3-9cd7-968b49db5da3",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 339,
"position": {
"x": 4095.757337055795,
"y": -455.63440891935863
}
},
{
"id": "9db25398-c869-4a63-8815-c6559341ef12",
"type": "invocation",
"data": {
"id": "9db25398-c869-4a63-8815-c6559341ef12",
"type": "l2i",
"inputs": {
"metadata": {
"id": "2f269793-72e5-4ff3-b76c-fab4f93e983f",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "4aaedd3b-cc77-420c-806e-c7fa74ec4cdf",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"vae": {
"id": "432b066a-2462-4d18-83d9-64620b72df45",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
},
"tiled": {
"id": "61f86e0f-7c46-40f8-b3f5-fe2f693595ca",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"fp32": {
"id": "39b6c89a-37ef-4a7e-9509-daeca49d5092",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
}
},
"outputs": {
"image": {
"id": "6204e9b0-61dd-4250-b685-2092ba0e28e6",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "b4140649-8d5d-4d2d-bfa6-09e389ede5f9",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "f3a0c0c8-fc24-4646-8be1-ed8cdd140828",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": false,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 267,
"position": {
"x": 5678.726701377887,
"y": -351.6792416734579
}
},
{
"id": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"type": "invocation",
"data": {
"id": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"type": "denoise_latents",
"inputs": {
"positive_conditioning": {
"id": "869cd309-c238-444b-a1a0-5021f99785ba",
"name": "positive_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"negative_conditioning": {
"id": "343447b4-1e37-4e9e-8ac7-4d04864066af",
"name": "negative_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"noise": {
"id": "b556571e-0cf9-4e03-8cfc-5caad937d957",
"name": "noise",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"steps": {
"id": "a3b3d2de-9308-423e-b00d-c209c3e6e808",
"name": "steps",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 10
},
"cfg_scale": {
"id": "b13c50a4-ec7e-4579-b0ef-2fe5df2605ea",
"name": "cfg_scale",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 7.5
},
"denoising_start": {
"id": "57d5d755-f58f-4347-b991-f0bca4a0ab29",
"name": "denoising_start",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"denoising_end": {
"id": "323e78a6-880a-4d73-a62c-70faff965aa6",
"name": "denoising_end",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"scheduler": {
"id": "c25fdc17-a089-43ac-953e-067c45d5c76b",
"name": "scheduler",
"type": "Scheduler",
"fieldKind": "input",
"label": "",
"value": "euler"
},
"unet": {
"id": "6cde662b-e633-4569-b6b4-ec87c52c9c11",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
},
"control": {
"id": "276a4df9-bb26-4505-a4d3-a94e18c7b541",
"name": "control",
"type": "ControlPolymorphic",
"fieldKind": "input",
"label": ""
},
"ip_adapter": {
"id": "48d40c51-b5e2-4457-a428-eef0696695e8",
"name": "ip_adapter",
"type": "IPAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"t2i_adapter": {
"id": "75dd8af2-e7d7-48b4-a574-edd9f6e686ad",
"name": "t2i_adapter",
"type": "T2IAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "9223d67b-1dd7-4b34-a45f-ed0a725d9702",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"denoise_mask": {
"id": "4ee99177-6923-4b7f-8fe0-d721dd7cb05b",
"name": "denoise_mask",
"type": "DenoiseMaskField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"latents": {
"id": "7fb4e326-a974-43e8-9ee7-2e3ab235819d",
"name": "latents",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "6bb8acd0-8973-4195-a095-e376385dc705",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "795dea52-1c7d-4e64-99f7-2f60ec6e3ab9",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.4.0"
},
"width": 320,
"height": 646,
"position": {
"x": 5274.672987098195,
"y": -823.0752416664332
}
}
],
"edges": [
{
"source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"sourceHandle": "clip",
"target": "7ce68934-3419-42d4-ac70-82cfc9397306",
"targetHandle": "clip",
"id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9clip-7ce68934-3419-42d4-ac70-82cfc9397306clip",
"type": "default"
},
{
"source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"sourceHandle": "clip",
"target": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
"targetHandle": "clip",
"id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9clip-273e3f96-49ea-4dc5-9d5b-9660390f14e1clip",
"type": "default"
},
{
"source": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
"sourceHandle": "control",
"target": "ca4d5059-8bfb-447f-b415-da0faba5a143",
"targetHandle": "item",
"id": "reactflow__edge-a33199c2-8340-401e-b8a2-42ffa875fc1ccontrol-ca4d5059-8bfb-447f-b415-da0faba5a143item",
"type": "default"
},
{
"source": "d204d184-f209-4fae-a0a1-d152800844e1",
"sourceHandle": "control",
"target": "ca4d5059-8bfb-447f-b415-da0faba5a143",
"targetHandle": "item",
"id": "reactflow__edge-d204d184-f209-4fae-a0a1-d152800844e1control-ca4d5059-8bfb-447f-b415-da0faba5a143item",
"type": "default"
},
{
"source": "8e860e51-5045-456e-bf04-9a62a2a5c49e",
"sourceHandle": "image",
"target": "018b1214-c2af-43a7-9910-fb687c6726d7",
"targetHandle": "image",
"id": "reactflow__edge-8e860e51-5045-456e-bf04-9a62a2a5c49eimage-018b1214-c2af-43a7-9910-fb687c6726d7image",
"type": "default"
},
{
"source": "018b1214-c2af-43a7-9910-fb687c6726d7",
"sourceHandle": "image",
"target": "a33199c2-8340-401e-b8a2-42ffa875fc1c",
"targetHandle": "image",
"id": "reactflow__edge-018b1214-c2af-43a7-9910-fb687c6726d7image-a33199c2-8340-401e-b8a2-42ffa875fc1cimage",
"type": "default"
},
{
"source": "c4b23e64-7986-40c4-9cad-46327b12e204",
"sourceHandle": "image",
"target": "c826ba5e-9676-4475-b260-07b85e88753c",
"targetHandle": "image",
"id": "reactflow__edge-c4b23e64-7986-40c4-9cad-46327b12e204image-c826ba5e-9676-4475-b260-07b85e88753cimage",
"type": "default"
},
{
"source": "c826ba5e-9676-4475-b260-07b85e88753c",
"sourceHandle": "image",
"target": "d204d184-f209-4fae-a0a1-d152800844e1",
"targetHandle": "image",
"id": "reactflow__edge-c826ba5e-9676-4475-b260-07b85e88753cimage-d204d184-f209-4fae-a0a1-d152800844e1image",
"type": "default"
},
{
"source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"sourceHandle": "vae",
"target": "9db25398-c869-4a63-8815-c6559341ef12",
"targetHandle": "vae",
"id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9vae-9db25398-c869-4a63-8815-c6559341ef12vae",
"type": "default"
},
{
"source": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"sourceHandle": "latents",
"target": "9db25398-c869-4a63-8815-c6559341ef12",
"targetHandle": "latents",
"id": "reactflow__edge-ac481b7f-08bf-4a9d-9e0c-3a82ea5243celatents-9db25398-c869-4a63-8815-c6559341ef12latents",
"type": "default"
},
{
"source": "ca4d5059-8bfb-447f-b415-da0faba5a143",
"sourceHandle": "collection",
"target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"targetHandle": "control",
"id": "reactflow__edge-ca4d5059-8bfb-447f-b415-da0faba5a143collection-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cecontrol",
"type": "default"
},
{
"source": "54486974-835b-4d81-8f82-05f9f32ce9e9",
"sourceHandle": "unet",
"target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"targetHandle": "unet",
"id": "reactflow__edge-54486974-835b-4d81-8f82-05f9f32ce9e9unet-ac481b7f-08bf-4a9d-9e0c-3a82ea5243ceunet",
"type": "default"
},
{
"source": "273e3f96-49ea-4dc5-9d5b-9660390f14e1",
"sourceHandle": "conditioning",
"target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"targetHandle": "negative_conditioning",
"id": "reactflow__edge-273e3f96-49ea-4dc5-9d5b-9660390f14e1conditioning-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cenegative_conditioning",
"type": "default"
},
{
"source": "7ce68934-3419-42d4-ac70-82cfc9397306",
"sourceHandle": "conditioning",
"target": "ac481b7f-08bf-4a9d-9e0c-3a82ea5243ce",
"targetHandle": "positive_conditioning",
"id": "reactflow__edge-7ce68934-3419-42d4-ac70-82cfc9397306conditioning-ac481b7f-08bf-4a9d-9e0c-3a82ea5243cepositive_conditioning",
"type": "default"
}
]
}

719
docs/workflows/Prompt_from_File.json Normal file
View File

@ -0,0 +1,719 @@
{
"name": "Prompt from File",
"author": "InvokeAI",
"description": "Sample workflow using prompt from file capabilities of InvokeAI ",
"version": "0.1.0",
"contact": "millun@invoke.ai",
"tags": "text2image, prompt from file, default",
"notes": "",
"exposedFields": [
{
"nodeId": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"fieldName": "model"
},
{
"nodeId": "1b7e0df8-8589-4915-a4ea-c0088f15d642",
"fieldName": "file_path"
}
],
"meta": {
"version": "1.0.0"
},
"nodes": [
{
"id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
"type": "invocation",
"data": {
"id": "c2eaf1ba-5708-4679-9e15-945b8b432692",
"type": "compel",
"inputs": {
"prompt": {
"id": "dcdf3f6d-9b96-4bcd-9b8d-f992fefe4f62",
"name": "prompt",
"type": "string",
"fieldKind": "input",
"label": "",
"value": ""
},
"clip": {
"id": "3f1981c9-d8a9-42eb-a739-4f120eb80745",
"name": "clip",
"type": "ClipField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"conditioning": {
"id": "46205e6c-c5e2-44cb-9c82-1cd20b95674a",
"name": "conditioning",
"type": "ConditioningField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 261,
"position": {
"x": 1177.3417789657444,
"y": -102.0924766641035
}
},
{
"id": "1b7e0df8-8589-4915-a4ea-c0088f15d642",
"type": "invocation",
"data": {
"id": "1b7e0df8-8589-4915-a4ea-c0088f15d642",
"type": "prompt_from_file",
"inputs": {
"file_path": {
"id": "37e37684-4f30-4ec8-beae-b333e550f904",
"name": "file_path",
"type": "string",
"fieldKind": "input",
"label": "Prompts File Path",
"value": ""
},
"pre_prompt": {
"id": "7de02feb-819a-4992-bad3-72a30920ddea",
"name": "pre_prompt",
"type": "string",
"fieldKind": "input",
"label": "",
"value": ""
},
"post_prompt": {
"id": "95f191d8-a282-428e-bd65-de8cb9b7513a",
"name": "post_prompt",
"type": "string",
"fieldKind": "input",
"label": "",
"value": ""
},
"start_line": {
"id": "efee9a48-05ab-4829-8429-becfa64a0782",
"name": "start_line",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 1
},
"max_prompts": {
"id": "abebb428-3d3d-49fd-a482-4e96a16fff08",
"name": "max_prompts",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 1
}
},
"outputs": {
"collection": {
"id": "77d5d7f1-9877-4ab1-9a8c-33e9ffa9abf3",
"name": "collection",
"type": "StringCollection",
"fieldKind": "output"
}
},
"label": "Prompts from File",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 589,
"position": {
"x": 394.181884547075,
"y": -423.5345157864633
}
},
{
"id": "1b89067c-3f6b-42c8-991f-e3055789b251",
"type": "invocation",
"data": {
"id": "1b89067c-3f6b-42c8-991f-e3055789b251",
"type": "iterate",
"inputs": {
"collection": {
"id": "4c564bf8-5ed6-441e-ad2c-dda265d5785f",
"name": "collection",
"type": "Collection",
"fieldKind": "input",
"label": "",
"value": []
}
},
"outputs": {
"item": {
"id": "36340f9a-e7a5-4afa-b4b5-313f4e292380",
"name": "item",
"type": "CollectionItem",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 104,
"position": {
"x": 792.8735298060233,
"y": -432.6964953027252
}
},
{
"id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"type": "invocation",
"data": {
"id": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"type": "main_model_loader",
"inputs": {
"model": {
"id": "3f264259-3418-47d5-b90d-b6600e36ae46",
"name": "model",
"type": "MainModelField",
"fieldKind": "input",
"label": "",
"value": {
"model_name": "stable-diffusion-v1-5",
"base_model": "sd-1",
"model_type": "main"
}
}
},
"outputs": {
"unet": {
"id": "8e182ea2-9d0a-4c02-9407-27819288d4b5",
"name": "unet",
"type": "UNetField",
"fieldKind": "output"
},
"clip": {
"id": "d67d9d30-058c-46d5-bded-3d09d6d1aa39",
"name": "clip",
"type": "ClipField",
"fieldKind": "output"
},
"vae": {
"id": "89641601-0429-4448-98d5-190822d920d8",
"name": "vae",
"type": "VaeField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 226,
"position": {
"x": -47.66201354137797,
"y": -299.218193067033
}
},
{
"id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
"type": "invocation",
"data": {
"id": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
"type": "compel",
"inputs": {
"prompt": {
"id": "dcdf3f6d-9b96-4bcd-9b8d-f992fefe4f62",
"name": "prompt",
"type": "string",
"fieldKind": "input",
"label": "",
"value": ""
},
"clip": {
"id": "3f1981c9-d8a9-42eb-a739-4f120eb80745",
"name": "clip",
"type": "ClipField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"conditioning": {
"id": "46205e6c-c5e2-44cb-9c82-1cd20b95674a",
"name": "conditioning",
"type": "ConditioningField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 261,
"position": {
"x": 1175.0187896425462,
"y": -420.64289413577114
}
},
{
"id": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
"type": "invocation",
"data": {
"id": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
"type": "noise",
"inputs": {
"seed": {
"id": "b722d84a-eeee-484f-bef2-0250c027cb67",
"name": "seed",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 0
},
"width": {
"id": "d5f8ce11-0502-4bfc-9a30-5757dddf1f94",
"name": "width",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 512
},
"height": {
"id": "f187d5ff-38a5-4c3f-b780-fc5801ef34af",
"name": "height",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 512
},
"use_cpu": {
"id": "12f112b8-8b76-4816-b79e-662edc9f9aa5",
"name": "use_cpu",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": true
}
},
"outputs": {
"noise": {
"id": "08576ad1-96d9-42d2-96ef-6f5c1961933f",
"name": "noise",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "f3e1f94a-258d-41ff-9789-bd999bd9f40d",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "6cefc357-4339-415e-a951-49b9c2be32f4",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 389,
"position": {
"x": 809.1964864135837,
"y": 183.2735123359796
}
},
{
"id": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5",
"type": "invocation",
"data": {
"id": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5",
"type": "rand_int",
"inputs": {
"low": {
"id": "b9fc6cf1-469c-4037-9bf0-04836965826f",
"name": "low",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 0
},
"high": {
"id": "06eac725-0f60-4ba2-b8cd-7ad9f757488c",
"name": "high",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 2147483647
}
},
"outputs": {
"value": {
"id": "df08c84e-7346-4e92-9042-9e5cb773aaff",
"name": "value",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": false,
"version": "1.0.0"
},
"width": 320,
"height": 218,
"position": {
"x": 354.19913145404166,
"y": 301.86324846905165
}
},
{
"id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
"type": "invocation",
"data": {
"id": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
"type": "l2i",
"inputs": {
"metadata": {
"id": "022e4b33-562b-438d-b7df-41c3fd931f40",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "67cb6c77-a394-4a66-a6a9-a0a7dcca69ec",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"vae": {
"id": "7b3fd9ad-a4ef-4e04-89fa-3832a9902dbd",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
},
"tiled": {
"id": "5ac5680d-3add-4115-8ec0-9ef5bb87493b",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"fp32": {
"id": "db8297f5-55f8-452f-98cf-6572c2582152",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
}
},
"outputs": {
"image": {
"id": "d8778d0c-592a-4960-9280-4e77e00a7f33",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "c8b0a75a-f5de-4ff2-9227-f25bb2b97bec",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "83c05fbf-76b9-49ab-93c4-fa4b10e793e4",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 267,
"position": {
"x": 2037.861329274915,
"y": -329.8393457509562
}
},
{
"id": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"type": "invocation",
"data": {
"id": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"type": "denoise_latents",
"inputs": {
"positive_conditioning": {
"id": "751fb35b-3f23-45ce-af1c-053e74251337",
"name": "positive_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"negative_conditioning": {
"id": "b9dc06b6-7481-4db1-a8c2-39d22a5eacff",
"name": "negative_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"noise": {
"id": "6e15e439-3390-48a4-8031-01e0e19f0e1d",
"name": "noise",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"steps": {
"id": "bfdfb3df-760b-4d51-b17b-0abb38b976c2",
"name": "steps",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 10
},
"cfg_scale": {
"id": "47770858-322e-41af-8494-d8b63ed735f3",
"name": "cfg_scale",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 7.5
},
"denoising_start": {
"id": "2ba78720-ee02-4130-a348-7bc3531f790b",
"name": "denoising_start",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"denoising_end": {
"id": "a874dffb-d433-4d1a-9f59-af4367bb05e4",
"name": "denoising_end",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"scheduler": {
"id": "36e021ad-b762-4fe4-ad4d-17f0291c40b2",
"name": "scheduler",
"type": "Scheduler",
"fieldKind": "input",
"label": "",
"value": "euler"
},
"unet": {
"id": "98d3282d-f9f6-4b5e-b9e8-58658f1cac78",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
},
"control": {
"id": "f2ea3216-43d5-42b4-887f-36e8f7166d53",
"name": "control",
"type": "ControlPolymorphic",
"fieldKind": "input",
"label": ""
},
"ip_adapter": {
"id": "d0780610-a298-47c8-a54e-70e769e0dfe2",
"name": "ip_adapter",
"type": "IPAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"t2i_adapter": {
"id": "fdb40970-185e-4ea8-8bb5-88f06f91f46a",
"name": "t2i_adapter",
"type": "T2IAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "e05b538a-1b5a-4aa5-84b1-fd2361289a81",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"denoise_mask": {
"id": "463a419e-df30-4382-8ffb-b25b25abe425",
"name": "denoise_mask",
"type": "DenoiseMaskField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"latents": {
"id": "559ee688-66cf-4139-8b82-3d3aa69995ce",
"name": "latents",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "0b4285c2-e8b9-48e5-98f6-0a49d3f98fd2",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "8b0881b9-45e5-47d5-b526-24b6661de0ee",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.4.0"
},
"width": 320,
"height": 646,
"position": {
"x": 1570.9941088179146,
"y": -407.6505491604564
}
}
],
"edges": [
{
"source": "1b7e0df8-8589-4915-a4ea-c0088f15d642",
"sourceHandle": "collection",
"target": "1b89067c-3f6b-42c8-991f-e3055789b251",
"targetHandle": "collection",
"id": "reactflow__edge-1b7e0df8-8589-4915-a4ea-c0088f15d642collection-1b89067c-3f6b-42c8-991f-e3055789b251collection",
"type": "default"
},
{
"source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"sourceHandle": "clip",
"target": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
"targetHandle": "clip",
"id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426clip-fc9d0e35-a6de-4a19-84e1-c72497c823f6clip",
"type": "default"
},
{
"source": "1b89067c-3f6b-42c8-991f-e3055789b251",
"sourceHandle": "item",
"target": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
"targetHandle": "prompt",
"id": "reactflow__edge-1b89067c-3f6b-42c8-991f-e3055789b251item-fc9d0e35-a6de-4a19-84e1-c72497c823f6prompt",
"type": "default"
},
{
"source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"sourceHandle": "clip",
"target": "c2eaf1ba-5708-4679-9e15-945b8b432692",
"targetHandle": "clip",
"id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426clip-c2eaf1ba-5708-4679-9e15-945b8b432692clip",
"type": "default"
},
{
"source": "dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5",
"sourceHandle": "value",
"target": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
"targetHandle": "seed",
"id": "reactflow__edge-dfc20e07-7aef-4fc0-a3a1-7bf68ec6a4e5value-0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77seed",
"type": "default"
},
{
"source": "fc9d0e35-a6de-4a19-84e1-c72497c823f6",
"sourceHandle": "conditioning",
"target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"targetHandle": "positive_conditioning",
"id": "reactflow__edge-fc9d0e35-a6de-4a19-84e1-c72497c823f6conditioning-2fb1577f-0a56-4f12-8711-8afcaaaf1d5epositive_conditioning",
"type": "default"
},
{
"source": "c2eaf1ba-5708-4679-9e15-945b8b432692",
"sourceHandle": "conditioning",
"target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"targetHandle": "negative_conditioning",
"id": "reactflow__edge-c2eaf1ba-5708-4679-9e15-945b8b432692conditioning-2fb1577f-0a56-4f12-8711-8afcaaaf1d5enegative_conditioning",
"type": "default"
},
{
"source": "0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77",
"sourceHandle": "noise",
"target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"targetHandle": "noise",
"id": "reactflow__edge-0eb5f3f5-1b91-49eb-9ef0-41d67c7eae77noise-2fb1577f-0a56-4f12-8711-8afcaaaf1d5enoise",
"type": "default"
},
{
"source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"sourceHandle": "unet",
"target": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"targetHandle": "unet",
"id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426unet-2fb1577f-0a56-4f12-8711-8afcaaaf1d5eunet",
"type": "default"
},
{
"source": "2fb1577f-0a56-4f12-8711-8afcaaaf1d5e",
"sourceHandle": "latents",
"target": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
"targetHandle": "latents",
"id": "reactflow__edge-2fb1577f-0a56-4f12-8711-8afcaaaf1d5elatents-491ec988-3c77-4c37-af8a-39a0c4e7a2a1latents",
"type": "default"
},
{
"source": "d6353b7f-b447-4e17-8f2e-80a88c91d426",
"sourceHandle": "vae",
"target": "491ec988-3c77-4c37-af8a-39a0c4e7a2a1",
"targetHandle": "vae",
"id": "reactflow__edge-d6353b7f-b447-4e17-8f2e-80a88c91d426vae-491ec988-3c77-4c37-af8a-39a0c4e7a2a1vae",
"type": "default"
}
]
}

758
docs/workflows/QR_Code_Monster.json Normal file
View File

@ -0,0 +1,758 @@
{
"name": "QR Code Monster",
"author": "InvokeAI",
"description": "Sample workflow for create images with QR code Monster ControlNet",
"version": "1.0.1",
"contact": "invoke@invoke.ai",
"tags": "qrcode, controlnet, default",
"notes": "",
"exposedFields": [
{
"nodeId": "a6cc0986-f928-4a7e-8d44-ba2d4b36f54a",
"fieldName": "image"
},
{
"nodeId": "aca3b054-bfba-4392-bd20-6476f59504df",
"fieldName": "prompt"
},
{
"nodeId": "3db7cee0-31e2-4a3d-94a1-268cb16177dd",
"fieldName": "prompt"
}
],
"meta": {
"version": "1.0.0"
},
"nodes": [
{
"id": "3db7cee0-31e2-4a3d-94a1-268cb16177dd",
"type": "invocation",
"data": {
"id": "3db7cee0-31e2-4a3d-94a1-268cb16177dd",
"type": "compel",
"inputs": {
"prompt": {
"id": "6a1fe244-5656-4f8c-91d1-1fb474e28807",
"name": "prompt",
"type": "string",
"fieldKind": "input",
"label": "Negative Prompt",
"value": ""
},
"clip": {
"id": "f24688f3-29b8-4a2d-8603-046e5a5c7250",
"name": "clip",
"type": "ClipField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"conditioning": {
"id": "700528eb-3f8b-4745-b540-34f919b5b228",
"name": "conditioning",
"type": "ConditioningField",
"fieldKind": "output"
}
},
"label": "Prompt",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 261,
"position": {
"x": 773.0502679628016,
"y": 1622.4836086770556
}
},
{
"id": "610384f1-6f0c-4847-a9a2-37ce7f456ed1",
"type": "invocation",
"data": {
"id": "610384f1-6f0c-4847-a9a2-37ce7f456ed1",
"type": "main_model_loader",
"inputs": {
"model": {
"id": "cb36b6d3-6c1f-4911-a200-646745b0ff74",
"name": "model",
"type": "MainModelField",
"fieldKind": "input",
"label": "",
"value": {
"model_name": "stable-diffusion-v1-5",
"base_model": "sd-1",
"model_type": "main"
}
}
},
"outputs": {
"unet": {
"id": "7246895b-b252-49bc-b952-8d801b4672f7",
"name": "unet",
"type": "UNetField",
"fieldKind": "output"
},
"clip": {
"id": "3c2aedb8-30d5-4d4b-99df-d06a0d7bedc6",
"name": "clip",
"type": "ClipField",
"fieldKind": "output"
},
"vae": {
"id": "b9743815-5501-4bbb-8bde-8bd6ba298a4e",
"name": "vae",
"type": "VaeField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 226,
"position": {
"x": 211.58866462619744,
"y": 1376.0542388105248
}
},
{
"id": "aca3b054-bfba-4392-bd20-6476f59504df",
"type": "invocation",
"data": {
"id": "aca3b054-bfba-4392-bd20-6476f59504df",
"type": "compel",
"inputs": {
"prompt": {
"id": "6a1fe244-5656-4f8c-91d1-1fb474e28807",
"name": "prompt",
"type": "string",
"fieldKind": "input",
"label": "Positive Prompt",
"value": ""
},
"clip": {
"id": "f24688f3-29b8-4a2d-8603-046e5a5c7250",
"name": "clip",
"type": "ClipField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"conditioning": {
"id": "700528eb-3f8b-4745-b540-34f919b5b228",
"name": "conditioning",
"type": "ConditioningField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 261,
"position": {
"x": 770.6491131680111,
"y": 1316.379247112241
}
},
{
"id": "a6cc0986-f928-4a7e-8d44-ba2d4b36f54a",
"type": "invocation",
"data": {
"id": "a6cc0986-f928-4a7e-8d44-ba2d4b36f54a",
"type": "image",
"inputs": {
"image": {
"id": "89ba5d58-28c9-4e04-a5df-79fb7a6f3531",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": "QR Code / Hidden Image"
}
},
"outputs": {
"image": {
"id": "54335653-0e17-42da-b9e8-83c5fb5af670",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "a3c65953-39ea-4d97-8858-d65154ff9d11",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "2c7db511-ebc9-4286-a46b-bc11e0fd779f",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 225,
"position": {
"x": 700.5034176864369,
"y": 1981.749600549388
}
},
{
"id": "280fd8a7-3b0c-49fe-8be4-6246e08b6c9a",
"type": "invocation",
"data": {
"id": "280fd8a7-3b0c-49fe-8be4-6246e08b6c9a",
"type": "noise",
"inputs": {
"seed": {
"id": "7c6c76dd-127b-4829-b1ec-430790cb7ed7",
"name": "seed",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 0
},
"width": {
"id": "8ec6a525-a421-40d8-a17e-39e7b6836438",
"name": "width",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 512
},
"height": {
"id": "6af1e58a-e2ee-4ec4-9f06-d8d0412922ca",
"name": "height",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 512
},
"use_cpu": {
"id": "26662e99-5720-43a6-a5d8-06c9dab0e261",
"name": "use_cpu",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": true
}
},
"outputs": {
"noise": {
"id": "cb4c4dfc-a744-49eb-af4f-677448e28407",
"name": "noise",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "97e87be6-e81f-40a3-a522-28ebe4aad0ac",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "80784420-f1e1-47b0-bd1d-1d381a15e22d",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": false,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 32,
"position": {
"x": 1182.460291960481,
"y": 1759.592972960265
}
},
{
"id": "2ac03cf6-0326-454a-bed0-d8baef2bf30d",
"type": "invocation",
"data": {
"id": "2ac03cf6-0326-454a-bed0-d8baef2bf30d",
"type": "controlnet",
"inputs": {
"image": {
"id": "1f683889-9f14-40c8-af29-4b991b211a3a",
"name": "image",
"type": "ImageField",
"fieldKind": "input",
"label": ""
},
"control_model": {
"id": "a933b21d-22c1-4e06-818f-15416b971282",
"name": "control_model",
"type": "ControlNetModelField",
"fieldKind": "input",
"label": "",
"value": {
"model_name": "qrcode_monster",
"base_model": "sd-1"
}
},
"control_weight": {
"id": "198a0825-e55e-4496-bc54-c3d7b02f3d75",
"name": "control_weight",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 1.4
},
"begin_step_percent": {
"id": "c85ce42f-22af-42a0-8993-676002fb275e",
"name": "begin_step_percent",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"end_step_percent": {
"id": "a61a65c4-9e6f-4fe2-96a5-1294d17ec6e4",
"name": "end_step_percent",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"control_mode": {
"id": "1aa45cfa-0249-46b7-bf24-3e38e92f5fa0",
"name": "control_mode",
"type": "enum",
"fieldKind": "input",
"label": "",
"value": "balanced"
},
"resize_mode": {
"id": "a89d3cb9-a141-4cea-bb49-977bf267377b",
"name": "resize_mode",
"type": "enum",
"fieldKind": "input",
"label": "",
"value": "just_resize"
}
},
"outputs": {
"control": {
"id": "c9a1fc7e-cb25-45a9-adff-1a97c9ff04d6",
"name": "control",
"type": "ControlField",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 508,
"position": {
"x": 1165.434407461108,
"y": 1862.916856351665
}
},
{
"id": "28542b66-5a00-4780-a318-0a036d2df914",
"type": "invocation",
"data": {
"id": "28542b66-5a00-4780-a318-0a036d2df914",
"type": "l2i",
"inputs": {
"metadata": {
"id": "a38e8f55-7f2c-4fcc-a71f-d51e2eb0374a",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "80e97bc8-e716-4175-9115-5b58495aa30c",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"vae": {
"id": "5641bce6-ac2b-47eb-bb32-2f290026b7e1",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
},
"tiled": {
"id": "9e75eb16-ae48-47ed-b180-e0409d377436",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"fp32": {
"id": "0518b0ce-ee37-437b-8437-cc2976a3279f",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
}
},
"outputs": {
"image": {
"id": "ec2ff985-a7eb-401f-92c4-1217cddad6a2",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "ba1d1720-6d67-4eca-9e9d-b97d08636774",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "10bcf8f4-6394-422f-b0c0-51680f3bfb25",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 267,
"position": {
"x": 2110.8415693683014,
"y": 1487.253341116115
}
},
{
"id": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"type": "invocation",
"data": {
"id": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"type": "denoise_latents",
"inputs": {
"positive_conditioning": {
"id": "8e6aceaa-a986-4ab2-9c04-5b1027b3daf6",
"name": "positive_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"negative_conditioning": {
"id": "fbbaa712-ca1a-420b-9016-763f2a29d68c",
"name": "negative_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"noise": {
"id": "a3b3d5d2-c0f9-4b89-a9b3-8de9418f7bb5",
"name": "noise",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"steps": {
"id": "e491e664-2f8c-4f49-b3e4-57b051fbb9c5",
"name": "steps",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 10
},
"cfg_scale": {
"id": "f0318abd-ed65-4cad-86a7-48d1c19a6d14",
"name": "cfg_scale",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 7.5
},
"denoising_start": {
"id": "f7c24c51-496f-44c4-836a-c734e529fec0",
"name": "denoising_start",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"denoising_end": {
"id": "54f7656a-fb0d-4d9e-a459-f700f7dccd2e",
"name": "denoising_end",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"scheduler": {
"id": "363ee440-040d-499b-bf84-bf5391b08681",
"name": "scheduler",
"type": "Scheduler",
"fieldKind": "input",
"label": "",
"value": "euler"
},
"unet": {
"id": "5c93d4e5-1064-4700-ab1d-d12e1e9b5ba7",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
},
"control": {
"id": "e1948eb3-7407-43b0-93e3-139470f186b7",
"name": "control",
"type": "ControlPolymorphic",
"fieldKind": "input",
"label": ""
},
"ip_adapter": {
"id": "5675b2c3-adfb-49ee-b33c-26bdbfab1fed",
"name": "ip_adapter",
"type": "IPAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"t2i_adapter": {
"id": "89cd4ab3-3bfc-4063-9de5-91d42305c651",
"name": "t2i_adapter",
"type": "T2IAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "ec01df90-5042-418d-b6d6-86b251c13770",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"denoise_mask": {
"id": "561cde00-cb20-42ae-9bd3-4f477f73fbe1",
"name": "denoise_mask",
"type": "DenoiseMaskField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"latents": {
"id": "f9addefe-efcc-4e01-8945-6ebbc934b002",
"name": "latents",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "6d48f78b-d681-422a-8677-0111bd0625f1",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "f25997b8-6316-44ce-b696-b82e4ed51ae5",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.4.0"
},
"width": 320,
"height": 646,
"position": {
"x": 1597.9598293300219,
"y": 1420.4637727891632
}
},
{
"id": "59349822-af20-4e0e-a53f-3ba135d00c3f",
"type": "invocation",
"data": {
"id": "59349822-af20-4e0e-a53f-3ba135d00c3f",
"type": "rand_int",
"inputs": {
"low": {
"id": "051f22f9-2d4f-414f-bc51-84af2d626efa",
"name": "low",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 0
},
"high": {
"id": "77206186-f264-4224-9589-f925cf903dc9",
"name": "high",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 2147483647
}
},
"outputs": {
"value": {
"id": "a7ed9387-3a24-4d34-b7c5-f713bd544ab1",
"name": "value",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": false,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": false,
"version": "1.0.0"
},
"width": 320,
"height": 32,
"position": {
"x": 1178.16746986153,
"y": 1663.9433412808876
}
}
],
"edges": [
{
"source": "59349822-af20-4e0e-a53f-3ba135d00c3f",
"target": "280fd8a7-3b0c-49fe-8be4-6246e08b6c9a",
"id": "59349822-af20-4e0e-a53f-3ba135d00c3f-280fd8a7-3b0c-49fe-8be4-6246e08b6c9a-collapsed",
"type": "collapsed"
},
{
"source": "610384f1-6f0c-4847-a9a2-37ce7f456ed1",
"sourceHandle": "clip",
"target": "aca3b054-bfba-4392-bd20-6476f59504df",
"targetHandle": "clip",
"id": "reactflow__edge-610384f1-6f0c-4847-a9a2-37ce7f456ed1clip-aca3b054-bfba-4392-bd20-6476f59504dfclip",
"type": "default"
},
{
"source": "610384f1-6f0c-4847-a9a2-37ce7f456ed1",
"sourceHandle": "clip",
"target": "3db7cee0-31e2-4a3d-94a1-268cb16177dd",
"targetHandle": "clip",
"id": "reactflow__edge-610384f1-6f0c-4847-a9a2-37ce7f456ed1clip-3db7cee0-31e2-4a3d-94a1-268cb16177ddclip",
"type": "default"
},
{
"source": "a6cc0986-f928-4a7e-8d44-ba2d4b36f54a",
"sourceHandle": "image",
"target": "2ac03cf6-0326-454a-bed0-d8baef2bf30d",
"targetHandle": "image",
"id": "reactflow__edge-a6cc0986-f928-4a7e-8d44-ba2d4b36f54aimage-2ac03cf6-0326-454a-bed0-d8baef2bf30dimage",
"type": "default"
},
{
"source": "610384f1-6f0c-4847-a9a2-37ce7f456ed1",
"sourceHandle": "vae",
"target": "28542b66-5a00-4780-a318-0a036d2df914",
"targetHandle": "vae",
"id": "reactflow__edge-610384f1-6f0c-4847-a9a2-37ce7f456ed1vae-28542b66-5a00-4780-a318-0a036d2df914vae",
"type": "default"
},
{
"source": "280fd8a7-3b0c-49fe-8be4-6246e08b6c9a",
"sourceHandle": "noise",
"target": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"targetHandle": "noise",
"id": "reactflow__edge-280fd8a7-3b0c-49fe-8be4-6246e08b6c9anoise-9755ae4c-ef30-4db3-80f6-a31f98979a11noise",
"type": "default"
},
{
"source": "3db7cee0-31e2-4a3d-94a1-268cb16177dd",
"sourceHandle": "conditioning",
"target": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"targetHandle": "negative_conditioning",
"id": "reactflow__edge-3db7cee0-31e2-4a3d-94a1-268cb16177ddconditioning-9755ae4c-ef30-4db3-80f6-a31f98979a11negative_conditioning",
"type": "default"
},
{
"source": "aca3b054-bfba-4392-bd20-6476f59504df",
"sourceHandle": "conditioning",
"target": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"targetHandle": "positive_conditioning",
"id": "reactflow__edge-aca3b054-bfba-4392-bd20-6476f59504dfconditioning-9755ae4c-ef30-4db3-80f6-a31f98979a11positive_conditioning",
"type": "default"
},
{
"source": "610384f1-6f0c-4847-a9a2-37ce7f456ed1",
"sourceHandle": "unet",
"target": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"targetHandle": "unet",
"id": "reactflow__edge-610384f1-6f0c-4847-a9a2-37ce7f456ed1unet-9755ae4c-ef30-4db3-80f6-a31f98979a11unet",
"type": "default"
},
{
"source": "2ac03cf6-0326-454a-bed0-d8baef2bf30d",
"sourceHandle": "control",
"target": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"targetHandle": "control",
"id": "reactflow__edge-2ac03cf6-0326-454a-bed0-d8baef2bf30dcontrol-9755ae4c-ef30-4db3-80f6-a31f98979a11control",
"type": "default"
},
{
"source": "9755ae4c-ef30-4db3-80f6-a31f98979a11",
"sourceHandle": "latents",
"target": "28542b66-5a00-4780-a318-0a036d2df914",
"targetHandle": "latents",
"id": "reactflow__edge-9755ae4c-ef30-4db3-80f6-a31f98979a11latents-28542b66-5a00-4780-a318-0a036d2df914latents",
"type": "default"
},
{
"source": "59349822-af20-4e0e-a53f-3ba135d00c3f",
"sourceHandle": "value",
"target": "280fd8a7-3b0c-49fe-8be4-6246e08b6c9a",
"targetHandle": "seed",
"id": "reactflow__edge-59349822-af20-4e0e-a53f-3ba135d00c3fvalue-280fd8a7-3b0c-49fe-8be4-6246e08b6c9aseed",
"type": "default"
}
]
}

432
docs/workflows/SDXL_Text_to_Image.json
View File

@ -26,10 +26,6 @@
{
"nodeId": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
"fieldName": "style"
},
{
"nodeId": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"fieldName": "steps"
}
],
"meta": {
@ -40,7 +36,6 @@
"id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
"type": "sdxl_compel_prompt",
"inputs": {
@ -135,10 +130,12 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 764,
"height": 793,
"position": {
"x": 1275,
"y": -350
@ -148,7 +145,6 @@
"id": "55705012-79b9-4aac-9f26-c0b10309785b",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "55705012-79b9-4aac-9f26-c0b10309785b",
"type": "noise",
"inputs": {
@ -209,7 +205,9 @@
"isOpen": false,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 32,
@ -218,83 +216,10 @@
"y": -300
}
},
{
"id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"type": "l2i",
"inputs": {
"tiled": {
"id": "24f5bc7b-f6a1-425d-8ab1-f50b4db5d0df",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"fp32": {
"id": "b146d873-ffb9-4767-986a-5360504841a2",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": true
},
"latents": {
"id": "65441abd-7713-4b00-9d8d-3771404002e8",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"vae": {
"id": "a478b833-6e13-4611-9a10-842c89603c74",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"image": {
"id": "c87ae925-f858-417a-8940-8708ba9b4b53",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "4bcb8512-b5a1-45f1-9e52-6e92849f9d6c",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "23e41c00-a354-48e8-8f59-5875679c27ab",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": true,
"isIntermediate": false
},
"width": 320,
"height": 224,
"position": {
"x": 2025,
"y": -250
}
},
{
"id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
"type": "rand_int",
"inputs": {
@ -327,7 +252,9 @@
"isOpen": false,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": false,
"version": "1.0.0"
},
"width": 320,
"height": 32,
@ -340,7 +267,6 @@
"id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
"type": "sdxl_model_loader",
"inputs": {
@ -351,7 +277,7 @@
"fieldKind": "input",
"label": "",
"value": {
"model_name": "stable-diffusion-xl-base-1.0",
"model_name": "stable-diffusion-xl-base-1-0",
"base_model": "sdxl",
"model_type": "main"
}
@ -387,10 +313,12 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 234,
"height": 258,
"position": {
"x": 475,
"y": 25
@ -400,7 +328,6 @@
"id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
"type": "sdxl_compel_prompt",
"inputs": {
@ -495,128 +422,77 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 764,
"height": 793,
"position": {
"x": 900,
"y": -350
}
},
{
"id": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"id": "63e91020-83b2-4f35-b174-ad9692aabb48",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"type": "denoise_latents",
"id": "63e91020-83b2-4f35-b174-ad9692aabb48",
"type": "l2i",
"inputs": {
"noise": {
"id": "4884a4b7-cc19-4fea-83c7-1f940e6edd24",
"name": "noise",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"steps": {
"id": "4c61675c-b6b9-41ac-b187-b5c13b587039",
"name": "steps",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 36
},
"cfg_scale": {
"id": "f8213f35-4637-4a1a-83f4-1f8cfb9ccd2c",
"name": "cfg_scale",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 7.5
},
"denoising_start": {
"id": "01e2f30d-0acd-4e21-98b9-a9b8e24c6db2",
"name": "denoising_start",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"denoising_end": {
"id": "3db95479-a73b-4c75-9b44-08daec16b224",
"name": "denoising_end",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"scheduler": {
"id": "db8430a9-64c3-4c54-ae38-9f597cf7b6d5",
"name": "scheduler",
"type": "Scheduler",
"fieldKind": "input",
"label": "",
"value": "euler"
},
"control": {
"id": "599b49e8-6435-4576-be41-a5155f3a17e3",
"name": "control",
"type": "ControlField",
"metadata": {
"id": "88971324-3fdb-442d-b8b7-7612478a8622",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "226f9e91-454e-4159-9fa6-019c0cf29277",
"id": "da0e40cb-c49f-4fa5-9856-338b91a65f6b",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"denoise_mask": {
"id": "de019cb6-7fb5-45bf-a266-22e20889893f",
"name": "denoise_mask",
"type": "DenoiseMaskField",
"vae": {
"id": "ae5164ce-1710-4ec5-a83a-6113a0d1b5c0",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
},
"positive_conditioning": {
"id": "02fc400a-110d-470e-8411-f404f966a949",
"name": "positive_conditioning",
"type": "ConditioningField",
"tiled": {
"id": "2ccfd535-1a7b-4ecf-84db-9430a64fb3d7",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": ""
"label": "",
"value": false
},
"negative_conditioning": {
"id": "4bd3bdfa-fcf4-42be-8e47-1e314255798f",
"name": "negative_conditioning",
"type": "ConditioningField",
"fp32": {
"id": "64f07d5a-54a2-429c-8c5b-0c2a3a8e5cd5",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": ""
},
"unet": {
"id": "7c2d58a8-b5f1-4e63-8ffd-8ada52c35832",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
"label": "",
"value": false
}
},
"outputs": {
"latents": {
"id": "6a6fa492-de26-4e95-b1d9-a322fe37eb13",
"name": "latents",
"type": "LatentsField",
"image": {
"id": "9b281eaa-6504-407d-a5ca-1e5e8020a4bf",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "a9790729-7d6c-4418-903d-4da961fccf56",
"id": "98e545f3-b53b-490d-b94d-bed9418ccc75",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "fa74efe5-7330-4a3c-b256-c82a544585b4",
"id": "4a74bd43-d7f7-4c7f-bb3b-d09bb2992c46",
"name": "height",
"type": "integer",
"fieldKind": "output"
@ -626,13 +502,161 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": false,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 558,
"height": 267,
"position": {
"x": 1650,
"y": -250
"x": 2112.5626808057173,
"y": -174.24042139280238
}
},
{
"id": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
"type": "invocation",
"data": {
"id": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
"type": "denoise_latents",
"inputs": {
"positive_conditioning": {
"id": "29b73dfa-a06e-4b4a-a844-515b9eb93a81",
"name": "positive_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"negative_conditioning": {
"id": "a81e6f5b-f4de-4919-b483-b6e2f067465a",
"name": "negative_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"noise": {
"id": "4ba06bb7-eb45-4fb9-9984-31001b545587",
"name": "noise",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"steps": {
"id": "36ee8a45-ca69-44bc-9bc3-aa881e6045c0",
"name": "steps",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 10
},
"cfg_scale": {
"id": "2a2024e0-a736-46ec-933c-c1c1ebe96943",
"name": "cfg_scale",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 7.5
},
"denoising_start": {
"id": "be219d5e-41b7-430a-8fb5-bc21a31ad219",
"name": "denoising_start",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 0
},
"denoising_end": {
"id": "3adfb7ae-c9f7-4a40-b6e0-4c2050bd1a99",
"name": "denoising_end",
"type": "float",
"fieldKind": "input",
"label": "",
"value": 1
},
"scheduler": {
"id": "14423e0d-7215-4ee0-b065-f9e95eaa8d7d",
"name": "scheduler",
"type": "Scheduler",
"fieldKind": "input",
"label": "",
"value": "euler"
},
"unet": {
"id": "e73bbf98-6489-492b-b83c-faed215febac",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
},
"control": {
"id": "dab351b3-0c86-4ea5-9782-4e8edbfb0607",
"name": "control",
"type": "ControlPolymorphic",
"fieldKind": "input",
"label": ""
},
"ip_adapter": {
"id": "192daea0-a90a-43cc-a2ee-0114a8e90318",
"name": "ip_adapter",
"type": "IPAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"t2i_adapter": {
"id": "ee386a55-d4c7-48c1-ac57-7bc4e3aada7a",
"name": "t2i_adapter",
"type": "T2IAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "3a922c6a-3d8c-4c9e-b3ec-2f4d81cda077",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"denoise_mask": {
"id": "cd7ce032-835f-495f-8b45-d57272f33132",
"name": "denoise_mask",
"type": "DenoiseMaskField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"latents": {
"id": "6260b84f-8361-470a-98d8-5b22a45c2d8c",
"name": "latents",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "aede0ecf-25b6-46be-aa30-b77f79715deb",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "519abf62-d475-48ef-ab8f-66136bc0e499",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true,
"useCache": true,
"version": "1.4.0"
},
"width": 320,
"height": 646,
"position": {
"x": 1642.955772577545,
"y": -230.2485847594651
}
}
],
@ -686,50 +710,42 @@
{
"source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
"sourceHandle": "vae",
"target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"target": "63e91020-83b2-4f35-b174-ad9692aabb48",
"targetHandle": "vae",
"id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22vae-dbcd2f98-d809-48c8-bf64-2635f88a2fe9vae",
"type": "default"
},
{
"source": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"sourceHandle": "latents",
"target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"targetHandle": "latents",
"id": "reactflow__edge-87ee6243-fb0d-4f77-ad5f-56591659339elatents-dbcd2f98-d809-48c8-bf64-2635f88a2fe9latents",
"type": "default"
},
{
"source": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
"sourceHandle": "conditioning",
"target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"targetHandle": "positive_conditioning",
"id": "reactflow__edge-faf965a4-7530-427b-b1f3-4ba6505c2a08conditioning-87ee6243-fb0d-4f77-ad5f-56591659339epositive_conditioning",
"type": "default"
},
{
"source": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
"sourceHandle": "conditioning",
"target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"targetHandle": "negative_conditioning",
"id": "reactflow__edge-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204conditioning-87ee6243-fb0d-4f77-ad5f-56591659339enegative_conditioning",
"id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22vae-63e91020-83b2-4f35-b174-ad9692aabb48vae",
"type": "default"
},
{
"source": "30d3289c-773c-4152-a9d2-bd8a99c8fd22",
"sourceHandle": "unet",
"target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
"targetHandle": "unet",
"id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22unet-87ee6243-fb0d-4f77-ad5f-56591659339eunet",
"id": "reactflow__edge-30d3289c-773c-4152-a9d2-bd8a99c8fd22unet-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbunet",
"type": "default"
},
{
"source": "faf965a4-7530-427b-b1f3-4ba6505c2a08",
"sourceHandle": "conditioning",
"target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
"targetHandle": "positive_conditioning",
"id": "reactflow__edge-faf965a4-7530-427b-b1f3-4ba6505c2a08conditioning-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbpositive_conditioning",
"type": "default"
},
{
"source": "3193ad09-a7c2-4bf4-a3a9-1c61cc33a204",
"sourceHandle": "conditioning",
"target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
"targetHandle": "negative_conditioning",
"id": "reactflow__edge-3193ad09-a7c2-4bf4-a3a9-1c61cc33a204conditioning-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbnegative_conditioning",
"type": "default"
},
{
"source": "55705012-79b9-4aac-9f26-c0b10309785b",
"sourceHandle": "noise",
"target": "87ee6243-fb0d-4f77-ad5f-56591659339e",
"target": "50a36525-3c0a-4cc5-977c-e4bfc3fd6dfb",
"targetHandle": "noise",
"id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-87ee6243-fb0d-4f77-ad5f-56591659339enoise",
"id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-50a36525-3c0a-4cc5-977c-e4bfc3fd6dfbnoise",
"type": "default"
}
]
}
}

973
docs/workflows/SDXL_w_Refiner_Text_to_Image.json
View File

File diff suppressed because it is too large Load Diff

366
docs/workflows/Text_to_Image.json
View File

@ -18,10 +18,6 @@
{
"nodeId": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
"fieldName": "prompt"
},
{
"nodeId": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"fieldName": "steps"
}
],
"meta": {
@ -32,7 +28,6 @@
"id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
"type": "compel",
"inputs": {
@ -64,20 +59,21 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 235,
"height": 261,
"position": {
"x": 1400,
"y": -75
"x": 995.7263915923627,
"y": 239.67783573351227
}
},
{
"id": "55705012-79b9-4aac-9f26-c0b10309785b",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "55705012-79b9-4aac-9f26-c0b10309785b",
"type": "noise",
"inputs": {
@ -138,92 +134,21 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 364,
"height": 389,
"position": {
"x": 1000,
"y": 350
}
},
{
"id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"type": "l2i",
"inputs": {
"tiled": {
"id": "24f5bc7b-f6a1-425d-8ab1-f50b4db5d0df",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"fp32": {
"id": "b146d873-ffb9-4767-986a-5360504841a2",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"latents": {
"id": "65441abd-7713-4b00-9d8d-3771404002e8",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"vae": {
"id": "a478b833-6e13-4611-9a10-842c89603c74",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"image": {
"id": "c87ae925-f858-417a-8940-8708ba9b4b53",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "4bcb8512-b5a1-45f1-9e52-6e92849f9d6c",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "23e41c00-a354-48e8-8f59-5875679c27ab",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": true,
"isIntermediate": false
},
"width": 320,
"height": 266,
"position": {
"x": 1800,
"y": 200
"x": 993.4442117555518,
"y": 605.6757415334787
}
},
{
"id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
"type": "main_model_loader",
"inputs": {
@ -261,23 +186,24 @@
}
},
"label": "",
"isOpen": false,
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 32,
"height": 226,
"position": {
"x": 1000,
"y": 200
"x": 163.04436745878343,
"y": 254.63156870373479
}
},
{
"id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
"type": "compel",
"inputs": {
@ -309,20 +235,21 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 235,
"height": 261,
"position": {
"x": 1000,
"y": -75
"x": 595.7263915923627,
"y": 239.67783573351227
}
},
{
"id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "ea94bc37-d995-4a83-aa99-4af42479f2f2",
"type": "rand_int",
"inputs": {
@ -352,51 +279,66 @@
}
},
"label": "Random Seed",
"isOpen": false,
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": false,
"version": "1.0.0"
},
"width": 320,
"height": 32,
"height": 218,
"position": {
"x": 1000,
"y": 275
"x": 541.094822888628,
"y": 694.5704476446829
}
},
{
"id": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"id": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"type": "invocation",
"data": {
"version": "1.0.0",
"id": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"id": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"type": "denoise_latents",
"inputs": {
"positive_conditioning": {
"id": "90b7f4f8-ada7-4028-8100-d2e54f192052",
"name": "positive_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"negative_conditioning": {
"id": "9393779e-796c-4f64-b740-902a1177bf53",
"name": "negative_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"noise": {
"id": "8b18f3eb-40d2-45c1-9a9d-28d6af0dce2b",
"id": "8e17f1e5-4f98-40b1-b7f4-86aeeb4554c1",
"name": "noise",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"steps": {
"id": "0be4373c-46f3-441c-80a7-a4bb6ceb498c",
"id": "9b63302d-6bd2-42c9-ac13-9b1afb51af88",
"name": "steps",
"type": "integer",
"fieldKind": "input",
"label": "",
"value": 36
"value": 10
},
"cfg_scale": {
"id": "107267ce-4666-4cd7-94b3-7476b7973ae9",
"id": "87dd04d3-870e-49e1-98bf-af003a810109",
"name": "cfg_scale",
"type": "float",
"type": "FloatPolymorphic",
"fieldKind": "input",
"label": "",
"value": 7.5
},
"denoising_start": {
"id": "d2ce9f0f-5fc2-48b2-b917-53442941e9a1",
"id": "f369d80f-4931-4740-9bcd-9f0620719fab",
"name": "denoising_start",
"type": "float",
"fieldKind": "input",
@ -404,7 +346,7 @@
"value": 0
},
"denoising_end": {
"id": "8ad51505-b8d0-422a-beb8-96fc6fc6b65f",
"id": "747d10e5-6f02-445c-994c-0604d814de8c",
"name": "denoising_end",
"type": "float",
"fieldKind": "input",
@ -412,71 +354,71 @@
"value": 1
},
"scheduler": {
"id": "53092874-a43b-4623-91a2-76e62fdb1f2e",
"id": "1de84a4e-3a24-4ec8-862b-16ce49633b9b",
"name": "scheduler",
"type": "Scheduler",
"fieldKind": "input",
"label": "",
"value": "euler"
},
"unet": {
"id": "ffa6fef4-3ce2-4bdb-9296-9a834849489b",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
},
"control": {
"id": "7abe57cc-469d-437e-ad72-a18efa28215f",
"id": "077b64cb-34be-4fcc-83f2-e399807a02bd",
"name": "control",
"type": "ControlField",
"type": "ControlPolymorphic",
"fieldKind": "input",
"label": ""
},
"ip_adapter": {
"id": "1d6948f7-3a65-4a65-a20c-768b287251aa",
"name": "ip_adapter",
"type": "IPAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"t2i_adapter": {
"id": "75e67b09-952f-4083-aaf4-6b804d690412",
"name": "t2i_adapter",
"type": "T2IAdapterPolymorphic",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "add8bbe5-14d0-42d4-a867-9c65ab8dd129",
"id": "334d4ba3-5a99-4195-82c5-86fb3f4f7d43",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"denoise_mask": {
"id": "f373a190-0fc8-45b7-ae62-c4aa8e9687e1",
"id": "0d3dbdbf-b014-4e95-8b18-ff2ff9cb0bfa",
"name": "denoise_mask",
"type": "DenoiseMaskField",
"fieldKind": "input",
"label": ""
},
"positive_conditioning": {
"id": "c7160303-8a23-4f15-9197-855d48802a7f",
"name": "positive_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"negative_conditioning": {
"id": "fd750efa-1dfc-4d0b-accb-828e905ba320",
"name": "negative_conditioning",
"type": "ConditioningField",
"fieldKind": "input",
"label": ""
},
"unet": {
"id": "af1f41ba-ce2a-4314-8d7f-494bb5800381",
"name": "unet",
"type": "UNetField",
"fieldKind": "input",
"label": ""
}
},
"outputs": {
"latents": {
"id": "8508d04d-f999-4a44-94d0-388ab1401d27",
"id": "70fa5bbc-0c38-41bb-861a-74d6d78d2f38",
"name": "latents",
"type": "LatentsField",
"fieldKind": "output"
},
"width": {
"id": "93dc8287-0a2a-4320-83a4-5e994b7ba23e",
"id": "98ee0e6c-82aa-4e8f-8be5-dc5f00ee47f0",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "d9862f5c-0ab5-46fa-8c29-5059bb581d96",
"id": "e8cb184a-5e1a-47c8-9695-4b8979564f5d",
"name": "height",
"type": "integer",
"fieldKind": "output"
@ -486,13 +428,95 @@
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": true
"isIntermediate": true,
"useCache": true,
"version": "1.4.0"
},
"width": 320,
"height": 558,
"height": 646,
"position": {
"x": 1400,
"y": 200
"x": 1476.5794704734735,
"y": 256.80174342731783
}
},
{
"id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
"type": "invocation",
"data": {
"id": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
"type": "l2i",
"inputs": {
"metadata": {
"id": "ab375f12-0042-4410-9182-29e30db82c85",
"name": "metadata",
"type": "MetadataField",
"fieldKind": "input",
"label": ""
},
"latents": {
"id": "3a7e7efd-bff5-47d7-9d48-615127afee78",
"name": "latents",
"type": "LatentsField",
"fieldKind": "input",
"label": ""
},
"vae": {
"id": "a1f5f7a1-0795-4d58-b036-7820c0b0ef2b",
"name": "vae",
"type": "VaeField",
"fieldKind": "input",
"label": ""
},
"tiled": {
"id": "da52059a-0cee-4668-942f-519aa794d739",
"name": "tiled",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
},
"fp32": {
"id": "c4841df3-b24e-4140-be3b-ccd454c2522c",
"name": "fp32",
"type": "boolean",
"fieldKind": "input",
"label": "",
"value": false
}
},
"outputs": {
"image": {
"id": "72d667d0-cf85-459d-abf2-28bd8b823fe7",
"name": "image",
"type": "ImageField",
"fieldKind": "output"
},
"width": {
"id": "c8c907d8-1066-49d1-b9a6-83bdcd53addc",
"name": "width",
"type": "integer",
"fieldKind": "output"
},
"height": {
"id": "230f359c-b4ea-436c-b372-332d7dcdca85",
"name": "height",
"type": "integer",
"fieldKind": "output"
}
},
"label": "",
"isOpen": true,
"notes": "",
"embedWorkflow": false,
"isIntermediate": false,
"useCache": true,
"version": "1.0.0"
},
"width": 320,
"height": 267,
"position": {
"x": 2037.9648469717395,
"y": 426.10844427600136
}
}
],
@ -522,52 +546,52 @@
"type": "default"
},
{
"source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
"sourceHandle": "vae",
"target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"targetHandle": "vae",
"id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8vae-dbcd2f98-d809-48c8-bf64-2635f88a2fe9vae",
"type": "default"
},
{
"source": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"sourceHandle": "latents",
"target": "dbcd2f98-d809-48c8-bf64-2635f88a2fe9",
"targetHandle": "latents",
"id": "reactflow__edge-75899702-fa44-46d2-b2d5-3e17f234c3e7latents-dbcd2f98-d809-48c8-bf64-2635f88a2fe9latents",
"source": "55705012-79b9-4aac-9f26-c0b10309785b",
"sourceHandle": "noise",
"target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"targetHandle": "noise",
"id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-eea2702a-19fb-45b5-9d75-56b4211ec03cnoise",
"type": "default"
},
{
"source": "7d8bf987-284f-413a-b2fd-d825445a5d6c",
"sourceHandle": "conditioning",
"target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"targetHandle": "positive_conditioning",
"id": "reactflow__edge-7d8bf987-284f-413a-b2fd-d825445a5d6cconditioning-75899702-fa44-46d2-b2d5-3e17f234c3e7positive_conditioning",
"id": "reactflow__edge-7d8bf987-284f-413a-b2fd-d825445a5d6cconditioning-eea2702a-19fb-45b5-9d75-56b4211ec03cpositive_conditioning",
"type": "default"
},
{
"source": "93dc02a4-d05b-48ed-b99c-c9b616af3402",
"sourceHandle": "conditioning",
"target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"targetHandle": "negative_conditioning",
"id": "reactflow__edge-93dc02a4-d05b-48ed-b99c-c9b616af3402conditioning-75899702-fa44-46d2-b2d5-3e17f234c3e7negative_conditioning",
"id": "reactflow__edge-93dc02a4-d05b-48ed-b99c-c9b616af3402conditioning-eea2702a-19fb-45b5-9d75-56b4211ec03cnegative_conditioning",
"type": "default"
},
{
"source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
"sourceHandle": "unet",
"target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"target": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"targetHandle": "unet",
"id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8unet-75899702-fa44-46d2-b2d5-3e17f234c3e7unet",
"id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8unet-eea2702a-19fb-45b5-9d75-56b4211ec03cunet",
"type": "default"
},
{
"source": "55705012-79b9-4aac-9f26-c0b10309785b",
"sourceHandle": "noise",
"target": "75899702-fa44-46d2-b2d5-3e17f234c3e7",
"targetHandle": "noise",
"id": "reactflow__edge-55705012-79b9-4aac-9f26-c0b10309785bnoise-75899702-fa44-46d2-b2d5-3e17f234c3e7noise",
"source": "eea2702a-19fb-45b5-9d75-56b4211ec03c",
"sourceHandle": "latents",
"target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
"targetHandle": "latents",
"id": "reactflow__edge-eea2702a-19fb-45b5-9d75-56b4211ec03clatents-58c957f5-0d01-41fc-a803-b2bbf0413d4flatents",
"type": "default"
},
{
"source": "c8d55139-f380-4695-b7f2-8b3d1e1e3db8",
"sourceHandle": "vae",
"target": "58c957f5-0d01-41fc-a803-b2bbf0413d4f",
"targetHandle": "vae",
"id": "reactflow__edge-c8d55139-f380-4695-b7f2-8b3d1e1e3db8vae-58c957f5-0d01-41fc-a803-b2bbf0413d4fvae",
"type": "default"
}
]
}
}

13
installer/install.bat.in
View File

@ -1,7 +1,7 @@
@echo off
setlocal EnableExtensions EnableDelayedExpansion
@rem This script requires the user to install Python 3.9 or higher. All other
@rem This script requires the user to install Python 3.10 or higher. All other
@rem requirements are downloaded as needed.
@rem change to the script's directory
@ -19,7 +19,7 @@ set INVOKEAI_VERSION=latest
set INSTRUCTIONS=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
set TROUBLESHOOTING=https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/#troubleshooting
set PYTHON_URL=https://www.python.org/downloads/windows/
set MINIMUM_PYTHON_VERSION=3.9.0
set MINIMUM_PYTHON_VERSION=3.10.0
set PYTHON_URL=https://www.python.org/downloads/release/python-3109/
set err_msg=An error has occurred and the script could not continue.
@ -28,8 +28,7 @@ set err_msg=An error has occurred and the script could not continue.
echo This script will install InvokeAI and its dependencies.
echo.
echo BEFORE YOU START PLEASE MAKE SURE TO DO THE FOLLOWING
echo 1. Install python 3.9 or 3.10. Python version 3.11 and above are
echo not supported at the moment.
echo 1. Install python 3.10 or 3.11. Python version 3.9 is no longer supported.
echo 2. Double-click on the file WinLongPathsEnabled.reg in order to
echo enable long path support on your system.
echo 3. Install the Visual C++ core libraries.
@ -46,19 +45,19 @@ echo ***** Checking and Updating Python *****
call python --version >.tmp1 2>.tmp2
if %errorlevel% == 1 (
set err_msg=Please install Python 3.10. See %INSTRUCTIONS% for details.
set err_msg=Please install Python 3.10-11. See %INSTRUCTIONS% for details.
goto err_exit
)
for /f "tokens=2" %%i in (.tmp1) do set python_version=%%i
if "%python_version%" == "" (
set err_msg=No python was detected on your system. Please install Python version %MINIMUM_PYTHON_VERSION% or higher. We recommend Python 3.10.9 from %PYTHON_URL%
set err_msg=No python was detected on your system. Please install Python version %MINIMUM_PYTHON_VERSION% or higher. We recommend Python 3.10.12 from %PYTHON_URL%
goto err_exit
)
call :compareVersions %MINIMUM_PYTHON_VERSION% %python_version%
if %errorlevel% == 1 (
set err_msg=Your version of Python is too low. You need at least %MINIMUM_PYTHON_VERSION% but you have %python_version%. We recommend Python 3.10.9 from %PYTHON_URL%
set err_msg=Your version of Python is too low. You need at least %MINIMUM_PYTHON_VERSION% but you have %python_version%. We recommend Python 3.10.12 from %PYTHON_URL%
goto err_exit
)

4
installer/install.sh.in
View File

@ -8,10 +8,10 @@ cd $scriptdir
function version { echo "$@" | awk -F. '{ printf("%d%03d%03d%03d\n", $1,$2,$3,$4); }'; }
MINIMUM_PYTHON_VERSION=3.9.0
MINIMUM_PYTHON_VERSION=3.10.0
MAXIMUM_PYTHON_VERSION=3.11.100
PYTHON=""
for candidate in python3.11 python3.10 python3.9 python3 python ; do
for candidate in python3.11 python3.10 python3 python ; do
if ppath=`which $candidate`; then
# when using `pyenv`, the executable for an inactive Python version will exist but will not be operational
# we check that this found executable can actually run

10
installer/lib/installer.py
View File

@ -13,7 +13,7 @@ from pathlib import Path
from tempfile import TemporaryDirectory
from typing import Union
SUPPORTED_PYTHON = ">=3.9.0,<=3.11.100"
SUPPORTED_PYTHON = ">=3.10.0,<=3.11.100"
INSTALLER_REQS = ["rich", "semver", "requests", "plumbum", "prompt-toolkit"]
BOOTSTRAP_VENV_PREFIX = "invokeai-installer-tmp"
@ -67,7 +67,6 @@ class Installer:
# Cleaning up temporary directories on Windows results in a race condition
# and a stack trace.
# `ignore_cleanup_errors` was only added in Python 3.10
# users of Python 3.9 will see a gnarly stack trace on installer exit
if OS == "Windows" and int(platform.python_version_tuple()[1]) >= 10:
venv_dir = TemporaryDirectory(prefix=BOOTSTRAP_VENV_PREFIX, ignore_cleanup_errors=True)
else:
@ -139,13 +138,6 @@ class Installer:
except shutil.SameFileError:
venv.create(venv_dir, with_pip=True, symlinks=True)
# upgrade pip in Python 3.9 environments
if int(platform.python_version_tuple()[1]) == 9:
from plumbum import FG, local
pip = local[get_pip_from_venv(venv_dir)]
pip["install", "--upgrade", "pip"] & FG
return venv_dir
def install(

8
installer/readme.txt
View File

@ -4,7 +4,7 @@ Project homepage: https://github.com/invoke-ai/InvokeAI
Preparations:
You will need to install Python 3.9 or higher for this installer
You will need to install Python 3.10 or higher for this installer
to work. Instructions are given here:
https://invoke-ai.github.io/InvokeAI/installation/INSTALL_AUTOMATED/
@ -14,15 +14,15 @@ Preparations:
python --version
If all is well, it will print "Python 3.X.X", where the version number
is at least 3.9.*, and not higher than 3.11.*.
is at least 3.10.*, and not higher than 3.11.*.
If this works, check the version of the Python package manager, pip:
pip --version
You should get a message that indicates that the pip package
installer was derived from Python 3.9 or 3.10. For example:
"pip 22.3.1 from /usr/bin/pip (python 3.9)"
installer was derived from Python 3.10 or 3.11. For example:
"pip 22.0.1 from /usr/bin/pip (python 3.10)"
Long Paths on Windows:

40
installer/templates/invoke.bat.in
View File

@ -9,41 +9,37 @@ set INVOKEAI_ROOT=.
:start
echo Desired action:
echo 1. Generate images with the browser-based interface
echo 2. Explore InvokeAI nodes using a command-line interface
echo 3. Run textual inversion training
echo 4. Merge models (diffusers type only)
echo 5. Download and install models
echo 6. Change InvokeAI startup options
echo 7. Re-run the configure script to fix a broken install or to complete a major upgrade
echo 8. Open the developer console
echo 9. Update InvokeAI
echo 10. Run the InvokeAI image database maintenance script
echo 11. Command-line help
echo 2. Run textual inversion training
echo 3. Merge models (diffusers type only)
echo 4. Download and install models
echo 5. Change InvokeAI startup options
echo 6. Re-run the configure script to fix a broken install or to complete a major upgrade
echo 7. Open the developer console
echo 8. Update InvokeAI
echo 9. Run the InvokeAI image database maintenance script
echo 10. Command-line help
echo Q - Quit
set /P choice="Please enter 1-11, Q: [1] "
set /P choice="Please enter 1-10, Q: [1] "
if not defined choice set choice=1
IF /I "%choice%" == "1" (
echo Starting the InvokeAI browser-based UI..
python .venv\Scripts\invokeai-web.exe %*
) ELSE IF /I "%choice%" == "2" (
echo Starting the InvokeAI command-line..
python .venv\Scripts\invokeai.exe %*
) ELSE IF /I "%choice%" == "3" (
echo Starting textual inversion training..
python .venv\Scripts\invokeai-ti.exe --gui
) ELSE IF /I "%choice%" == "4" (
) ELSE IF /I "%choice%" == "3" (
echo Starting model merging script..
python .venv\Scripts\invokeai-merge.exe --gui
) ELSE IF /I "%choice%" == "5" (
) ELSE IF /I "%choice%" == "4" (
echo Running invokeai-model-install...
python .venv\Scripts\invokeai-model-install.exe
) ELSE IF /I "%choice%" == "6" (
) ELSE IF /I "%choice%" == "5" (
echo Running invokeai-configure...
python .venv\Scripts\invokeai-configure.exe --skip-sd-weight --skip-support-models
) ELSE IF /I "%choice%" == "7" (
) ELSE IF /I "%choice%" == "6" (
echo Running invokeai-configure...
python .venv\Scripts\invokeai-configure.exe --yes --skip-sd-weight
) ELSE IF /I "%choice%" == "8" (
) ELSE IF /I "%choice%" == "7" (
echo Developer Console
echo Python command is:
where python
@ -55,13 +51,13 @@ IF /I "%choice%" == "1" (
echo *************************
echo *** Type `exit` to quit this shell and deactivate the Python virtual environment ***
call cmd /k
) ELSE IF /I "%choice%" == "9" (
) ELSE IF /I "%choice%" == "8" (
echo Running invokeai-update...
python -m invokeai.frontend.install.invokeai_update
) ELSE IF /I "%choice%" == "10" (
) ELSE IF /I "%choice%" == "9" (
echo Running the db maintenance script...
python .venv\Scripts\invokeai-db-maintenance.exe
) ELSE IF /I "%choice%" == "11" (
) ELSE IF /I "%choice%" == "10" (
echo Displaying command line help...
python .venv\Scripts\invokeai-web.exe --help %*
pause

61
installer/templates/invoke.sh.in
View File

@ -58,52 +58,47 @@ do_choice() {
invokeai-web $PARAMS
;;
2)
clear
printf "Explore InvokeAI nodes using a command-line interface\n"
invokeai $PARAMS
;;
3)
clear
printf "Textual inversion training\n"
invokeai-ti --gui $PARAMS
;;
4)
3)
clear
printf "Merge models (diffusers type only)\n"
invokeai-merge --gui $PARAMS
;;
5)
4)
clear
printf "Download and install models\n"
invokeai-model-install --root ${INVOKEAI_ROOT}
;;
6)
5)
clear
printf "Change InvokeAI startup options\n"
invokeai-configure --root ${INVOKEAI_ROOT} --skip-sd-weights --skip-support-models
;;
7)
6)
clear
printf "Re-run the configure script to fix a broken install or to complete a major upgrade\n"
invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only --skip-sd-weights
;;
8)
7)
clear
printf "Open the developer console\n"
file_name=$(basename "${BASH_SOURCE[0]}")
bash --init-file "$file_name"
;;
9)
8)
clear
printf "Update InvokeAI\n"
python -m invokeai.frontend.install.invokeai_update
;;
10)
9)
clear
printf "Running the db maintenance script\n"
invokeai-db-maintenance --root ${INVOKEAI_ROOT}
;;
11)
10)
clear
printf "Command-line help\n"
invokeai-web --help
@ -121,16 +116,15 @@ do_choice() {
do_dialog() {
options=(
1 "Generate images with a browser-based interface"
2 "Explore InvokeAI nodes using a command-line interface"
3 "Textual inversion training"
4 "Merge models (diffusers type only)"
5 "Download and install models"
6 "Change InvokeAI startup options"
7 "Re-run the configure script to fix a broken install or to complete a major upgrade"
8 "Open the developer console"
9 "Update InvokeAI"
10 "Run the InvokeAI image database maintenance script"
11 "Command-line help"
2 "Textual inversion training"
3 "Merge models (diffusers type only)"
4 "Download and install models"
5 "Change InvokeAI startup options"
6 "Re-run the configure script to fix a broken install or to complete a major upgrade"
7 "Open the developer console"
8 "Update InvokeAI"
9 "Run the InvokeAI image database maintenance script"
10 "Command-line help"
)
choice=$(dialog --clear \
@ -155,18 +149,17 @@ do_line_input() {
printf " ** For a more attractive experience, please install the 'dialog' utility using your package manager. **\n\n"
printf "What would you like to do?\n"
printf "1: Generate images using the browser-based interface\n"
printf "2: Explore InvokeAI nodes using the command-line interface\n"
printf "3: Run textual inversion training\n"
printf "4: Merge models (diffusers type only)\n"
printf "5: Download and install models\n"
printf "6: Change InvokeAI startup options\n"
printf "7: Re-run the configure script to fix a broken install\n"
printf "8: Open the developer console\n"
printf "9: Update InvokeAI\n"
printf "10: Run the InvokeAI image database maintenance script\n"
printf "11: Command-line help\n"
printf "2: Run textual inversion training\n"
printf "3: Merge models (diffusers type only)\n"
printf "4: Download and install models\n"
printf "5: Change InvokeAI startup options\n"
printf "6: Re-run the configure script to fix a broken install\n"
printf "7: Open the developer console\n"
printf "8: Update InvokeAI\n"
printf "9: Run the InvokeAI image database maintenance script\n"
printf "10: Command-line help\n"
printf "Q: Quit\n\n"
read -p "Please enter 1-11, Q: [1] " yn
read -p "Please enter 1-10, Q: [1] " yn
choice=${yn:='1'}
do_choice $choice
clear

6
invokeai/app/api/dependencies.py
View File

@ -2,6 +2,7 @@
from logging import Logger
from invokeai.app.services.workflow_image_records.workflow_image_records_sqlite import SqliteWorkflowImageRecordsStorage
from invokeai.backend.util.logging import InvokeAILogger
from invokeai.version.invokeai_version import __version__
@ -30,6 +31,7 @@ from ..services.shared.default_graphs import create_system_graphs
from ..services.shared.graph import GraphExecutionState, LibraryGraph
from ..services.shared.sqlite import SqliteDatabase
from ..services.urls.urls_default import LocalUrlService
from ..services.workflow_records.workflow_records_sqlite import SqliteWorkflowRecordsStorage
from .events import FastAPIEventService
@ -90,6 +92,8 @@ class ApiDependencies:
session_processor = DefaultSessionProcessor()
session_queue = SqliteSessionQueue(db=db)
urls = LocalUrlService()
workflow_image_records = SqliteWorkflowImageRecordsStorage(db=db)
workflow_records = SqliteWorkflowRecordsStorage(db=db)
services = InvocationServices(
board_image_records=board_image_records,
@ -114,6 +118,8 @@ class ApiDependencies:
session_processor=session_processor,
session_queue=session_queue,
urls=urls,
workflow_image_records=workflow_image_records,
workflow_records=workflow_records,
)
create_system_graphs(services.graph_library)

52
invokeai/app/api/routers/images.py
View File

@ -1,13 +1,14 @@
import io
import traceback
from typing import Optional
from fastapi import Body, HTTPException, Path, Query, Request, Response, UploadFile
from fastapi.responses import FileResponse
from fastapi.routing import APIRouter
from PIL import Image
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, ValidationError
from invokeai.app.invocations.metadata import ImageMetadata
from invokeai.app.invocations.baseinvocation import MetadataField, MetadataFieldValidator, WorkflowFieldValidator
from invokeai.app.services.image_records.image_records_common import ImageCategory, ImageRecordChanges, ResourceOrigin
from invokeai.app.services.images.images_common import ImageDTO, ImageUrlsDTO
from invokeai.app.services.shared.pagination import OffsetPaginatedResults
@ -42,20 +43,41 @@ async def upload_image(
crop_visible: Optional[bool] = Query(default=False, description="Whether to crop the image"),
) -> ImageDTO:
"""Uploads an image"""
if not file.content_type.startswith("image"):
if not file.content_type or not file.content_type.startswith("image"):
raise HTTPException(status_code=415, detail="Not an image")
contents = await file.read()
metadata = None
workflow = None
contents = await file.read()
try:
pil_image = Image.open(io.BytesIO(contents))
if crop_visible:
bbox = pil_image.getbbox()
pil_image = pil_image.crop(bbox)
except Exception:
# Error opening the image
ApiDependencies.invoker.services.logger.error(traceback.format_exc())
raise HTTPException(status_code=415, detail="Failed to read image")
# TODO: retain non-invokeai metadata on upload?
# attempt to parse metadata from image
metadata_raw = pil_image.info.get("invokeai_metadata", None)
if metadata_raw:
try:
metadata = MetadataFieldValidator.validate_json(metadata_raw)
except ValidationError:
ApiDependencies.invoker.services.logger.warn("Failed to parse metadata for uploaded image")
pass
# attempt to parse workflow from image
workflow_raw = pil_image.info.get("invokeai_workflow", None)
if workflow_raw is not None:
try:
workflow = WorkflowFieldValidator.validate_json(workflow_raw)
except ValidationError:
ApiDependencies.invoker.services.logger.warn("Failed to parse metadata for uploaded image")
pass
try:
image_dto = ApiDependencies.invoker.services.images.create(
image=pil_image,
@ -63,6 +85,8 @@ async def upload_image(
image_category=image_category,
session_id=session_id,
board_id=board_id,
metadata=metadata,
workflow=workflow,
is_intermediate=is_intermediate,
)
@ -71,6 +95,7 @@ async def upload_image(
return image_dto
except Exception:
ApiDependencies.invoker.services.logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail="Failed to create image")
@ -87,7 +112,7 @@ async def delete_image(
pass
@images_router.post("/clear-intermediates", operation_id="clear_intermediates")
@images_router.delete("/intermediates", operation_id="clear_intermediates")
async def clear_intermediates() -> int:
"""Clears all intermediates"""
@ -99,6 +124,17 @@ async def clear_intermediates() -> int:
pass
@images_router.get("/intermediates", operation_id="get_intermediates_count")
async def get_intermediates_count() -> int:
"""Gets the count of intermediate images"""
try:
return ApiDependencies.invoker.services.images.get_intermediates_count()
except Exception:
raise HTTPException(status_code=500, detail="Failed to get intermediates")
pass
@images_router.patch(
"/i/{image_name}",
operation_id="update_image",
@ -135,11 +171,11 @@ async def get_image_dto(
@images_router.get(
"/i/{image_name}/metadata",
operation_id="get_image_metadata",
response_model=ImageMetadata,
response_model=Optional[MetadataField],
)
async def get_image_metadata(
image_name: str = Path(description="The name of image to get"),
) -> ImageMetadata:
) -> Optional[MetadataField]:
"""Gets an image's metadata"""
try:

110
invokeai/app/api/routers/models.py
View File

@ -2,11 +2,11 @@
import pathlib
from typing import List, Literal, Optional, Union
from typing import Annotated, List, Literal, Optional, Union
from fastapi import Body, Path, Query, Response
from fastapi.routing import APIRouter
from pydantic import BaseModel, parse_obj_as
from pydantic import BaseModel, ConfigDict, Field, TypeAdapter
from starlette.exceptions import HTTPException
from invokeai.backend import BaseModelType, ModelType
@ -23,8 +23,14 @@ from ..dependencies import ApiDependencies
models_router = APIRouter(prefix="/v1/models", tags=["models"])
UpdateModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
UpdateModelResponseValidator = TypeAdapter(UpdateModelResponse)
ImportModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
ImportModelResponseValidator = TypeAdapter(ImportModelResponse)
ConvertModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
ConvertModelResponseValidator = TypeAdapter(ConvertModelResponse)
MergeModelResponse = Union[tuple(OPENAPI_MODEL_CONFIGS)]
ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
@ -32,6 +38,11 @@ ImportModelAttributes = Union[tuple(OPENAPI_MODEL_CONFIGS)]
class ModelsList(BaseModel):
models: list[Union[tuple(OPENAPI_MODEL_CONFIGS)]]
model_config = ConfigDict(use_enum_values=True)
ModelsListValidator = TypeAdapter(ModelsList)
@models_router.get(
"/",
@ -49,7 +60,7 @@ async def list_models(
models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
else:
models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
models = parse_obj_as(ModelsList, {"models": models_raw})
models = ModelsListValidator.validate_python({"models": models_raw})
return models
@ -105,11 +116,14 @@ async def update_model(
info.path = new_info.get("path")
# replace empty string values with None/null to avoid phenomenon of vae: ''
info_dict = info.dict()
info_dict = info.model_dump()
info_dict = {x: info_dict[x] if info_dict[x] else None for x in info_dict.keys()}
ApiDependencies.invoker.services.model_manager.update_model(
model_name=model_name, base_model=base_model, model_type=model_type, model_attributes=info_dict
model_name=model_name,
base_model=base_model,
model_type=model_type,
model_attributes=info_dict,
)
model_raw = ApiDependencies.invoker.services.model_manager.list_model(
@ -117,7 +131,7 @@ async def update_model(
base_model=base_model,
model_type=model_type,
)
model_response = parse_obj_as(UpdateModelResponse, model_raw)
model_response = UpdateModelResponseValidator.validate_python(model_raw)
except ModelNotFoundException as e:
raise HTTPException(status_code=404, detail=str(e))
except ValueError as e:
@ -152,13 +166,15 @@ async def import_model(
) -> ImportModelResponse:
"""Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
location = location.strip("\"' ")
items_to_import = {location}
prediction_types = {x.value: x for x in SchedulerPredictionType}
logger = ApiDependencies.invoker.services.logger
try:
installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
items_to_import=items_to_import, prediction_type_helper=lambda x: prediction_types.get(prediction_type)
items_to_import=items_to_import,
prediction_type_helper=lambda x: prediction_types.get(prediction_type),
)
info = installed_models.get(location)
@ -170,7 +186,7 @@ async def import_model(
model_raw = ApiDependencies.invoker.services.model_manager.list_model(
model_name=info.name, base_model=info.base_model, model_type=info.model_type
)
return parse_obj_as(ImportModelResponse, model_raw)
return ImportModelResponseValidator.validate_python(model_raw)
except ModelNotFoundException as e:
logger.error(str(e))
@ -204,13 +220,18 @@ async def add_model(
try:
ApiDependencies.invoker.services.model_manager.add_model(
info.model_name, info.base_model, info.model_type, model_attributes=info.dict()
info.model_name,
info.base_model,
info.model_type,
model_attributes=info.model_dump(),
)
logger.info(f"Successfully added {info.model_name}")
model_raw = ApiDependencies.invoker.services.model_manager.list_model(
model_name=info.model_name, base_model=info.base_model, model_type=info.model_type
model_name=info.model_name,
base_model=info.base_model,
model_type=info.model_type,
)
return parse_obj_as(ImportModelResponse, model_raw)
return ImportModelResponseValidator.validate_python(model_raw)
except ModelNotFoundException as e:
logger.error(str(e))
raise HTTPException(status_code=404, detail=str(e))
@ -222,7 +243,10 @@ async def add_model(
@models_router.delete(
"/{base_model}/{model_type}/{model_name}",
operation_id="del_model",
responses={204: {"description": "Model deleted successfully"}, 404: {"description": "Model not found"}},
responses={
204: {"description": "Model deleted successfully"},
404: {"description": "Model not found"},
},
status_code=204,
response_model=None,
)
@ -278,7 +302,7 @@ async def convert_model(
model_raw = ApiDependencies.invoker.services.model_manager.list_model(
model_name, base_model=base_model, model_type=model_type
)
response = parse_obj_as(ConvertModelResponse, model_raw)
response = ConvertModelResponseValidator.validate_python(model_raw)
except ModelNotFoundException as e:
raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found: {str(e)}")
except ValueError as e:
@ -301,7 +325,8 @@ async def search_for_models(
) -> List[pathlib.Path]:
if not search_path.is_dir():
raise HTTPException(
status_code=404, detail=f"The search path '{search_path}' does not exist or is not directory"
status_code=404,
detail=f"The search path '{search_path}' does not exist or is not directory",
)
return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
@ -336,6 +361,26 @@ async def sync_to_config() -> bool:
return True
# There's some weird pydantic-fastapi behaviour that requires this to be a separate class
# TODO: After a few updates, see if it works inside the route operation handler?
class MergeModelsBody(BaseModel):
model_names: List[str] = Field(description="model name", min_length=2, max_length=3)
merged_model_name: Optional[str] = Field(description="Name of destination model")
alpha: Optional[float] = Field(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5)
interp: Optional[MergeInterpolationMethod] = Field(description="Interpolation method")
force: Optional[bool] = Field(
description="Force merging of models created with different versions of diffusers",
default=False,
)
merge_dest_directory: Optional[str] = Field(
description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
default=None,
)
model_config = ConfigDict(protected_namespaces=())
@models_router.put(
"/merge/{base_model}",
operation_id="merge_models",
@ -348,31 +393,23 @@ async def sync_to_config() -> bool:
response_model=MergeModelResponse,
)
async def merge_models(
body: Annotated[MergeModelsBody, Body(description="Model configuration", embed=True)],
base_model: BaseModelType = Path(description="Base model"),
model_names: List[str] = Body(description="model name", min_items=2, max_items=3),
merged_model_name: Optional[str] = Body(description="Name of destination model"),
alpha: Optional[float] = Body(description="Alpha weighting strength to apply to 2d and 3d models", default=0.5),
interp: Optional[MergeInterpolationMethod] = Body(description="Interpolation method"),
force: Optional[bool] = Body(
description="Force merging of models created with different versions of diffusers", default=False
),
merge_dest_directory: Optional[str] = Body(
description="Save the merged model to the designated directory (with 'merged_model_name' appended)",
default=None,
),
) -> MergeModelResponse:
"""Convert a checkpoint model into a diffusers model"""
logger = ApiDependencies.invoker.services.logger
try:
logger.info(f"Merging models: {model_names} into {merge_dest_directory or '<MODELS>'}/{merged_model_name}")
dest = pathlib.Path(merge_dest_directory) if merge_dest_directory else None
logger.info(
f"Merging models: {body.model_names} into {body.merge_dest_directory or '<MODELS>'}/{body.merged_model_name}"
)
dest = pathlib.Path(body.merge_dest_directory) if body.merge_dest_directory else None
result = ApiDependencies.invoker.services.model_manager.merge_models(
model_names,
base_model,
merged_model_name=merged_model_name or "+".join(model_names),
alpha=alpha,
interp=interp,
force=force,
model_names=body.model_names,
base_model=base_model,
merged_model_name=body.merged_model_name or "+".join(body.model_names),
alpha=body.alpha,
interp=body.interp,
force=body.force,
merge_dest_directory=dest,
)
model_raw = ApiDependencies.invoker.services.model_manager.list_model(
@ -380,9 +417,12 @@ async def merge_models(
base_model=base_model,
model_type=ModelType.Main,
)
response = parse_obj_as(ConvertModelResponse, model_raw)
response = ConvertModelResponseValidator.validate_python(model_raw)
except ModelNotFoundException:
raise HTTPException(status_code=404, detail=f"One or more of the models '{model_names}' not found")
raise HTTPException(
status_code=404,
detail=f"One or more of the models '{body.model_names}' not found",
)
except ValueError as e:
raise HTTPException(status_code=400, detail=str(e))
return response

19
invokeai/app/api/routers/session_queue.py
View File

@ -12,13 +12,11 @@ from invokeai.app.services.session_queue.session_queue_common import (
CancelByBatchIDsResult,
ClearResult,
EnqueueBatchResult,
EnqueueGraphResult,
PruneResult,
SessionQueueItem,
SessionQueueItemDTO,
SessionQueueStatus,
)
from invokeai.app.services.shared.graph import Graph
from invokeai.app.services.shared.pagination import CursorPaginatedResults
from ..dependencies import ApiDependencies
@ -33,23 +31,6 @@ class SessionQueueAndProcessorStatus(BaseModel):
processor: SessionProcessorStatus
@session_queue_router.post(
"/{queue_id}/enqueue_graph",
operation_id="enqueue_graph",
responses={
201: {"model": EnqueueGraphResult},
},
)
async def enqueue_graph(
queue_id: str = Path(description="The queue id to perform this operation on"),
graph: Graph = Body(description="The graph to enqueue"),
prepend: bool = Body(default=False, description="Whether or not to prepend this batch in the queue"),
) -> EnqueueGraphResult:
"""Enqueues a graph for single execution."""
return ApiDependencies.invoker.services.session_queue.enqueue_graph(queue_id=queue_id, graph=graph, prepend=prepend)
@session_queue_router.post(
"/{queue_id}/enqueue_batch",
operation_id="enqueue_batch",

456
invokeai/app/api/routers/sessions.py
View File

@ -1,57 +1,50 @@
# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
from typing import Annotated, Optional, Union
from fastapi import Body, HTTPException, Path, Query, Response
from fastapi import HTTPException, Path
from fastapi.routing import APIRouter
from pydantic.fields import Field
from invokeai.app.services.shared.pagination import PaginatedResults
# Importing * is bad karma but needed here for node detection
from ...invocations import * # noqa: F401 F403
from ...invocations.baseinvocation import BaseInvocation
from ...services.shared.graph import Edge, EdgeConnection, Graph, GraphExecutionState, NodeAlreadyExecutedError
from ...services.shared.graph import GraphExecutionState
from ..dependencies import ApiDependencies
session_router = APIRouter(prefix="/v1/sessions", tags=["sessions"])
@session_router.post(
"/",
operation_id="create_session",
responses={
200: {"model": GraphExecutionState},
400: {"description": "Invalid json"},
},
deprecated=True,
)
async def create_session(
queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
) -> GraphExecutionState:
"""Creates a new session, optionally initializing it with an invocation graph"""
session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
return session
# @session_router.post(
# "/",
# operation_id="create_session",
# responses={
# 200: {"model": GraphExecutionState},
# 400: {"description": "Invalid json"},
# },
# deprecated=True,
# )
# async def create_session(
# queue_id: str = Query(default="", description="The id of the queue to associate the session with"),
# graph: Optional[Graph] = Body(default=None, description="The graph to initialize the session with"),
# ) -> GraphExecutionState:
# """Creates a new session, optionally initializing it with an invocation graph"""
# session = ApiDependencies.invoker.create_execution_state(queue_id=queue_id, graph=graph)
# return session
@session_router.get(
"/",
operation_id="list_sessions",
responses={200: {"model": PaginatedResults[GraphExecutionState]}},
deprecated=True,
)
async def list_sessions(
page: int = Query(default=0, description="The page of results to get"),
per_page: int = Query(default=10, description="The number of results per page"),
query: str = Query(default="", description="The query string to search for"),
) -> PaginatedResults[GraphExecutionState]:
"""Gets a list of sessions, optionally searching"""
if query == "":
result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
else:
result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
return result
# @session_router.get(
# "/",
# operation_id="list_sessions",
# responses={200: {"model": PaginatedResults[GraphExecutionState]}},
# deprecated=True,
# )
# async def list_sessions(
# page: int = Query(default=0, description="The page of results to get"),
# per_page: int = Query(default=10, description="The number of results per page"),
# query: str = Query(default="", description="The query string to search for"),
# ) -> PaginatedResults[GraphExecutionState]:
# """Gets a list of sessions, optionally searching"""
# if query == "":
# result = ApiDependencies.invoker.services.graph_execution_manager.list(page, per_page)
# else:
# result = ApiDependencies.invoker.services.graph_execution_manager.search(query, page, per_page)
# return result
@session_router.get(
@ -61,7 +54,6 @@ async def list_sessions(
200: {"model": GraphExecutionState},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def get_session(
session_id: str = Path(description="The id of the session to get"),
@ -74,211 +66,211 @@ async def get_session(
return session
@session_router.post(
"/{session_id}/nodes",
operation_id="add_node",
responses={
200: {"model": str},
400: {"description": "Invalid node or link"},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def add_node(
session_id: str = Path(description="The id of the session"),
node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body( # type: ignore
description="The node to add"
),
) -> str:
"""Adds a node to the graph"""
session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
if session is None:
raise HTTPException(status_code=404)
# @session_router.post(
# "/{session_id}/nodes",
# operation_id="add_node",
# responses={
# 200: {"model": str},
# 400: {"description": "Invalid node or link"},
# 404: {"description": "Session not found"},
# },
# deprecated=True,
# )
# async def add_node(
# session_id: str = Path(description="The id of the session"),
# node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body( # type: ignore
# description="The node to add"
# ),
# ) -> str:
# """Adds a node to the graph"""
# session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
# if session is None:
# raise HTTPException(status_code=404)
try:
session.add_node(node)
ApiDependencies.invoker.services.graph_execution_manager.set(
session
) # TODO: can this be done automatically, or add node through an API?
return session.id
except NodeAlreadyExecutedError:
raise HTTPException(status_code=400)
except IndexError:
raise HTTPException(status_code=400)
# try:
# session.add_node(node)
# ApiDependencies.invoker.services.graph_execution_manager.set(
# session
# ) # TODO: can this be done automatically, or add node through an API?
# return session.id
# except NodeAlreadyExecutedError:
# raise HTTPException(status_code=400)
# except IndexError:
# raise HTTPException(status_code=400)
@session_router.put(
"/{session_id}/nodes/{node_path}",
operation_id="update_node",
responses={
200: {"model": GraphExecutionState},
400: {"description": "Invalid node or link"},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def update_node(
session_id: str = Path(description="The id of the session"),
node_path: str = Path(description="The path to the node in the graph"),
node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body( # type: ignore
description="The new node"
),
) -> GraphExecutionState:
"""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:
raise HTTPException(status_code=404)
# @session_router.put(
# "/{session_id}/nodes/{node_path}",
# operation_id="update_node",
# responses={
# 200: {"model": GraphExecutionState},
# 400: {"description": "Invalid node or link"},
# 404: {"description": "Session not found"},
# },
# deprecated=True,
# )
# async def update_node(
# session_id: str = Path(description="The id of the session"),
# node_path: str = Path(description="The path to the node in the graph"),
# node: Annotated[Union[BaseInvocation.get_invocations()], Field(discriminator="type")] = Body( # type: ignore
# description="The new node"
# ),
# ) -> GraphExecutionState:
# """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:
# raise HTTPException(status_code=404)
try:
session.update_node(node_path, node)
ApiDependencies.invoker.services.graph_execution_manager.set(
session
) # TODO: can this be done automatically, or add node through an API?
return session
except NodeAlreadyExecutedError:
raise HTTPException(status_code=400)
except IndexError:
raise HTTPException(status_code=400)
# try:
# session.update_node(node_path, node)
# ApiDependencies.invoker.services.graph_execution_manager.set(
# session
# ) # TODO: can this be done automatically, or add node through an API?
# return session
# except NodeAlreadyExecutedError:
# raise HTTPException(status_code=400)
# except IndexError:
# raise HTTPException(status_code=400)
@session_router.delete(
"/{session_id}/nodes/{node_path}",
operation_id="delete_node",
responses={
200: {"model": GraphExecutionState},
400: {"description": "Invalid node or link"},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def delete_node(
session_id: str = Path(description="The id of the session"),
node_path: str = Path(description="The path to the node to delete"),
) -> GraphExecutionState:
"""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:
raise HTTPException(status_code=404)
# @session_router.delete(
# "/{session_id}/nodes/{node_path}",
# operation_id="delete_node",
# responses={
# 200: {"model": GraphExecutionState},
# 400: {"description": "Invalid node or link"},
# 404: {"description": "Session not found"},
# },
# deprecated=True,
# )
# async def delete_node(
# session_id: str = Path(description="The id of the session"),
# node_path: str = Path(description="The path to the node to delete"),
# ) -> GraphExecutionState:
# """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:
# raise HTTPException(status_code=404)
try:
session.delete_node(node_path)
ApiDependencies.invoker.services.graph_execution_manager.set(
session
) # TODO: can this be done automatically, or add node through an API?
return session
except NodeAlreadyExecutedError:
raise HTTPException(status_code=400)
except IndexError:
raise HTTPException(status_code=400)
# try:
# session.delete_node(node_path)
# ApiDependencies.invoker.services.graph_execution_manager.set(
# session
# ) # TODO: can this be done automatically, or add node through an API?
# return session
# except NodeAlreadyExecutedError:
# raise HTTPException(status_code=400)
# except IndexError:
# raise HTTPException(status_code=400)
@session_router.post(
"/{session_id}/edges",
operation_id="add_edge",
responses={
200: {"model": GraphExecutionState},
400: {"description": "Invalid node or link"},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def add_edge(
session_id: str = Path(description="The id of the session"),
edge: Edge = Body(description="The edge to add"),
) -> GraphExecutionState:
"""Adds an edge to the graph"""
session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
if session is None:
raise HTTPException(status_code=404)
# @session_router.post(
# "/{session_id}/edges",
# operation_id="add_edge",
# responses={
# 200: {"model": GraphExecutionState},
# 400: {"description": "Invalid node or link"},
# 404: {"description": "Session not found"},
# },
# deprecated=True,
# )
# async def add_edge(
# session_id: str = Path(description="The id of the session"),
# edge: Edge = Body(description="The edge to add"),
# ) -> GraphExecutionState:
# """Adds an edge to the graph"""
# session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
# if session is None:
# raise HTTPException(status_code=404)
try:
session.add_edge(edge)
ApiDependencies.invoker.services.graph_execution_manager.set(
session
) # TODO: can this be done automatically, or add node through an API?
return session
except NodeAlreadyExecutedError:
raise HTTPException(status_code=400)
except IndexError:
raise HTTPException(status_code=400)
# try:
# session.add_edge(edge)
# ApiDependencies.invoker.services.graph_execution_manager.set(
# session
# ) # TODO: can this be done automatically, or add node through an API?
# return session
# except NodeAlreadyExecutedError:
# raise HTTPException(status_code=400)
# except IndexError:
# raise HTTPException(status_code=400)
# TODO: the edge being in the path here is really ugly, find a better solution
@session_router.delete(
"/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
operation_id="delete_edge",
responses={
200: {"model": GraphExecutionState},
400: {"description": "Invalid node or link"},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def delete_edge(
session_id: str = Path(description="The id of the session"),
from_node_id: str = Path(description="The id of the node the edge is coming from"),
from_field: str = Path(description="The field of the node the edge is coming from"),
to_node_id: str = Path(description="The id of the node the edge is going to"),
to_field: str = Path(description="The field of the node the edge is going to"),
) -> GraphExecutionState:
"""Deletes an edge from the graph"""
session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
if session is None:
raise HTTPException(status_code=404)
# # TODO: the edge being in the path here is really ugly, find a better solution
# @session_router.delete(
# "/{session_id}/edges/{from_node_id}/{from_field}/{to_node_id}/{to_field}",
# operation_id="delete_edge",
# responses={
# 200: {"model": GraphExecutionState},
# 400: {"description": "Invalid node or link"},
# 404: {"description": "Session not found"},
# },
# deprecated=True,
# )
# async def delete_edge(
# session_id: str = Path(description="The id of the session"),
# from_node_id: str = Path(description="The id of the node the edge is coming from"),
# from_field: str = Path(description="The field of the node the edge is coming from"),
# to_node_id: str = Path(description="The id of the node the edge is going to"),
# to_field: str = Path(description="The field of the node the edge is going to"),
# ) -> GraphExecutionState:
# """Deletes an edge from the graph"""
# session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
# if session is None:
# raise HTTPException(status_code=404)
try:
edge = Edge(
source=EdgeConnection(node_id=from_node_id, field=from_field),
destination=EdgeConnection(node_id=to_node_id, field=to_field),
)
session.delete_edge(edge)
ApiDependencies.invoker.services.graph_execution_manager.set(
session
) # TODO: can this be done automatically, or add node through an API?
return session
except NodeAlreadyExecutedError:
raise HTTPException(status_code=400)
except IndexError:
raise HTTPException(status_code=400)
# try:
# edge = Edge(
# source=EdgeConnection(node_id=from_node_id, field=from_field),
# destination=EdgeConnection(node_id=to_node_id, field=to_field),
# )
# session.delete_edge(edge)
# ApiDependencies.invoker.services.graph_execution_manager.set(
# session
# ) # TODO: can this be done automatically, or add node through an API?
# return session
# except NodeAlreadyExecutedError:
# raise HTTPException(status_code=400)
# except IndexError:
# raise HTTPException(status_code=400)
@session_router.put(
"/{session_id}/invoke",
operation_id="invoke_session",
responses={
200: {"model": None},
202: {"description": "The invocation is queued"},
400: {"description": "The session has no invocations ready to invoke"},
404: {"description": "Session not found"},
},
deprecated=True,
)
async def invoke_session(
queue_id: str = Query(description="The id of the queue to associate the session with"),
session_id: str = Path(description="The id of the session to invoke"),
all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
) -> Response:
"""Invokes a session"""
session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
if session is None:
raise HTTPException(status_code=404)
# @session_router.put(
# "/{session_id}/invoke",
# operation_id="invoke_session",
# responses={
# 200: {"model": None},
# 202: {"description": "The invocation is queued"},
# 400: {"description": "The session has no invocations ready to invoke"},
# 404: {"description": "Session not found"},
# },
# deprecated=True,
# )
# async def invoke_session(
# queue_id: str = Query(description="The id of the queue to associate the session with"),
# session_id: str = Path(description="The id of the session to invoke"),
# all: bool = Query(default=False, description="Whether or not to invoke all remaining invocations"),
# ) -> Response:
# """Invokes a session"""
# session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
# if session is None:
# raise HTTPException(status_code=404)
if session.is_complete():
raise HTTPException(status_code=400)
# if session.is_complete():
# raise HTTPException(status_code=400)
ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
return Response(status_code=202)
# ApiDependencies.invoker.invoke(queue_id, session, invoke_all=all)
# return Response(status_code=202)
@session_router.delete(
"/{session_id}/invoke",
operation_id="cancel_session_invoke",
responses={202: {"description": "The invocation is canceled"}},
deprecated=True,
)
async def cancel_session_invoke(
session_id: str = Path(description="The id of the session to cancel"),
) -> Response:
"""Invokes a session"""
ApiDependencies.invoker.cancel(session_id)
return Response(status_code=202)
# @session_router.delete(
# "/{session_id}/invoke",
# operation_id="cancel_session_invoke",
# responses={202: {"description": "The invocation is canceled"}},
# deprecated=True,
# )
# async def cancel_session_invoke(
# session_id: str = Path(description="The id of the session to cancel"),
# ) -> Response:
# """Invokes a session"""
# ApiDependencies.invoker.cancel(session_id)
# return Response(status_code=202)

3
invokeai/app/api/routers/utilities.py
View File

@ -1,4 +1,4 @@
from typing import Optional
from typing import Optional, Union
from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
from fastapi import Body
@ -27,6 +27,7 @@ async def parse_dynamicprompts(
combinatorial: bool = Body(default=True, description="Whether to use the combinatorial generator"),
) -> DynamicPromptsResponse:
"""Creates a batch process"""
generator: Union[RandomPromptGenerator, CombinatorialPromptGenerator]
try:
error: Optional[str] = None
if combinatorial:

20
invokeai/app/api/routers/workflows.py Normal file
View File

@ -0,0 +1,20 @@
from fastapi import APIRouter, Path
from invokeai.app.api.dependencies import ApiDependencies
from invokeai.app.invocations.baseinvocation import WorkflowField
workflows_router = APIRouter(prefix="/v1/workflows", tags=["workflows"])
@workflows_router.get(
"/i/{workflow_id}",
operation_id="get_workflow",
responses={
200: {"model": WorkflowField},
},
)
async def get_workflow(
workflow_id: str = Path(description="The workflow to get"),
) -> WorkflowField:
"""Gets a workflow"""
return ApiDependencies.invoker.services.workflow_records.get(workflow_id)

4
invokeai/app/api/sockets.py
View File

@ -30,8 +30,8 @@ class SocketIO:
async def _handle_sub_queue(self, sid, data, *args, **kwargs):
if "queue_id" in data:
self.__sio.enter_room(sid, data["queue_id"])
await self.__sio.enter_room(sid, data["queue_id"])
async def _handle_unsub_queue(self, sid, data, *args, **kwargs):
if "queue_id" in data:
self.__sio.enter_room(sid, data["queue_id"])
await self.__sio.enter_room(sid, data["queue_id"])

127
invokeai/app/api_app.py
View File

@ -1,3 +1,7 @@
from typing import Any
from fastapi.responses import HTMLResponse
from .services.config import InvokeAIAppConfig
# parse_args() must be called before any other imports. if it is not called first, consumers of the config
@ -13,17 +17,20 @@ if True: # hack to make flake8 happy with imports coming after setting up the c
from inspect import signature
from pathlib import Path
import torch
import uvicorn
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.middleware.gzip import GZipMiddleware
from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
from fastapi.openapi.utils import get_openapi
from fastapi.responses import FileResponse
from fastapi.staticfiles import StaticFiles
from fastapi_events.handlers.local import local_handler
from fastapi_events.middleware import EventHandlerASGIMiddleware
from pydantic.schema import schema
from pydantic.json_schema import models_json_schema
from torch.backends.mps import is_available as is_mps_available
# for PyCharm:
# noinspection PyUnresolvedReferences
import invokeai.backend.util.hotfixes # noqa: F401 (monkeypatching on import)
import invokeai.frontend.web as web_dir
@ -31,19 +38,27 @@ if True: # hack to make flake8 happy with imports coming after setting up the c
from ..backend.util.logging import InvokeAILogger
from .api.dependencies import ApiDependencies
from .api.routers import app_info, board_images, boards, images, models, session_queue, sessions, utilities
from .api.routers import (
app_info,
board_images,
boards,
images,
models,
session_queue,
sessions,
utilities,
workflows,
)
from .api.sockets import SocketIO
from .invocations.baseinvocation import BaseInvocation, UIConfigBase, _InputField, _OutputField
if torch.backends.mps.is_available():
# noinspection PyUnresolvedReferences
if is_mps_available():
import invokeai.backend.util.mps_fixes # noqa: F401 (monkeypatching on import)
app_config = InvokeAIAppConfig.get_config()
app_config.parse_args()
logger = InvokeAILogger.get_logger(config=app_config)
# 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")
@ -51,7 +66,7 @@ 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)
app = FastAPI(title="Invoke AI", docs_url=None, redoc_url=None, separate_input_output_schemas=False)
# Add event handler
event_handler_id: int = id(app)
@ -63,53 +78,45 @@ app.add_middleware(
socket_io = SocketIO(app)
app.add_middleware(
CORSMiddleware,
allow_origins=app_config.allow_origins,
allow_credentials=app_config.allow_credentials,
allow_methods=app_config.allow_methods,
allow_headers=app_config.allow_headers,
)
app.add_middleware(GZipMiddleware, minimum_size=1000)
# Add startup event to load dependencies
@app.on_event("startup")
async def startup_event():
app.add_middleware(
CORSMiddleware,
allow_origins=app_config.allow_origins,
allow_credentials=app_config.allow_credentials,
allow_methods=app_config.allow_methods,
allow_headers=app_config.allow_headers,
)
async def startup_event() -> None:
ApiDependencies.initialize(config=app_config, event_handler_id=event_handler_id, logger=logger)
# Shut down threads
@app.on_event("shutdown")
async def shutdown_event():
async def shutdown_event() -> None:
ApiDependencies.shutdown()
# Include all routers
# TODO: REMOVE
# app.include_router(
# invocation.invocation_router,
# prefix = '/api')
app.include_router(sessions.session_router, prefix="/api")
app.include_router(utilities.utilities_router, prefix="/api")
app.include_router(models.models_router, prefix="/api")
app.include_router(images.images_router, prefix="/api")
app.include_router(boards.boards_router, prefix="/api")
app.include_router(board_images.board_images_router, prefix="/api")
app.include_router(app_info.app_router, prefix="/api")
app.include_router(session_queue.session_queue_router, prefix="/api")
app.include_router(workflows.workflows_router, prefix="/api")
# Build a custom OpenAPI to include all outputs
# TODO: can outputs be included on metadata of invocation schemas somehow?
def custom_openapi():
def custom_openapi() -> dict[str, Any]:
if app.openapi_schema:
return app.openapi_schema
openapi_schema = get_openapi(
@ -117,6 +124,7 @@ def custom_openapi():
description="An API for invoking AI image operations",
version="1.0.0",
routes=app.routes,
separate_input_output_schemas=False, # https://fastapi.tiangolo.com/how-to/separate-openapi-schemas/
)
# Add all outputs
@ -127,29 +135,32 @@ def custom_openapi():
output_type = signature(invoker.invoke).return_annotation
output_types.add(output_type)
output_schemas = schema(output_types, ref_prefix="#/components/schemas/")
for schema_key, output_schema in output_schemas["definitions"].items():
output_schema["class"] = "output"
openapi_schema["components"]["schemas"][schema_key] = output_schema
output_schemas = models_json_schema(
models=[(o, "serialization") for o in output_types], ref_template="#/components/schemas/{model}"
)
for schema_key, output_schema in output_schemas[1]["$defs"].items():
# TODO: note that we assume the schema_key here is the TYPE.__name__
# This could break in some cases, figure out a better way to do it
output_type_titles[schema_key] = output_schema["title"]
# Add Node Editor UI helper schemas
ui_config_schemas = schema([UIConfigBase, _InputField, _OutputField], ref_prefix="#/components/schemas/")
for schema_key, ui_config_schema in ui_config_schemas["definitions"].items():
ui_config_schemas = models_json_schema(
[(UIConfigBase, "serialization"), (_InputField, "serialization"), (_OutputField, "serialization")],
ref_template="#/components/schemas/{model}",
)
for schema_key, ui_config_schema in ui_config_schemas[1]["$defs"].items():
openapi_schema["components"]["schemas"][schema_key] = ui_config_schema
# Add a reference to the output type to additionalProperties of the invoker schema
for invoker in all_invocations:
invoker_name = invoker.__name__
output_type = signature(invoker.invoke).return_annotation
output_type = signature(obj=invoker.invoke).return_annotation
output_type_title = output_type_titles[output_type.__name__]
invoker_schema = openapi_schema["components"]["schemas"][invoker_name]
invoker_schema = openapi_schema["components"]["schemas"][f"{invoker_name}"]
outputs_ref = {"$ref": f"#/components/schemas/{output_type_title}"}
invoker_schema["output"] = outputs_ref
invoker_schema["class"] = "invocation"
openapi_schema["components"]["schemas"][f"{output_type_title}"]["class"] = "output"
from invokeai.backend.model_management.models import get_model_config_enums
@ -160,7 +171,6 @@ def custom_openapi():
# print(f"Config with name {name} already defined")
continue
# "BaseModelType":{"title":"BaseModelType","description":"An enumeration.","enum":["sd-1","sd-2"],"type":"string"}
openapi_schema["components"]["schemas"][name] = dict(
title=name,
description="An enumeration.",
@ -172,36 +182,45 @@ def custom_openapi():
return app.openapi_schema
app.openapi = custom_openapi
# Override API doc favicons
app.mount("/static", StaticFiles(directory=Path(web_dir.__path__[0], "static/dream_web")), name="static")
app.openapi = custom_openapi # type: ignore [method-assign] # this is a valid assignment
@app.get("/docs", include_in_schema=False)
def overridden_swagger():
def overridden_swagger() -> HTMLResponse:
return get_swagger_ui_html(
openapi_url=app.openapi_url,
openapi_url=app.openapi_url, # type: ignore [arg-type] # this is always a string
title=app.title,
swagger_favicon_url="/static/favicon.ico",
swagger_favicon_url="/static/docs/favicon.ico",
)
@app.get("/redoc", include_in_schema=False)
def overridden_redoc():
def overridden_redoc() -> HTMLResponse:
return get_redoc_html(
openapi_url=app.openapi_url,
openapi_url=app.openapi_url, # type: ignore [arg-type] # this is always a string
title=app.title,
redoc_favicon_url="/static/favicon.ico",
redoc_favicon_url="/static/docs/favicon.ico",
)
# Must mount *after* the other routes else it borks em
app.mount("/", StaticFiles(directory=Path(web_dir.__path__[0], "dist"), html=True), name="ui")
web_root_path = Path(list(web_dir.__path__)[0])
def invoke_api():
def find_port(port: int):
# Cannot add headers to StaticFiles, so we must serve index.html with a custom route
# Add cache-control: no-store header to prevent caching of index.html, which leads to broken UIs at release
@app.get("/", include_in_schema=False, name="ui_root")
def get_index() -> FileResponse:
return FileResponse(Path(web_root_path, "dist/index.html"), headers={"Cache-Control": "no-store"})
# # Must mount *after* the other routes else it borks em
app.mount("/static", StaticFiles(directory=Path(web_root_path, "static/")), name="static") # docs favicon is in here
app.mount("/assets", StaticFiles(directory=Path(web_root_path, "dist/assets/")), name="assets")
app.mount("/locales", StaticFiles(directory=Path(web_root_path, "dist/locales/")), name="locales")
def invoke_api() -> None:
def find_port(port: int) -> int:
"""Find a port not in use starting at given port"""
# Taken from https://waylonwalker.com/python-find-available-port/, thanks Waylon!
# https://github.com/WaylonWalker
@ -236,7 +255,7 @@ def invoke_api():
app=app,
host=app_config.host,
port=port,
loop=loop,
loop="asyncio",
log_level=app_config.log_level,
)
server = uvicorn.Server(config)

313
invokeai/app/cli/commands.py
View File

@ -1,313 +0,0 @@
# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
import argparse
from abc import ABC, abstractmethod
from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
import matplotlib.pyplot as plt
import networkx as nx
from pydantic import BaseModel, Field
import invokeai.backend.util.logging as logger
from ..invocations.baseinvocation import BaseInvocation
from ..invocations.image import ImageField
from ..services.graph import Edge, GraphExecutionState, LibraryGraph
from ..services.invoker import Invoker
def add_field_argument(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 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=default,
choices=allowed_values,
help=field.field_info.description,
)
else:
command_parser.add_argument(
f"--{name}",
dest=name,
type=field.type_,
default=default,
help=field.field_info.description,
)
def add_parsers(
subparsers,
commands: list[type],
command_field: str = "type",
exclude_fields: list[str] = ["id", "type"],
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__)
if add_arguments is not None:
add_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
add_field_argument(command_parser, name, field)
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:
add_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)
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):
"""A CLI command"""
# All commands must include a type name like this:
# type: Literal['your_command_name'] = 'your_command_name'
@classmethod
def get_all_subclasses(cls):
subclasses = []
toprocess = [cls]
while len(toprocess) > 0:
next = toprocess.pop(0)
next_subclasses = next.__subclasses__()
subclasses.extend(next_subclasses)
toprocess.extend(next_subclasses)
return subclasses
@classmethod
def get_commands(cls):
return tuple(BaseCommand.get_all_subclasses())
@classmethod
def get_commands_map(cls):
# Get the type strings out of the literals and into a dictionary
return dict(map(lambda t: (get_args(get_type_hints(t)["type"])[0], t), BaseCommand.get_all_subclasses()))
@abstractmethod
def run(self, context: CliContext) -> None:
"""Run the command. Raise ExitCli to exit."""
pass
class ExitCommand(BaseCommand):
"""Exits the CLI"""
type: Literal["exit"] = "exit"
def run(self, context: CliContext) -> None:
raise ExitCli()
class HelpCommand(BaseCommand):
"""Shows help"""
type: Literal["help"] = "help"
def run(self, context: CliContext) -> None:
context.parser.print_help()
def get_graph_execution_history(
graph_execution_state: GraphExecutionState,
) -> Iterable[str]:
"""Gets the history of fully-executed invocations for a graph execution"""
return (n for n in reversed(graph_execution_state.executed_history) if n in graph_execution_state.graph.nodes)
def get_invocation_command(invocation) -> str:
fields = invocation.__fields__.items()
type_hints = get_type_hints(type(invocation))
command = [invocation.type]
for name, field in fields:
if name in ["id", "type"]:
continue
# TODO: add links
# Skip image fields when serializing command
type_hint = type_hints.get(name) or None
if type_hint is ImageField or ImageField in get_args(type_hint):
continue
field_value = getattr(invocation, name)
field_default = field.default
if field_value != field_default:
if type_hint is str or str in get_args(type_hint):
command.append(f'--{name} "{field_value}"')
else:
command.append(f"--{name} {field_value}")
return " ".join(command)
class HistoryCommand(BaseCommand):
"""Shows the invocation history"""
type: Literal["history"] = "history"
# Inputs
# fmt: off
count: int = Field(default=5, gt=0, description="The number of history entries to show")
# fmt: on
def run(self, context: CliContext) -> None:
history = list(get_graph_execution_history(context.get_session()))
for i in range(min(self.count, len(history))):
entry_id = history[-1 - i]
entry = context.get_session().graph.get_node(entry_id)
logger.info(f"{entry_id}: {get_invocation_command(entry)}")
class SetDefaultCommand(BaseCommand):
"""Sets a default value for a field"""
type: Literal["default"] = "default"
# Inputs
# fmt: off
field: str = Field(description="The field to set the default for")
value: str = Field(description="The value to set the default to, or None to clear the default")
# fmt: on
def run(self, context: CliContext) -> None:
if self.value is None:
if self.field in context.defaults:
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()
class SortedHelpFormatter(argparse.HelpFormatter):
def _iter_indented_subactions(self, action):
try:
get_subactions = action._get_subactions
except AttributeError:
pass
else:
self._indent()
if isinstance(action, argparse._SubParsersAction):
for subaction in sorted(get_subactions(), key=lambda x: x.dest):
yield subaction
else:
for subaction in get_subactions():
yield subaction
self._dedent()

171
invokeai/app/cli/completer.py
View File

@ -1,171 +0,0 @@
"""
Readline helper functions for cli_app.py
You may import the global singleton `completer` to get access to the
completer object.
"""
import atexit
import readline
import shlex
from pathlib import Path
from typing import Dict, List, Literal, get_args, get_origin, get_type_hints
import invokeai.backend.util.logging as logger
from ...backend import ModelManager
from ..invocations.baseinvocation import BaseInvocation
from ..services.invocation_services import InvocationServices
from .commands import BaseCommand
# singleton object, class variable
completer = None
class Completer(object):
def __init__(self, model_manager: ModelManager):
self.commands = self.get_commands()
self.matches = None
self.linebuffer = None
self.manager = model_manager
return
def complete(self, text, state):
"""
Complete commands and switches fromm the node CLI command line.
Switches are determined in a context-specific manner.
"""
buffer = readline.get_line_buffer()
if state == 0:
options = None
try:
current_command, current_switch = self.get_current_command(buffer)
options = self.get_command_options(current_command, current_switch)
except IndexError:
pass
options = options or list(self.parse_commands().keys())
if not text: # first time
self.matches = options
else:
self.matches = [s for s in options if s and s.startswith(text)]
try:
match = self.matches[state]
except IndexError:
match = None
return match
@classmethod
def get_commands(self) -> List[object]:
"""
Return a list of all the client commands and invocations.
"""
return BaseCommand.get_commands() + BaseInvocation.get_invocations()
def get_current_command(self, buffer: str) -> tuple[str, str]:
"""
Parse the readline buffer to find the most recent command and its switch.
"""
if len(buffer) == 0:
return None, None
tokens = shlex.split(buffer)
command = None
switch = None
for t in tokens:
if t[0].isalpha():
if switch is None:
command = t
else:
switch = t
# don't try to autocomplete switches that are already complete
if switch and buffer.endswith(" "):
switch = None
return command or "", switch or ""
def parse_commands(self) -> Dict[str, List[str]]:
"""
Return a dict in which the keys are the command name
and the values are the parameters the command takes.
"""
result = dict()
for command in self.commands:
hints = get_type_hints(command)
name = get_args(hints["type"])[0]
result.update({name: hints})
return result
def get_command_options(self, command: str, switch: str) -> List[str]:
"""
Return all the parameters that can be passed to the command as
command-line switches. Returns None if the command is unrecognized.
"""
parsed_commands = self.parse_commands()
if command not in parsed_commands:
return None
# handle switches in the format "-foo=bar"
argument = None
if switch and "=" in switch:
switch, argument = switch.split("=")
parameter = switch.strip("-")
if parameter in parsed_commands[command]:
if argument is None:
return self.get_parameter_options(parameter, parsed_commands[command][parameter])
else:
return [
f"--{parameter}={x}"
for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])
]
else:
return [f"--{x}" for x in parsed_commands[command].keys()]
def get_parameter_options(self, parameter: str, typehint) -> List[str]:
"""
Given a parameter type (such as Literal), offers autocompletions.
"""
if get_origin(typehint) == Literal:
return get_args(typehint)
if parameter == "model":
return self.manager.model_names()
def _pre_input_hook(self):
if self.linebuffer:
readline.insert_text(self.linebuffer)
readline.redisplay()
self.linebuffer = None
def set_autocompleter(services: InvocationServices) -> Completer:
global completer
if completer:
return completer
completer = Completer(services.model_manager)
readline.set_completer(completer.complete)
try:
readline.set_auto_history(True)
except AttributeError:
# pyreadline3 does not have a set_auto_history() method
pass
readline.set_pre_input_hook(completer._pre_input_hook)
readline.set_completer_delims(" ")
readline.parse_and_bind("tab: complete")
readline.parse_and_bind("set print-completions-horizontally off")
readline.parse_and_bind("set page-completions on")
readline.parse_and_bind("set skip-completed-text on")
readline.parse_and_bind("set show-all-if-ambiguous on")
histfile = Path(services.configuration.root_dir / ".invoke_history")
try:
readline.read_history_file(histfile)
readline.set_history_length(1000)
except FileNotFoundError:
pass
except OSError: # file likely corrupted
newname = f"{histfile}.old"
logger.error(f"Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}")
histfile.replace(Path(newname))
atexit.register(readline.write_history_file, histfile)

484
invokeai/app/cli_app.py
View File

@ -1,484 +0,0 @@
# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
from invokeai.app.services.invocation_cache.invocation_cache_memory import MemoryInvocationCache
from .services.config import InvokeAIAppConfig
# parse_args() must be called before any other imports. if it is not called first, consumers of the config
# which are imported/used before parse_args() is called will get the default config values instead of the
# values from the command line or config file.
if True: # hack to make flake8 happy with imports coming after setting up the config
import argparse
import re
import shlex
import sqlite3
import sys
import time
from typing import Optional, Union, get_type_hints
import torch
from pydantic import BaseModel, ValidationError
from pydantic.fields import Field
import invokeai.backend.util.hotfixes # noqa: F401 (monkeypatching on import)
from invokeai.app.services.board_image_record_storage import SqliteBoardImageRecordStorage
from invokeai.app.services.board_images import BoardImagesService, BoardImagesServiceDependencies
from invokeai.app.services.board_record_storage import SqliteBoardRecordStorage
from invokeai.app.services.boards import BoardService, BoardServiceDependencies
from invokeai.app.services.image_record_storage import SqliteImageRecordStorage
from invokeai.app.services.images import ImageService, ImageServiceDependencies
from invokeai.app.services.invocation_stats import InvocationStatsService
from invokeai.app.services.resource_name import SimpleNameService
from invokeai.app.services.urls import LocalUrlService
from invokeai.backend.util.logging import InvokeAILogger
from invokeai.version.invokeai_version import __version__
from .cli.commands import BaseCommand, CliContext, ExitCli, SortedHelpFormatter, add_graph_parsers, add_parsers
from .cli.completer import set_autocompleter
from .invocations.baseinvocation import BaseInvocation
from .services.default_graphs import create_system_graphs, default_text_to_image_graph_id
from .services.events import EventServiceBase
from .services.graph import (
Edge,
EdgeConnection,
GraphExecutionState,
GraphInvocation,
LibraryGraph,
are_connection_types_compatible,
)
from .services.image_file_storage import DiskImageFileStorage
from .services.invocation_queue import MemoryInvocationQueue
from .services.invocation_services import InvocationServices
from .services.invoker import Invoker
from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
from .services.model_manager_service import ModelManagerService
from .services.processor import DefaultInvocationProcessor
from .services.sqlite import SqliteItemStorage
if torch.backends.mps.is_available():
import invokeai.backend.util.mps_fixes # noqa: F401 (monkeypatching on import)
config = InvokeAIAppConfig.get_config()
config.parse_args()
logger = InvokeAILogger().get_logger(config=config)
class CliCommand(BaseModel):
command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type") # type: ignore
class InvalidArgs(Exception):
pass
def add_invocation_args(command_parser):
# Add linking capability
command_parser.add_argument(
"--link",
"-l",
action="append",
nargs=3,
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(
"--link_node",
"-ln",
action="append",
help="A link from all fields in the specified node. Node can be relative to history (e.g. -1)",
)
def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
# Create invocation parser
parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
def exit(*args, **kwargs):
raise InvalidArgs
parser.exit = exit
subparsers = parser.add_subparsers(dest="type")
# Create subparsers for each invocation
invocations = BaseInvocation.get_all_subclasses()
add_parsers(subparsers, invocations, add_arguments=add_invocation_args)
# Create subparsers for each command
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, context: CliContext) -> list[Edge]:
"""Generates all possible edges between two invocations"""
afields = get_node_outputs(a, context)
bfields = get_node_inputs(b, context)
matching_fields = set(afields.keys()).intersection(bfields.keys())
# Remove invalid fields
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=afields[alias].node_path, field=afields[alias].field),
destination=EdgeConnection(node_id=bfields[alias].node_path, field=bfields[alias].field),
)
for alias in matching_fields
]
return edges
class SessionError(Exception):
"""Raised when a session error has occurred"""
pass
def invoke_all(context: CliContext):
"""Runs all invocations in the specified session"""
context.invoker.invoke(context.session, invoke_all=True)
while not context.get_session().is_complete():
# Wait some time
time.sleep(0.1)
# Print any errors
if context.session.has_error():
for n in context.session.errors:
context.invoker.services.logger.error(
f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
)
raise SessionError()
def invoke_cli():
logger.info(f"InvokeAI version {__version__}")
# get the optional list of invocations to execute on the command line
parser = config.get_parser()
parser.add_argument("commands", nargs="*")
invocation_commands = parser.parse_args().commands
# get the optional file to read commands from.
# Simplest is to use it for STDIN
if infile := config.from_file:
sys.stdin = open(infile, "r")
model_manager = ModelManagerService(config, logger)
events = EventServiceBase()
output_folder = config.output_path
# TODO: build a file/path manager?
if config.use_memory_db:
db_location = ":memory:"
else:
db_location = config.db_path
db_location.parent.mkdir(parents=True, exist_ok=True)
db_conn = sqlite3.connect(db_location, check_same_thread=False) # TODO: figure out a better threading solution
logger.info(f'InvokeAI database location is "{db_location}"')
graph_execution_manager = SqliteItemStorage[GraphExecutionState](conn=db_conn, table_name="graph_executions")
urls = LocalUrlService()
image_record_storage = SqliteImageRecordStorage(conn=db_conn)
image_file_storage = DiskImageFileStorage(f"{output_folder}/images")
names = SimpleNameService()
board_record_storage = SqliteBoardRecordStorage(conn=db_conn)
board_image_record_storage = SqliteBoardImageRecordStorage(conn=db_conn)
boards = BoardService(
services=BoardServiceDependencies(
board_image_record_storage=board_image_record_storage,
board_record_storage=board_record_storage,
image_record_storage=image_record_storage,
url=urls,
logger=logger,
)
)
board_images = BoardImagesService(
services=BoardImagesServiceDependencies(
board_image_record_storage=board_image_record_storage,
board_record_storage=board_record_storage,
image_record_storage=image_record_storage,
url=urls,
logger=logger,
)
)
images = ImageService(
services=ImageServiceDependencies(
board_image_record_storage=board_image_record_storage,
image_record_storage=image_record_storage,
image_file_storage=image_file_storage,
url=urls,
logger=logger,
names=names,
graph_execution_manager=graph_execution_manager,
)
)
services = InvocationServices(
model_manager=model_manager,
events=events,
latents=ForwardCacheLatentsStorage(DiskLatentsStorage(f"{output_folder}/latents")),
images=images,
boards=boards,
board_images=board_images,
queue=MemoryInvocationQueue(),
graph_library=SqliteItemStorage[LibraryGraph](conn=db_conn, table_name="graphs"),
graph_execution_manager=graph_execution_manager,
processor=DefaultInvocationProcessor(),
performance_statistics=InvocationStatsService(graph_execution_manager),
logger=logger,
configuration=config,
invocation_cache=MemoryInvocationCache(max_cache_size=config.node_cache_size),
)
system_graphs = create_system_graphs(services.graph_library)
system_graph_names = set([g.name for g in system_graphs])
set_autocompleter(services)
invoker = Invoker(services)
session: GraphExecutionState = invoker.create_execution_state()
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)
command_line_args_exist = len(invocation_commands) > 0
done = False
while not done:
try:
if command_line_args_exist:
cmd_input = invocation_commands.pop(0)
done = len(invocation_commands) == 0
else:
cmd_input = input("invoke> ")
except (KeyboardInterrupt, EOFError):
# Ctrl-c exits
break
try:
# Refresh the state of the 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(context.nodes_added)
current_id = start_id
new_invocations = list()
for cmd in cmds:
if cmd is None or cmd.strip() == "":
raise InvalidArgs("Empty command")
# Parse args to create invocation
args = vars(context.parser.parse_args(shlex.split(cmd.strip())))
# Override defaults
for field_name, field_default in context.defaults.items():
if field_name in args:
args[field_name] = field_default
# Parse invocation
command: CliCommand = None # type:ignore
system_graph: Optional[LibraryGraph] = 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:
args["id"] = current_id
command = CliCommand(command=args)
if command is None:
continue
# Run any CLI commands immediately
if isinstance(command.command, BaseCommand):
# Invoke all current nodes to preserve operation order
invoke_all(context)
# Run the command
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:
from_id = history[0] if current_id == start_id else str(current_id - 1)
from_node = (
next(filter(lambda n: n[0].id == from_id, new_invocations))[0]
if current_id != start_id
else context.session.graph.get_node(from_id)
)
matching_edges = generate_matching_edges(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"]:
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, context)
matching_destinations = [e.destination for e in matching_edges]
edges = [e for e in edges if e.destination not in matching_destinations]
edges.extend(matching_edges)
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 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=node_output.node_path, field=node_output.field),
destination=EdgeConnection(node_id=node_input.node_path, field=node_input.field),
)
)
new_invocations.append((command.command, edges))
current_id = current_id + 1
# Add the node to the session
context.add_node(command.command)
for edge in edges:
print(edge)
context.add_edge(edge)
# Execute all remaining nodes
invoke_all(context)
except InvalidArgs:
invoker.services.logger.warning('Invalid command, use "help" to list commands')
continue
except ValidationError:
invoker.services.logger.warning('Invalid command arguments, run "<command> --help" for summary')
except SessionError:
# Start a new session
invoker.services.logger.warning("Session error: creating a new session")
context.reset()
except ExitCli:
break
except SystemExit:
continue
invoker.stop()
if __name__ == "__main__":
if config.version:
print(f"InvokeAI version {__version__}")
else:
invoke_cli()

32
invokeai/app/invocations/__init__.py
View File

@ -1,8 +1,28 @@
import os
import shutil
import sys
from importlib.util import module_from_spec, spec_from_file_location
from pathlib import Path
__all__ = []
from invokeai.app.services.config.config_default import InvokeAIAppConfig
dirname = os.path.dirname(os.path.abspath(__file__))
for f in os.listdir(dirname):
if f != "__init__.py" and os.path.isfile("%s/%s" % (dirname, f)) and f[-3:] == ".py":
__all__.append(f[:-3])
custom_nodes_path = Path(InvokeAIAppConfig.get_config().custom_nodes_path.absolute())
custom_nodes_path.mkdir(parents=True, exist_ok=True)
custom_nodes_init_path = str(custom_nodes_path / "__init__.py")
custom_nodes_readme_path = str(custom_nodes_path / "README.md")
# copy our custom nodes __init__.py to the custom nodes directory
shutil.copy(Path(__file__).parent / "custom_nodes/init.py", custom_nodes_init_path)
shutil.copy(Path(__file__).parent / "custom_nodes/README.md", custom_nodes_readme_path)
# Import custom nodes, see https://docs.python.org/3/library/importlib.html#importing-programmatically
spec = spec_from_file_location("custom_nodes", custom_nodes_init_path)
if spec is None or spec.loader is None:
raise RuntimeError(f"Could not load custom nodes from {custom_nodes_init_path}")
module = module_from_spec(spec)
sys.modules[spec.name] = module
spec.loader.exec_module(module)
# add core nodes to __all__
python_files = filter(lambda f: not f.name.startswith("_"), Path(__file__).parent.glob("*.py"))
__all__ = list(f.stem for f in python_files) # type: ignore

686
invokeai/app/invocations/baseinvocation.py
View File

@ -2,33 +2,21 @@
from __future__ import annotations
import json
import inspect
import re
from abc import ABC, abstractmethod
from enum import Enum
from inspect import signature
from typing import (
TYPE_CHECKING,
AbstractSet,
Any,
Callable,
ClassVar,
Literal,
Mapping,
Optional,
Type,
TypeVar,
Union,
get_args,
get_type_hints,
)
from types import UnionType
from typing import TYPE_CHECKING, Any, Callable, ClassVar, Iterable, Literal, Optional, Type, TypeVar, Union
import semver
from pydantic import BaseModel, Field, validator
from pydantic.fields import ModelField, Undefined
from pydantic.typing import NoArgAnyCallable
from pydantic import BaseModel, ConfigDict, Field, RootModel, TypeAdapter, create_model
from pydantic.fields import FieldInfo, _Unset
from pydantic_core import PydanticUndefined
from invokeai.app.services.config.config_default import InvokeAIAppConfig
from invokeai.app.util.misc import uuid_string
if TYPE_CHECKING:
from ..services.invocation_services import InvocationServices
@ -38,6 +26,10 @@ class InvalidVersionError(ValueError):
pass
class InvalidFieldError(TypeError):
pass
class FieldDescriptions:
denoising_start = "When to start denoising, expressed a percentage of total steps"
denoising_end = "When to stop denoising, expressed a percentage of total steps"
@ -72,7 +64,12 @@ class FieldDescriptions:
denoised_latents = "Denoised latents tensor"
latents = "Latents tensor"
strength = "Strength of denoising (proportional to steps)"
core_metadata = "Optional core metadata to be written to image"
metadata = "Optional metadata to be saved with the image"
metadata_collection = "Collection of Metadata"
metadata_item_polymorphic = "A single metadata item or collection of metadata items"
metadata_item_label = "Label for this metadata item"
metadata_item_value = "The value for this metadata item (may be any type)"
workflow = "Optional workflow to be saved with the image"
interp_mode = "Interpolation mode"
torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
fp32 = "Whether or not to use full float32 precision"
@ -95,6 +92,10 @@ class FieldDescriptions:
inclusive_low = "The inclusive low value"
exclusive_high = "The exclusive high value"
decimal_places = "The number of decimal places to round to"
freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
class Input(str, Enum):
@ -179,8 +180,12 @@ class UIType(str, Enum):
Scheduler = "Scheduler"
WorkflowField = "WorkflowField"
IsIntermediate = "IsIntermediate"
MetadataField = "MetadataField"
BoardField = "BoardField"
Any = "Any"
MetadataItem = "MetadataItem"
MetadataItemCollection = "MetadataItemCollection"
MetadataItemPolymorphic = "MetadataItemPolymorphic"
MetadataDict = "MetadataDict"
# endregion
@ -211,6 +216,11 @@ class _InputField(BaseModel):
ui_choice_labels: Optional[dict[str, str]]
item_default: Optional[Any]
model_config = ConfigDict(
validate_assignment=True,
json_schema_serialization_defaults_required=True,
)
class _OutputField(BaseModel):
"""
@ -224,34 +234,36 @@ class _OutputField(BaseModel):
ui_type: Optional[UIType]
ui_order: Optional[int]
model_config = ConfigDict(
validate_assignment=True,
json_schema_serialization_defaults_required=True,
)
def get_type(klass: BaseModel) -> str:
"""Helper function to get an invocation or invocation output's type. This is the default value of the `type` field."""
return klass.model_fields["type"].default
def InputField(
*args: Any,
default: Any = Undefined,
default_factory: Optional[NoArgAnyCallable] = None,
alias: Optional[str] = None,
title: Optional[str] = None,
description: Optional[str] = None,
exclude: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
include: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
const: Optional[bool] = None,
gt: Optional[float] = None,
ge: Optional[float] = None,
lt: Optional[float] = None,
le: Optional[float] = None,
multiple_of: Optional[float] = None,
allow_inf_nan: Optional[bool] = None,
max_digits: Optional[int] = None,
decimal_places: Optional[int] = None,
min_items: Optional[int] = None,
max_items: Optional[int] = None,
unique_items: Optional[bool] = None,
min_length: Optional[int] = None,
max_length: Optional[int] = None,
allow_mutation: bool = True,
regex: Optional[str] = None,
discriminator: Optional[str] = None,
repr: bool = True,
# copied from pydantic's Field
default: Any = _Unset,
default_factory: Callable[[], Any] | None = _Unset,
title: str | None = _Unset,
description: str | None = _Unset,
pattern: str | None = _Unset,
strict: bool | None = _Unset,
gt: float | None = _Unset,
ge: float | None = _Unset,
lt: float | None = _Unset,
le: float | None = _Unset,
multiple_of: float | None = _Unset,
allow_inf_nan: bool | None = _Unset,
max_digits: int | None = _Unset,
decimal_places: int | None = _Unset,
min_length: int | None = _Unset,
max_length: int | None = _Unset,
# custom
input: Input = Input.Any,
ui_type: Optional[UIType] = None,
ui_component: Optional[UIComponent] = None,
@ -259,7 +271,6 @@ def InputField(
ui_order: Optional[int] = None,
ui_choice_labels: Optional[dict[str, str]] = None,
item_default: Optional[Any] = None,
**kwargs: Any,
) -> Any:
"""
Creates an input field for an invocation.
@ -289,18 +300,27 @@ def InputField(
: param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
: param bool item_default: [None] Specifies the default item value, if this is a collection input. \
Ignored for non-collection fields..
Ignored for non-collection fields.
"""
return Field(
*args,
json_schema_extra_: dict[str, Any] = dict(
input=input,
ui_type=ui_type,
ui_component=ui_component,
ui_hidden=ui_hidden,
ui_order=ui_order,
item_default=item_default,
ui_choice_labels=ui_choice_labels,
_field_kind="input",
)
field_args = dict(
default=default,
default_factory=default_factory,
alias=alias,
title=title,
description=description,
exclude=exclude,
include=include,
const=const,
pattern=pattern,
strict=strict,
gt=gt,
ge=ge,
lt=lt,
@ -309,57 +329,92 @@ def InputField(
allow_inf_nan=allow_inf_nan,
max_digits=max_digits,
decimal_places=decimal_places,
min_items=min_items,
max_items=max_items,
unique_items=unique_items,
min_length=min_length,
max_length=max_length,
allow_mutation=allow_mutation,
regex=regex,
discriminator=discriminator,
repr=repr,
input=input,
ui_type=ui_type,
ui_component=ui_component,
ui_hidden=ui_hidden,
ui_order=ui_order,
item_default=item_default,
ui_choice_labels=ui_choice_labels,
**kwargs,
)
"""
Invocation definitions have their fields typed correctly for their `invoke()` functions.
This typing is often more specific than the actual invocation definition requires, because
fields may have values provided only by connections.
For example, consider an ResizeImageInvocation with an `image: ImageField` field.
`image` is required during the call to `invoke()`, but when the python class is instantiated,
the field may not be present. This is fine, because that image field will be provided by a
an ancestor node that outputs the image.
So we'd like to type that `image` field as `Optional[ImageField]`. If we do that, however, then
we need to handle a lot of extra logic in the `invoke()` function to check if the field has a
value or not. This is very tedious.
Ideally, the invocation definition would be able to specify that the field is required during
invocation, but optional during instantiation. So the field would be typed as `image: ImageField`,
but when calling the `invoke()` function, we raise an error if the field is not present.
To do this, we need to do a bit of fanagling to make the pydantic field optional, and then do
extra validation when calling `invoke()`.
There is some additional logic here to cleaning create the pydantic field via the wrapper.
"""
# Filter out field args not provided
provided_args = {k: v for (k, v) in field_args.items() if v is not PydanticUndefined}
if (default is not PydanticUndefined) and (default_factory is not PydanticUndefined):
raise ValueError("Cannot specify both default and default_factory")
# because we are manually making fields optional, we need to store the original required bool for reference later
if default is PydanticUndefined and default_factory is PydanticUndefined:
json_schema_extra_.update(dict(orig_required=True))
else:
json_schema_extra_.update(dict(orig_required=False))
# make Input.Any and Input.Connection fields optional, providing None as a default if the field doesn't already have one
if (input is Input.Any or input is Input.Connection) and default_factory is PydanticUndefined:
default_ = None if default is PydanticUndefined else default
provided_args.update(dict(default=default_))
if default is not PydanticUndefined:
# before invoking, we'll grab the original default value and set it on the field if the field wasn't provided a value
json_schema_extra_.update(dict(default=default))
json_schema_extra_.update(dict(orig_default=default))
elif default is not PydanticUndefined and default_factory is PydanticUndefined:
default_ = default
provided_args.update(dict(default=default_))
json_schema_extra_.update(dict(orig_default=default_))
elif default_factory is not PydanticUndefined:
provided_args.update(dict(default_factory=default_factory))
# TODO: cannot serialize default_factory...
# json_schema_extra_.update(dict(orig_default_factory=default_factory))
return Field(
**provided_args,
json_schema_extra=json_schema_extra_,
)
def OutputField(
*args: Any,
default: Any = Undefined,
default_factory: Optional[NoArgAnyCallable] = None,
alias: Optional[str] = None,
title: Optional[str] = None,
description: Optional[str] = None,
exclude: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
include: Optional[Union[AbstractSet[Union[int, str]], Mapping[Union[int, str], Any], Any]] = None,
const: Optional[bool] = None,
gt: Optional[float] = None,
ge: Optional[float] = None,
lt: Optional[float] = None,
le: Optional[float] = None,
multiple_of: Optional[float] = None,
allow_inf_nan: Optional[bool] = None,
max_digits: Optional[int] = None,
decimal_places: Optional[int] = None,
min_items: Optional[int] = None,
max_items: Optional[int] = None,
unique_items: Optional[bool] = None,
min_length: Optional[int] = None,
max_length: Optional[int] = None,
allow_mutation: bool = True,
regex: Optional[str] = None,
discriminator: Optional[str] = None,
repr: bool = True,
# copied from pydantic's Field
default: Any = _Unset,
default_factory: Callable[[], Any] | None = _Unset,
title: str | None = _Unset,
description: str | None = _Unset,
pattern: str | None = _Unset,
strict: bool | None = _Unset,
gt: float | None = _Unset,
ge: float | None = _Unset,
lt: float | None = _Unset,
le: float | None = _Unset,
multiple_of: float | None = _Unset,
allow_inf_nan: bool | None = _Unset,
max_digits: int | None = _Unset,
decimal_places: int | None = _Unset,
min_length: int | None = _Unset,
max_length: int | None = _Unset,
# custom
ui_type: Optional[UIType] = None,
ui_hidden: bool = False,
ui_order: Optional[int] = None,
**kwargs: Any,
) -> Any:
"""
Creates an output field for an invocation output.
@ -379,15 +434,12 @@ def OutputField(
: param int ui_order: [None] Specifies the order in which this field should be rendered in the UI. \
"""
return Field(
*args,
default=default,
default_factory=default_factory,
alias=alias,
title=title,
description=description,
exclude=exclude,
include=include,
const=const,
pattern=pattern,
strict=strict,
gt=gt,
ge=ge,
lt=lt,
@ -396,19 +448,14 @@ def OutputField(
allow_inf_nan=allow_inf_nan,
max_digits=max_digits,
decimal_places=decimal_places,
min_items=min_items,
max_items=max_items,
unique_items=unique_items,
min_length=min_length,
max_length=max_length,
allow_mutation=allow_mutation,
regex=regex,
discriminator=discriminator,
repr=repr,
ui_type=ui_type,
ui_hidden=ui_hidden,
ui_order=ui_order,
**kwargs,
json_schema_extra=dict(
ui_type=ui_type,
ui_hidden=ui_hidden,
ui_order=ui_order,
_field_kind="output",
),
)
@ -422,7 +469,13 @@ class UIConfigBase(BaseModel):
title: Optional[str] = Field(default=None, description="The node's display name")
category: Optional[str] = Field(default=None, description="The node's category")
version: Optional[str] = Field(
default=None, description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".'
default=None,
description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".',
)
model_config = ConfigDict(
validate_assignment=True,
json_schema_serialization_defaults_required=True,
)
@ -457,23 +510,39 @@ class BaseInvocationOutput(BaseModel):
All invocation outputs must use the `@invocation_output` decorator to provide their unique type.
"""
@classmethod
def get_all_subclasses_tuple(cls):
subclasses = []
toprocess = [cls]
while len(toprocess) > 0:
next = toprocess.pop(0)
next_subclasses = next.__subclasses__()
subclasses.extend(next_subclasses)
toprocess.extend(next_subclasses)
return tuple(subclasses)
_output_classes: ClassVar[set[BaseInvocationOutput]] = set()
class Config:
@staticmethod
def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
if "required" not in schema or not isinstance(schema["required"], list):
schema["required"] = list()
schema["required"].extend(["type"])
@classmethod
def register_output(cls, output: BaseInvocationOutput) -> None:
cls._output_classes.add(output)
@classmethod
def get_outputs(cls) -> Iterable[BaseInvocationOutput]:
return cls._output_classes
@classmethod
def get_outputs_union(cls) -> UnionType:
outputs_union = Union[tuple(cls._output_classes)] # type: ignore [valid-type]
return outputs_union # type: ignore [return-value]
@classmethod
def get_output_types(cls) -> Iterable[str]:
return map(lambda i: get_type(i), BaseInvocationOutput.get_outputs())
@staticmethod
def json_schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
# Because we use a pydantic Literal field with default value for the invocation type,
# it will be typed as optional in the OpenAPI schema. Make it required manually.
if "required" not in schema or not isinstance(schema["required"], list):
schema["required"] = list()
schema["required"].extend(["type"])
model_config = ConfigDict(
protected_namespaces=(),
validate_assignment=True,
json_schema_serialization_defaults_required=True,
json_schema_extra=json_schema_extra,
)
class RequiredConnectionException(Exception):
@ -492,110 +561,94 @@ class MissingInputException(Exception):
class BaseInvocation(ABC, BaseModel):
"""
A node to process inputs and produce outputs.
May use dependency injection in __init__ to receive providers.
All invocations must use the `@invocation` decorator to provide their unique type.
"""
_invocation_classes: ClassVar[set[BaseInvocation]] = set()
@classmethod
def get_all_subclasses(cls):
def register_invocation(cls, invocation: BaseInvocation) -> None:
cls._invocation_classes.add(invocation)
@classmethod
def get_invocations_union(cls) -> UnionType:
invocations_union = Union[tuple(cls._invocation_classes)] # type: ignore [valid-type]
return invocations_union # type: ignore [return-value]
@classmethod
def get_invocations(cls) -> Iterable[BaseInvocation]:
app_config = InvokeAIAppConfig.get_config()
subclasses = []
toprocess = [cls]
while len(toprocess) > 0:
next = toprocess.pop(0)
next_subclasses = next.__subclasses__()
subclasses.extend(next_subclasses)
toprocess.extend(next_subclasses)
allowed_invocations = []
for sc in subclasses:
allowed_invocations: set[BaseInvocation] = set()
for sc in cls._invocation_classes:
invocation_type = get_type(sc)
is_in_allowlist = (
sc.__fields__.get("type").default in app_config.allow_nodes
if isinstance(app_config.allow_nodes, list)
else True
invocation_type in app_config.allow_nodes if isinstance(app_config.allow_nodes, list) else True
)
is_in_denylist = (
sc.__fields__.get("type").default in app_config.deny_nodes
if isinstance(app_config.deny_nodes, list)
else False
invocation_type in app_config.deny_nodes if isinstance(app_config.deny_nodes, list) else False
)
if is_in_allowlist and not is_in_denylist:
allowed_invocations.append(sc)
allowed_invocations.add(sc)
return allowed_invocations
@classmethod
def get_invocations(cls):
return tuple(BaseInvocation.get_all_subclasses())
@classmethod
def get_invocations_map(cls):
def get_invocations_map(cls) -> dict[str, BaseInvocation]:
# Get the type strings out of the literals and into a dictionary
return dict(
map(
lambda t: (get_args(get_type_hints(t)["type"])[0], t),
BaseInvocation.get_all_subclasses(),
lambda i: (get_type(i), i),
BaseInvocation.get_invocations(),
)
)
@classmethod
def get_output_type(cls):
def get_invocation_types(cls) -> Iterable[str]:
return map(lambda i: get_type(i), BaseInvocation.get_invocations())
@classmethod
def get_output_type(cls) -> BaseInvocationOutput:
return signature(cls.invoke).return_annotation
class Config:
validate_assignment = True
validate_all = True
@staticmethod
def schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
uiconfig = getattr(model_class, "UIConfig", None)
if uiconfig and hasattr(uiconfig, "title"):
schema["title"] = uiconfig.title
if uiconfig and hasattr(uiconfig, "tags"):
schema["tags"] = uiconfig.tags
if uiconfig and hasattr(uiconfig, "category"):
schema["category"] = uiconfig.category
if uiconfig and hasattr(uiconfig, "version"):
schema["version"] = uiconfig.version
if "required" not in schema or not isinstance(schema["required"], list):
schema["required"] = list()
schema["required"].extend(["type", "id"])
@staticmethod
def json_schema_extra(schema: dict[str, Any], model_class: Type[BaseModel]) -> None:
# Add the various UI-facing attributes to the schema. These are used to build the invocation templates.
uiconfig = getattr(model_class, "UIConfig", None)
if uiconfig and hasattr(uiconfig, "title"):
schema["title"] = uiconfig.title
if uiconfig and hasattr(uiconfig, "tags"):
schema["tags"] = uiconfig.tags
if uiconfig and hasattr(uiconfig, "category"):
schema["category"] = uiconfig.category
if uiconfig and hasattr(uiconfig, "version"):
schema["version"] = uiconfig.version
if "required" not in schema or not isinstance(schema["required"], list):
schema["required"] = list()
schema["required"].extend(["type", "id"])
@abstractmethod
def invoke(self, context: InvocationContext) -> BaseInvocationOutput:
"""Invoke with provided context and return outputs."""
pass
def __init__(self, **data):
# nodes may have required fields, that can accept input from connections
# on instantiation of the model, we need to exclude these from validation
restore = dict()
try:
field_names = list(self.__fields__.keys())
for field_name in field_names:
# if the field is required and may get its value from a connection, exclude it from validation
field = self.__fields__[field_name]
_input = field.field_info.extra.get("input", None)
if _input in [Input.Connection, Input.Any] and field.required:
if field_name not in data:
restore[field_name] = self.__fields__.pop(field_name)
# instantiate the node, which will validate the data
super().__init__(**data)
finally:
# restore the removed fields
for field_name, field in restore.items():
self.__fields__[field_name] = field
def invoke_internal(self, context: InvocationContext) -> BaseInvocationOutput:
for field_name, field in self.__fields__.items():
_input = field.field_info.extra.get("input", None)
if field.required and not hasattr(self, field_name):
if _input == Input.Connection:
raise RequiredConnectionException(self.__fields__["type"].default, field_name)
elif _input == Input.Any:
raise MissingInputException(self.__fields__["type"].default, field_name)
for field_name, field in self.model_fields.items():
if not field.json_schema_extra or callable(field.json_schema_extra):
# something has gone terribly awry, we should always have this and it should be a dict
continue
# Here we handle the case where the field is optional in the pydantic class, but required
# in the `invoke()` method.
orig_default = field.json_schema_extra.get("orig_default", PydanticUndefined)
orig_required = field.json_schema_extra.get("orig_required", True)
input_ = field.json_schema_extra.get("input", None)
if orig_default is not PydanticUndefined and not hasattr(self, field_name):
setattr(self, field_name, orig_default)
if orig_required and orig_default is PydanticUndefined and getattr(self, field_name) is None:
if input_ == Input.Connection:
raise RequiredConnectionException(self.model_fields["type"].default, field_name)
elif input_ == Input.Any:
raise MissingInputException(self.model_fields["type"].default, field_name)
# skip node cache codepath if it's disabled
if context.services.configuration.node_cache_size == 0:
@ -618,35 +671,96 @@ class BaseInvocation(ABC, BaseModel):
return self.invoke(context)
def get_type(self) -> str:
return self.__fields__["type"].default
return self.model_fields["type"].default
id: str = Field(
description="The id of this instance of an invocation. Must be unique among all instances of invocations."
default_factory=uuid_string,
description="The id of this instance of an invocation. Must be unique among all instances of invocations.",
json_schema_extra=dict(_field_kind="internal"),
)
is_intermediate: bool = InputField(
default=False, description="Whether or not this is an intermediate invocation.", ui_type=UIType.IsIntermediate
is_intermediate: bool = Field(
default=False,
description="Whether or not this is an intermediate invocation.",
json_schema_extra=dict(ui_type=UIType.IsIntermediate, _field_kind="internal"),
)
workflow: Optional[str] = InputField(
default=None,
description="The workflow to save with the image",
ui_type=UIType.WorkflowField,
use_cache: bool = Field(
default=True, description="Whether or not to use the cache", json_schema_extra=dict(_field_kind="internal")
)
use_cache: bool = InputField(default=True, description="Whether or not to use the cache")
@validator("workflow", pre=True)
def validate_workflow_is_json(cls, v):
if v is None:
return None
try:
json.loads(v)
except json.decoder.JSONDecodeError:
raise ValueError("Workflow must be valid JSON")
return v
UIConfig: ClassVar[Type[UIConfigBase]]
model_config = ConfigDict(
protected_namespaces=(),
validate_assignment=True,
json_schema_extra=json_schema_extra,
json_schema_serialization_defaults_required=True,
coerce_numbers_to_str=True,
)
GenericBaseInvocation = TypeVar("GenericBaseInvocation", bound=BaseInvocation)
TBaseInvocation = TypeVar("TBaseInvocation", bound=BaseInvocation)
RESERVED_INPUT_FIELD_NAMES = {
"id",
"is_intermediate",
"use_cache",
"type",
"workflow",
"metadata",
}
RESERVED_OUTPUT_FIELD_NAMES = {"type"}
class _Model(BaseModel):
pass
# Get all pydantic model attrs, methods, etc
RESERVED_PYDANTIC_FIELD_NAMES = set(map(lambda m: m[0], inspect.getmembers(_Model())))
def validate_fields(model_fields: dict[str, FieldInfo], model_type: str) -> None:
"""
Validates the fields of an invocation or invocation output:
- must not override any pydantic reserved fields
- must be created via `InputField`, `OutputField`, or be an internal field defined in this file
"""
for name, field in model_fields.items():
if name in RESERVED_PYDANTIC_FIELD_NAMES:
raise InvalidFieldError(f'Invalid field name "{name}" on "{model_type}" (reserved by pydantic)')
field_kind = (
# _field_kind is defined via InputField(), OutputField() or by one of the internal fields defined in this file
field.json_schema_extra.get("_field_kind", None)
if field.json_schema_extra
else None
)
# must have a field_kind
if field_kind is None or field_kind not in {"input", "output", "internal"}:
raise InvalidFieldError(
f'Invalid field definition for "{name}" on "{model_type}" (maybe it\'s not an InputField or OutputField?)'
)
if field_kind == "input" and name in RESERVED_INPUT_FIELD_NAMES:
raise InvalidFieldError(f'Invalid field name "{name}" on "{model_type}" (reserved input field name)')
if field_kind == "output" and name in RESERVED_OUTPUT_FIELD_NAMES:
raise InvalidFieldError(f'Invalid field name "{name}" on "{model_type}" (reserved output field name)')
# internal fields *must* be in the reserved list
if (
field_kind == "internal"
and name not in RESERVED_INPUT_FIELD_NAMES
and name not in RESERVED_OUTPUT_FIELD_NAMES
):
raise InvalidFieldError(
f'Invalid field name "{name}" on "{model_type}" (internal field without reserved name)'
)
return None
def invocation(
@ -656,9 +770,9 @@ def invocation(
category: Optional[str] = None,
version: Optional[str] = None,
use_cache: Optional[bool] = True,
) -> Callable[[Type[GenericBaseInvocation]], Type[GenericBaseInvocation]]:
) -> Callable[[Type[TBaseInvocation]], Type[TBaseInvocation]]:
"""
Adds metadata to an invocation.
Registers an invocation.
:param str invocation_type: The type of the invocation. Must be unique among all invocations.
:param Optional[str] title: Adds a title to the invocation. Use if the auto-generated title isn't quite right. Defaults to None.
@ -668,12 +782,17 @@ def invocation(
:param Optional[bool] use_cache: Whether or not to use the invocation cache. Defaults to True. The user may override this in the workflow editor.
"""
def wrapper(cls: Type[GenericBaseInvocation]) -> Type[GenericBaseInvocation]:
def wrapper(cls: Type[TBaseInvocation]) -> Type[TBaseInvocation]:
# Validate invocation types on creation of invocation classes
# TODO: ensure unique?
if re.compile(r"^\S+$").match(invocation_type) is None:
raise ValueError(f'"invocation_type" must consist of non-whitespace characters, got "{invocation_type}"')
if invocation_type in BaseInvocation.get_invocation_types():
raise ValueError(f'Invocation type "{invocation_type}" already exists')
validate_fields(cls.model_fields, invocation_type)
# Add OpenAPI schema extras
uiconf_name = cls.__qualname__ + ".UIConfig"
if not hasattr(cls, "UIConfig") or cls.UIConfig.__qualname__ != uiconf_name:
@ -691,59 +810,114 @@ def invocation(
raise InvalidVersionError(f'Invalid version string for node "{invocation_type}": "{version}"') from e
cls.UIConfig.version = version
if use_cache is not None:
cls.__fields__["use_cache"].default = use_cache
cls.model_fields["use_cache"].default = use_cache
# Add the invocation type to the model.
# You'd be tempted to just add the type field and rebuild the model, like this:
# cls.model_fields.update(type=FieldInfo.from_annotated_attribute(Literal[invocation_type], invocation_type))
# cls.model_rebuild() or cls.model_rebuild(force=True)
# Unfortunately, because the `GraphInvocation` uses a forward ref in its `graph` field's annotation, this does
# not work. Instead, we have to create a new class with the type field and patch the original class with it.
# Add the invocation type to the pydantic model of the invocation
invocation_type_annotation = Literal[invocation_type] # type: ignore
invocation_type_field = ModelField.infer(
name="type",
value=invocation_type,
annotation=invocation_type_annotation,
class_validators=None,
config=cls.__config__,
invocation_type_field = Field(
title="type", default=invocation_type, json_schema_extra=dict(_field_kind="internal")
)
cls.__fields__.update({"type": invocation_type_field})
# to support 3.9, 3.10 and 3.11, as described in https://docs.python.org/3/howto/annotations.html
if annotations := cls.__dict__.get("__annotations__", None):
annotations.update({"type": invocation_type_annotation})
docstring = cls.__doc__
cls = create_model(
cls.__qualname__,
__base__=cls,
__module__=cls.__module__,
type=(invocation_type_annotation, invocation_type_field),
)
cls.__doc__ = docstring
# TODO: how to type this correctly? it's typed as ModelMetaclass, a private class in pydantic
BaseInvocation.register_invocation(cls) # type: ignore
return cls
return wrapper
GenericBaseInvocationOutput = TypeVar("GenericBaseInvocationOutput", bound=BaseInvocationOutput)
TBaseInvocationOutput = TypeVar("TBaseInvocationOutput", bound=BaseInvocationOutput)
def invocation_output(
output_type: str,
) -> Callable[[Type[GenericBaseInvocationOutput]], Type[GenericBaseInvocationOutput]]:
) -> Callable[[Type[TBaseInvocationOutput]], Type[TBaseInvocationOutput]]:
"""
Adds metadata to an invocation output.
:param str output_type: The type of the invocation output. Must be unique among all invocation outputs.
"""
def wrapper(cls: Type[GenericBaseInvocationOutput]) -> Type[GenericBaseInvocationOutput]:
def wrapper(cls: Type[TBaseInvocationOutput]) -> Type[TBaseInvocationOutput]:
# Validate output types on creation of invocation output classes
# TODO: ensure unique?
if re.compile(r"^\S+$").match(output_type) is None:
raise ValueError(f'"output_type" must consist of non-whitespace characters, got "{output_type}"')
# Add the output type to the pydantic model of the invocation output
output_type_annotation = Literal[output_type] # type: ignore
output_type_field = ModelField.infer(
name="type",
value=output_type,
annotation=output_type_annotation,
class_validators=None,
config=cls.__config__,
)
cls.__fields__.update({"type": output_type_field})
if output_type in BaseInvocationOutput.get_output_types():
raise ValueError(f'Invocation type "{output_type}" already exists')
# to support 3.9, 3.10 and 3.11, as described in https://docs.python.org/3/howto/annotations.html
if annotations := cls.__dict__.get("__annotations__", None):
annotations.update({"type": output_type_annotation})
validate_fields(cls.model_fields, output_type)
# Add the output type to the model.
output_type_annotation = Literal[output_type] # type: ignore
output_type_field = Field(title="type", default=output_type, json_schema_extra=dict(_field_kind="internal"))
docstring = cls.__doc__
cls = create_model(
cls.__qualname__,
__base__=cls,
__module__=cls.__module__,
type=(output_type_annotation, output_type_field),
)
cls.__doc__ = docstring
BaseInvocationOutput.register_output(cls) # type: ignore # TODO: how to type this correctly?
return cls
return wrapper
class WorkflowField(RootModel):
"""
Pydantic model for workflows with custom root of type dict[str, Any].
Workflows are stored without a strict schema.
"""
root: dict[str, Any] = Field(description="The workflow")
WorkflowFieldValidator = TypeAdapter(WorkflowField)
class WithWorkflow(BaseModel):
workflow: Optional[WorkflowField] = Field(
default=None, description=FieldDescriptions.workflow, json_schema_extra=dict(_field_kind="internal")
)
class MetadataField(RootModel):
"""
Pydantic model for metadata with custom root of type dict[str, Any].
Metadata is stored without a strict schema.
"""
root: dict[str, Any] = Field(description="The metadata")
MetadataFieldValidator = TypeAdapter(MetadataField)
class WithMetadata(BaseModel):
metadata: Optional[MetadataField] = Field(
default=None, description=FieldDescriptions.metadata, json_schema_extra=dict(_field_kind="internal")
)

8
invokeai/app/invocations/collections.py
View File

@ -2,7 +2,7 @@
import numpy as np
from pydantic import validator
from pydantic import ValidationInfo, field_validator
from invokeai.app.invocations.primitives import IntegerCollectionOutput
from invokeai.app.util.misc import SEED_MAX, get_random_seed
@ -20,9 +20,9 @@ class RangeInvocation(BaseInvocation):
stop: int = InputField(default=10, description="The stop of the range")
step: int = InputField(default=1, description="The step of the range")
@validator("stop")
def stop_gt_start(cls, v, values):
if "start" in values and v <= values["start"]:
@field_validator("stop")
def stop_gt_start(cls, v: int, info: ValidationInfo):
if "start" in info.data and v <= info.data["start"]:
raise ValueError("stop must be greater than start")
return v

76
invokeai/app/invocations/compel.py
View File

@ -1,6 +1,6 @@
import re
from dataclasses import dataclass
from typing import List, Union
from typing import List, Optional, Union
import torch
from compel import Compel, ReturnedEmbeddingsType
@ -43,7 +43,13 @@ class ConditioningFieldData:
# PerpNeg = "perp_neg"
@invocation("compel", title="Prompt", tags=["prompt", "compel"], category="conditioning", version="1.0.0")
@invocation(
"compel",
title="Prompt",
tags=["prompt", "compel"],
category="conditioning",
version="1.0.0",
)
class CompelInvocation(BaseInvocation):
"""Parse prompt using compel package to conditioning."""
@ -61,17 +67,19 @@ class CompelInvocation(BaseInvocation):
@torch.no_grad()
def invoke(self, context: InvocationContext) -> ConditioningOutput:
tokenizer_info = context.services.model_manager.get_model(
**self.clip.tokenizer.dict(),
**self.clip.tokenizer.model_dump(),
context=context,
)
text_encoder_info = context.services.model_manager.get_model(
**self.clip.text_encoder.dict(),
**self.clip.text_encoder.model_dump(),
context=context,
)
def _lora_loader():
for lora in self.clip.loras:
lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
lora_info = context.services.model_manager.get_model(
**lora.model_dump(exclude={"weight"}), context=context
)
yield (lora_info.context.model, lora.weight)
del lora_info
return
@ -100,13 +108,14 @@ class CompelInvocation(BaseInvocation):
print(f'Warn: trigger: "{trigger}" not found')
with (
ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),
ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
tokenizer,
ti_manager,
),
ModelPatcher.apply_clip_skip(text_encoder_info.context.model, self.clip.skipped_layers),
text_encoder_info as text_encoder,
# Apply the LoRA after text_encoder has been moved to its target device for faster patching.
ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
):
compel = Compel(
tokenizer=tokenizer,
@ -160,11 +169,11 @@ class SDXLPromptInvocationBase:
zero_on_empty: bool,
):
tokenizer_info = context.services.model_manager.get_model(
**clip_field.tokenizer.dict(),
**clip_field.tokenizer.model_dump(),
context=context,
)
text_encoder_info = context.services.model_manager.get_model(
**clip_field.text_encoder.dict(),
**clip_field.text_encoder.model_dump(),
context=context,
)
@ -172,7 +181,11 @@ class SDXLPromptInvocationBase:
if prompt == "" and zero_on_empty:
cpu_text_encoder = text_encoder_info.context.model
c = torch.zeros(
(1, cpu_text_encoder.config.max_position_embeddings, cpu_text_encoder.config.hidden_size),
(
1,
cpu_text_encoder.config.max_position_embeddings,
cpu_text_encoder.config.hidden_size,
),
dtype=text_encoder_info.context.cache.precision,
)
if get_pooled:
@ -186,7 +199,9 @@ class SDXLPromptInvocationBase:
def _lora_loader():
for lora in clip_field.loras:
lora_info = context.services.model_manager.get_model(**lora.dict(exclude={"weight"}), context=context)
lora_info = context.services.model_manager.get_model(
**lora.model_dump(exclude={"weight"}), context=context
)
yield (lora_info.context.model, lora.weight)
del lora_info
return
@ -215,13 +230,14 @@ class SDXLPromptInvocationBase:
print(f'Warn: trigger: "{trigger}" not found')
with (
ModelPatcher.apply_lora(text_encoder_info.context.model, _lora_loader(), lora_prefix),
ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (
tokenizer,
ti_manager,
),
ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),
text_encoder_info as text_encoder,
# Apply the LoRA after text_encoder has been moved to its target device for faster patching.
ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
):
compel = Compel(
tokenizer=tokenizer,
@ -273,8 +289,16 @@ class SDXLPromptInvocationBase:
class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
"""Parse prompt using compel package to conditioning."""
prompt: str = InputField(default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea)
style: str = InputField(default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea)
prompt: str = InputField(
default="",
description=FieldDescriptions.compel_prompt,
ui_component=UIComponent.Textarea,
)
style: str = InputField(
default="",
description=FieldDescriptions.compel_prompt,
ui_component=UIComponent.Textarea,
)
original_width: int = InputField(default=1024, description="")
original_height: int = InputField(default=1024, description="")
crop_top: int = InputField(default=0, description="")
@ -310,7 +334,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
[
c1,
torch.zeros(
(c1.shape[0], c2.shape[1] - c1.shape[1], c1.shape[2]), device=c1.device, dtype=c1.dtype
(c1.shape[0], c2.shape[1] - c1.shape[1], c1.shape[2]),
device=c1.device,
dtype=c1.dtype,
),
],
dim=1,
@ -321,7 +347,9 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
[
c2,
torch.zeros(
(c2.shape[0], c1.shape[1] - c2.shape[1], c2.shape[2]), device=c2.device, dtype=c2.dtype
(c2.shape[0], c1.shape[1] - c2.shape[1], c2.shape[2]),
device=c2.device,
dtype=c2.dtype,
),
],
dim=1,
@ -359,7 +387,9 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
"""Parse prompt using compel package to conditioning."""
style: str = InputField(
default="", description=FieldDescriptions.compel_prompt, ui_component=UIComponent.Textarea
default="",
description=FieldDescriptions.compel_prompt,
ui_component=UIComponent.Textarea,
) # TODO: ?
original_width: int = InputField(default=1024, description="")
original_height: int = InputField(default=1024, description="")
@ -403,10 +433,16 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
class ClipSkipInvocationOutput(BaseInvocationOutput):
"""Clip skip node output"""
clip: ClipField = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
@invocation("clip_skip", title="CLIP Skip", tags=["clipskip", "clip", "skip"], category="conditioning", version="1.0.0")
@invocation(
"clip_skip",
title="CLIP Skip",
tags=["clipskip", "clip", "skip"],
category="conditioning",
version="1.0.0",
)
class ClipSkipInvocation(BaseInvocation):
"""Skip layers in clip text_encoder model."""
@ -421,7 +457,9 @@ class ClipSkipInvocation(BaseInvocation):
def get_max_token_count(
tokenizer, prompt: Union[FlattenedPrompt, Blend, Conjunction], truncate_if_too_long=False
tokenizer,
prompt: Union[FlattenedPrompt, Blend, Conjunction],
truncate_if_too_long=False,
) -> int:
if type(prompt) is Blend:
blend: Blend = prompt

31
invokeai/app/invocations/controlnet_image_processors.py
View File

@ -2,7 +2,7 @@
# initial implementation by Gregg Helt, 2023
# heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
from builtins import bool, float
from typing import Dict, List, Literal, Optional, Union
from typing import Dict, List, Literal, Union
import cv2
import numpy as np
@ -24,7 +24,7 @@ from controlnet_aux import (
)
from controlnet_aux.util import HWC3, ade_palette
from PIL import Image
from pydantic import BaseModel, Field, validator
from pydantic import BaseModel, ConfigDict, Field, field_validator
from invokeai.app.invocations.primitives import ImageField, ImageOutput
from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
@ -38,6 +38,8 @@ from .baseinvocation import (
InputField,
InvocationContext,
OutputField,
WithMetadata,
WithWorkflow,
invocation,
invocation_output,
)
@ -57,6 +59,8 @@ class ControlNetModelField(BaseModel):
model_name: str = Field(description="Name of the ControlNet model")
base_model: BaseModelType = Field(description="Base model")
model_config = ConfigDict(protected_namespaces=())
class ControlField(BaseModel):
image: ImageField = Field(description="The control image")
@ -71,7 +75,7 @@ class ControlField(BaseModel):
control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use")
resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
@validator("control_weight")
@field_validator("control_weight")
def validate_control_weight(cls, v):
"""Validate that all control weights in the valid range"""
if isinstance(v, list):
@ -124,15 +128,13 @@ class ControlNetInvocation(BaseInvocation):
)
@invocation(
"image_processor", title="Base Image Processor", tags=["controlnet"], category="controlnet", version="1.0.0"
)
class ImageProcessorInvocation(BaseInvocation):
# This invocation exists for other invocations to subclass it - do not register with @invocation!
class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Base class for invocations that preprocess images for ControlNet"""
image: ImageField = InputField(description="The image to process")
def run_processor(self, image):
def run_processor(self, image: Image.Image) -> Image.Image:
# superclass just passes through image without processing
return image
@ -150,6 +152,7 @@ class ImageProcessorInvocation(BaseInvocation):
session_id=context.graph_execution_state_id,
node_id=self.id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -393,9 +396,9 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
detect_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.detect_res)
image_resolution: int = InputField(default=512, ge=0, description=FieldDescriptions.image_res)
h: Optional[int] = InputField(default=512, ge=0, description="Content shuffle `h` parameter")
w: Optional[int] = InputField(default=512, ge=0, description="Content shuffle `w` parameter")
f: Optional[int] = InputField(default=256, ge=0, description="Content shuffle `f` parameter")
h: int = InputField(default=512, ge=0, description="Content shuffle `h` parameter")
w: int = InputField(default=512, ge=0, description="Content shuffle `w` parameter")
f: int = InputField(default=256, ge=0, description="Content shuffle `f` parameter")
def run_processor(self, image):
content_shuffle_processor = ContentShuffleDetector()
@ -575,14 +578,14 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
def run_processor(self, image: Image.Image):
image = image.convert("RGB")
image = np.array(image, dtype=np.uint8)
height, width = image.shape[:2]
np_image = np.array(image, dtype=np.uint8)
height, width = np_image.shape[:2]
width_tile_size = min(self.color_map_tile_size, width)
height_tile_size = min(self.color_map_tile_size, height)
color_map = cv2.resize(
image,
np_image,
(width // width_tile_size, height // height_tile_size),
interpolation=cv2.INTER_CUBIC,
)

51
invokeai/app/invocations/custom_nodes/README.md Normal file
View File

@ -0,0 +1,51 @@
# Custom Nodes / Node Packs
Copy your node packs to this directory.
When nodes are added or changed, you must restart the app to see the changes.
## Directory Structure
For a node pack to be loaded, it must be placed in a directory alongside this
file. Here's an example structure:
```py
.
├── __init__.py # Invoke-managed custom node loader
│
├── cool_node
│ ├── __init__.py # see example below
│ └── cool_node.py
│
└── my_node_pack
├── __init__.py # see example below
├── tasty_node.py
├── bodacious_node.py
├── utils.py
└── extra_nodes
└── fancy_node.py
```
## Node Pack `__init__.py`
Each node pack must have an `__init__.py` file that imports its nodes.
The structure of each node or node pack is otherwise not important.
Here are examples, based on the example directory structure.
### `cool_node/__init__.py`
```py
from .cool_node import CoolInvocation
```
### `my_node_pack/__init__.py`
```py
from .tasty_node import TastyInvocation
from .bodacious_node import BodaciousInvocation
from .extra_nodes.fancy_node import FancyInvocation
```
Only nodes imported in the `__init__.py` file are loaded.

51
invokeai/app/invocations/custom_nodes/init.py Normal file
View File

@ -0,0 +1,51 @@
"""
Invoke-managed custom node loader. See README.md for more information.
"""
import sys
from importlib.util import module_from_spec, spec_from_file_location
from pathlib import Path
from invokeai.backend.util.logging import InvokeAILogger
logger = InvokeAILogger.get_logger()
loaded_count = 0
for d in Path(__file__).parent.iterdir():
# skip files
if not d.is_dir():
continue
# skip hidden directories
if d.name.startswith("_") or d.name.startswith("."):
continue
# skip directories without an `__init__.py`
init = d / "__init__.py"
if not init.exists():
continue
module_name = init.parent.stem
# skip if already imported
if module_name in globals():
continue
# we have a legit module to import
spec = spec_from_file_location(module_name, init.absolute())
if spec is None or spec.loader is None:
logger.warn(f"Could not load {init}")
continue
module = module_from_spec(spec)
sys.modules[spec.name] = module
spec.loader.exec_module(module)
loaded_count += 1
del init, module_name
logger.info(f"Loaded {loaded_count} modules from {Path(__file__).parent}")

4
invokeai/app/invocations/cv.py
View File

@ -8,11 +8,11 @@ from PIL import Image, ImageOps
from invokeai.app.invocations.primitives import ImageField, ImageOutput
from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
@invocation("cv_inpaint", title="OpenCV Inpaint", tags=["opencv", "inpaint"], category="inpaint", version="1.0.0")
class CvInpaintInvocation(BaseInvocation):
class CvInpaintInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Simple inpaint using opencv."""
image: ImageField = InputField(description="The image to inpaint")

120
invokeai/app/invocations/facetools.py
View File

@ -8,7 +8,7 @@ import numpy as np
from mediapipe.python.solutions.face_mesh import FaceMesh # type: ignore[import]
from PIL import Image, ImageDraw, ImageFilter, ImageFont, ImageOps
from PIL.Image import Image as ImageType
from pydantic import validator
from pydantic import field_validator
import invokeai.assets.fonts as font_assets
from invokeai.app.invocations.baseinvocation import (
@ -16,6 +16,8 @@ from invokeai.app.invocations.baseinvocation import (
InputField,
InvocationContext,
OutputField,
WithMetadata,
WithWorkflow,
invocation,
invocation_output,
)
@ -46,6 +48,8 @@ class FaceResultData(TypedDict):
y_center: float
mesh_width: int
mesh_height: int
chunk_x_offset: int
chunk_y_offset: int
class FaceResultDataWithId(FaceResultData):
@ -78,6 +82,48 @@ FONT_SIZE = 32
FONT_STROKE_WIDTH = 4
def coalesce_faces(face1: FaceResultData, face2: FaceResultData) -> FaceResultData:
face1_x_offset = face1["chunk_x_offset"] - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
face2_x_offset = face2["chunk_x_offset"] - min(face1["chunk_x_offset"], face2["chunk_x_offset"])
face1_y_offset = face1["chunk_y_offset"] - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
face2_y_offset = face2["chunk_y_offset"] - min(face1["chunk_y_offset"], face2["chunk_y_offset"])
new_im_width = (
max(face1["image"].width, face2["image"].width)
+ max(face1["chunk_x_offset"], face2["chunk_x_offset"])
- min(face1["chunk_x_offset"], face2["chunk_x_offset"])
)
new_im_height = (
max(face1["image"].height, face2["image"].height)
+ max(face1["chunk_y_offset"], face2["chunk_y_offset"])
- min(face1["chunk_y_offset"], face2["chunk_y_offset"])
)
pil_image = Image.new(mode=face1["image"].mode, size=(new_im_width, new_im_height))
pil_image.paste(face1["image"], (face1_x_offset, face1_y_offset))
pil_image.paste(face2["image"], (face2_x_offset, face2_y_offset))
# Mask images are always from the origin
new_mask_im_width = max(face1["mask"].width, face2["mask"].width)
new_mask_im_height = max(face1["mask"].height, face2["mask"].height)
mask_pil = create_white_image(new_mask_im_width, new_mask_im_height)
black_image = create_black_image(face1["mask"].width, face1["mask"].height)
mask_pil.paste(black_image, (0, 0), ImageOps.invert(face1["mask"]))
black_image = create_black_image(face2["mask"].width, face2["mask"].height)
mask_pil.paste(black_image, (0, 0), ImageOps.invert(face2["mask"]))
new_face = FaceResultData(
image=pil_image,
mask=mask_pil,
x_center=max(face1["x_center"], face2["x_center"]),
y_center=max(face1["y_center"], face2["y_center"]),
mesh_width=max(face1["mesh_width"], face2["mesh_width"]),
mesh_height=max(face1["mesh_height"], face2["mesh_height"]),
chunk_x_offset=max(face1["chunk_x_offset"], face2["chunk_x_offset"]),
chunk_y_offset=max(face2["chunk_y_offset"], face2["chunk_y_offset"]),
)
return new_face
def prepare_faces_list(
face_result_list: list[FaceResultData],
) -> list[FaceResultDataWithId]:
@ -91,7 +137,7 @@ def prepare_faces_list(
should_add = True
candidate_x_center = candidate["x_center"]
candidate_y_center = candidate["y_center"]
for face in deduped_faces:
for idx, face in enumerate(deduped_faces):
face_center_x = face["x_center"]
face_center_y = face["y_center"]
face_radius_w = face["mesh_width"] / 2
@ -105,6 +151,7 @@ def prepare_faces_list(
)
if p < 1: # Inside of the already-added face's radius
deduped_faces[idx] = coalesce_faces(face, candidate)
should_add = False
break
@ -138,7 +185,6 @@ def generate_face_box_mask(
chunk_x_offset: int = 0,
chunk_y_offset: int = 0,
draw_mesh: bool = True,
check_bounds: bool = True,
) -> list[FaceResultData]:
result = []
mask_pil = None
@ -211,33 +257,20 @@ def generate_face_box_mask(
mask_pil = create_white_image(w + chunk_x_offset, h + chunk_y_offset)
mask_pil.paste(init_mask_pil, (chunk_x_offset, chunk_y_offset))
left_side = x_center - mesh_width
right_side = x_center + mesh_width
top_side = y_center - mesh_height
bottom_side = y_center + mesh_height
im_width, im_height = pil_image.size
over_w = im_width * 0.1
over_h = im_height * 0.1
if not check_bounds or (
(left_side >= -over_w)
and (right_side < im_width + over_w)
and (top_side >= -over_h)
and (bottom_side < im_height + over_h)
):
x_center = float(x_center)
y_center = float(y_center)
face = FaceResultData(
image=pil_image,
mask=mask_pil or create_white_image(*pil_image.size),
x_center=x_center + chunk_x_offset,
y_center=y_center + chunk_y_offset,
mesh_width=mesh_width,
mesh_height=mesh_height,
)
x_center = float(x_center)
y_center = float(y_center)
face = FaceResultData(
image=pil_image,
mask=mask_pil or create_white_image(*pil_image.size),
x_center=x_center + chunk_x_offset,
y_center=y_center + chunk_y_offset,
mesh_width=mesh_width,
mesh_height=mesh_height,
chunk_x_offset=chunk_x_offset,
chunk_y_offset=chunk_y_offset,
)
result.append(face)
else:
context.services.logger.info("FaceTools --> Face out of bounds, ignoring.")
result.append(face)
return result
@ -346,7 +379,6 @@ def get_faces_list(
chunk_x_offset=0,
chunk_y_offset=0,
draw_mesh=draw_mesh,
check_bounds=False,
)
if should_chunk or len(result) == 0:
context.services.logger.info("FaceTools --> Chunking image (chunk toggled on, or no face found in full image).")
@ -360,24 +392,26 @@ def get_faces_list(
if width > height:
# Landscape - slice the image horizontally
fx = 0.0
steps = int(width * 2 / height)
steps = int(width * 2 / height) + 1
increment = (width - height) / (steps - 1)
while fx <= (width - height):
x = int(fx)
image_chunks.append(image.crop((x, 0, x + height - 1, height - 1)))
image_chunks.append(image.crop((x, 0, x + height, height)))
x_offsets.append(x)
y_offsets.append(0)
fx += (width - height) / steps
fx += increment
context.services.logger.info(f"FaceTools --> Chunk starting at x = {x}")
elif height > width:
# Portrait - slice the image vertically
fy = 0.0
steps = int(height * 2 / width)
steps = int(height * 2 / width) + 1
increment = (height - width) / (steps - 1)
while fy <= (height - width):
y = int(fy)
image_chunks.append(image.crop((0, y, width - 1, y + width - 1)))
image_chunks.append(image.crop((0, y, width, y + width)))
x_offsets.append(0)
y_offsets.append(y)
fy += (height - width) / steps
fy += increment
context.services.logger.info(f"FaceTools --> Chunk starting at y = {y}")
for idx in range(len(image_chunks)):
@ -404,8 +438,8 @@ def get_faces_list(
return all_faces
@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.0.1")
class FaceOffInvocation(BaseInvocation):
@invocation("face_off", title="FaceOff", tags=["image", "faceoff", "face", "mask"], category="image", version="1.0.2")
class FaceOffInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Bound, extract, and mask a face from an image using MediaPipe detection"""
image: ImageField = InputField(description="Image for face detection")
@ -498,8 +532,8 @@ class FaceOffInvocation(BaseInvocation):
return output
@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.0.1")
class FaceMaskInvocation(BaseInvocation):
@invocation("face_mask_detection", title="FaceMask", tags=["image", "face", "mask"], category="image", version="1.0.2")
class FaceMaskInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Face mask creation using mediapipe face detection"""
image: ImageField = InputField(description="Image to face detect")
@ -518,7 +552,7 @@ class FaceMaskInvocation(BaseInvocation):
)
invert_mask: bool = InputField(default=False, description="Toggle to invert the mask")
@validator("face_ids")
@field_validator("face_ids")
def validate_comma_separated_ints(cls, v) -> str:
comma_separated_ints_regex = re.compile(r"^\d*(,\d+)*$")
if comma_separated_ints_regex.match(v) is None:
@ -616,9 +650,9 @@ class FaceMaskInvocation(BaseInvocation):
@invocation(
"face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.0.1"
"face_identifier", title="FaceIdentifier", tags=["image", "face", "identifier"], category="image", version="1.0.2"
)
class FaceIdentifierInvocation(BaseInvocation):
class FaceIdentifierInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Outputs an image with detected face IDs printed on each face. For use with other FaceTools."""
image: ImageField = InputField(description="Image to face detect")

111
invokeai/app/invocations/image.py
View File

@ -7,13 +7,21 @@ import cv2
import numpy
from PIL import Image, ImageChops, ImageFilter, ImageOps
from invokeai.app.invocations.metadata import CoreMetadata
from invokeai.app.invocations.primitives import BoardField, ColorField, ImageField, ImageOutput
from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
from invokeai.backend.image_util.safety_checker import SafetyChecker
from .baseinvocation import BaseInvocation, FieldDescriptions, Input, InputField, InvocationContext, invocation
from .baseinvocation import (
BaseInvocation,
FieldDescriptions,
Input,
InputField,
InvocationContext,
WithMetadata,
WithWorkflow,
invocation,
)
@invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.0")
@ -37,7 +45,7 @@ class ShowImageInvocation(BaseInvocation):
@invocation("blank_image", title="Blank Image", tags=["image"], category="image", version="1.0.0")
class BlankImageInvocation(BaseInvocation):
class BlankImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Creates a blank image and forwards it to the pipeline"""
width: int = InputField(default=512, description="The width of the image")
@ -55,6 +63,7 @@ class BlankImageInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -66,7 +75,7 @@ class BlankImageInvocation(BaseInvocation):
@invocation("img_crop", title="Crop Image", tags=["image", "crop"], category="image", version="1.0.0")
class ImageCropInvocation(BaseInvocation):
class ImageCropInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Crops an image to a specified box. The box can be outside of the image."""
image: ImageField = InputField(description="The image to crop")
@ -88,6 +97,7 @@ class ImageCropInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -99,7 +109,7 @@ class ImageCropInvocation(BaseInvocation):
@invocation("img_paste", title="Paste Image", tags=["image", "paste"], category="image", version="1.0.1")
class ImagePasteInvocation(BaseInvocation):
class ImagePasteInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Pastes an image into another image."""
base_image: ImageField = InputField(description="The base image")
@ -141,6 +151,7 @@ class ImagePasteInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -152,7 +163,7 @@ class ImagePasteInvocation(BaseInvocation):
@invocation("tomask", title="Mask from Alpha", tags=["image", "mask"], category="image", version="1.0.0")
class MaskFromAlphaInvocation(BaseInvocation):
class MaskFromAlphaInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Extracts the alpha channel of an image as a mask."""
image: ImageField = InputField(description="The image to create the mask from")
@ -172,6 +183,7 @@ class MaskFromAlphaInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -183,7 +195,7 @@ class MaskFromAlphaInvocation(BaseInvocation):
@invocation("img_mul", title="Multiply Images", tags=["image", "multiply"], category="image", version="1.0.0")
class ImageMultiplyInvocation(BaseInvocation):
class ImageMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Multiplies two images together using `PIL.ImageChops.multiply()`."""
image1: ImageField = InputField(description="The first image to multiply")
@ -202,6 +214,7 @@ class ImageMultiplyInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -216,7 +229,7 @@ IMAGE_CHANNELS = Literal["A", "R", "G", "B"]
@invocation("img_chan", title="Extract Image Channel", tags=["image", "channel"], category="image", version="1.0.0")
class ImageChannelInvocation(BaseInvocation):
class ImageChannelInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Gets a channel from an image."""
image: ImageField = InputField(description="The image to get the channel from")
@ -234,6 +247,7 @@ class ImageChannelInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -248,7 +262,7 @@ IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F
@invocation("img_conv", title="Convert Image Mode", tags=["image", "convert"], category="image", version="1.0.0")
class ImageConvertInvocation(BaseInvocation):
class ImageConvertInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Converts an image to a different mode."""
image: ImageField = InputField(description="The image to convert")
@ -266,6 +280,7 @@ class ImageConvertInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -277,7 +292,7 @@ class ImageConvertInvocation(BaseInvocation):
@invocation("img_blur", title="Blur Image", tags=["image", "blur"], category="image", version="1.0.0")
class ImageBlurInvocation(BaseInvocation):
class ImageBlurInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Blurs an image"""
image: ImageField = InputField(description="The image to blur")
@ -300,6 +315,7 @@ class ImageBlurInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -331,16 +347,13 @@ PIL_RESAMPLING_MAP = {
@invocation("img_resize", title="Resize Image", tags=["image", "resize"], category="image", version="1.0.0")
class ImageResizeInvocation(BaseInvocation):
class ImageResizeInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Resizes an image to specific dimensions"""
image: ImageField = InputField(description="The image to resize")
width: int = InputField(default=512, gt=0, description="The width to resize to (px)")
height: int = InputField(default=512, gt=0, description="The height to resize to (px)")
resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
metadata: Optional[CoreMetadata] = InputField(
default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
)
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
@ -359,7 +372,7 @@ class ImageResizeInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
metadata=self.metadata,
workflow=self.workflow,
)
@ -371,7 +384,7 @@ class ImageResizeInvocation(BaseInvocation):
@invocation("img_scale", title="Scale Image", tags=["image", "scale"], category="image", version="1.0.0")
class ImageScaleInvocation(BaseInvocation):
class ImageScaleInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Scales an image by a factor"""
image: ImageField = InputField(description="The image to scale")
@ -401,6 +414,7 @@ class ImageScaleInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -412,7 +426,7 @@ class ImageScaleInvocation(BaseInvocation):
@invocation("img_lerp", title="Lerp Image", tags=["image", "lerp"], category="image", version="1.0.0")
class ImageLerpInvocation(BaseInvocation):
class ImageLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Linear interpolation of all pixels of an image"""
image: ImageField = InputField(description="The image to lerp")
@ -434,6 +448,7 @@ class ImageLerpInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -445,7 +460,7 @@ class ImageLerpInvocation(BaseInvocation):
@invocation("img_ilerp", title="Inverse Lerp Image", tags=["image", "ilerp"], category="image", version="1.0.0")
class ImageInverseLerpInvocation(BaseInvocation):
class ImageInverseLerpInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Inverse linear interpolation of all pixels of an image"""
image: ImageField = InputField(description="The image to lerp")
@ -456,7 +471,7 @@ class ImageInverseLerpInvocation(BaseInvocation):
image = context.services.images.get_pil_image(self.image.image_name)
image_arr = numpy.asarray(image, dtype=numpy.float32)
image_arr = numpy.minimum(numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1) * 255
image_arr = numpy.minimum(numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1) * 255 # type: ignore [assignment]
ilerp_image = Image.fromarray(numpy.uint8(image_arr))
@ -467,6 +482,7 @@ class ImageInverseLerpInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -478,13 +494,10 @@ class ImageInverseLerpInvocation(BaseInvocation):
@invocation("img_nsfw", title="Blur NSFW Image", tags=["image", "nsfw"], category="image", version="1.0.0")
class ImageNSFWBlurInvocation(BaseInvocation):
class ImageNSFWBlurInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Add blur to NSFW-flagged images"""
image: ImageField = InputField(description="The image to check")
metadata: Optional[CoreMetadata] = InputField(
default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
)
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
@ -505,7 +518,7 @@ class ImageNSFWBlurInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
metadata=self.metadata,
workflow=self.workflow,
)
@ -515,7 +528,7 @@ class ImageNSFWBlurInvocation(BaseInvocation):
height=image_dto.height,
)
def _get_caution_img(self) -> Image:
def _get_caution_img(self) -> Image.Image:
import invokeai.app.assets.images as image_assets
caution = Image.open(Path(image_assets.__path__[0]) / "caution.png")
@ -523,16 +536,17 @@ class ImageNSFWBlurInvocation(BaseInvocation):
@invocation(
"img_watermark", title="Add Invisible Watermark", tags=["image", "watermark"], category="image", version="1.0.0"
"img_watermark",
title="Add Invisible Watermark",
tags=["image", "watermark"],
category="image",
version="1.0.0",
)
class ImageWatermarkInvocation(BaseInvocation):
class ImageWatermarkInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Add an invisible watermark to an image"""
image: ImageField = InputField(description="The image to check")
text: str = InputField(default="InvokeAI", description="Watermark text")
metadata: Optional[CoreMetadata] = InputField(
default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
)
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
@ -544,7 +558,7 @@ class ImageWatermarkInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
metadata=self.metadata,
workflow=self.workflow,
)
@ -556,7 +570,7 @@ class ImageWatermarkInvocation(BaseInvocation):
@invocation("mask_edge", title="Mask Edge", tags=["image", "mask", "inpaint"], category="image", version="1.0.0")
class MaskEdgeInvocation(BaseInvocation):
class MaskEdgeInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Applies an edge mask to an image"""
image: ImageField = InputField(description="The image to apply the mask to")
@ -590,6 +604,7 @@ class MaskEdgeInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -601,9 +616,13 @@ class MaskEdgeInvocation(BaseInvocation):
@invocation(
"mask_combine", title="Combine Masks", tags=["image", "mask", "multiply"], category="image", version="1.0.0"
"mask_combine",
title="Combine Masks",
tags=["image", "mask", "multiply"],
category="image",
version="1.0.0",
)
class MaskCombineInvocation(BaseInvocation):
class MaskCombineInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Combine two masks together by multiplying them using `PIL.ImageChops.multiply()`."""
mask1: ImageField = InputField(description="The first mask to combine")
@ -622,6 +641,7 @@ class MaskCombineInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -633,7 +653,7 @@ class MaskCombineInvocation(BaseInvocation):
@invocation("color_correct", title="Color Correct", tags=["image", "color"], category="image", version="1.0.0")
class ColorCorrectInvocation(BaseInvocation):
class ColorCorrectInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""
Shifts the colors of a target image to match the reference image, optionally
using a mask to only color-correct certain regions of the target image.
@ -732,6 +752,7 @@ class ColorCorrectInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -743,7 +764,7 @@ class ColorCorrectInvocation(BaseInvocation):
@invocation("img_hue_adjust", title="Adjust Image Hue", tags=["image", "hue"], category="image", version="1.0.0")
class ImageHueAdjustmentInvocation(BaseInvocation):
class ImageHueAdjustmentInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Adjusts the Hue of an image."""
image: ImageField = InputField(description="The image to adjust")
@ -771,6 +792,7 @@ class ImageHueAdjustmentInvocation(BaseInvocation):
node_id=self.id,
is_intermediate=self.is_intermediate,
session_id=context.graph_execution_state_id,
metadata=self.metadata,
workflow=self.workflow,
)
@ -846,7 +868,7 @@ CHANNEL_FORMATS = {
category="image",
version="1.0.0",
)
class ImageChannelOffsetInvocation(BaseInvocation):
class ImageChannelOffsetInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Add or subtract a value from a specific color channel of an image."""
image: ImageField = InputField(description="The image to adjust")
@ -880,6 +902,7 @@ class ImageChannelOffsetInvocation(BaseInvocation):
node_id=self.id,
is_intermediate=self.is_intermediate,
session_id=context.graph_execution_state_id,
metadata=self.metadata,
workflow=self.workflow,
)
@ -916,7 +939,7 @@ class ImageChannelOffsetInvocation(BaseInvocation):
category="image",
version="1.0.0",
)
class ImageChannelMultiplyInvocation(BaseInvocation):
class ImageChannelMultiplyInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Scale a specific color channel of an image."""
image: ImageField = InputField(description="The image to adjust")
@ -956,6 +979,7 @@ class ImageChannelMultiplyInvocation(BaseInvocation):
is_intermediate=self.is_intermediate,
session_id=context.graph_execution_state_id,
workflow=self.workflow,
metadata=self.metadata,
)
return ImageOutput(
@ -975,16 +999,11 @@ class ImageChannelMultiplyInvocation(BaseInvocation):
version="1.0.1",
use_cache=False,
)
class SaveImageInvocation(BaseInvocation):
class SaveImageInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Saves an image. Unlike an image primitive, this invocation stores a copy of the image."""
image: ImageField = InputField(description=FieldDescriptions.image)
board: Optional[BoardField] = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
metadata: CoreMetadata = InputField(
default=None,
description=FieldDescriptions.core_metadata,
ui_hidden=True,
)
board: BoardField = InputField(default=None, description=FieldDescriptions.board, input=Input.Direct)
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
@ -997,7 +1016,7 @@ class SaveImageInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
metadata=self.metadata,
workflow=self.workflow,
)

21
invokeai/app/invocations/infill.py
View File

@ -13,7 +13,7 @@ from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
from invokeai.backend.image_util.lama import LaMA
from invokeai.backend.image_util.patchmatch import PatchMatch
from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
@ -119,7 +119,7 @@ def tile_fill_missing(im: Image.Image, tile_size: int = 16, seed: Optional[int]
@invocation("infill_rgba", title="Solid Color Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
class InfillColorInvocation(BaseInvocation):
class InfillColorInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Infills transparent areas of an image with a solid color"""
image: ImageField = InputField(description="The image to infill")
@ -143,6 +143,7 @@ class InfillColorInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -154,7 +155,7 @@ class InfillColorInvocation(BaseInvocation):
@invocation("infill_tile", title="Tile Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
class InfillTileInvocation(BaseInvocation):
class InfillTileInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Infills transparent areas of an image with tiles of the image"""
image: ImageField = InputField(description="The image to infill")
@ -179,6 +180,7 @@ class InfillTileInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -192,7 +194,7 @@ class InfillTileInvocation(BaseInvocation):
@invocation(
"infill_patchmatch", title="PatchMatch Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0"
)
class InfillPatchMatchInvocation(BaseInvocation):
class InfillPatchMatchInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Infills transparent areas of an image using the PatchMatch algorithm"""
image: ImageField = InputField(description="The image to infill")
@ -232,6 +234,7 @@ class InfillPatchMatchInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
@ -243,7 +246,7 @@ class InfillPatchMatchInvocation(BaseInvocation):
@invocation("infill_lama", title="LaMa Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
class LaMaInfillInvocation(BaseInvocation):
class LaMaInfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Infills transparent areas of an image using the LaMa model"""
image: ImageField = InputField(description="The image to infill")
@ -260,6 +263,8 @@ class LaMaInfillInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
return ImageOutput(
@ -269,8 +274,8 @@ class LaMaInfillInvocation(BaseInvocation):
)
@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint", version="1.0.0")
class CV2InfillInvocation(BaseInvocation):
@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint")
class CV2InfillInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Infills transparent areas of an image using OpenCV Inpainting"""
image: ImageField = InputField(description="The image to infill")
@ -287,6 +292,8 @@ class CV2InfillInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)
return ImageOutput(

14
invokeai/app/invocations/ip_adapter.py
View File

@ -2,7 +2,7 @@ import os
from builtins import float
from typing import List, Union
from pydantic import BaseModel, Field
from pydantic import BaseModel, ConfigDict, Field
from invokeai.app.invocations.baseinvocation import (
BaseInvocation,
@ -25,14 +25,18 @@ class IPAdapterModelField(BaseModel):
model_name: str = Field(description="Name of the IP-Adapter model")
base_model: BaseModelType = Field(description="Base model")
model_config = ConfigDict(protected_namespaces=())
class CLIPVisionModelField(BaseModel):
model_name: str = Field(description="Name of the CLIP Vision image encoder model")
base_model: BaseModelType = Field(description="Base model (usually 'Any')")
model_config = ConfigDict(protected_namespaces=())
class IPAdapterField(BaseModel):
image: ImageField = Field(description="The IP-Adapter image prompt.")
image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
image_encoder_model: CLIPVisionModelField = Field(description="The name of the CLIP image encoder model.")
weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
@ -51,19 +55,19 @@ class IPAdapterOutput(BaseInvocationOutput):
ip_adapter: IPAdapterField = OutputField(description=FieldDescriptions.ip_adapter, title="IP-Adapter")
@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.0.0")
@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.1.0")
class IPAdapterInvocation(BaseInvocation):
"""Collects IP-Adapter info to pass to other nodes."""
# Inputs
image: ImageField = InputField(description="The IP-Adapter image prompt.")
image: Union[ImageField, List[ImageField]] = InputField(description="The IP-Adapter image prompt(s).")
ip_adapter_model: IPAdapterModelField = InputField(
description="The IP-Adapter model.", title="IP-Adapter Model", input=Input.Direct, ui_order=-1
)
# weight: float = InputField(default=1.0, description="The weight of the IP-Adapter.", ui_type=UIType.Float)
weight: Union[float, List[float]] = InputField(
default=1, ge=0, description="The weight given to the IP-Adapter", ui_type=UIType.Float, title="Weight"
default=1, ge=-1, description="The weight given to the IP-Adapter", ui_type=UIType.Float, title="Weight"
)
begin_step_percent: float = InputField(

165
invokeai/app/invocations/latent.py
View File

@ -19,11 +19,10 @@ from diffusers.models.attention_processor import (
)
from diffusers.schedulers import DPMSolverSDEScheduler
from diffusers.schedulers import SchedulerMixin as Scheduler
from pydantic import validator
from pydantic import field_validator
from torchvision.transforms.functional import resize as tv_resize
from invokeai.app.invocations.ip_adapter import IPAdapterField
from invokeai.app.invocations.metadata import CoreMetadata
from invokeai.app.invocations.primitives import (
DenoiseMaskField,
DenoiseMaskOutput,
@ -64,6 +63,8 @@ from .baseinvocation import (
InvocationContext,
OutputField,
UIType,
WithMetadata,
WithWorkflow,
invocation,
invocation_output,
)
@ -84,12 +85,20 @@ class SchedulerOutput(BaseInvocationOutput):
scheduler: SAMPLER_NAME_VALUES = OutputField(description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler)
@invocation("scheduler", title="Scheduler", tags=["scheduler"], category="latents", version="1.0.0")
@invocation(
"scheduler",
title="Scheduler",
tags=["scheduler"],
category="latents",
version="1.0.0",
)
class SchedulerInvocation(BaseInvocation):
"""Selects a scheduler."""
scheduler: SAMPLER_NAME_VALUES = InputField(
default="euler", description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler
default="euler",
description=FieldDescriptions.scheduler,
ui_type=UIType.Scheduler,
)
def invoke(self, context: InvocationContext) -> SchedulerOutput:
@ -97,7 +106,11 @@ class SchedulerInvocation(BaseInvocation):
@invocation(
"create_denoise_mask", title="Create Denoise Mask", tags=["mask", "denoise"], category="latents", version="1.0.0"
"create_denoise_mask",
title="Create Denoise Mask",
tags=["mask", "denoise"],
category="latents",
version="1.0.0",
)
class CreateDenoiseMaskInvocation(BaseInvocation):
"""Creates mask for denoising model run."""
@ -106,7 +119,11 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
image: Optional[ImageField] = InputField(default=None, description="Image which will be masked", ui_order=1)
mask: ImageField = InputField(description="The mask to use when pasting", ui_order=2)
tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=3)
fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32, ui_order=4)
fp32: bool = InputField(
default=DEFAULT_PRECISION == "float32",
description=FieldDescriptions.fp32,
ui_order=4,
)
def prep_mask_tensor(self, mask_image):
if mask_image.mode != "L":
@ -134,7 +151,7 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
if image is not None:
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
**self.vae.vae.model_dump(),
context=context,
)
@ -167,7 +184,7 @@ def get_scheduler(
) -> Scheduler:
scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
orig_scheduler_info = context.services.model_manager.get_model(
**scheduler_info.dict(),
**scheduler_info.model_dump(),
context=context,
)
with orig_scheduler_info as orig_scheduler:
@ -198,7 +215,7 @@ def get_scheduler(
title="Denoise Latents",
tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
category="latents",
version="1.3.0",
version="1.4.0",
)
class DenoiseLatentsInvocation(BaseInvocation):
"""Denoises noisy latents to decodable images"""
@ -209,34 +226,64 @@ class DenoiseLatentsInvocation(BaseInvocation):
negative_conditioning: ConditioningField = InputField(
description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=1
)
noise: Optional[LatentsField] = InputField(description=FieldDescriptions.noise, input=Input.Connection, ui_order=3)
noise: Optional[LatentsField] = InputField(
default=None,
description=FieldDescriptions.noise,
input=Input.Connection,
ui_order=3,
)
steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
cfg_scale: Union[float, List[float]] = InputField(
default=7.5, ge=1, description=FieldDescriptions.cfg_scale, title="CFG Scale"
)
denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
denoising_start: float = InputField(
default=0.0,
ge=0,
le=1,
description=FieldDescriptions.denoising_start,
)
denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
scheduler: SAMPLER_NAME_VALUES = InputField(
default="euler", description=FieldDescriptions.scheduler, ui_type=UIType.Scheduler
default="euler",
description=FieldDescriptions.scheduler,
ui_type=UIType.Scheduler,
)
unet: UNetField = InputField(description=FieldDescriptions.unet, input=Input.Connection, title="UNet", ui_order=2)
control: Union[ControlField, list[ControlField]] = InputField(
unet: UNetField = InputField(
description=FieldDescriptions.unet,
input=Input.Connection,
title="UNet",
ui_order=2,
)
control: Optional[Union[ControlField, list[ControlField]]] = InputField(
default=None,
input=Input.Connection,
ui_order=5,
)
ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]] = InputField(
description=FieldDescriptions.ip_adapter, title="IP-Adapter", default=None, input=Input.Connection, ui_order=6
description=FieldDescriptions.ip_adapter,
title="IP-Adapter",
default=None,
input=Input.Connection,
ui_order=6,
)
t2i_adapter: Union[T2IAdapterField, list[T2IAdapterField]] = InputField(
description=FieldDescriptions.t2i_adapter, title="T2I-Adapter", default=None, input=Input.Connection, ui_order=7
t2i_adapter: Optional[Union[T2IAdapterField, list[T2IAdapterField]]] = InputField(
description=FieldDescriptions.t2i_adapter,
title="T2I-Adapter",
default=None,
input=Input.Connection,
ui_order=7,
)
latents: Optional[LatentsField] = InputField(
default=None, description=FieldDescriptions.latents, input=Input.Connection
)
latents: Optional[LatentsField] = InputField(description=FieldDescriptions.latents, input=Input.Connection)
denoise_mask: Optional[DenoiseMaskField] = InputField(
default=None, description=FieldDescriptions.mask, input=Input.Connection, ui_order=8
default=None,
description=FieldDescriptions.mask,
input=Input.Connection,
ui_order=8,
)
@validator("cfg_scale")
@field_validator("cfg_scale")
def ge_one(cls, v):
"""validate that all cfg_scale values are >= 1"""
if isinstance(v, list):
@ -259,7 +306,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
stable_diffusion_step_callback(
context=context,
intermediate_state=intermediate_state,
node=self.dict(),
node=self.model_dump(),
source_node_id=source_node_id,
base_model=base_model,
)
@ -445,15 +492,21 @@ class DenoiseLatentsInvocation(BaseInvocation):
context=context,
)
input_image = context.services.images.get_pil_image(single_ip_adapter.image.image_name)
# `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
single_ipa_images = single_ip_adapter.image
if not isinstance(single_ipa_images, list):
single_ipa_images = [single_ipa_images]
single_ipa_images = [context.services.images.get_pil_image(image.image_name) for image in single_ipa_images]
# TODO(ryand): With some effort, the step of running the CLIP Vision encoder could be done before any other
# models are needed in memory. This would help to reduce peak memory utilization in low-memory environments.
with image_encoder_model_info as image_encoder_model:
# Get image embeddings from CLIP and ImageProjModel.
image_prompt_embeds, uncond_image_prompt_embeds = ip_adapter_model.get_image_embeds(
input_image, image_encoder_model
single_ipa_images, image_encoder_model
)
conditioning_data.ip_adapter_conditioning.append(
IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
)
@ -628,7 +681,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
# TODO(ryand): I have hard-coded `do_classifier_free_guidance=True` to mirror the behaviour of ControlNets,
# below. Investigate whether this is appropriate.
t2i_adapter_data = self.run_t2i_adapters(
context, self.t2i_adapter, latents.shape, do_classifier_free_guidance=True
context,
self.t2i_adapter,
latents.shape,
do_classifier_free_guidance=True,
)
# Get the source node id (we are invoking the prepared node)
@ -641,7 +697,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
def _lora_loader():
for lora in self.unet.loras:
lora_info = context.services.model_manager.get_model(
**lora.dict(exclude={"weight"}),
**lora.model_dump(exclude={"weight"}),
context=context,
)
yield (lora_info.context.model, lora.weight)
@ -649,14 +705,17 @@ class DenoiseLatentsInvocation(BaseInvocation):
return
unet_info = context.services.model_manager.get_model(
**self.unet.unet.dict(),
**self.unet.unet.model_dump(),
context=context,
)
with (
ExitStack() as exit_stack,
ModelPatcher.apply_lora_unet(unet_info.context.model, _lora_loader()),
ModelPatcher.apply_freeu(unet_info.context.model, self.unet.freeu_config),
set_seamless(unet_info.context.model, self.unet.seamless_axes),
unet_info as unet,
# Apply the LoRA after unet has been moved to its target device for faster patching.
ModelPatcher.apply_lora_unet(unet, _lora_loader()),
):
latents = latents.to(device=unet.device, dtype=unet.dtype)
if noise is not None:
@ -700,7 +759,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
denoising_end=self.denoising_end,
)
result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
(
result_latents,
result_attention_map_saver,
) = pipeline.latents_from_embeddings(
latents=latents,
timesteps=timesteps,
init_timestep=init_timestep,
@ -728,9 +790,13 @@ class DenoiseLatentsInvocation(BaseInvocation):
@invocation(
"l2i", title="Latents to Image", tags=["latents", "image", "vae", "l2i"], category="latents", version="1.0.0"
"l2i",
title="Latents to Image",
tags=["latents", "image", "vae", "l2i"],
category="latents",
version="1.0.0",
)
class LatentsToImageInvocation(BaseInvocation):
class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Generates an image from latents."""
latents: LatentsField = InputField(
@ -743,18 +809,13 @@ class LatentsToImageInvocation(BaseInvocation):
)
tiled: bool = InputField(default=False, description=FieldDescriptions.tiled)
fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
metadata: CoreMetadata = InputField(
default=None,
description=FieldDescriptions.core_metadata,
ui_hidden=True,
)
@torch.no_grad()
def invoke(self, context: InvocationContext) -> ImageOutput:
latents = context.services.latents.get(self.latents.latents_name)
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
**self.vae.vae.model_dump(),
context=context,
)
@ -816,7 +877,7 @@ class LatentsToImageInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
metadata=self.metadata,
workflow=self.workflow,
)
@ -830,7 +891,13 @@ class LatentsToImageInvocation(BaseInvocation):
LATENTS_INTERPOLATION_MODE = Literal["nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"]
@invocation("lresize", title="Resize Latents", tags=["latents", "resize"], category="latents", version="1.0.0")
@invocation(
"lresize",
title="Resize Latents",
tags=["latents", "resize"],
category="latents",
version="1.0.0",
)
class ResizeLatentsInvocation(BaseInvocation):
"""Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
@ -876,7 +943,13 @@ class ResizeLatentsInvocation(BaseInvocation):
return build_latents_output(latents_name=name, latents=resized_latents, seed=self.latents.seed)
@invocation("lscale", title="Scale Latents", tags=["latents", "resize"], category="latents", version="1.0.0")
@invocation(
"lscale",
title="Scale Latents",
tags=["latents", "resize"],
category="latents",
version="1.0.0",
)
class ScaleLatentsInvocation(BaseInvocation):
"""Scales latents by a given factor."""
@ -915,7 +988,11 @@ class ScaleLatentsInvocation(BaseInvocation):
@invocation(
"i2l", title="Image to Latents", tags=["latents", "image", "vae", "i2l"], category="latents", version="1.0.0"
"i2l",
title="Image to Latents",
tags=["latents", "image", "vae", "i2l"],
category="latents",
version="1.0.0",
)
class ImageToLatentsInvocation(BaseInvocation):
"""Encodes an image into latents."""
@ -979,7 +1056,7 @@ class ImageToLatentsInvocation(BaseInvocation):
image = context.services.images.get_pil_image(self.image.image_name)
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
**self.vae.vae.model_dump(),
context=context,
)
@ -1007,7 +1084,13 @@ class ImageToLatentsInvocation(BaseInvocation):
return vae.encode(image_tensor).latents
@invocation("lblend", title="Blend Latents", tags=["latents", "blend"], category="latents", version="1.0.0")
@invocation(
"lblend",
title="Blend Latents",
tags=["latents", "blend"],
category="latents",
version="1.0.0",
)
class BlendLatentsInvocation(BaseInvocation):
"""Blend two latents using a given alpha. Latents must have same size."""

39
invokeai/app/invocations/math.py
View File

@ -3,7 +3,7 @@
from typing import Literal
import numpy as np
from pydantic import validator
from pydantic import ValidationInfo, field_validator
from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
@ -72,7 +72,14 @@ class RandomIntInvocation(BaseInvocation):
return IntegerOutput(value=np.random.randint(self.low, self.high))
@invocation("rand_float", title="Random Float", tags=["math", "float", "random"], category="math", version="1.0.0")
@invocation(
"rand_float",
title="Random Float",
tags=["math", "float", "random"],
category="math",
version="1.0.1",
use_cache=False,
)
class RandomFloatInvocation(BaseInvocation):
"""Outputs a single random float"""
@ -175,16 +182,16 @@ class IntegerMathInvocation(BaseInvocation):
operation: INTEGER_OPERATIONS = InputField(
default="ADD", description="The operation to perform", ui_choice_labels=INTEGER_OPERATIONS_LABELS
)
a: int = InputField(default=0, description=FieldDescriptions.num_1)
b: int = InputField(default=0, description=FieldDescriptions.num_2)
a: int = InputField(default=1, description=FieldDescriptions.num_1)
b: int = InputField(default=1, description=FieldDescriptions.num_2)
@validator("b")
def no_unrepresentable_results(cls, v, values):
if values["operation"] == "DIV" and v == 0:
@field_validator("b")
def no_unrepresentable_results(cls, v: int, info: ValidationInfo):
if info.data["operation"] == "DIV" and v == 0:
raise ValueError("Cannot divide by zero")
elif values["operation"] == "MOD" and v == 0:
elif info.data["operation"] == "MOD" and v == 0:
raise ValueError("Cannot divide by zero")
elif values["operation"] == "EXP" and v < 0:
elif info.data["operation"] == "EXP" and v < 0:
raise ValueError("Result of exponentiation is not an integer")
return v
@ -249,16 +256,16 @@ class FloatMathInvocation(BaseInvocation):
operation: FLOAT_OPERATIONS = InputField(
default="ADD", description="The operation to perform", ui_choice_labels=FLOAT_OPERATIONS_LABELS
)
a: float = InputField(default=0, description=FieldDescriptions.num_1)
b: float = InputField(default=0, description=FieldDescriptions.num_2)
a: float = InputField(default=1, description=FieldDescriptions.num_1)
b: float = InputField(default=1, description=FieldDescriptions.num_2)
@validator("b")
def no_unrepresentable_results(cls, v, values):
if values["operation"] == "DIV" and v == 0:
@field_validator("b")
def no_unrepresentable_results(cls, v: float, info: ValidationInfo):
if info.data["operation"] == "DIV" and v == 0:
raise ValueError("Cannot divide by zero")
elif values["operation"] == "EXP" and values["a"] == 0 and v < 0:
elif info.data["operation"] == "EXP" and info.data["a"] == 0 and v < 0:
raise ValueError("Cannot raise zero to a negative power")
elif values["operation"] == "EXP" and type(values["a"] ** v) is complex:
elif info.data["operation"] == "EXP" and type(info.data["a"] ** v) is complex:
raise ValueError("Root operation resulted in a complex number")
return v

233
invokeai/app/invocations/metadata.py
View File

@ -1,13 +1,16 @@
from typing import Optional
from typing import Any, Literal, Optional, Union
from pydantic import Field
from pydantic import BaseModel, ConfigDict, Field
from invokeai.app.invocations.baseinvocation import (
BaseInvocation,
BaseInvocationOutput,
FieldDescriptions,
InputField,
InvocationContext,
MetadataField,
OutputField,
UIType,
invocation,
invocation_output,
)
@ -16,133 +19,133 @@ from invokeai.app.invocations.ip_adapter import IPAdapterModelField
from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
from invokeai.app.invocations.primitives import ImageField
from invokeai.app.invocations.t2i_adapter import T2IAdapterField
from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
from ...version import __version__
class LoRAMetadataField(BaseModelExcludeNull):
"""LoRA metadata for an image generated in InvokeAI."""
lora: LoRAModelField = Field(description="The LoRA model")
weight: float = Field(description="The weight of the LoRA model")
class MetadataItemField(BaseModel):
label: str = Field(description=FieldDescriptions.metadata_item_label)
value: Any = Field(description=FieldDescriptions.metadata_item_value)
class IPAdapterMetadataField(BaseModelExcludeNull):
class LoRAMetadataField(BaseModel):
"""LoRA Metadata Field"""
lora: LoRAModelField = Field(description=FieldDescriptions.lora_model)
weight: float = Field(description=FieldDescriptions.lora_weight)
class IPAdapterMetadataField(BaseModel):
"""IP Adapter Field, minus the CLIP Vision Encoder model"""
image: ImageField = Field(description="The IP-Adapter image prompt.")
ip_adapter_model: IPAdapterModelField = Field(description="The IP-Adapter model to use.")
weight: float = Field(description="The weight of the IP-Adapter model")
begin_step_percent: float = Field(
default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
ip_adapter_model: IPAdapterModelField = Field(
description="The IP-Adapter model.",
)
end_step_percent: float = Field(
default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
weight: Union[float, list[float]] = Field(
description="The weight given to the IP-Adapter",
)
begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")
end_step_percent: float = Field(description="When the IP-Adapter is last applied (% of total steps)")
@invocation_output("metadata_item_output")
class MetadataItemOutput(BaseInvocationOutput):
"""Metadata Item Output"""
item: MetadataItemField = OutputField(description="Metadata Item")
@invocation("metadata_item", title="Metadata Item", tags=["metadata"], category="metadata", version="1.0.0")
class MetadataItemInvocation(BaseInvocation):
"""Used to create an arbitrary metadata item. Provide "label" and make a connection to "value" to store that data as the value."""
label: str = InputField(description=FieldDescriptions.metadata_item_label)
value: Any = InputField(description=FieldDescriptions.metadata_item_value, ui_type=UIType.Any)
def invoke(self, context: InvocationContext) -> MetadataItemOutput:
return MetadataItemOutput(item=MetadataItemField(label=self.label, value=self.value))
@invocation_output("metadata_output")
class MetadataOutput(BaseInvocationOutput):
metadata: MetadataField = OutputField(description="Metadata Dict")
@invocation("metadata", title="Metadata", tags=["metadata"], category="metadata", version="1.0.0")
class MetadataInvocation(BaseInvocation):
"""Takes a MetadataItem or collection of MetadataItems and outputs a MetadataDict."""
items: Union[list[MetadataItemField], MetadataItemField] = InputField(
description=FieldDescriptions.metadata_item_polymorphic
)
def invoke(self, context: InvocationContext) -> MetadataOutput:
if isinstance(self.items, MetadataItemField):
# single metadata item
data = {self.items.label: self.items.value}
else:
# collection of metadata items
data = {item.label: item.value for item in self.items}
class CoreMetadata(BaseModelExcludeNull):
"""Core generation metadata for an image generated in InvokeAI."""
# add app version
data.update({"app_version": __version__})
return MetadataOutput(metadata=MetadataField.model_validate(data))
app_version: str = Field(default=__version__, description="The version of InvokeAI used to generate this image")
generation_mode: str = Field(
@invocation("merge_metadata", title="Metadata Merge", tags=["metadata"], category="metadata", version="1.0.0")
class MergeMetadataInvocation(BaseInvocation):
"""Merged a collection of MetadataDict into a single MetadataDict."""
collection: list[MetadataField] = InputField(description=FieldDescriptions.metadata_collection)
def invoke(self, context: InvocationContext) -> MetadataOutput:
data = {}
for item in self.collection:
data.update(item.model_dump())
return MetadataOutput(metadata=MetadataField.model_validate(data))
GENERATION_MODES = Literal[
"txt2img", "img2img", "inpaint", "outpaint", "sdxl_txt2img", "sdxl_img2img", "sdxl_inpaint", "sdxl_outpaint"
]
@invocation("core_metadata", title="Core Metadata", tags=["metadata"], category="metadata", version="1.0.0")
class CoreMetadataInvocation(BaseInvocation):
"""Collects core generation metadata into a MetadataField"""
generation_mode: Optional[GENERATION_MODES] = InputField(
default=None,
description="The generation mode that output this image",
)
created_by: Optional[str] = Field(description="The name of the creator of the image")
positive_prompt: str = Field(description="The positive prompt parameter")
negative_prompt: str = Field(description="The negative prompt parameter")
width: int = Field(description="The width parameter")
height: int = Field(description="The height parameter")
seed: int = Field(description="The seed used for noise generation")
rand_device: str = Field(description="The device used for random number generation")
cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
steps: int = Field(description="The number of steps used for inference")
scheduler: str = Field(description="The scheduler used for inference")
clip_skip: Optional[int] = Field(
positive_prompt: Optional[str] = InputField(default=None, description="The positive prompt parameter")
negative_prompt: Optional[str] = InputField(default=None, description="The negative prompt parameter")
width: Optional[int] = InputField(default=None, description="The width parameter")
height: Optional[int] = InputField(default=None, description="The height parameter")
seed: Optional[int] = InputField(default=None, description="The seed used for noise generation")
rand_device: Optional[str] = InputField(default=None, description="The device used for random number generation")
cfg_scale: Optional[float] = InputField(default=None, description="The classifier-free guidance scale parameter")
steps: Optional[int] = InputField(default=None, description="The number of steps used for inference")
scheduler: Optional[str] = InputField(default=None, description="The scheduler used for inference")
seamless_x: Optional[bool] = InputField(default=None, description="Whether seamless tiling was used on the X axis")
seamless_y: Optional[bool] = InputField(default=None, description="Whether seamless tiling was used on the Y axis")
clip_skip: Optional[int] = InputField(
default=None,
description="The number of skipped CLIP layers",
)
model: MainModelField = Field(description="The main model used for inference")
controlnets: list[ControlField] = Field(description="The ControlNets used for inference")
ipAdapters: list[IPAdapterMetadataField] = Field(description="The IP Adapters used for inference")
t2iAdapters: list[T2IAdapterField] = Field(description="The IP Adapters used for inference")
loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
vae: Optional[VAEModelField] = Field(
default=None,
description="The VAE used for decoding, if the main model's default was not used",
model: Optional[MainModelField] = InputField(default=None, description="The main model used for inference")
controlnets: Optional[list[ControlField]] = InputField(
default=None, description="The ControlNets used for inference"
)
# Latents-to-Latents
strength: Optional[float] = Field(
default=None,
description="The strength used for latents-to-latents",
ipAdapters: Optional[list[IPAdapterMetadataField]] = InputField(
default=None, description="The IP Adapters used for inference"
)
init_image: Optional[str] = Field(default=None, description="The name of the initial image")
# SDXL
positive_style_prompt: Optional[str] = Field(default=None, description="The positive style prompt parameter")
negative_style_prompt: Optional[str] = Field(default=None, description="The negative style prompt parameter")
# SDXL Refiner
refiner_model: Optional[MainModelField] = Field(default=None, description="The SDXL Refiner model used")
refiner_cfg_scale: Optional[float] = Field(
default=None,
description="The classifier-free guidance scale parameter used for the refiner",
t2iAdapters: Optional[list[T2IAdapterField]] = InputField(
default=None, description="The IP Adapters used for inference"
)
refiner_steps: Optional[int] = Field(default=None, description="The number of steps used for the refiner")
refiner_scheduler: Optional[str] = Field(default=None, description="The scheduler used for the refiner")
refiner_positive_aesthetic_score: Optional[float] = Field(
default=None, description="The aesthetic score used for the refiner"
)
refiner_negative_aesthetic_score: Optional[float] = Field(
default=None, description="The aesthetic score used for the refiner"
)
refiner_start: Optional[float] = Field(default=None, description="The start value used for refiner denoising")
class ImageMetadata(BaseModelExcludeNull):
"""An image's generation metadata"""
metadata: Optional[dict] = Field(
default=None,
description="The image's core metadata, if it was created in the Linear or Canvas UI",
)
graph: Optional[dict] = Field(default=None, description="The graph that created the image")
@invocation_output("metadata_accumulator_output")
class MetadataAccumulatorOutput(BaseInvocationOutput):
"""The output of the MetadataAccumulator node"""
metadata: CoreMetadata = OutputField(description="The core metadata for the image")
@invocation(
"metadata_accumulator", title="Metadata Accumulator", tags=["metadata"], category="metadata", version="1.0.0"
)
class MetadataAccumulatorInvocation(BaseInvocation):
"""Outputs a Core Metadata Object"""
generation_mode: str = InputField(
description="The generation mode that output this image",
)
positive_prompt: str = InputField(description="The positive prompt parameter")
negative_prompt: str = InputField(description="The negative prompt parameter")
width: int = InputField(description="The width parameter")
height: int = InputField(description="The height parameter")
seed: int = InputField(description="The seed used for noise generation")
rand_device: str = InputField(description="The device used for random number generation")
cfg_scale: float = InputField(description="The classifier-free guidance scale parameter")
steps: int = InputField(description="The number of steps used for inference")
scheduler: str = InputField(description="The scheduler used for inference")
clip_skip: Optional[int] = Field(
default=None,
description="The number of skipped CLIP layers",
)
model: MainModelField = InputField(description="The main model used for inference")
controlnets: list[ControlField] = InputField(description="The ControlNets used for inference")
ipAdapters: list[IPAdapterMetadataField] = InputField(description="The IP Adapters used for inference")
t2iAdapters: list[T2IAdapterField] = Field(description="The IP Adapters used for inference")
loras: list[LoRAMetadataField] = InputField(description="The LoRAs used for inference")
loras: Optional[list[LoRAMetadataField]] = InputField(default=None, description="The LoRAs used for inference")
strength: Optional[float] = InputField(
default=None,
description="The strength used for latents-to-latents",
@ -158,9 +161,11 @@ class MetadataAccumulatorInvocation(BaseInvocation):
# High resolution fix metadata.
hrf_width: Optional[int] = InputField(
default=None,
description="The high resolution fix height and width multipler.",
)
hrf_height: Optional[int] = InputField(
default=None,
description="The high resolution fix height and width multipler.",
)
hrf_strength: Optional[float] = InputField(
@ -208,7 +213,13 @@ class MetadataAccumulatorInvocation(BaseInvocation):
description="The start value used for refiner denoising",
)
def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
def invoke(self, context: InvocationContext) -> MetadataOutput:
"""Collects and outputs a CoreMetadata object"""
return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.dict()))
return MetadataOutput(
metadata=MetadataField.model_validate(
self.model_dump(exclude_none=True, exclude={"id", "type", "is_intermediate", "use_cache"})
)
)
model_config = ConfigDict(extra="allow")

138
invokeai/app/invocations/model.py
View File

@ -1,7 +1,9 @@
import copy
from typing import List, Optional
from pydantic import BaseModel, Field
from pydantic import BaseModel, ConfigDict, Field
from invokeai.app.invocations.shared import FreeUConfig
from ...backend.model_management import BaseModelType, ModelType, SubModelType
from .baseinvocation import (
@ -24,6 +26,8 @@ class ModelInfo(BaseModel):
model_type: ModelType = Field(description="Info to load submodel")
submodel: Optional[SubModelType] = Field(default=None, description="Info to load submodel")
model_config = ConfigDict(protected_namespaces=())
class LoraInfo(ModelInfo):
weight: float = Field(description="Lora's weight which to use when apply to model")
@ -34,6 +38,7 @@ class UNetField(BaseModel):
scheduler: ModelInfo = Field(description="Info to load scheduler submodel")
loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
freeu_config: Optional[FreeUConfig] = Field(default=None, description="FreeU configuration")
class ClipField(BaseModel):
@ -49,15 +54,34 @@ class VaeField(BaseModel):
seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
@invocation_output("model_loader_output")
class ModelLoaderOutput(BaseInvocationOutput):
"""Model loader output"""
@invocation_output("unet_output")
class UNetOutput(BaseInvocationOutput):
"""Base class for invocations that output a UNet field"""
unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP")
@invocation_output("vae_output")
class VAEOutput(BaseInvocationOutput):
"""Base class for invocations that output a VAE field"""
vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
@invocation_output("clip_output")
class CLIPOutput(BaseInvocationOutput):
"""Base class for invocations that output a CLIP field"""
clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP")
@invocation_output("model_loader_output")
class ModelLoaderOutput(UNetOutput, CLIPOutput, VAEOutput):
"""Model loader output"""
pass
class MainModelField(BaseModel):
"""Main model field"""
@ -65,6 +89,8 @@ class MainModelField(BaseModel):
base_model: BaseModelType = Field(description="Base model")
model_type: ModelType = Field(description="Model Type")
model_config = ConfigDict(protected_namespaces=())
class LoRAModelField(BaseModel):
"""LoRA model field"""
@ -72,8 +98,16 @@ class LoRAModelField(BaseModel):
model_name: str = Field(description="Name of the LoRA model")
base_model: BaseModelType = Field(description="Base model")
model_config = ConfigDict(protected_namespaces=())
@invocation("main_model_loader", title="Main Model", tags=["model"], category="model", version="1.0.0")
@invocation(
"main_model_loader",
title="Main Model",
tags=["model"],
category="model",
version="1.0.0",
)
class MainModelLoaderInvocation(BaseInvocation):
"""Loads a main model, outputting its submodels."""
@ -180,10 +214,16 @@ class LoraLoaderInvocation(BaseInvocation):
lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
unet: Optional[UNetField] = InputField(
default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
default=None,
description=FieldDescriptions.unet,
input=Input.Connection,
title="UNet",
)
clip: Optional[ClipField] = InputField(
default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP"
default=None,
description=FieldDescriptions.clip,
input=Input.Connection,
title="CLIP",
)
def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
@ -244,20 +284,35 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
clip2: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
@invocation("sdxl_lora_loader", title="SDXL LoRA", tags=["lora", "model"], category="model", version="1.0.0")
@invocation(
"sdxl_lora_loader",
title="SDXL LoRA",
tags=["lora", "model"],
category="model",
version="1.0.0",
)
class SDXLLoraLoaderInvocation(BaseInvocation):
"""Apply selected lora to unet and text_encoder."""
lora: LoRAModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
weight: float = InputField(default=0.75, description=FieldDescriptions.lora_weight)
unet: Optional[UNetField] = InputField(
default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
default=None,
description=FieldDescriptions.unet,
input=Input.Connection,
title="UNet",
)
clip: Optional[ClipField] = InputField(
default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1"
default=None,
description=FieldDescriptions.clip,
input=Input.Connection,
title="CLIP 1",
)
clip2: Optional[ClipField] = InputField(
default=None, description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2"
default=None,
description=FieldDescriptions.clip,
input=Input.Connection,
title="CLIP 2",
)
def invoke(self, context: InvocationContext) -> SDXLLoraLoaderOutput:
@ -330,12 +385,7 @@ class VAEModelField(BaseModel):
model_name: str = Field(description="Name of the model")
base_model: BaseModelType = Field(description="Base model")
@invocation_output("vae_loader_output")
class VaeLoaderOutput(BaseInvocationOutput):
"""VAE output"""
vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
model_config = ConfigDict(protected_namespaces=())
@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.0")
@ -343,10 +393,13 @@ class VaeLoaderInvocation(BaseInvocation):
"""Loads a VAE model, outputting a VaeLoaderOutput"""
vae_model: VAEModelField = InputField(
description=FieldDescriptions.vae_model, input=Input.Direct, ui_type=UIType.VaeModel, title="VAE"
description=FieldDescriptions.vae_model,
input=Input.Direct,
ui_type=UIType.VaeModel,
title="VAE",
)
def invoke(self, context: InvocationContext) -> VaeLoaderOutput:
def invoke(self, context: InvocationContext) -> VAEOutput:
base_model = self.vae_model.base_model
model_name = self.vae_model.model_name
model_type = ModelType.Vae
@ -357,7 +410,7 @@ class VaeLoaderInvocation(BaseInvocation):
model_type=model_type,
):
raise Exception(f"Unkown vae name: {model_name}!")
return VaeLoaderOutput(
return VAEOutput(
vae=VaeField(
vae=ModelInfo(
model_name=model_name,
@ -372,19 +425,31 @@ class VaeLoaderInvocation(BaseInvocation):
class SeamlessModeOutput(BaseInvocationOutput):
"""Modified Seamless Model output"""
unet: Optional[UNetField] = OutputField(description=FieldDescriptions.unet, title="UNet")
vae: Optional[VaeField] = OutputField(description=FieldDescriptions.vae, title="VAE")
unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
vae: Optional[VaeField] = OutputField(default=None, description=FieldDescriptions.vae, title="VAE")
@invocation("seamless", title="Seamless", tags=["seamless", "model"], category="model", version="1.0.0")
@invocation(
"seamless",
title="Seamless",
tags=["seamless", "model"],
category="model",
version="1.0.0",
)
class SeamlessModeInvocation(BaseInvocation):
"""Applies the seamless transformation to the Model UNet and VAE."""
unet: Optional[UNetField] = InputField(
default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
default=None,
description=FieldDescriptions.unet,
input=Input.Connection,
title="UNet",
)
vae: Optional[VaeField] = InputField(
default=None, description=FieldDescriptions.vae_model, input=Input.Connection, title="VAE"
default=None,
description=FieldDescriptions.vae_model,
input=Input.Connection,
title="VAE",
)
seamless_y: bool = InputField(default=True, input=Input.Any, description="Specify whether Y axis is seamless")
seamless_x: bool = InputField(default=True, input=Input.Any, description="Specify whether X axis is seamless")
@ -407,3 +472,24 @@ class SeamlessModeInvocation(BaseInvocation):
vae.seamless_axes = seamless_axes_list
return SeamlessModeOutput(unet=unet, vae=vae)
@invocation("freeu", title="FreeU", tags=["freeu"], category="unet", version="1.0.0")
class FreeUInvocation(BaseInvocation):
"""
Applies FreeU to the UNet. Suggested values (b1/b2/s1/s2):
SD1.5: 1.2/1.4/0.9/0.2,
SD2: 1.1/1.2/0.9/0.2,
SDXL: 1.1/1.2/0.6/0.4,
"""
unet: UNetField = InputField(description=FieldDescriptions.unet, input=Input.Connection, title="UNet")
b1: float = InputField(default=1.2, ge=-1, le=3, description=FieldDescriptions.freeu_b1)
b2: float = InputField(default=1.4, ge=-1, le=3, description=FieldDescriptions.freeu_b2)
s1: float = InputField(default=0.9, ge=-1, le=3, description=FieldDescriptions.freeu_s1)
s2: float = InputField(default=0.2, ge=-1, le=3, description=FieldDescriptions.freeu_s2)
def invoke(self, context: InvocationContext) -> UNetOutput:
self.unet.freeu_config = FreeUConfig(s1=self.s1, s2=self.s2, b1=self.b1, b2=self.b2)
return UNetOutput(unet=self.unet)

14
invokeai/app/invocations/noise.py
View File

@ -2,7 +2,7 @@
import torch
from pydantic import validator
from pydantic import field_validator
from invokeai.app.invocations.latent import LatentsField
from invokeai.app.util.misc import SEED_MAX, get_random_seed
@ -65,7 +65,7 @@ Nodes
class NoiseOutput(BaseInvocationOutput):
"""Invocation noise output"""
noise: LatentsField = OutputField(default=None, description=FieldDescriptions.noise)
noise: LatentsField = OutputField(description=FieldDescriptions.noise)
width: int = OutputField(description=FieldDescriptions.width)
height: int = OutputField(description=FieldDescriptions.height)
@ -78,7 +78,13 @@ def build_noise_output(latents_name: str, latents: torch.Tensor, seed: int):
)
@invocation("noise", title="Noise", tags=["latents", "noise"], category="latents", version="1.0.0")
@invocation(
"noise",
title="Noise",
tags=["latents", "noise"],
category="latents",
version="1.0.0",
)
class NoiseInvocation(BaseInvocation):
"""Generates latent noise."""
@ -105,7 +111,7 @@ class NoiseInvocation(BaseInvocation):
description="Use CPU for noise generation (for reproducible results across platforms)",
)
@validator("seed", pre=True)
@field_validator("seed", mode="before")
def modulo_seed(cls, v):
"""Returns the seed modulo (SEED_MAX + 1) to ensure it is within the valid range."""
return v % (SEED_MAX + 1)

42
invokeai/app/invocations/onnx.py
View File

@ -4,15 +4,14 @@ import inspect
import re
# from contextlib import ExitStack
from typing import List, Literal, Optional, Union
from typing import List, Literal, Union
import numpy as np
import torch
from diffusers.image_processor import VaeImageProcessor
from pydantic import BaseModel, Field, validator
from pydantic import BaseModel, ConfigDict, Field, field_validator
from tqdm import tqdm
from invokeai.app.invocations.metadata import CoreMetadata
from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput, ImageField, ImageOutput
from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
from invokeai.app.util.step_callback import stable_diffusion_step_callback
@ -31,6 +30,8 @@ from .baseinvocation import (
OutputField,
UIComponent,
UIType,
WithMetadata,
WithWorkflow,
invocation,
invocation_output,
)
@ -63,14 +64,17 @@ class ONNXPromptInvocation(BaseInvocation):
def invoke(self, context: InvocationContext) -> ConditioningOutput:
tokenizer_info = context.services.model_manager.get_model(
**self.clip.tokenizer.dict(),
**self.clip.tokenizer.model_dump(),
)
text_encoder_info = context.services.model_manager.get_model(
**self.clip.text_encoder.dict(),
**self.clip.text_encoder.model_dump(),
)
with tokenizer_info as orig_tokenizer, text_encoder_info as text_encoder: # , ExitStack() as stack:
loras = [
(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight)
(
context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
lora.weight,
)
for lora in self.clip.loras
]
@ -175,14 +179,14 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
description=FieldDescriptions.unet,
input=Input.Connection,
)
control: Optional[Union[ControlField, list[ControlField]]] = InputField(
control: Union[ControlField, list[ControlField]] = InputField(
default=None,
description=FieldDescriptions.control,
)
# seamless: bool = InputField(default=False, description="Whether or not to generate an image that can tile without seams", )
# seamless_axes: str = InputField(default="", description="The axes to tile the image on, 'x' and/or 'y'")
@validator("cfg_scale")
@field_validator("cfg_scale")
def ge_one(cls, v):
"""validate that all cfg_scale values are >= 1"""
if isinstance(v, list):
@ -241,7 +245,7 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
stable_diffusion_step_callback(
context=context,
intermediate_state=intermediate_state,
node=self.dict(),
node=self.model_dump(),
source_node_id=source_node_id,
)
@ -254,12 +258,15 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
eta=0.0,
)
unet_info = context.services.model_manager.get_model(**self.unet.unet.dict())
unet_info = context.services.model_manager.get_model(**self.unet.unet.model_dump())
with unet_info as unet: # , ExitStack() as stack:
# loras = [(stack.enter_context(context.services.model_manager.get_model(**lora.dict(exclude={"weight"}))), lora.weight) for lora in self.unet.loras]
loras = [
(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight)
(
context.services.model_manager.get_model(**lora.model_dump(exclude={"weight"})).context.model,
lora.weight,
)
for lora in self.unet.loras
]
@ -321,7 +328,7 @@ class ONNXTextToLatentsInvocation(BaseInvocation):
category="image",
version="1.0.0",
)
class ONNXLatentsToImageInvocation(BaseInvocation):
class ONNXLatentsToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
"""Generates an image from latents."""
latents: LatentsField = InputField(
@ -332,11 +339,6 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
description=FieldDescriptions.vae,
input=Input.Connection,
)
metadata: Optional[CoreMetadata] = InputField(
default=None,
description=FieldDescriptions.core_metadata,
ui_hidden=True,
)
# tiled: bool = InputField(default=False, description="Decode latents by overlaping tiles(less memory consumption)")
def invoke(self, context: InvocationContext) -> ImageOutput:
@ -346,7 +348,7 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
raise Exception(f"Expected vae_decoder, found: {self.vae.vae.model_type}")
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
**self.vae.vae.model_dump(),
)
# clear memory as vae decode can request a lot
@ -375,7 +377,7 @@ class ONNXLatentsToImageInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
metadata=self.metadata,
workflow=self.workflow,
)
@ -403,6 +405,8 @@ class OnnxModelField(BaseModel):
base_model: BaseModelType = Field(description="Base model")
model_type: ModelType = Field(description="Model Type")
model_config = ConfigDict(protected_namespaces=())
@invocation("onnx_model_loader", title="ONNX Main Model", tags=["onnx", "model"], category="model", version="1.0.0")
class OnnxModelLoaderInvocation(BaseInvocation):

31
invokeai/app/invocations/param_easing.py
View File

@ -44,13 +44,22 @@ from invokeai.app.invocations.primitives import FloatCollectionOutput
from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
@invocation("float_range", title="Float Range", tags=["math", "range"], category="math", version="1.0.0")
@invocation(
"float_range",
title="Float Range",
tags=["math", "range"],
category="math",
version="1.0.0",
)
class FloatLinearRangeInvocation(BaseInvocation):
"""Creates a range"""
start: float = InputField(default=5, description="The first value of the range")
stop: float = InputField(default=10, description="The last value of the range")
steps: int = InputField(default=30, description="number of values to interpolate over (including start and stop)")
steps: int = InputField(
default=30,
description="number of values to interpolate over (including start and stop)",
)
def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
param_list = list(np.linspace(self.start, self.stop, self.steps))
@ -95,7 +104,13 @@ EASING_FUNCTION_KEYS = Literal[tuple(list(EASING_FUNCTIONS_MAP.keys()))]
# actually I think for now could just use CollectionOutput (which is list[Any]
@invocation("step_param_easing", title="Step Param Easing", tags=["step", "easing"], category="step", version="1.0.0")
@invocation(
"step_param_easing",
title="Step Param Easing",
tags=["step", "easing"],
category="step",
version="1.0.0",
)
class StepParamEasingInvocation(BaseInvocation):
"""Experimental per-step parameter easing for denoising steps"""
@ -159,7 +174,9 @@ class StepParamEasingInvocation(BaseInvocation):
context.services.logger.debug("base easing duration: " + str(base_easing_duration))
even_num_steps = num_easing_steps % 2 == 0 # even number of steps
easing_function = easing_class(
start=self.start_value, end=self.end_value, duration=base_easing_duration - 1
start=self.start_value,
end=self.end_value,
duration=base_easing_duration - 1,
)
base_easing_vals = list()
for step_index in range(base_easing_duration):
@ -199,7 +216,11 @@ class StepParamEasingInvocation(BaseInvocation):
#
else: # no mirroring (default)
easing_function = easing_class(start=self.start_value, end=self.end_value, duration=num_easing_steps - 1)
easing_function = easing_class(
start=self.start_value,
end=self.end_value,
duration=num_easing_steps - 1,
)
for step_index in range(num_easing_steps):
step_val = easing_function.ease(step_index)
easing_list.append(step_val)

6
invokeai/app/invocations/primitives.py
View File

@ -251,7 +251,9 @@ class ImageCollectionOutput(BaseInvocationOutput):
@invocation("image", title="Image Primitive", tags=["primitives", "image"], category="primitives", version="1.0.0")
class ImageInvocation(BaseInvocation):
class ImageInvocation(
BaseInvocation,
):
"""An image primitive value"""
image: ImageField = InputField(description="The image to load")
@ -291,7 +293,7 @@ class DenoiseMaskField(BaseModel):
"""An inpaint mask field"""
mask_name: str = Field(description="The name of the mask image")
masked_latents_name: Optional[str] = Field(description="The name of the masked image latents")
masked_latents_name: Optional[str] = Field(default=None, description="The name of the masked image latents")
@invocation_output("denoise_mask_output")

31
invokeai/app/invocations/prompt.py
View File

@ -3,7 +3,7 @@ from typing import Optional, Union
import numpy as np
from dynamicprompts.generators import CombinatorialPromptGenerator, RandomPromptGenerator
from pydantic import validator
from pydantic import field_validator
from invokeai.app.invocations.primitives import StringCollectionOutput
@ -21,7 +21,10 @@ from .baseinvocation import BaseInvocation, InputField, InvocationContext, UICom
class DynamicPromptInvocation(BaseInvocation):
"""Parses a prompt using adieyal/dynamicprompts' random or combinatorial generator"""
prompt: str = InputField(description="The prompt to parse with dynamicprompts", ui_component=UIComponent.Textarea)
prompt: str = InputField(
description="The prompt to parse with dynamicprompts",
ui_component=UIComponent.Textarea,
)
max_prompts: int = InputField(default=1, description="The number of prompts to generate")
combinatorial: bool = InputField(default=False, description="Whether to use the combinatorial generator")
@ -36,21 +39,31 @@ class DynamicPromptInvocation(BaseInvocation):
return StringCollectionOutput(collection=prompts)
@invocation("prompt_from_file", title="Prompts from File", tags=["prompt", "file"], category="prompt", version="1.0.0")
@invocation(
"prompt_from_file",
title="Prompts from File",
tags=["prompt", "file"],
category="prompt",
version="1.0.0",
)
class PromptsFromFileInvocation(BaseInvocation):
"""Loads prompts from a text file"""
file_path: str = InputField(description="Path to prompt text file")
pre_prompt: Optional[str] = InputField(
default=None, description="String to prepend to each prompt", ui_component=UIComponent.Textarea
default=None,
description="String to prepend to each prompt",
ui_component=UIComponent.Textarea,
)
post_prompt: Optional[str] = InputField(
default=None, description="String to append to each prompt", ui_component=UIComponent.Textarea
default=None,
description="String to append to each prompt",
ui_component=UIComponent.Textarea,
)
start_line: int = InputField(default=1, ge=1, description="Line in the file to start start from")
max_prompts: int = InputField(default=1, ge=0, description="Max lines to read from file (0=all)")
@validator("file_path")
@field_validator("file_path")
def file_path_exists(cls, v):
if not exists(v):
raise ValueError(FileNotFoundError)
@ -79,6 +92,10 @@ class PromptsFromFileInvocation(BaseInvocation):
def invoke(self, context: InvocationContext) -> StringCollectionOutput:
prompts = self.promptsFromFile(
self.file_path, self.pre_prompt, self.post_prompt, self.start_line, self.max_prompts
self.file_path,
self.pre_prompt,
self.post_prompt,
self.start_line,
self.max_prompts,
)
return StringCollectionOutput(collection=prompts)

16
invokeai/app/invocations/shared.py Normal file
View File

@ -0,0 +1,16 @@
from pydantic import BaseModel, Field
from invokeai.app.invocations.baseinvocation import FieldDescriptions
class FreeUConfig(BaseModel):
"""
Configuration for the FreeU hyperparameters.
- https://huggingface.co/docs/diffusers/main/en/using-diffusers/freeu
- https://github.com/ChenyangSi/FreeU
"""
s1: float = Field(ge=-1, le=3, description=FieldDescriptions.freeu_s1)
s2: float = Field(ge=-1, le=3, description=FieldDescriptions.freeu_s2)
b1: float = Field(ge=-1, le=3, description=FieldDescriptions.freeu_b1)
b2: float = Field(ge=-1, le=3, description=FieldDescriptions.freeu_b2)

4
invokeai/app/invocations/t2i_adapter.py
View File

@ -1,6 +1,6 @@
from typing import Union
from pydantic import BaseModel, Field
from pydantic import BaseModel, ConfigDict, Field
from invokeai.app.invocations.baseinvocation import (
BaseInvocation,
@ -23,6 +23,8 @@ class T2IAdapterModelField(BaseModel):
model_name: str = Field(description="Name of the T2I-Adapter model")
base_model: BaseModelType = Field(description="Base model")
model_config = ConfigDict(protected_namespaces=())
class T2IAdapterField(BaseModel):
image: ImageField = Field(description="The T2I-Adapter image prompt.")

8
invokeai/app/invocations/upscale.py
View File

@ -7,13 +7,14 @@ import numpy as np
import torch
from basicsr.archs.rrdbnet_arch import RRDBNet
from PIL import Image
from pydantic import ConfigDict
from realesrgan import RealESRGANer
from invokeai.app.invocations.primitives import ImageField, ImageOutput
from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
from invokeai.backend.util.devices import choose_torch_device
from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
from .baseinvocation import BaseInvocation, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
# TODO: Populate this from disk?
# TODO: Use model manager to load?
@ -29,7 +30,7 @@ if choose_torch_device() == torch.device("mps"):
@invocation("esrgan", title="Upscale (RealESRGAN)", tags=["esrgan", "upscale"], category="esrgan", version="1.1.0")
class ESRGANInvocation(BaseInvocation):
class ESRGANInvocation(BaseInvocation, WithWorkflow, WithMetadata):
"""Upscales an image using RealESRGAN."""
image: ImageField = InputField(description="The input image")
@ -38,6 +39,8 @@ class ESRGANInvocation(BaseInvocation):
default=400, ge=0, description="Tile size for tiled ESRGAN upscaling (0=tiling disabled)"
)
model_config = ConfigDict(protected_namespaces=())
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
models_path = context.services.configuration.models_path
@ -120,6 +123,7 @@ class ESRGANInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata,
workflow=self.workflow,
)

2
invokeai/app/services/board_image_records/board_image_records_sqlite.py
View File

@ -12,7 +12,7 @@ from .board_image_records_base import BoardImageRecordStorageBase
class SqliteBoardImageRecordStorage(BoardImageRecordStorageBase):
_conn: sqlite3.Connection
_cursor: sqlite3.Cursor
_lock: threading.Lock
_lock: threading.RLock
def __init__(self, db: SqliteDatabase) -> None:
super().__init__()

12
invokeai/app/services/board_records/board_records_common.py
View File

@ -1,7 +1,7 @@
from datetime import datetime
from typing import Optional, Union
from pydantic import BaseModel, Extra, Field
from pydantic import BaseModel, Field
from invokeai.app.util.misc import get_iso_timestamp
from invokeai.app.util.model_exclude_null import BaseModelExcludeNull
@ -18,9 +18,9 @@ class BoardRecord(BaseModelExcludeNull):
"""The created timestamp of the image."""
updated_at: Union[datetime, str] = Field(description="The updated timestamp of the board.")
"""The updated timestamp of the image."""
deleted_at: Union[datetime, str, None] = Field(description="The deleted timestamp of the board.")
deleted_at: Optional[Union[datetime, str]] = Field(default=None, description="The deleted timestamp of the board.")
"""The updated timestamp of the image."""
cover_image_name: Optional[str] = Field(description="The name of the cover image of the board.")
cover_image_name: Optional[str] = Field(default=None, description="The name of the cover image of the board.")
"""The name of the cover image of the board."""
@ -46,9 +46,9 @@ def deserialize_board_record(board_dict: dict) -> BoardRecord:
)
class BoardChanges(BaseModel, extra=Extra.forbid):
board_name: Optional[str] = Field(description="The board's new name.")
cover_image_name: Optional[str] = Field(description="The name of the board's new cover image.")
class BoardChanges(BaseModel, extra="forbid"):
board_name: Optional[str] = Field(default=None, description="The board's new name.")
cover_image_name: Optional[str] = Field(default=None, description="The name of the board's new cover image.")
class BoardRecordNotFoundException(Exception):

2
invokeai/app/services/board_records/board_records_sqlite.py
View File

@ -20,7 +20,7 @@ from .board_records_common import (
class SqliteBoardRecordStorage(BoardRecordStorageBase):
_conn: sqlite3.Connection
_cursor: sqlite3.Cursor
_lock: threading.Lock
_lock: threading.RLock
def __init__(self, db: SqliteDatabase) -> None:
super().__init__()

2
invokeai/app/services/boards/boards_common.py
View File

@ -17,7 +17,7 @@ class BoardDTO(BoardRecord):
def board_record_to_dto(board_record: BoardRecord, cover_image_name: Optional[str], image_count: int) -> BoardDTO:
"""Converts a board record to a board DTO."""
return BoardDTO(
**board_record.dict(exclude={"cover_image_name"}),
**board_record.model_dump(exclude={"cover_image_name"}),
cover_image_name=cover_image_name,
image_count=image_count,
)

47
invokeai/app/services/config/config_base.py
View File

@ -18,7 +18,7 @@ from pathlib import Path
from typing import ClassVar, Dict, List, Literal, Optional, Union, get_args, get_origin, get_type_hints
from omegaconf import DictConfig, ListConfig, OmegaConf
from pydantic import BaseSettings
from pydantic_settings import BaseSettings, SettingsConfigDict
from invokeai.app.services.config.config_common import PagingArgumentParser, int_or_float_or_str
@ -32,12 +32,14 @@ class InvokeAISettings(BaseSettings):
initconf: ClassVar[Optional[DictConfig]] = None
argparse_groups: ClassVar[Dict] = {}
model_config = SettingsConfigDict(env_file_encoding="utf-8", arbitrary_types_allowed=True, case_sensitive=True)
def parse_args(self, argv: Optional[list] = sys.argv[1:]):
parser = self.get_parser()
opt, unknown_opts = parser.parse_known_args(argv)
if len(unknown_opts) > 0:
print("Unknown args:", unknown_opts)
for name in self.__fields__:
for name in self.model_fields:
if name not in self._excluded():
value = getattr(opt, name)
if isinstance(value, ListConfig):
@ -54,10 +56,12 @@ class InvokeAISettings(BaseSettings):
cls = self.__class__
type = get_args(get_type_hints(cls)["type"])[0]
field_dict = dict({type: dict()})
for name, field in self.__fields__.items():
for name, field in self.model_fields.items():
if name in cls._excluded_from_yaml():
continue
category = field.field_info.extra.get("category") or "Uncategorized"
category = (
field.json_schema_extra.get("category", "Uncategorized") if field.json_schema_extra else "Uncategorized"
)
value = getattr(self, name)
if category not in field_dict[type]:
field_dict[type][category] = dict()
@ -73,7 +77,7 @@ class InvokeAISettings(BaseSettings):
else:
settings_stanza = "Uncategorized"
env_prefix = getattr(cls.Config, "env_prefix", None)
env_prefix = getattr(cls.model_config, "env_prefix", None)
env_prefix = env_prefix if env_prefix is not None else settings_stanza.upper()
initconf = (
@ -89,14 +93,18 @@ class InvokeAISettings(BaseSettings):
for key, value in os.environ.items():
upcase_environ[key.upper()] = value
fields = cls.__fields__
fields = cls.model_fields
cls.argparse_groups = {}
for name, field in fields.items():
if name not in cls._excluded():
current_default = field.default
category = field.field_info.extra.get("category", "Uncategorized")
category = (
field.json_schema_extra.get("category", "Uncategorized")
if field.json_schema_extra
else "Uncategorized"
)
env_name = env_prefix + "_" + name
if category in initconf and name in initconf.get(category):
field.default = initconf.get(category).get(name)
@ -146,11 +154,6 @@ class InvokeAISettings(BaseSettings):
"tiled_decode",
]
class Config:
env_file_encoding = "utf-8"
arbitrary_types_allowed = True
case_sensitive = True
@classmethod
def add_field_argument(cls, command_parser, name: str, field, default_override=None):
field_type = get_type_hints(cls).get(name)
@ -161,7 +164,7 @@ class InvokeAISettings(BaseSettings):
if field.default_factory is None
else field.default_factory()
)
if category := field.field_info.extra.get("category"):
if category := (field.json_schema_extra.get("category", None) if field.json_schema_extra else None):
if category not in cls.argparse_groups:
cls.argparse_groups[category] = command_parser.add_argument_group(category)
argparse_group = cls.argparse_groups[category]
@ -169,7 +172,7 @@ class InvokeAISettings(BaseSettings):
argparse_group = command_parser
if get_origin(field_type) == Literal:
allowed_values = get_args(field.type_)
allowed_values = get_args(field.annotation)
allowed_types = set()
for val in allowed_values:
allowed_types.add(type(val))
@ -182,7 +185,7 @@ class InvokeAISettings(BaseSettings):
type=field_type,
default=default,
choices=allowed_values,
help=field.field_info.description,
help=field.description,
)
elif get_origin(field_type) == Union:
@ -191,7 +194,7 @@ class InvokeAISettings(BaseSettings):
dest=name,
type=int_or_float_or_str,
default=default,
help=field.field_info.description,
help=field.description,
)
elif get_origin(field_type) == list:
@ -199,17 +202,17 @@ class InvokeAISettings(BaseSettings):
f"--{name}",
dest=name,
nargs="*",
type=field.type_,
type=field.annotation,
default=default,
action=argparse.BooleanOptionalAction if field.type_ == bool else "store",
help=field.field_info.description,
action=argparse.BooleanOptionalAction if field.annotation == bool else "store",
help=field.description,
)
else:
argparse_group.add_argument(
f"--{name}",
dest=name,
type=field.type_,
type=field.annotation,
default=default,
action=argparse.BooleanOptionalAction if field.type_ == bool else "store",
help=field.field_info.description,
action=argparse.BooleanOptionalAction if field.annotation == bool else "store",
help=field.description,
)

148
invokeai/app/services/config/config_default.py
View File

@ -45,6 +45,7 @@ InvokeAI:
ram: 13.5
vram: 0.25
lazy_offload: true
log_memory_usage: false
Device:
device: auto
precision: auto
@ -144,8 +145,8 @@ which is set to the desired top-level name. For example, to create a
class InvokeBatch(InvokeAISettings):
type: Literal["InvokeBatch"] = "InvokeBatch"
node_count : int = Field(default=1, description="Number of nodes to run on", category='Resources')
cpu_count : int = Field(default=8, description="Number of GPUs to run on per node", category='Resources')
node_count : int = Field(default=1, description="Number of nodes to run on", json_schema_extra=dict(category='Resources'))
cpu_count : int = Field(default=8, description="Number of GPUs to run on per node", json_schema_extra=dict(category='Resources'))
This will now read and write from the "InvokeBatch" section of the
config file, look for environment variables named INVOKEBATCH_*, and
@ -175,7 +176,8 @@ from pathlib import Path
from typing import ClassVar, Dict, List, Literal, Optional, Union, get_type_hints
from omegaconf import DictConfig, OmegaConf
from pydantic import Field, parse_obj_as
from pydantic import Field, TypeAdapter
from pydantic_settings import SettingsConfigDict
from .config_base import InvokeAISettings
@ -185,6 +187,21 @@ LEGACY_INIT_FILE = Path("invokeai.init")
DEFAULT_MAX_VRAM = 0.5
class Categories(object):
WebServer = dict(category="Web Server")
Features = dict(category="Features")
Paths = dict(category="Paths")
Logging = dict(category="Logging")
Development = dict(category="Development")
Other = dict(category="Other")
ModelCache = dict(category="Model Cache")
Device = dict(category="Device")
Generation = dict(category="Generation")
Queue = dict(category="Queue")
Nodes = dict(category="Nodes")
MemoryPerformance = dict(category="Memory/Performance")
class InvokeAIAppConfig(InvokeAISettings):
"""
Generate images using Stable Diffusion. Use "invokeai" to launch
@ -201,86 +218,90 @@ class InvokeAIAppConfig(InvokeAISettings):
type: Literal["InvokeAI"] = "InvokeAI"
# WEB
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')
allow_origins : List[str] = Field(default=[], description="Allowed CORS origins", category='Web Server')
allow_credentials : bool = Field(default=True, description="Allow CORS credentials", category='Web Server')
allow_methods : List[str] = Field(default=["*"], description="Methods allowed for CORS", category='Web Server')
allow_headers : List[str] = Field(default=["*"], description="Headers allowed for CORS", category='Web Server')
host : str = Field(default="127.0.0.1", description="IP address to bind to", json_schema_extra=Categories.WebServer)
port : int = Field(default=9090, description="Port to bind to", json_schema_extra=Categories.WebServer)
allow_origins : List[str] = Field(default=[], description="Allowed CORS origins", json_schema_extra=Categories.WebServer)
allow_credentials : bool = Field(default=True, description="Allow CORS credentials", json_schema_extra=Categories.WebServer)
allow_methods : List[str] = Field(default=["*"], description="Methods allowed for CORS", json_schema_extra=Categories.WebServer)
allow_headers : List[str] = Field(default=["*"], description="Headers allowed for CORS", json_schema_extra=Categories.WebServer)
# FEATURES
esrgan : bool = Field(default=True, description="Enable/disable upscaling 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')
patchmatch : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
ignore_missing_core_models : bool = Field(default=False, description='Ignore missing models in models/core/convert', category='Features')
esrgan : bool = Field(default=True, description="Enable/disable upscaling code", json_schema_extra=Categories.Features)
internet_available : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", json_schema_extra=Categories.Features)
log_tokenization : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", json_schema_extra=Categories.Features)
patchmatch : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", json_schema_extra=Categories.Features)
ignore_missing_core_models : bool = Field(default=False, description='Ignore missing models in models/core/convert', json_schema_extra=Categories.Features)
# PATHS
root : Path = Field(default=None, description='InvokeAI runtime root directory', category='Paths')
autoimport_dir : Path = Field(default='autoimport', description='Path to a directory of models files to be imported on startup.', category='Paths')
lora_dir : Path = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', category='Paths')
embedding_dir : Path = Field(default=None, description='Path to a directory of Textual Inversion embeddings to be imported on startup.', category='Paths')
controlnet_dir : Path = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', category='Paths')
conf_path : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
models_dir : Path = Field(default='models', description='Path to the models directory', category='Paths')
legacy_conf_dir : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
db_dir : Path = Field(default='databases', description='Path to InvokeAI databases directory', category='Paths')
outdir : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
use_memory_db : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
from_file : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
root : Optional[Path] = Field(default=None, description='InvokeAI runtime root directory', json_schema_extra=Categories.Paths)
autoimport_dir : Optional[Path] = Field(default=Path('autoimport'), description='Path to a directory of models files to be imported on startup.', json_schema_extra=Categories.Paths)
lora_dir : Optional[Path] = Field(default=None, description='Path to a directory of LoRA/LyCORIS models to be imported on startup.', json_schema_extra=Categories.Paths)
embedding_dir : Optional[Path] = Field(default=None, description='Path to a directory of Textual Inversion embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
controlnet_dir : Optional[Path] = Field(default=None, description='Path to a directory of ControlNet embeddings to be imported on startup.', json_schema_extra=Categories.Paths)
conf_path : Optional[Path] = Field(default=Path('configs/models.yaml'), description='Path to models definition file', json_schema_extra=Categories.Paths)
models_dir : Optional[Path] = Field(default=Path('models'), description='Path to the models directory', json_schema_extra=Categories.Paths)
legacy_conf_dir : Optional[Path] = Field(default=Path('configs/stable-diffusion'), description='Path to directory of legacy checkpoint config files', json_schema_extra=Categories.Paths)
db_dir : Optional[Path] = Field(default=Path('databases'), description='Path to InvokeAI databases directory', json_schema_extra=Categories.Paths)
outdir : Optional[Path] = Field(default=Path('outputs'), description='Default folder for output images', json_schema_extra=Categories.Paths)
use_memory_db : bool = Field(default=False, description='Use in-memory database for storing image metadata', json_schema_extra=Categories.Paths)
custom_nodes_dir : Path = Field(default=Path('nodes'), description='Path to directory for custom nodes', json_schema_extra=Categories.Paths)
from_file : Optional[Path] = Field(default=None, description='Take command input from the indicated file (command-line client only)', json_schema_extra=Categories.Paths)
# LOGGING
log_handlers : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', category="Logging")
log_handlers : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', json_schema_extra=Categories.Logging)
# note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
log_format : Literal['plain', 'color', 'syslog', 'legacy'] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', category="Logging")
log_level : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or higher", category="Logging")
log_sql : bool = Field(default=False, description="Log SQL queries", category="Logging")
log_format : Literal['plain', 'color', 'syslog', 'legacy'] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', json_schema_extra=Categories.Logging)
log_level : Literal["debug", "info", "warning", "error", "critical"] = Field(default="info", description="Emit logging messages at this level or higher", json_schema_extra=Categories.Logging)
log_sql : bool = Field(default=False, description="Log SQL queries", json_schema_extra=Categories.Logging)
dev_reload : bool = Field(default=False, description="Automatically reload when Python sources are changed.", category="Development")
dev_reload : bool = Field(default=False, description="Automatically reload when Python sources are changed.", json_schema_extra=Categories.Development)
version : bool = Field(default=False, description="Show InvokeAI version and exit", category="Other")
version : bool = Field(default=False, description="Show InvokeAI version and exit", json_schema_extra=Categories.Other)
# CACHE
ram : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", category="Model Cache", )
vram : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", category="Model Cache", )
lazy_offload : bool = Field(default=True, description="Keep models in VRAM until their space is needed", category="Model Cache", )
ram : float = Field(default=7.5, gt=0, description="Maximum memory amount used by model cache for rapid switching (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
vram : float = Field(default=0.25, ge=0, description="Amount of VRAM reserved for model storage (floating point number, GB)", json_schema_extra=Categories.ModelCache, )
lazy_offload : bool = Field(default=True, description="Keep models in VRAM until their space is needed", json_schema_extra=Categories.ModelCache, )
log_memory_usage : bool = Field(default=False, description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.", json_schema_extra=Categories.ModelCache)
# DEVICE
device : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", category="Device", )
precision : Literal["auto", "float16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", category="Device", )
device : Literal["auto", "cpu", "cuda", "cuda:1", "mps"] = Field(default="auto", description="Generation device", json_schema_extra=Categories.Device)
precision : Literal["auto", "float16", "float32", "autocast"] = Field(default="auto", description="Floating point precision", json_schema_extra=Categories.Device)
# GENERATION
sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category="Generation", )
attention_type : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", category="Generation", )
attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', category="Generation", )
force_tiled_decode : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category="Generation",)
force_tiled_decode: bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category="Generation",)
png_compress_level : int = Field(default=6, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", category="Generation", )
sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", json_schema_extra=Categories.Generation)
attention_type : Literal["auto", "normal", "xformers", "sliced", "torch-sdp"] = Field(default="auto", description="Attention type", json_schema_extra=Categories.Generation)
attention_slice_size: Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8] = Field(default="auto", description='Slice size, valid when attention_type=="sliced"', json_schema_extra=Categories.Generation)
force_tiled_decode : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.Generation)
png_compress_level : int = Field(default=6, description="The compress_level setting of PIL.Image.save(), used for PNG encoding. All settings are lossless. 0 = fastest, largest filesize, 9 = slowest, smallest filesize", json_schema_extra=Categories.Generation)
# QUEUE
max_queue_size : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", category="Queue", )
max_queue_size : int = Field(default=10000, gt=0, description="Maximum number of items in the session queue", json_schema_extra=Categories.Queue)
# NODES
allow_nodes : Optional[List[str]] = Field(default=None, description="List of nodes to allow. Omit to allow all.", category="Nodes")
deny_nodes : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", category="Nodes")
node_cache_size : int = Field(default=512, description="How many cached nodes to keep in memory", category="Nodes", )
allow_nodes : Optional[List[str]] = Field(default=None, description="List of nodes to allow. Omit to allow all.", json_schema_extra=Categories.Nodes)
deny_nodes : Optional[List[str]] = Field(default=None, description="List of nodes to deny. Omit to deny none.", json_schema_extra=Categories.Nodes)
node_cache_size : int = Field(default=512, description="How many cached nodes to keep in memory", json_schema_extra=Categories.Nodes)
# DEPRECATED FIELDS - STILL HERE IN ORDER TO OBTAN VALUES FROM PRE-3.1 CONFIG FILES
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 : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
max_cache_size : Optional[float] = Field(default=None, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
max_vram_cache_size : Optional[float] = Field(default=None, ge=0, description="Amount of VRAM reserved for model storage", category='Memory/Performance')
xformers_enabled : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
tiled_decode : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", category='Memory/Performance')
always_use_cpu : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", json_schema_extra=Categories.MemoryPerformance)
free_gpu_mem : Optional[bool] = Field(default=None, description="If true, purge model from GPU after each generation.", json_schema_extra=Categories.MemoryPerformance)
max_cache_size : Optional[float] = Field(default=None, gt=0, description="Maximum memory amount used by model cache for rapid switching", json_schema_extra=Categories.MemoryPerformance)
max_vram_cache_size : Optional[float] = Field(default=None, ge=0, description="Amount of VRAM reserved for model storage", json_schema_extra=Categories.MemoryPerformance)
xformers_enabled : bool = Field(default=True, description="Enable/disable memory-efficient attention", json_schema_extra=Categories.MemoryPerformance)
tiled_decode : bool = Field(default=False, description="Whether to enable tiled VAE decode (reduces memory consumption with some performance penalty)", json_schema_extra=Categories.MemoryPerformance)
# See InvokeAIAppConfig subclass below for CACHE and DEVICE categories
# fmt: on
class Config:
validate_assignment = True
env_prefix = "INVOKEAI"
model_config = SettingsConfigDict(validate_assignment=True, env_prefix="INVOKEAI")
def parse_args(self, argv: Optional[list[str]] = None, conf: Optional[DictConfig] = None, clobber=False):
def parse_args(
self,
argv: Optional[list[str]] = None,
conf: Optional[DictConfig] = None,
clobber=False,
):
"""
Update settings with contents of init file, environment, and
command-line settings.
@ -308,7 +329,11 @@ class InvokeAIAppConfig(InvokeAISettings):
if self.singleton_init and not clobber:
hints = get_type_hints(self.__class__)
for k in self.singleton_init:
setattr(self, k, parse_obj_as(hints[k], self.singleton_init[k]))
setattr(
self,
k,
TypeAdapter(hints[k]).validate_python(self.singleton_init[k]),
)
@classmethod
def get_config(cls, **kwargs) -> InvokeAIAppConfig:
@ -388,6 +413,13 @@ class InvokeAIAppConfig(InvokeAISettings):
"""
return self._resolve(self.models_dir)
@property
def custom_nodes_path(self) -> Path:
"""
Path to the custom nodes directory
"""
return self._resolve(self.custom_nodes_dir)
# the following methods support legacy calls leftover from the Globals era
@property
def full_precision(self) -> bool:

8
invokeai/app/services/events/events_base.py
View File

@ -2,7 +2,6 @@
from typing import Any, Optional
from invokeai.app.invocations.model import ModelInfo
from invokeai.app.services.invocation_processor.invocation_processor_common import ProgressImage
from invokeai.app.services.session_queue.session_queue_common import (
BatchStatus,
@ -11,6 +10,7 @@ from invokeai.app.services.session_queue.session_queue_common import (
SessionQueueStatus,
)
from invokeai.app.util.misc import get_timestamp
from invokeai.backend.model_management.model_manager import ModelInfo
from invokeai.backend.model_management.models.base import BaseModelType, ModelType, SubModelType
@ -55,7 +55,7 @@ class EventServiceBase:
graph_execution_state_id=graph_execution_state_id,
node_id=node.get("id"),
source_node_id=source_node_id,
progress_image=progress_image.dict() if progress_image is not None else None,
progress_image=progress_image.model_dump() if progress_image is not None else None,
step=step,
order=order,
total_steps=total_steps,
@ -291,8 +291,8 @@ class EventServiceBase:
started_at=str(session_queue_item.started_at) if session_queue_item.started_at else None,
completed_at=str(session_queue_item.completed_at) if session_queue_item.completed_at else None,
),
batch_status=batch_status.dict(),
queue_status=queue_status.dict(),
batch_status=batch_status.model_dump(),
queue_status=queue_status.model_dump(),
),
)

9
invokeai/app/services/image_files/image_files_base.py
View File

@ -1,8 +1,11 @@
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Optional
from PIL.Image import Image as PILImageType
from invokeai.app.invocations.baseinvocation import MetadataField, WorkflowField
class ImageFileStorageBase(ABC):
"""Low-level service responsible for storing and retrieving image files."""
@ -13,7 +16,7 @@ class ImageFileStorageBase(ABC):
pass
@abstractmethod
def get_path(self, image_name: str, thumbnail: bool = False) -> str:
def get_path(self, image_name: str, thumbnail: bool = False) -> Path:
"""Gets the internal path to an image or thumbnail."""
pass
@ -29,8 +32,8 @@ class ImageFileStorageBase(ABC):
self,
image: PILImageType,
image_name: str,
metadata: Optional[dict] = None,
workflow: Optional[str] = None,
metadata: Optional[MetadataField] = None,
workflow: Optional[WorkflowField] = None,
thumbnail_size: int = 256,
) -> None:
"""Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""

24
invokeai/app/services/image_files/image_files_disk.py
View File

@ -1,5 +1,4 @@
# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
import json
from pathlib import Path
from queue import Queue
from typing import Dict, Optional, Union
@ -8,6 +7,7 @@ from PIL import Image, PngImagePlugin
from PIL.Image import Image as PILImageType
from send2trash import send2trash
from invokeai.app.invocations.baseinvocation import MetadataField, WorkflowField
from invokeai.app.services.invoker import Invoker
from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
@ -55,8 +55,8 @@ class DiskImageFileStorage(ImageFileStorageBase):
self,
image: PILImageType,
image_name: str,
metadata: Optional[dict] = None,
workflow: Optional[str] = None,
metadata: Optional[MetadataField] = None,
workflow: Optional[WorkflowField] = None,
thumbnail_size: int = 256,
) -> None:
try:
@ -65,20 +65,10 @@ class DiskImageFileStorage(ImageFileStorageBase):
pnginfo = PngImagePlugin.PngInfo()
if metadata is not None or workflow is not None:
if metadata is not None:
pnginfo.add_text("invokeai_metadata", json.dumps(metadata))
if workflow is not None:
pnginfo.add_text("invokeai_workflow", workflow)
else:
# For uploaded images, we want to retain metadata. PIL strips it on save; manually add it back
# TODO: retain non-invokeai metadata on save...
original_metadata = image.info.get("invokeai_metadata", None)
if original_metadata is not None:
pnginfo.add_text("invokeai_metadata", original_metadata)
original_workflow = image.info.get("invokeai_workflow", None)
if original_workflow is not None:
pnginfo.add_text("invokeai_workflow", original_workflow)
if metadata is not None:
pnginfo.add_text("invokeai_metadata", metadata.model_dump_json())
if workflow is not None:
pnginfo.add_text("invokeai_workflow", workflow.model_dump_json())
image.save(
image_path,

22
invokeai/app/services/image_records/image_records_base.py
View File

@ -2,6 +2,7 @@ from abc import ABC, abstractmethod
from datetime import datetime
from typing import Optional
from invokeai.app.invocations.metadata import MetadataField
from invokeai.app.services.shared.pagination import OffsetPaginatedResults
from .image_records_common import ImageCategory, ImageRecord, ImageRecordChanges, ResourceOrigin
@ -18,7 +19,7 @@ class ImageRecordStorageBase(ABC):
pass
@abstractmethod
def get_metadata(self, image_name: str) -> Optional[dict]:
def get_metadata(self, image_name: str) -> Optional[MetadataField]:
"""Gets an image's metadata'."""
pass
@ -34,8 +35,8 @@ class ImageRecordStorageBase(ABC):
@abstractmethod
def get_many(
self,
offset: Optional[int] = None,
limit: Optional[int] = None,
offset: int = 0,
limit: int = 10,
image_origin: Optional[ResourceOrigin] = None,
categories: Optional[list[ImageCategory]] = None,
is_intermediate: Optional[bool] = None,
@ -61,6 +62,11 @@ class ImageRecordStorageBase(ABC):
"""Deletes all intermediate image records, returning a list of deleted image names."""
pass
@abstractmethod
def get_intermediates_count(self) -> int:
"""Gets a count of all intermediate images."""
pass
@abstractmethod
def save(
self,
@ -69,11 +75,11 @@ class ImageRecordStorageBase(ABC):
image_category: ImageCategory,
width: int,
height: int,
session_id: Optional[str],
node_id: Optional[str],
metadata: Optional[dict],
is_intermediate: bool = False,
starred: bool = False,
is_intermediate: Optional[bool] = False,
starred: Optional[bool] = False,
session_id: Optional[str] = None,
node_id: Optional[str] = None,
metadata: Optional[MetadataField] = None,
) -> datetime:
"""Saves an image record."""
pass

8
invokeai/app/services/image_records/image_records_common.py
View File

@ -3,7 +3,7 @@ import datetime
from enum import Enum
from typing import Optional, Union
from pydantic import Extra, Field, StrictBool, StrictStr
from pydantic import Field, StrictBool, StrictStr
from invokeai.app.util.metaenum import MetaEnum
from invokeai.app.util.misc import get_iso_timestamp
@ -129,7 +129,9 @@ class ImageRecord(BaseModelExcludeNull):
"""The created timestamp of the image."""
updated_at: Union[datetime.datetime, str] = Field(description="The updated timestamp of the image.")
"""The updated timestamp of the image."""
deleted_at: Union[datetime.datetime, str, None] = Field(description="The deleted timestamp of the image.")
deleted_at: Optional[Union[datetime.datetime, str]] = Field(
default=None, description="The deleted timestamp of the image."
)
"""The deleted timestamp of the image."""
is_intermediate: bool = Field(description="Whether this is an intermediate image.")
"""Whether this is an intermediate image."""
@ -147,7 +149,7 @@ class ImageRecord(BaseModelExcludeNull):
"""Whether this image is starred."""
class ImageRecordChanges(BaseModelExcludeNull, extra=Extra.forbid):
class ImageRecordChanges(BaseModelExcludeNull, extra="allow"):
"""A set of changes to apply to an image record.
Only limited changes are valid:

Some files were not shown because too many files have changed in this diff Show More