diff --git a/docs/assets/features/upscale-dialog.png b/docs/assets/features/upscale-dialog.png index 937bda9db3..fd91f90a65 100644 Binary files a/docs/assets/features/upscale-dialog.png and b/docs/assets/features/upscale-dialog.png differ diff --git a/docs/assets/invoke-web-server-1.png b/docs/assets/invoke-web-server-1.png index 1834bce32e..e1cf27a217 100644 Binary files a/docs/assets/invoke-web-server-1.png and b/docs/assets/invoke-web-server-1.png differ diff --git a/docs/assets/invoke_ai_banner.png b/docs/assets/invoke_ai_banner.png index af2c9b1323..74d23f514d 100644 Binary files a/docs/assets/invoke_ai_banner.png and b/docs/assets/invoke_ai_banner.png differ diff --git a/docs/assets/nodes/groupsconditioning.png b/docs/assets/nodes/groupsconditioning.png index cf38a00290..baaf2b44e0 100644 Binary files a/docs/assets/nodes/groupsconditioning.png and b/docs/assets/nodes/groupsconditioning.png differ diff --git a/docs/assets/nodes/groupscontrol.png b/docs/assets/nodes/groupscontrol.png index f2e3d43e7d..a38e4e4bba 100644 Binary files a/docs/assets/nodes/groupscontrol.png and b/docs/assets/nodes/groupscontrol.png differ diff --git a/docs/assets/nodes/groupsimgvae.png b/docs/assets/nodes/groupsimgvae.png index ae6967cab1..03ac8d1f4a 100644 Binary files a/docs/assets/nodes/groupsimgvae.png and b/docs/assets/nodes/groupsimgvae.png differ diff --git a/docs/assets/nodes/groupsiterate.png b/docs/assets/nodes/groupsiterate.png index 82ec8bf020..50b762099a 100644 Binary files a/docs/assets/nodes/groupsiterate.png and b/docs/assets/nodes/groupsiterate.png differ diff --git a/docs/assets/nodes/groupslora.png b/docs/assets/nodes/groupslora.png index 736aff5914..74ae8a7073 100644 Binary files a/docs/assets/nodes/groupslora.png and b/docs/assets/nodes/groupslora.png differ diff --git a/docs/assets/nodes/groupsmultigenseeding.png b/docs/assets/nodes/groupsmultigenseeding.png index b54ec2afb7..dcd64c7758 100644 Binary files a/docs/assets/nodes/groupsmultigenseeding.png and b/docs/assets/nodes/groupsmultigenseeding.png differ diff --git a/docs/assets/nodes/groupsnoise.png b/docs/assets/nodes/groupsnoise.png index c825e314ae..d95b7ba307 100644 Binary files a/docs/assets/nodes/groupsnoise.png and b/docs/assets/nodes/groupsnoise.png differ diff --git a/docs/assets/nodes/groupsrandseed.png b/docs/assets/nodes/groupsrandseed.png deleted file mode 100644 index 9b8bcfdb17..0000000000 Binary files a/docs/assets/nodes/groupsrandseed.png and /dev/null differ diff --git a/docs/assets/nodes/linearview.png b/docs/assets/nodes/linearview.png index 0dc28534e3..fb6b3efca0 100644 Binary files a/docs/assets/nodes/linearview.png and b/docs/assets/nodes/linearview.png differ diff --git a/docs/assets/nodes/workflow_library.png b/docs/assets/nodes/workflow_library.png new file mode 100644 index 0000000000..a17593d3b6 Binary files /dev/null and b/docs/assets/nodes/workflow_library.png differ diff --git a/docs/deprecated/2to3.md b/docs/deprecated/2to3.md new file mode 100644 index 0000000000..453ec8f6a1 --- /dev/null +++ b/docs/deprecated/2to3.md @@ -0,0 +1,53 @@ +## :octicons-log-16: Important Changes Since Version 2.3 + +### Nodes + +Behind the scenes, InvokeAI has been completely rewritten to support +"nodes," small unitary operations that can be combined into graphs to +form arbitrary workflows. For example, there is a prompt node that +processes the prompt string and feeds it to a text2latent node that +generates a latent image. The latents are then fed to a latent2image +node that translates the latent image into a PNG. + +The WebGUI has a node editor that allows you to graphically design and +execute custom node graphs. The ability to save and load graphs is +still a work in progress, but coming soon. + +### Command-Line Interface Retired + +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`. + +### ControlNet + +This version of InvokeAI features ControlNet, a system that allows you +to achieve exact poses for human and animal figures by providing a +model to follow. Full details are found in [ControlNet](features/CONTROLNET.md) + +### New Schedulers + +The list of schedulers has been completely revamped and brought up to date: + +| **Short Name** | **Scheduler** | **Notes** | +|----------------|---------------------------------|-----------------------------| +| **ddim** | DDIMScheduler | | +| **ddpm** | DDPMScheduler | | +| **deis** | DEISMultistepScheduler | | +| **lms** | LMSDiscreteScheduler | | +| **pndm** | PNDMScheduler | | +| **heun** | HeunDiscreteScheduler | original noise schedule | +| **heun_k** | HeunDiscreteScheduler | using karras noise schedule | +| **euler** | EulerDiscreteScheduler | original noise schedule | +| **euler_k** | EulerDiscreteScheduler | using karras noise schedule | +| **kdpm_2** | KDPM2DiscreteScheduler | | +| **kdpm_2_a** | KDPM2AncestralDiscreteScheduler | | +| **dpmpp_2s** | DPMSolverSinglestepScheduler | | +| **dpmpp_2m** | DPMSolverMultistepScheduler | original noise scnedule | +| **dpmpp_2m_k** | DPMSolverMultistepScheduler | using karras noise schedule | +| **unipc** | UniPCMultistepScheduler | CPU only | +| **lcm** | LCMScheduler | | + +Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details. \ No newline at end of file diff --git a/docs/features/UNIFIED_CANVAS.md b/docs/features/UNIFIED_CANVAS.md index 9eada92708..476d2009be 100644 --- a/docs/features/UNIFIED_CANVAS.md +++ b/docs/features/UNIFIED_CANVAS.md @@ -229,29 +229,28 @@ clarity on the intent and common use cases we expect for utilizing them. currently being rendered by your browser into a merged copy of the image. This lowers the resource requirements and should improve performance. -### Seam Correction +### Compositing / Seam Correction When doing Inpainting or Outpainting, Invoke needs to merge the pixels generated -by Stable Diffusion into your existing image. To do this, the area around the -`seam` at the boundary between your image and the new generation is +by Stable Diffusion into your existing image. This is achieved through compositing - the area around the the boundary between your image and the new generation is automatically blended to produce a seamless output. In a fully automatic -process, a mask is generated to cover the seam, and then the area of the seam is +process, a mask is generated to cover the boundary, and then the area of the boundary is Inpainted. Although the default options should work well most of the time, sometimes it can -help to alter the parameters that control the seam Inpainting. A wider seam and -a blur setting of about 1/3 of the seam have been noted as producing -consistently strong results (e.g. 96 wide and 16 blur - adds up to 32 blur with -both sides). Seam strength of 0.7 is best for reducing hard seams. +help to alter the parameters that control the Compositing. A larger blur and +a blur setting have been noted as producing +consistently strong results . Strength of 0.7 is best for reducing hard seams. + +- **Mode** - What part of the image will have the the Compositing applied to it. + - **Mask edge** will apply Compositing to the edge of the masked area + - **Mask** will apply Compositing to the entire masked area + - **Unmasked** will apply Compositing to the entire image +- **Steps** - Number of generation steps that will occur during the Coherence Pass, similar to Denoising Steps. Higher step counts will generally have better results. +- **Strength** - How much noise is added for the Coherence Pass, similar to Denoising Strength. A strength of 0 will result in an unchanged image, while a strength of 1 will result in an image with a completely new area as defined by the Mode setting. +- **Blur** - Adjusts the pixel radius of the the mask. A larger blur radius will cause the mask to extend past the visibly masked area, while too small of a blur radius will result in a mask that is smaller than the visibly masked area. +- **Blur Method** - The method of blur applied to the masked area. -- **Seam Size** - The size of the seam masked area. Set higher to make a larger - mask around the seam. -- **Seam Blur** - The size of the blur that is applied on _each_ side of the - masked area. -- **Seam Strength** - The Image To Image Strength parameter used for the - Inpainting generation that is applied to the seam area. -- **Seam Steps** - The number of generation steps that should be used to Inpaint - the seam. ### Infill & Scaling diff --git a/docs/index.md b/docs/index.md index 124abf222d..1fdc063c46 100644 --- a/docs/index.md +++ b/docs/index.md @@ -18,7 +18,7 @@ title: Home width: 100%; max-width: 100%; height: 50px; - background-color: #448AFF; + background-color: #35A4DB; color: #fff; font-size: 16px; border: none; @@ -43,7 +43,7 @@ title: Home
-[![project logo](assets/invoke_ai_banner.png)](https://github.com/invoke-ai/InvokeAI) +[![project logo](https://github.com/invoke-ai/InvokeAI/assets/31807370/6e3728c7-e90e-4711-905c-3b55844ff5be)](https://github.com/invoke-ai/InvokeAI) [![discord badge]][discord link] @@ -145,60 +145,6 @@ Mac and Linux machines, and runs on GPU cards with as little as 4 GB of RAM. - [Guide to InvokeAI Runtime Settings](features/CONFIGURATION.md) - [Database Maintenance and other Command Line Utilities](features/UTILITIES.md) -## :octicons-log-16: Important Changes Since Version 2.3 - -### Nodes - -Behind the scenes, InvokeAI has been completely rewritten to support -"nodes," small unitary operations that can be combined into graphs to -form arbitrary workflows. For example, there is a prompt node that -processes the prompt string and feeds it to a text2latent node that -generates a latent image. The latents are then fed to a latent2image -node that translates the latent image into a PNG. - -The WebGUI has a node editor that allows you to graphically design and -execute custom node graphs. The ability to save and load graphs is -still a work in progress, but coming soon. - -### Command-Line Interface Retired - -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`. - -### ControlNet - -This version of InvokeAI features ControlNet, a system that allows you -to achieve exact poses for human and animal figures by providing a -model to follow. Full details are found in [ControlNet](features/CONTROLNET.md) - -### New Schedulers - -The list of schedulers has been completely revamped and brought up to date: - -| **Short Name** | **Scheduler** | **Notes** | -|----------------|---------------------------------|-----------------------------| -| **ddim** | DDIMScheduler | | -| **ddpm** | DDPMScheduler | | -| **deis** | DEISMultistepScheduler | | -| **lms** | LMSDiscreteScheduler | | -| **pndm** | PNDMScheduler | | -| **heun** | HeunDiscreteScheduler | original noise schedule | -| **heun_k** | HeunDiscreteScheduler | using karras noise schedule | -| **euler** | EulerDiscreteScheduler | original noise schedule | -| **euler_k** | EulerDiscreteScheduler | using karras noise schedule | -| **kdpm_2** | KDPM2DiscreteScheduler | | -| **kdpm_2_a** | KDPM2AncestralDiscreteScheduler | | -| **dpmpp_2s** | DPMSolverSinglestepScheduler | | -| **dpmpp_2m** | DPMSolverMultistepScheduler | original noise scnedule | -| **dpmpp_2m_k** | DPMSolverMultistepScheduler | using karras noise schedule | -| **unipc** | UniPCMultistepScheduler | CPU only | -| **lcm** | LCMScheduler | | - -Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details. - ## :material-target: Troubleshooting Please check out our **[:material-frequently-asked-questions: diff --git a/docs/nodes/NODES.md b/docs/nodes/NODES.md index f6496c09bb..b7f7aa82ad 100644 --- a/docs/nodes/NODES.md +++ b/docs/nodes/NODES.md @@ -6,10 +6,17 @@ If you're not familiar with Diffusion, take a look at our [Diffusion Overview.]( ## Features +### Workflow Library +The Workflow Library enables you to save workflows to the Invoke database, allowing you to easily creating, modify and share workflows as needed. + +A curated set of workflows are provided by default - these are designed to help explain important nodes' usage in the Workflow Editor. + +![workflow_library](../assets/nodes/workflow_library.png) + ### Linear View The Workflow Editor allows you to create a UI for your workflow, to make it easier to iterate on your generations. -To add an input to the Linear UI, right click on the input label and select "Add to Linear View". +To add an input to the Linear UI, right click on the **input label** and select "Add to Linear View". The Linear UI View will also be part of the saved workflow, allowing you share workflows and enable other to use them, regardless of complexity. @@ -30,7 +37,7 @@ Any node or input field can be renamed in the workflow editor. If the input fiel Nodes have a "Use Cache" option in their footer. This allows for performance improvements by using the previously cached values during the workflow processing. -## Important Concepts +## Important Nodes & Concepts There are several node grouping concepts that can be examined with a narrow focus. These (and other) groupings can be pieced together to make up functional graph setups, and are important to understanding how groups of nodes work together as part of a whole. Note that the screenshots below aren't examples of complete functioning node graphs (see Examples). @@ -56,7 +63,7 @@ The ImageToLatents node takes in a pixel image and a VAE and outputs a latents. It is common to want to use both the same seed (for continuity) and random seeds (for variety). To define a seed, simply enter it into the 'Seed' field on a noise node. Conversely, the RandomInt node generates a random integer between 'Low' and 'High', and can be used as input to the 'Seed' edge point on a noise node to randomize your seed. -![groupsrandseed](../assets/nodes/groupsrandseed.png) +![groupsrandseed](../assets/nodes/groupsnoise.png) ### ControlNet diff --git a/docs/nodes/exampleWorkflows.md b/docs/nodes/exampleWorkflows.md index 17eea5677e..b52493f365 100644 --- a/docs/nodes/exampleWorkflows.md +++ b/docs/nodes/exampleWorkflows.md @@ -1,6 +1,6 @@ # Example Workflows -We've curated some example workflows for you to get started with Workflows in InvokeAI +We've curated some example workflows for you to get started with Workflows in InvokeAI! These can also be found in the Workflow Library, located in the Workflow Editor of Invoke. 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! diff --git a/docs/other/CONTRIBUTORS.md b/docs/other/CONTRIBUTORS.md index f35db8919c..704f218027 100644 --- a/docs/other/CONTRIBUTORS.md +++ b/docs/other/CONTRIBUTORS.md @@ -215,6 +215,7 @@ We thank them for all of their time and hard work. - Robert Bolender - Robin Rombach - Rohan Barar +- rohinish404 - rpagliuca - rromb - Rupesh Sreeraman diff --git a/docs/stylesheets/extra.css b/docs/stylesheets/extra.css new file mode 100644 index 0000000000..42a2cfe74a --- /dev/null +++ b/docs/stylesheets/extra.css @@ -0,0 +1,5 @@ +:root { + --md-primary-fg-color: #35A4DB; + --md-primary-fg-color--light: #35A4DB; + --md-primary-fg-color--dark: #35A4DB; + } \ No newline at end of file diff --git a/mkdocs.yml b/mkdocs.yml index c8875c0ff1..fc41f68087 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -14,6 +14,9 @@ edit_uri: edit/main/docs/ # Copyright copyright: Copyright © 2023 InvokeAI Team +extra_css: + - stylesheets/extra.css + # Configuration theme: name: material @@ -21,17 +24,18 @@ theme: repo: fontawesome/brands/github edit: material/file-document-edit-outline palette: - - media: '(prefers-color-scheme: light)' - scheme: default - toggle: - icon: material/lightbulb - name: Switch to dark mode + # - media: '(prefers-color-scheme: light)' + # scheme: default + # primary: custom + # toggle: + # icon: material/lightbulb + # name: Switch to dark mode - media: '(prefers-color-scheme: dark)' scheme: slate - primary: blue - toggle: - icon: material/lightbulb-outline - name: Switch to light mode + primary: custom + # toggle: + # icon: material/lightbulb-outline + # name: Switch to light mode features: - navigation.instant - navigation.tabs @@ -43,6 +47,7 @@ theme: - search.suggest - toc.integrate + # Extensions markdown_extensions: - abbr @@ -130,14 +135,14 @@ nav: - Installing Invoke with pip: 'installation/deprecated_documentation/INSTALL_PCP.md' - Source Installer: 'installation/deprecated_documentation/INSTALL_SOURCE.md' - Workflows & Nodes: - - Community Nodes: 'nodes/communityNodes.md' - - Example Workflows: 'nodes/exampleWorkflows.md' - Nodes Overview: 'nodes/overview.md' + - Workflow Editor Basics: 'nodes/NODES.md' - List of Default Nodes: 'nodes/defaultNodes.md' - - Workflow Editor Usage: 'nodes/NODES.md' + - Example Workflows: 'nodes/exampleWorkflows.md' - ComfyUI to InvokeAI: 'nodes/comfyToInvoke.md' - Facetool Node: 'nodes/detailedNodes/faceTools.md' - Contributing Nodes: 'nodes/contributingNodes.md' + - Community Nodes: 'nodes/communityNodes.md' - Features: - Overview: 'features/index.md' - New to InvokeAI?: 'help/gettingStartedWithAI.md' @@ -147,7 +152,7 @@ nav: - Controlling Logging: 'features/LOGGING.md' - LoRAs & LCM-LoRAs: 'features/LORAS.md' - Model Merging: 'features/MODEL_MERGING.md' - - Nodes & Workflows: 'nodes/overview.md' + - Workflows & Nodes : 'nodes/overview' - NSFW Checker: 'features/WATERMARK+NSFW.md' - Postprocessing: 'features/POSTPROCESS.md' - Prompting Features: 'features/PROMPTS.md' @@ -165,20 +170,20 @@ nav: - Development: - Overview: 'contributing/contribution_guides/development.md' - New Contributors: 'contributing/contribution_guides/newContributorChecklist.md' - - InvokeAI Architecture: 'contributing/ARCHITECTURE.md' - Model Manager v2: 'contributing/MODEL_MANAGER.md' - Frontend Documentation: 'contributing/contribution_guides/contributingToFrontend.md' - Local Development: 'contributing/LOCAL_DEVELOPMENT.md' - - Adding Tests: 'contributing/TESTS.md' + - Testing: 'contributing/TESTS.md' - Documentation: 'contributing/contribution_guides/documentation.md' - Nodes: 'contributing/INVOCATIONS.md' - Model Manager: 'contributing/MODEL_MANAGER.md' - Download Queue: 'contributing/DOWNLOAD_QUEUE.md' - Translation: 'contributing/contribution_guides/translation.md' - Tutorials: 'contributing/contribution_guides/tutorials.md' - - Changelog: 'CHANGELOG.md' - Deprecated: + - InvokeAI 2.3: 'deprecated/2to3.md' - Command Line Interface: 'deprecated/CLI.md' + - Changelog: 'CHANGELOG.md' - Variations: 'deprecated/VARIATIONS.md' - Translations: 'deprecated/TRANSLATION.md' - Embiggen: 'deprecated/EMBIGGEN.md'