github invoke-ai/InvokeAI v5.4.1rc1

pre-release14 hours ago

This release brings support for SD 3.5 to Workflows, plus a number of fixes and improvements.

We pulled v5.4.0 due to issues with model installation and loading. This release (v5.4.1) resolves those issues and includes all changes from v5.4.0.

SD 3.5

We've added initial support for SD 3.5 in workflows. Currently, only Text-to-Image is supported. We'll add Image-to-Image support along Canvas support in the next few days.

Both SD 3.5 Large and Medium are supported and available via starter models. A sample workflow to get you started is in the Workflow Library. The node is marked as prototype; it's possible we will make some changes to it before marking it stable.

Other Changes

Enhancements

  • Moved Denoising Strength slider to top of Layers panel with updated UI and info popover.
  • Update viewer styling to have a menubar-ish header. Also used for image comparison.
  • Layer preview tooltip with larger sized preview.
  • Empty state for Control Layers, guiding user to upload an image, drag an image from gallery or start drawing.
  • "Simple" mode for control layers filtering, triggered when you select a control model. This automatically selects and processes the default filter for that model, if a default exists. If the user clicks Advanced, they get the full filter settings UI. Control Layers now start with no model selected, implicitly directing users into this flow.
  • Update default control weight to 0.75, end step % to 0.75. Update label for the Balanced control mode, indicating it is the recommended setting.

Fixes

  • Canvas progress images do not clear when canceling generation after at least one image has been staged.
  • Tooltips on boards list stay open when scrolling, potentially causing the whole app to scroll.
  • Saving canvas to gallery does not create a new image in gallery.
  • Applying a filter could erase or otherwise change a layer's data unexpectedly, causing a range of user-facing generation issues.
  • Unable to queue graphs with the Segment Anything node when its inputs were provided by connection.
  • Unable to load a workflow from file when using the three-dots menu.
  • pip downloads torch twice. This didn't cause any application issues - just a waste of time and bandwidth. We pinned torch to <2.5.0 to prevent pip's dependency resolver from getting confused.
  • mediapipe install issue on Windows, related to its latest release. We pinned mediapipe to a known working version.

Internal

  • Simplified parameter schema declarations. Thanks @rikublock!

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

Full Changelog: v5.3.1...v5.4.1rc1

Don't miss a new InvokeAI release

NewReleases is sending notifications on new releases.