github invoke-ai/InvokeAI v5.8.0a2

pre-releaseone day ago

This alpha release introduces an upgraded Workflow Library and FLUX Redux support.

Changes since the previous alpha

  • FLUX Redux support on Canvas.
  • Support for uploading WEBP images. They are converted to PNG after uploading.
  • Internal, transparent changes to custom node loading.
  • Fixed an issue where a "shared" category was displayed in the new Workflow Library.

Workflow Library

We'll flesh out the details in a future release, but the goal is to make the Workflow Library more approachable. We are investing in expanded default workflows, and with the recent introduction of the Workflow Builder, a good library is more important.

This rework makes the library into a larger, easier-to-navigate modal. It may feel a bit empty if you do not already have a large library of workflows. We will ship an updated collection of workflows in the v5.8.0 stable release that fills it out nicely.

Notable changes include:

  • Browse by tag (default workflows only)
  • Search by name/description/tags
  • Opened at works correctly
  • Workflows may have thumbnails
  • Recently opened workflows area (the list will be incorrect at first, because we haven't been tracking this information until now)

The UI is a WIP - we know it is a bit rough in places. Feedback appreciated!

FLUX Redux

This release includes support for FLUX Redux in Workflows and Canvas.

FLUX Redux is an add-on model for FLUX. It works similarly to IP Adapter or an "instant" LoRA, where an input image guides the generation's style and composition. It can provide some degree of character consistency.

To use it on Canvas, add a Global Reference Image layer and drag a reference image onto the layer - same as you would for IP Adapter - and select the FLUX Redux from the model drop-down.

You can also use it in Regional Guidance layers. Add a Reference Image to the layer and select FLUX Redux from the model drop-down.

Other Changes

  • Support for uploading WEBP images. They are converted to PNG after uploading.
  • Internal, transparent changes to custom node loading.
  • Updated translations.

Download the models from the Starter Models tab in the Model Manager.

Installing and Updating

The new Invoke Launcher is the recommended way to install, update and run Invoke. It takes care of a lot of details for you - like installing the right version of python - and runs Invoke as a desktop application.

Follow the Quick Start guide to get started with the launcher.

If you don't want to use the launcher, or need a headless install, you can follow the manual install guide.

What's Changed

Full Changelog: v5.7.2...v5.8.0a2

Don't miss a new InvokeAI release

NewReleases is sending notifications on new releases.