●Change8

v5.9.0rc1

📦 invokeaiView on GitHub →
✨ 3 features🐛 2 fixes🔧 1 symbols

Summary

This release introduces FLUX Fill support for advanced inpainting/outpainting and adds support for the LLaVA OneVision multimodal model family, alongside several UX and internal improvements.

Migration Steps

  1. Download the FLUX Fill model from Starter Models and select it from the main model drop-down on Canvas to use it.
  2. Download the 0.5B variant of the LLaVA OneVision model from Starter Models and use the `LLaVA OneVision VLLM` node in Workflows.
  3. 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.

✨ New Features

  • Added FLUX Fill support in Workflows and Canvas for high quality inpainting and outpainting.
  • Added support for the LLaVA OneVision VLLM family of multimodal models, usable in Workflows via the `LLaVA OneVision VLLM` node.
  • Improved error messages when scanning models with `picklescan`.

🐛 Bug Fixes

  • Fixed issue where shift-clicking to draw on Canvas ignored the `Clip to Bbox` setting.
  • Improved UX for missing or unexpected fields in Workflows.

🔧 Affected Symbols

LLaVA OneVision VLLM node