InvokeAI Files

This release includes a handful of fixes and enhancements.

Enhancements

Shout-out to @csehatt741 for knocking out some great QoL improvements. Thank you!

• Canvas Bbox visibility can be toggled with shift+o. Thanks @csehatt741!
• Nodes with execution errors are highlighted red. Thanks @csehatt741!
• Prevent a field from being added to Workflow Builder forms multiple times. Thanks @csehatt741!
• Support recall of CLIP Skip metadata. Thanks @csehatt741!
• Fixed some issues with model install paths.
• Tweaked state persistence strategy - now debounced to 300ms instead of throttled to 2000ms. This should reduce stutters while doing things like panning around the Canvas.
• SDXL Style prompts have been removed from the Generate, Canvas and Upscaling tabs. This rarely-used setting was unintuitive at best. You can still use it in Workflows, but we are removing this footgun from the linear UI tabs.
• Prompt and seed metadata may now be recalled on the Upscaling tab.
• The buttons to download potentially very large starter model bundles show a confirmation dialog before starting the download. Thanks @csehatt741!
• Merged layers are inserted in the right spot in the layers panel. Thanks @csehatt741!
• Added button to image context menu and viewer toolbar to locate an image in the gallery. The image's board is selected and image scrolled to. Thanks @csehatt741!
• Support FLUX PEFT LoRAs with base_model.model key prefix.
• Improved VAE encode VRAM usage.
• Updated translations. Thanks @Harvester62!

Fixes

• Minor bug when concatenating Kontext ref images in latent space that could result in some images not being "seen".
• Fit to Bbox functionality could result in the layer being sized correctly but positioned incorrectly when the bbox was not aligned to the 64px grid.
• Allow use of mouse in node title editable inputs.

Internal/Dev

• Fix AMD docker image build issue related to disk space. Thanks @heathen711!

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 if you need help.

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

• chore: prep for v6.3.0 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8397
• bugfix(container-builder) Use the mnt space instead of root space for docker images by @heathen711 in https://github.com/invoke-ai/InvokeAI/pull/8361
• feat(ui): add toggle for bbox with hotkey by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8385
• feat(ui): outline error nodes in red by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8398
• fix(ui): same field cannot be added to form multiple times in workflow editor by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8403
• feat(mm): improved VAE encode VRAM usage by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8414
• fix(mm): only add suffix to model paths when path is file by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8413
• feat(ui): debounce persistence instead of throttle by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8410
• fix(ui): upscaling prompt metadata by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8411
• fix(ui): input field error styling specificity by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8418
• feat(ui): add missing translation strings by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8412
• fix(mm): fail when model exists at path instead of finding unused new path by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8419
• Update NODES.md by @solkyoshiro in https://github.com/invoke-ai/InvokeAI/pull/8378
• chore: fix some comments by @jiangmencity in https://github.com/invoke-ai/InvokeAI/pull/7575
• feat(ui): remove SDXL style prompt from linear UI by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8417
• ui: translations update from weblate by @weblate in https://github.com/invoke-ai/InvokeAI/pull/8404
• feat(ui)/clip skip by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8422
• feat(ui): confirmation before downloading starter bundle by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8427
• feat(ui): layer behaviour after merging by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8428
• feat(ui): locate in gallery image context menu by @csehatt741 in https://github.com/invoke-ai/InvokeAI/pull/8434
• tests: skip flaky MPS tests on CI by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8442
• fix(ui): update board totals when generation completes by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8424
• fix(ui): export NumericalParameterConfig type by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8436
• refactor: estimate working vae memory during encode/decode by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8438
• Support PEFT Loras with Base_Model.model prefix by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/8433
• fix(ui): fit to bbox when bbox is not aligned to 64px grid by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8439
• fix(ui): prevent node drag when editing title by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8440
• chore: prep for v6.4.0rc2 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8441
• ui: translations update from weblate by @weblate in https://github.com/invoke-ai/InvokeAI/pull/8432
• git: move test LoRA to LFS by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/8446

New Contributors

• @csehatt741 made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/8385
• @solkyoshiro made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/8378
• @jiangmencity made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/7575

Full Changelog: https://github.com/invoke-ai/InvokeAI/compare/v6.3.0...v6.4.0