Releases

Find a version

All versions All versions forward View on GitHub

Version v5.0.1

Sep 30, 2024

This minor release includes support for Kohya FLUX LoRAs and a handful of fixes and enhancements.

Be sure to review the v5 release notes if you haven’t already upgraded to v5.

Enhancements

• Support for Kohya FLUX LoRAs with lora_te1 layers (i.e. CLIP LoRA layers)
• Default scheduler is now dpmpp_3m_k
• First round of v5 translations @Harvester62 @Vasyanator @Atalanttore @Ery4z @rikublock
• Improved FLUX img2img/inpainting
  • ❗ This is a breaking change. The trajectory_guidance_strength field on FluxDenoiseInvocation was removed in favor of a simpler solution that doesn’t need the extra field. More details in #6938.
• Revised hotkeys focus tracking
• Recall hotkeys work when viewer is closed and gallery is open
• Added enter and esc hotkeys to apply and cancel filters and transforms
• Model default settings support for FLUX guidance parameter

Fixes

• Hide brush preview while staging
• Prevent error toasts from being so large they cannot be closed
• UI crash with TypeError: i.map is not a function
• Canvas erroneously interactable after refresh while staging

Internal

• More efficient image selection handling
• More efficient newly-generated image handling
• Revised resizable panels logic

Installation and Updating

To install or update to v5.0.1, download the 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(ui): reduce extraneous image selection by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6930
• feat(ui): cleanup resizable panels by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6932
• fix(ui): incorrect translations for flux bbox constraints by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6933
• fix,feat: canvas followups 18 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6941
• fix(ui): restore send-to functionality by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6937
• update default scheduler to dpmpp_3m_k by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6943
• fix workflow tab translations by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6944
• fix(ui): gallery nav hotkeys not working by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6949
• fix(ui): handle resizable panels not rendered in DOM by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6948
• fix(ui): truncate error description so toast is always close-able by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6946
• fix(ui): new image selection logic by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6951
• ui: translations update from weblate by @weblate in https://github.com/invoke-ai/InvokeAI/pull/6818
• fix(ui): resizable panels collapsed on first app startup by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6953
• fix(ui): canvas interactable after refresh while staging by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6956
• Further improvements to FLUX image-to-image by @RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/6938
• (ui): add button to learn more about supported models by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6958
• fix(api): UI crash with TypeError: i.map is not a function by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6985
• Support FLUX LoRA models in kohya format with lora_te1 layers (i.e. CLIP LoRA layers) by @RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/6967
• refactor(ui): hotkey/focus handling by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6987
• ui: translations update from weblate by @weblate in https://github.com/invoke-ai/InvokeAI/pull/6963
• chore: bump version to v5.0.1 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6993
• Update communityNodes.md add OBP by @AIrjen in https://github.com/invoke-ai/InvokeAI/pull/6990
• feat(ui,api): add guidance as a default setting option for FLUX models by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6959

New Contributors

• @AIrjen made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/6990

Full Changelog: https://github.com/invoke-ai/InvokeAI/compare/v5.0.0…v5.0.1