●Change8

v5.6.1rc1

📦 invokeaiView on GitHub →
✨ 9 features🐛 4 fixes🔧 5 symbols

Summary

This release introduces several UI and workflow enhancements, including new canvas editing features and improved node connectivity, alongside fixes for LoRA loading and model initialization.

Migration Steps

  1. The new Invoke Launcher is the recommended way to install, update and run Invoke. Follow the Quick Start guide to get started with the launcher.
  2. If you require a headless install, follow the manual install guide.

✨ New Features

  • Expanded FLUX LoRA compatibility, including support for FLUX OneTrainer LoRA formats (incl. DoRA).
  • On-demand model cache clearing via a button on the Queue tab.
  • Canvas Adjust Image filter added (e.g., levels, hue adjustments).
  • Button added to cancel all queue items except the currently running one.
  • Functionality to Copy Canvas/Bbox as image via the Canvas right-click menu.
  • Functionality to Paste image into Canvas/Bbox using the normal paste hotkey, prompting for placement.
  • Allow 'Collect' nodes to be connected directly to 'Iterate' nodes.
  • Allow 'Any' type node inputs to accept collections (e.g., 'Metadata Item' node's value field now accepts collections).
  • LoRA Loader node LoRA collection input is now optional.

🐛 Bug Fixes

  • Fixed bug with some LoRA variants when applied to bitsandbytes NF4 quantized models.
  • Improved MaskOutput dimension consistency.
  • Fixed T5EncoderField initialization in SD3 model loader.
  • Improved error messages when invalid graphs are queued.

🔧 Affected Symbols

LoRA Loader nodeCollect nodeIterate nodeMetadata Item nodeT5EncoderField