invoke-ai/InvokeAI v5.4.3rc2

on GitHub

This minor release adds initial support for FLUX Regional Guidance, arrow key nudge on Canvas, plus an assortment of fixes and enhancements.

Changes

Enhancements

• Add 1-pixel nudge to the move tool on Canvas. Use the arrow keys to make fine adjustments to a layer's position. Thanks @hippalectryon-0!
• Change the default infill method from patchmatch to lama. You can use patchmatch.
• Add empty state for Global Reference Images and Regional Guidance Reference Images, similar to the empty state for Control Layers. A blurb directs users to upload an image or drag an image from gallery to set the image.
• FLUX performance improvements (~10% speed-up).
• Added ImagePanelLayoutInvocation to facilitate FLUX IC-LoRA workflows.
• FLUX Regional Guidance support (beta). Only positive prompts are supported; negative prompts, reference images and auto-negative are not supported for FLUX Regional Guidance.
• Canvas layers now have a warning indicator that indicates issues with the layer that could prevent invoking or cause a problem.
• New Layer from Image functions added to Canvas Staging Area Toolbar. These create a new layer without dismissing the rest of the staged images.
• Improved empty state for Regional Guidance Reference Images.
• Added missing New from... image context menu actions: Reference Image (Regional) and Reference Image (Global)
• Added Vietnamese to language picker in Settings.

Fixes

• Soft Edge (Lineart, Lineart Anime) Control Layers default to the Soft Edge filter correctly.
• Remove the nonfunctional width and height outputs from the Image Batch node. If you want to use width and height in a batch, route the image from Image Batch to an Image Primitive node, which outputs width and height.
• Ensure invocation templates have fully parsed before running studio init actions.
• Bumped transformers to get a fix for Depth Anything artifacts.
• False negative edge case with picklescan.
• Invoke queue actions menu's Cancel Current action erroneously cleared the entire queue. Thanks @rikublock!
• New Reference Images could inadvertently have the last-used Reference Image populated on creation.
• Error when importing GGUF models. Thanks @JPPhoto!
• Canceling any queue item from the Queue tab also erroneously canceled the currently-executing queue item.

Internal

• Add redux actions for support video modal.
• Tidied various things related to the queue. Thanks @rikublock!

Docs

• General tidy across many docs pages. Thanks @magnusviri!
• Fixed a few broken links. Thanks @emmanuel-ferdman!

Translations

• Updated Italian translations. Thanks @Harvester62!

Installation and Updating

To install or update, download the latest installer and follow the installation instructions

To update, select the same installation location. Your user data (images, models, etc) will be retained.

What's Changed

• fix(api): make sure Soft Edge Detection has preprocessor applied by @maryhipp in #7360
• fix(ui): disable width and height output on image batch output by @psychedelicious in #7361
• feat(ui): set default infill method to lama by @psychedelicious in #7362
• fix(ui): make sure schema has loaded before trying to load any workflows by @maryhipp in #7364
• feat(ui): add actions for video modal clicks by @maryhipp in #7365
• feat(ui): add empty state for regional guidance ref image by @psychedelicious in #7363
• feat(ui): nudge on canvas by @psychedelicious in #7368
• chore: bump version to v5.4.3rc1 by @psychedelicious in #7369
• fix(ui): use token for download if its in store by @maryhipp in #7373
• Create SECURITY.md by @hipsterusername in #7376
• misc(ui): various copy updates by @maryhipp in #7382
• fix: Fail scan on InvalidMagicError in picklescan, update default for… by @brandonrising in #7381
• Add ImagePanelLayoutInvocation utility to facilitate In-Context LoRA workflows by @RyanJDick in #7374
• Bump transformers to ingest a DepthAnything post-processing fix by @RyanJDick in #7386
• docs: update code of conduct reference by @emmanuel-ferdman in #7380
• FLUX Regional Prompting by @RyanJDick in #7388
• FLUX Speed Improvements (~10% speedup) by @RyanJDick in #7399
• Update node vers by @JPPhoto in #7403
• feat(ui): add New Layer from Image menu to staging area toolbar by @psychedelicious in #7389
• refactor(ui): move clear queue hook to separate file by @rikublock in #7391
• fix(ui): call cancel instead of clear queue by @rikublock in #7392
• chore(ui): update typegen schema by @rikublock in #7394
• fix(app): adjust session queue api type by @rikublock in #7393
• ui: translations update from weblate by @weblate in #7397
• feat(ui): less confusing empty state for rg ref images by @psychedelicious in #7407
• fix(ui): ref image defaults to prev ref image's image selection by @psychedelicious in #7408
• feat(ui): add gallery image ctx menu items to create ref image from image by @psychedelicious in #7409
• fix(ui): allow invoke when inpaint/raster layers are empty by @psychedelicious in #7410
• fix(ui): remove "adding to" text on Invoke tooltip on Workflows/Upscaling tabs by @psychedelicious in #7411
• feat(ui): add vietnamese to language picker by @psychedelicious in #7412
• fix(worker): only apply processor cancel logic if cancel event is for current item by @maryhipp in #7416
• ui: translations update from weblate by @weblate in #7415
• Fix gguf importing by @JPPhoto in #7405
• [docs] Fix documentation broken links and remove whitespace at end of lines by @magnusviri in #7402
• ui: translations update from weblate by @weblate in #7418
• chore: bump version to v5.4.3rc2 by @psychedelicious in #7413

New Contributors

• @emmanuel-ferdman made their first contribution in #7380

Full Changelog: v5.4.2...v5.4.3rc2