v6.8.0

invoke-ai/InvokeAIv6.8.0Oct 8, 2025by psychedelicious

Upgrading?

Release notes summary

A minor release focusing on fixes and enhancements, including a crop tool for reference images, improvements to the Model Manager UI, and keyboard shortcuts for prompt history navigation.

Key Highlights

  • Added a crop tool for Global Ref Images allowing users to adjust and save cropped portions.
  • Improved Model Manager tab UI for better usability.
  • Keyboard shortcuts (Alt/Option+Up/Down) to navigate prompt history.
  • Support for the NOOB-IPA-MARK1 IP Adapter.

New Features

  • Crop tool for ref images.
  • Model Manager UI refactor.
  • Prompt history navigation shortcuts.
  • NOOB-IPA-MARK1 IP Adapter support.
  • Dynamic model drop-downs in Workflow Editor.

Full Release Notes

This minor release includes a handful of fixes and enhancements.

### Fixes

- When accepting raster layer adjustments, the opacity of the layer was "baked" in.
- Corrected help text for non-in-place model installation. Previously, the help text said that a non-in-place model install would copy the model files. This is incorrect; it _moves_ them into the Invoke-managed models dir.
- Failure to queue generations with an error like `Failed to Queue Batch / Unknown Error`.

### Enhancements

- Added a crop tool. For now, it is only enabled for Global Ref Images.
  - Click the crop icon on the Ref Image preview to open the tool.
  - Adjust the crop box and click apply to save the cropped image for that ref image.
  - To revert, open the crop tool, click Reset, then Apply to revert to the original image. 
  - We'll explore integrating this new tool elsewhere in the app in a future update.
- Improved Model Manager tab UI. Thanks @joshistoast!
- Keyboard shortcuts to navigate prompt history. Use `alt/option+up/down` to move through history.
- Support for the `NOOB-IPA-MARK1` IP Adapter. Thanks @Iq1pl!

### Internal

- Support for dynamic model drop-downs in Workflow Editor. This change greatly reduces the amount of frontend code changes needed to support a new model type. **Node authors may need to update their nodes to prevent warnings from being displayed. However, there are no breakages expected.** See #8577 for more details.

## Installing and Updating

**The 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.

Note: With recent updates to `torch`, users on older GPUs (20xx and 10xx series) will likely run into issues with installing/updating. We are still evaluating how we can support older GPUs, but in the meantime users have found success manually downgrading `torch`. Head over to [discord](https://discord.gg/ZmtBAhwWhy) if you need help.

Follow the [Quick Start guide](https://invoke-ai.github.io/InvokeAI/installation/quick_start/) 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](https://invoke-ai.github.io/InvokeAI/installation/manual/).

## What's Changed
* fix(ui): do not reset params state on studio init nav to generate tab by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8572
* feat(model manager): :lipstick: refactor model manager ui by @joshistoast in https://github.com/invoke-ai/InvokeAI/pull/8564
* Prompt history shortcuts by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/8571
* feat(ui): crop tool by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8562
* chore: prep for v6.8.0rc1 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8574
* fix(ui): allow scrolling in ModelPane by @joshistoast in https://github.com/invoke-ai/InvokeAI/pull/8580
* added support for NOOB-IPA-MARK1 by @Iq1pl in https://github.com/invoke-ai/InvokeAI/pull/8576
* feat: dynamic model fields in workflow editor by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8577
* ui: translations update from weblate by @weblate in https://github.com/invoke-ai/InvokeAI/pull/8575
* fix(ui): ref images for flux kontext not parsed correctly by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8587
* feat(nodes): better ui_type deprecations by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8586
* restore list_queue_items method by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/8583
* fix(ui): do not bake opacity when rasterizing layer adjustments by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8592
* fix(ui): correct the in-place install verbiage, add tooltip by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8593
* docs: add BiRefNet and Image Export to communityNodes.md by @veeliks in https://github.com/invoke-ai/InvokeAI/pull/8602
* chore: prep for v6.8.0rc2 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8581
* chore: prep for v6.8.0 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8604

## New Contributors
* @Iq1pl made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/8576
* @veeliks made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/8602

**Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v6.7.0...v6.8.0

Related Repositories