InvokeAI

InvokeAI v6.10.0 introduces major support for the Z-Image Turbo model family and several quality-of-life improvements, including workflow tagging, prompt weighting hotkeys, and a new hotkey editor. This release also adds VRAM management options and PBR map generation capabilities.

InvokeAI v6.10.0rc2 introduces significant backend support for the Z-Image-Turbo model family and adds several major quality-of-life features, including a Hotkey Editor, Workflow Tags, and bulk operations in the Model Manager.

InvokeAI v6.10.0rc1 introduces major backend support for the Z-Image-Turbo model family and significant UI enhancements, including a Hotkey Editor, Workflow Tagging, and bulk model operations. This release marks the first Community Edition update since the commercial venture closure.

This release significantly improves Invoke's Model Manager by refactoring model identification logic and normalizing the internal model storage directory structure. A key user-facing change is that previously unidentifiable models are now installed as 'Unknown' rather than being deleted.

This release significantly improves Invoke's Model Manager by refactoring model identification, introducing support for installing unknown models, and normalizing the internal model directory structure to a flat, UUID-based layout.

This release significantly improves Invoke's Model Manager by restructuring internal model storage to a flat, UUID-based directory and refactoring the model identification system. A key user-facing change is that previously unidentified models are now installed as 'Unknown' rather than being deleted.

This release significantly improves Invoke's Model Manager by refactoring model identification logic and changing the internal storage structure for Invoke-managed models to a flat, UUID-based directory system. A data migration is performed on first run to adapt existing models to the new structure.

This patch release resolves a critical startup error by pinning the fastapi dependency. Users are encouraged to use the Invoke Launcher for installation and updates.

This minor release introduces a new crop tool for reference images, enhances the Model Manager UI, and adds prompt history navigation shortcuts. It also includes several bug fixes related to layer opacity baking and model installation help text.

This minor release introduces several enhancements, including a new crop tool for reference images and improved UI for the Model Manager. It also includes various bug fixes and internal improvements for workflow editor flexibility.

This minor release introduces a new crop tool for reference images, enhances the Model Manager UI, and adds keyboard shortcuts for prompt history navigation.

This minor release introduces major improvements to object selection with SAM2 support and text prompting, adds non-destructive raster layer adjustments, and includes prompt history functionality. Several bugs related to LoRA weights and UI rendering have also been resolved.

This minor release introduces major improvements to object selection with SAM2 support and box selection, adds non-destructive raster layer adjustments, and enables math evaluation in workflow number fields.

This minor release introduces several quality-of-life enhancements, including improved Canvas color controls and LoRA weight defaults, alongside numerous bug fixes across the UI and internal processes.

This minor release introduces quality-of-life improvements, notably enhanced Canvas color controls and default LoRA weight settings, alongside numerous bug fixes across the UI and internal organization.

This minor release introduces quality-of-life improvements, notably enhanced Canvas Color Picker functionality and default LoRA weight settings, alongside various bug fixes across the UI and internal organization.

This is a patch release focused on fixing high-priority bugs, including a hard crash related to FLUX on Windows and several UI rendering issues on Canvas.

This release introduces several UI enhancements, particularly in the Workflow Builder and Canvas interactions, alongside fixes for token handling, float precision, and image viewing issues.

This release introduces several UI enhancements, including better bounding box resizing controls and workflow field management, alongside fixes for token handling and specific attribute errors.

This release introduces several quality-of-life improvements, including hotkeys for canvas visibility and error highlighting for nodes, alongside fixes for model installation paths and VAE memory usage. SDXL Style prompt settings have been removed from linear UI tabs.

This minor release introduces several quality-of-life improvements, including UI enhancements like error highlighting and new metadata recall features. It also addresses VRAM usage, model installation paths, and state persistence strategy.

This minor release introduces several UI enhancements, including hotkey toggles and error highlighting, alongside fixes for VRAM usage and model installation paths. State persistence has been improved via debouncing.

This minor release introduces database persistence for Studio state, enabling cross-device synchronization, and adds comprehensive support for multiple reference images in FLUX Kontext workflows. It also includes an optional, dangerous setting to disable model scanning via picklescan.

This minor release introduces database persistence for Studio state, enabling cross-device synchronization, and adds significant enhancements to FLUX Kontext handling, including support for multiple reference images and a dedicated image preparation node.

This minor release introduces persistent Studio state stored in the database across devices and includes numerous fixes related to model installation, queue management, and UI responsiveness. A migration path is included to move existing browser-stored state to the new database storage.

This minor release restores several key UI features like "Cancel and Clear All" and the viewer toggle hotkey, alongside various bug fixes in the Workflow Editor and Canvas scrolling.

This minor release restores the highly requested 'Send to Gallery' workflow via a renamed setting in Canvas and introduces numerous quality-of-life enhancements, including new hotkeys and workflow editor improvements.

This minor release restores the highly requested 'Send to Gallery' workflow via an updated Canvas setting and introduces several UI enhancements and bug fixes across the application.

This minor release restores the highly requested 'Send to Gallery' workflow via an updated Canvas setting and introduces several UI enhancements and bug fixes across the application.

This patch release primarily fixes an issue where drag-and-drop from the gallery was not working.

This patch release focuses on stability and performance improvements, including fixing UI crashes, enhancing database thread safety, and optimizing gallery loading.

This patch release primarily focuses on bug fixes, including UI stability and database concurrency issues, alongside performance improvements for the image gallery and staging area.

Invoke 6.0 introduces a major UI overhaul with customizable layouts, new Launchpads, and enhanced Canvas features like PSD export and FLUX Kontext integration. This release also brings significant performance improvements and addresses numerous bugs.

This release candidate (v6.0.0rc5) introduces significant UI/UX improvements, including new Launchpads, a dedicated Generate tab, and enhanced Canvas features like composition guides and PSD export. It also adds support for FLUX Kontext and OMI LoRA, alongside Prompt Expansion for Pro users.

Invoke v6.0.0rc4 introduces significant UI/UX improvements, including new Launchpads, a dedicated Generate tab, and enhanced Canvas features like PSD export. This release also adds support for FLUX Kontext and OMI LoRAs, alongside Prompt Expansion for Pro users.

Invoke v6.0.0rc3 introduces major UI/UX improvements including new Launchpads, a dedicated Generate tab, and enhanced Canvas features like PSD export and composition guides. This release also adds support for FLUX Kontext and OMI LoRAs, alongside numerous bug fixes.

This release introduces support for FLUX LoRAs and SDXL IP Adapter Plus, alongside significant stability improvements including fixes for rare validation errors and memory usage optimization. Users are encouraged to use the Invoke Launcher for installation and updates.

Version 5.14.0 introduces smoother Canvas layer fitting animations and fixes critical bugs related to inpainting models and Canvas viewport scaling. Installation is now strongly recommended via the Invoke Launcher.

This release introduces advanced Inpainting mask controls with noise and denoising limits, alongside performance improvements and better handling for SDXL aspect ratios. Users are encouraged to use the Invoke Launcher for installation and updates.

This release introduces advanced per-mask controls for Canvas Inpainting, including noise level and denoising limits, alongside performance improvements and UI enhancements.

This release introduces advanced per-mask controls for Canvas Inpainting, including noise level and denoising limits, alongside performance improvements and better handling for SDXL aspect ratios.

This release introduces advanced per-mask controls for Canvas Inpainting, including noise level and denoising limits, alongside general Canvas enhancements and improved SDXL aspect ratio handling.

This release introduces support for Nvidia 50xx GPUs via a PyTorch bump, adds model relationship management, and implements stricter validation for node default values, which may require updates for custom node authors.

This release introduces support for Nvidia 50xx GPUs and a new model relationship feature for linking LoRAs. It also enforces stricter validation on node default values, which may require updates for custom node developers.

This release introduces support for Nvidia 50xx GPUs via a PyTorch update, adds model relationship management for linking LoRAs, and provides new IP Adapter methods. Internal changes were also made to improve stability regarding pydantic validation errors.

This release introduces a major new model drop-down component and critical installation updates requiring the latest launcher (v1.5.0). Users must take specific steps to ensure a smooth upgrade, including backing up Form Builder state.

This release introduces significant installation prerequisites, including a mandatory launcher update, and brings new UI components like the model combobox, alongside internal preparation for Imagen3/ChatGPT 4o support.

This release introduces a new model selection combobox and ensures image output nodes correctly update the gallery. Critical installation updates require using the latest launcher (v1.5.0) and awareness of a potential Form Builder reset for older versions.

This patch introduces VRAM optimization via partial loading for LLaVA and SigLIP models and fixes installation issues for older versions. Critical pre-update steps are required for users on versions older than v5.10.0.

This release introduces support for the CogView4 model and major internal improvements, including Python 3.12 and PyTorch 2.6.0 compatibility, alongside critical installation updates.

This release introduces support for the CogView4 model and major dependency bumps, including Python 3.12 and PyTorch 2.6.0. A significant internal change merges Form Builder and Node Editor state, requiring users to save Form Builder state before updating.

This release focuses on bug fixes related to masking, FLUX Fill behavior, and installation errors, alongside internal CI improvements. The Invoke Launcher is now the recommended installation method.

This release introduces FLUX Fill support for high-quality inpainting/outpainting and beta support for the LLaVA OneVision VLLM multimodal model. It also includes numerous UX improvements, bug fixes, and internal refactoring for model handling.

This release introduces major features including FLUX Fill support for high-quality inpainting/outpainting and support for the LLaVA OneVision VLLM multimodal model. It also includes several bug fixes and developer enhancements like custom string field dropdowns in the Workflow Builder.

This release introduces FLUX Fill support for advanced inpainting/outpainting and adds support for the LLaVA OneVision multimodal model family, alongside several UX and internal improvements.

This release introduces UI enhancements for queue management and resolves a critical bug related to retry functionality that caused infinite error loops. The Invoke Launcher is now the preferred installation method.

This release introduces an upgraded Workflow Library with enhanced browsing capabilities and adds support for FLUX Redux in Workflows and Canvas for improved image guidance. Numerous bug fixes address issues in the Form Builder, workflow saving, and UI rendering.

This release candidate introduces an upgraded Workflow Library UI/navigation and adds support for the FLUX Redux add-on model for image generation guidance. Several stability improvements were made regarding workflow loading and form element rendering.

This alpha release introduces significant upgrades to the Workflow Library UI and adds support for FLUX Redux integration in Canvas and Regional Guidance layers. It also includes support for WEBP image uploads.

This alpha release introduces significant upgrades to the Workflow Library UI and adds initial support for FLUX Redux. The Invoke Launcher is now the recommended installation method.

This release introduces an optional configuration to use the CUDA memory allocator for reduced peak VRAM usage and performance improvements, alongside fixes for UI rendering, ControlNet validation, and backend database handling.

This release introduces memory management improvements via an optional CUDA memory allocator setting and makes the enqueue operation non-blocking for better responsiveness. It also includes fixes for UI rendering, workflow downloads, and VAE memory estimation.

This release introduces an optional configuration to switch to the CUDA memory allocator for better VRAM management and performance, alongside support for WEBP image uploads and several UI fixes.

This release focuses on improving workflow usability with auto-linking and menu restructuring, alongside several bug fixes related to UI feedback and form rendering. The Invoke Launcher is now the recommended installation method.

This release introduces the powerful Form Builder, replacing the old Linear View in the Workflow Editor, and integrates popular metadata nodes into the core package. Numerous performance enhancements and bug fixes across the UI and backend queueing logic accompany these major feature updates.

This release introduces the major Workflow Builder, replacing the Linear View with a feature-rich form builder, alongside substantial performance improvements in batch queuing logic and various UI fixes.

This release introduces the Workflow Builder, a major replacement for the Workflow Editor's Linear View, offering a new form-based interface with drag-and-drop support. It also includes numerous performance enhancements and quality-of-life fixes across the application.

This minor release separates Upscaling settings from Canvas settings for better control and includes several bug fixes, notably for the Multiply Image Channel node, alongside dependency updates.

This release focuses on stability and usability improvements, including expanded LoRA compatibility, new canvas editing features, and better memory management defaults. Users are encouraged to adopt the new Invoke Launcher for installation and updates.

This release introduces several UI and workflow enhancements, including new canvas editing features and improved node connectivity, alongside fixes for LoRA loading and model initialization.

This release introduces significant memory management improvements (Low-VRAM mode) to support larger models, alongside major enhancements to Workflow Batches including new data types and grouping functionality. New Blur and Noise Canvas filters were also added.

This release introduces significant memory management improvements, enabling Low-VRAM mode for larger model generation, alongside major enhancements to Workflow Batches with new data types and grouping capabilities. New Blur and Noise Canvas filters are also available.

This release focuses heavily on memory management improvements, introducing Low-VRAM mode capabilities to run large models on constrained hardware, alongside significant enhancements to Workflow batch processing with new data types and grouping features.