mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
c647056287
* Testing change to LatentsToText to allow setting different cfg_scale values per diffusion step. * Adding first attempt at float param easing node, using Penner easing functions. * Core implementation of ControlNet and MultiControlNet. * Added support for ControlNet and MultiControlNet to legacy non-nodal Txt2Img in backend/generator. Although backend/generator will likely disappear by v3.x, right now they are very useful for testing core ControlNet and MultiControlNet functionality while node codebase is rapidly evolving. * Added example of using ControlNet with legacy Txt2Img generator * Resolving rebase conflict * Added first controlnet preprocessor node for canny edge detection. * Initial port of controlnet node support from generator-based TextToImageInvocation node to latent-based TextToLatentsInvocation node * Switching to ControlField for output from controlnet nodes. * Resolving conflicts in rebase to origin/main * Refactored ControlNet nodes so they subclass from PreprocessedControlInvocation, and only need to override run_processor(image) (instead of reimplementing invoke()) * changes to base class for controlnet nodes * Added HED, LineArt, and OpenPose ControlNet nodes * Added an additional "raw_processed_image" output port to controlnets, mainly so could route ImageField to a ShowImage node * Added more preprocessor nodes for: MidasDepth ZoeDepth MLSD NormalBae Pidi LineartAnime ContentShuffle Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup. * Prep for splitting pre-processor and controlnet nodes * Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. * Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. * More rebase repair. * Added support for using multiple control nets. Unfortunately this breaks direct usage of Control node output port ==> TextToLatent control input port -- passing through a Collect node is now required. Working on fixing this... * Fixed use of ControlNet control_weight parameter * Fixed lint-ish formatting error * Core implementation of ControlNet and MultiControlNet. * Added first controlnet preprocessor node for canny edge detection. * Initial port of controlnet node support from generator-based TextToImageInvocation node to latent-based TextToLatentsInvocation node * Switching to ControlField for output from controlnet nodes. * Refactored controlnet node to output ControlField that bundles control info. * changes to base class for controlnet nodes * Added more preprocessor nodes for: MidasDepth ZoeDepth MLSD NormalBae Pidi LineartAnime ContentShuffle Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup. * Prep for splitting pre-processor and controlnet nodes * Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. * Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. * Cleaning up TextToLatent arg testing * Cleaning up mistakes after rebase. * Removed last bits of dtype and and device hardwiring from controlnet section * Refactored ControNet support to consolidate multiple parameters into data struct. Also redid how multiple controlnets are handled. * Added support for specifying which step iteration to start using each ControlNet, and which step to end using each controlnet (specified as fraction of total steps) * Cleaning up prior to submitting ControlNet PR. Mostly turning off diagnostic printing. Also fixed error when there is no controlnet input. * Added dependency on controlnet-aux v0.0.3 * Commented out ZoeDetector. Will re-instate once there's a controlnet-aux release that supports it. * Switched CotrolNet node modelname input from free text to default list of popular ControlNet model names. * Fix to work with current stable release of controlnet_aux (v0.0.3). Turned of pre-processor params that were added post v0.0.3. Also change defaults for shuffle. * Refactored most of controlnet code into its own method to declutter TextToLatents.invoke(), and make upcoming integration with LatentsToLatents easier. * Cleaning up after ControlNet refactor in TextToLatentsInvocation * Extended node-based ControlNet support to LatentsToLatentsInvocation. * chore(ui): regen api client * fix(ui): add value to conditioning field * fix(ui): add control field type * fix(ui): fix node ui type hints * fix(nodes): controlnet input accepts list or single controlnet * Moved to controlnet_aux v0.0.4, reinstated Zoe controlnet preprocessor. Also in pyproject.toml had to specify downgrade of timm to 0.6.13 _after_ controlnet-aux installs timm >= 0.9.2, because timm >0.6.13 breaks Zoe preprocessor. * Core implementation of ControlNet and MultiControlNet. * Added first controlnet preprocessor node for canny edge detection. * Switching to ControlField for output from controlnet nodes. * Resolving conflicts in rebase to origin/main * Refactored ControlNet nodes so they subclass from PreprocessedControlInvocation, and only need to override run_processor(image) (instead of reimplementing invoke()) * changes to base class for controlnet nodes * Added HED, LineArt, and OpenPose ControlNet nodes * Added more preprocessor nodes for: MidasDepth ZoeDepth MLSD NormalBae Pidi LineartAnime ContentShuffle Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup. * Prep for splitting pre-processor and controlnet nodes * Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. * Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. * Added support for using multiple control nets. Unfortunately this breaks direct usage of Control node output port ==> TextToLatent control input port -- passing through a Collect node is now required. Working on fixing this... * Fixed use of ControlNet control_weight parameter * Core implementation of ControlNet and MultiControlNet. * Added first controlnet preprocessor node for canny edge detection. * Initial port of controlnet node support from generator-based TextToImageInvocation node to latent-based TextToLatentsInvocation node * Switching to ControlField for output from controlnet nodes. * Refactored controlnet node to output ControlField that bundles control info. * changes to base class for controlnet nodes * Added more preprocessor nodes for: MidasDepth ZoeDepth MLSD NormalBae Pidi LineartAnime ContentShuffle Removed pil_output options, ControlNet preprocessors should always output as PIL. Removed diagnostics and other general cleanup. * Prep for splitting pre-processor and controlnet nodes * Refactored controlnet nodes: split out controlnet stuff into separate node, stripped controlnet stuff form image processing/analysis nodes. * Added resizing of controlnet image based on noise latent. Fixes a tensor mismatch issue. * Cleaning up TextToLatent arg testing * Cleaning up mistakes after rebase. * Removed last bits of dtype and and device hardwiring from controlnet section * Refactored ControNet support to consolidate multiple parameters into data struct. Also redid how multiple controlnets are handled. * Added support for specifying which step iteration to start using each ControlNet, and which step to end using each controlnet (specified as fraction of total steps) * Cleaning up prior to submitting ControlNet PR. Mostly turning off diagnostic printing. Also fixed error when there is no controlnet input. * Commented out ZoeDetector. Will re-instate once there's a controlnet-aux release that supports it. * Switched CotrolNet node modelname input from free text to default list of popular ControlNet model names. * Fix to work with current stable release of controlnet_aux (v0.0.3). Turned of pre-processor params that were added post v0.0.3. Also change defaults for shuffle. * Refactored most of controlnet code into its own method to declutter TextToLatents.invoke(), and make upcoming integration with LatentsToLatents easier. * Cleaning up after ControlNet refactor in TextToLatentsInvocation * Extended node-based ControlNet support to LatentsToLatentsInvocation. * chore(ui): regen api client * fix(ui): fix node ui type hints * fix(nodes): controlnet input accepts list or single controlnet * Added Mediapipe image processor for use as ControlNet preprocessor. Also hacked in ability to specify HF subfolder when loading ControlNet models from string. * Fixed bug where MediapipFaceProcessorInvocation was ignoring max_faces and min_confidence params. * Added nodes for float params: ParamFloatInvocation and FloatCollectionOutput. Also added FloatOutput. * Added mediapipe install requirement. Should be able to remove once controlnet_aux package adds mediapipe to its requirements. * Added float to FIELD_TYPE_MAP ins constants.ts * Progress toward improvement in fieldTemplateBuilder.ts getFieldType() * Fixed controlnet preprocessors and controlnet handling in TextToLatents to work with revised Image services. * Cleaning up from merge, re-adding cfg_scale to FIELD_TYPE_MAP * Making sure cfg_scale of type list[float] can be used in image metadata, to support param easing for cfg_scale * Fixed math for per-step param easing. * Added option to show plot of param value at each step * Just cleaning up after adding param easing plot option, removing vestigial code. * Modified control_weight ControlNet param to be polistmorphic -- can now be either a single float weight applied for all steps, or a list of floats of size total_steps, that specifies weight for each step. * Added more informative error message when _validat_edge() throws an error. * Just improving parm easing bar chart title to include easing type. * Added requirement for easing-functions package * Taking out some diagnostic prints. * Added option to use both easing function and mirror of easing function together. * Fixed recently introduced problem (when pulled in main), triggered by num_steps in StepParamEasingInvocation not having a default value -- just added default. --------- Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
174 lines
5.4 KiB
TOML
174 lines
5.4 KiB
TOML
[build-system]
|
|
requires = ["setuptools~=65.5", "pip~=22.3", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "InvokeAI"
|
|
description = "An implementation of Stable Diffusion which provides various new features and options to aid the image generation process"
|
|
requires-python = ">=3.9, <3.11"
|
|
readme = { content-type = "text/markdown", file = "README.md" }
|
|
keywords = ["stable-diffusion", "AI"]
|
|
dynamic = ["version"]
|
|
license = { file = "LICENSE" }
|
|
authors = [{ name = "The InvokeAI Project", email = "lincoln.stein@gmail.com" }]
|
|
classifiers = [
|
|
'Development Status :: 4 - Beta',
|
|
'Environment :: GPU',
|
|
'Environment :: GPU :: NVIDIA CUDA',
|
|
'Environment :: MacOS X',
|
|
'Intended Audience :: End Users/Desktop',
|
|
'Intended Audience :: Developers',
|
|
'License :: OSI Approved :: MIT License',
|
|
'Operating System :: POSIX :: Linux',
|
|
'Operating System :: MacOS',
|
|
'Operating System :: Microsoft :: Windows',
|
|
'Programming Language :: Python :: 3 :: Only',
|
|
'Programming Language :: Python :: 3.8',
|
|
'Programming Language :: Python :: 3.9',
|
|
'Programming Language :: Python :: 3.10',
|
|
'Topic :: Artistic Software',
|
|
'Topic :: Internet :: WWW/HTTP :: WSGI :: Application',
|
|
'Topic :: Internet :: WWW/HTTP :: WSGI :: Server',
|
|
'Topic :: Multimedia :: Graphics',
|
|
'Topic :: Scientific/Engineering :: Artificial Intelligence',
|
|
'Topic :: Scientific/Engineering :: Image Processing',
|
|
]
|
|
dependencies = [
|
|
"accelerate~=0.16",
|
|
"albumentations",
|
|
"click",
|
|
"clip_anytorch", # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
|
|
"compel>=1.2.1",
|
|
"controlnet-aux>=0.0.4",
|
|
"timm==0.6.13", # needed to override timm latest in controlnet_aux, see https://github.com/isl-org/ZoeDepth/issues/26
|
|
"datasets",
|
|
"diffusers[torch]~=0.16.1",
|
|
"dnspython==2.2.1",
|
|
"easing-functions",
|
|
"einops",
|
|
"eventlet",
|
|
"facexlib",
|
|
"fastapi==0.88.0",
|
|
"fastapi-events==0.8.0",
|
|
"fastapi-socketio==0.0.10",
|
|
"flask==2.1.3",
|
|
"flask_cors==3.0.10",
|
|
"flask_socketio==5.3.0",
|
|
"flaskwebgui==1.0.3",
|
|
"gfpgan==1.3.8",
|
|
"huggingface-hub>=0.11.1",
|
|
"matplotlib", # needed for plotting of Penner easing functions
|
|
"mediapipe", # needed for "mediapipeface" controlnet model
|
|
"npyscreen",
|
|
"numpy<1.24",
|
|
"omegaconf",
|
|
"opencv-python",
|
|
"picklescan",
|
|
"pillow",
|
|
"prompt-toolkit",
|
|
"pypatchmatch",
|
|
'pyperclip',
|
|
"pyreadline3",
|
|
"python-multipart==0.0.6",
|
|
"pytorch-lightning==1.7.7",
|
|
"realesrgan",
|
|
"requests==2.28.2",
|
|
"rich~=13.3",
|
|
"safetensors~=0.3.0",
|
|
"scikit-image>=0.19",
|
|
"send2trash",
|
|
"test-tube>=0.7.5",
|
|
"torch~=2.0.0",
|
|
"torchvision>=0.14.1",
|
|
"torchmetrics",
|
|
"transformers~=4.26",
|
|
"uvicorn[standard]==0.21.1",
|
|
"windows-curses; sys_platform=='win32'",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
"dist" = ["pip-tools", "pipdeptree", "twine"]
|
|
"docs" = [
|
|
"mkdocs-material<9.0",
|
|
"mkdocs-git-revision-date-localized-plugin",
|
|
"mkdocs-redirects==1.2.0",
|
|
]
|
|
"dev" = [
|
|
"pudb",
|
|
]
|
|
"test" = ["pytest>6.0.0", "pytest-cov"]
|
|
"xformers" = [
|
|
"xformers~=0.0.19; sys_platform!='darwin'",
|
|
"triton; sys_platform=='linux'",
|
|
]
|
|
|
|
[project.scripts]
|
|
|
|
# legacy entrypoints; provided for backwards compatibility
|
|
"configure_invokeai.py" = "invokeai.frontend.install:invokeai_configure"
|
|
"textual_inversion.py" = "invokeai.frontend.training:invokeai_textual_inversion"
|
|
|
|
# shortcut commands to start cli and web
|
|
"invokeai" = "invokeai.app.cli_app:invoke_cli"
|
|
"invokeai-web" = "invokeai.app.api_app:invoke_api"
|
|
|
|
# full commands
|
|
"invokeai-configure" = "invokeai.frontend.install:invokeai_configure"
|
|
"invokeai-merge" = "invokeai.frontend.merge:invokeai_merge_diffusers"
|
|
"invokeai-ti" = "invokeai.frontend.training:invokeai_textual_inversion"
|
|
"invokeai-model-install" = "invokeai.frontend.install:invokeai_model_install"
|
|
"invokeai-update" = "invokeai.frontend.install:invokeai_update"
|
|
"invokeai-metadata" = "invokeai.frontend.CLI.sd_metadata:print_metadata"
|
|
"invokeai-node-cli" = "invokeai.app.cli_app:invoke_cli"
|
|
"invokeai-node-web" = "invokeai.app.api_app:invoke_api"
|
|
|
|
[project.urls]
|
|
"Homepage" = "https://invoke-ai.github.io/InvokeAI/"
|
|
"Documentation" = "https://invoke-ai.github.io/InvokeAI/"
|
|
"Source" = "https://github.com/invoke-ai/InvokeAI/"
|
|
"Bug Reports" = "https://github.com/invoke-ai/InvokeAI/issues"
|
|
"Discord" = "https://discord.gg/ZmtBAhwWhy"
|
|
|
|
[tool.setuptools.dynamic]
|
|
version = { attr = "invokeai.version.__version__" }
|
|
|
|
[tool.setuptools.packages.find]
|
|
"where" = ["."]
|
|
"include" = [
|
|
"invokeai.assets.web*","invokeai.version*",
|
|
"invokeai.generator*","invokeai.backend*",
|
|
"invokeai.frontend*", "invokeai.frontend.web.dist*",
|
|
"invokeai.frontend.web.static*",
|
|
"invokeai.configs*",
|
|
"invokeai.app*","ldm*",
|
|
]
|
|
|
|
[tool.setuptools.package-data]
|
|
"invokeai.assets.web" = ["**.png"]
|
|
"invokeai.backend" = ["**.png"]
|
|
"invokeai.configs" = ["*.example", "**/*.yaml", "*.txt"]
|
|
"invokeai.frontend.web.dist" = ["**"]
|
|
"invokeai.frontend.web.static" = ["**"]
|
|
|
|
#=== Begin: PyTest and Coverage
|
|
[tool.pytest.ini_options]
|
|
addopts = "--cov-report term --cov-report html --cov-report xml"
|
|
[tool.coverage.run]
|
|
branch = true
|
|
source = ["invokeai"]
|
|
omit = ["*tests*", "*migrations*", ".venv/*", "*.env"]
|
|
[tool.coverage.report]
|
|
show_missing = true
|
|
fail_under = 85 # let's set something sensible on Day 1 ...
|
|
[tool.coverage.json]
|
|
output = "coverage/coverage.json"
|
|
pretty_print = true
|
|
[tool.coverage.html]
|
|
directory = "coverage/html"
|
|
[tool.coverage.xml]
|
|
output = "coverage/index.xml"
|
|
#=== End: PyTest and Coverage
|
|
|
|
[flake8]
|
|
max-line-length = 120
|