v6.13.0.rc1
📦 invokeaiView on GitHub →
✨ 21 features🐛 1 fixes🔧 5 symbols
Summary
InvokeAI v6.13.0 RC1 introduces extensive support for new locally-hosted models (Qwen, Anima) and externally-hosted providers (OpenAI, Gemini). This release also brings significant feature additions to the Canvas, Workflow Editor, and new LLM-powered prompt manipulation tools.
Migration Steps
- To use LLM-powered prompt expansion, install a causal LM model (e.g., Qwen/Qwen2.5-1.5B-Instruct) via the Model Manager (HuggingFace tab).
- To use externally-hosted models, go to the Models tab, select 'External Providers', choose a service, and enter your API key.
- To use the Lasso Tool on Canvas, select it for freehand or polygon masking/selection.
- To apply custom workflows to Canvas images, create a workflow with an image input and Canvas Output node, then right-click the canvas and select 'Run Workflow'.
- To use workflow connectors, right-click the canvas and select 'Add Connector'.
✨ New Features
- Added support for remotely hosted models from external providers like OpenAI and Google (Gemini).
- Added support for locally-hosted Qwen Image models (txt2img and edit versions) and Anima.
- Introduced Qwen Image Lightning and Qwen Image Edit Lightning LoRAs for fast rendering.
- Qwen Image Edit 2.5 supports using up to three reference images with declarative editing statements.
- Anima model and Anima Turbo LoRA added for anime-themed generation.
- Model Manager improvements: rewritten installation queue display/progress bars, bulk reidentify action, and multiple sorting options for the model listing.
- New LLM-powered prompt expansion feature using a local TextLLM model.
- New Image to Prompt feature to generate descriptive prompts from uploaded images.
- Ability to automatically create virtual image boards grouped by characteristics (initially by date).
- Canvas feature to hide/show preview stage thumbnails.
- Added a Lasso Tool (freehand and polygon modes) to the Canvas for creating inpaint masks and selecting regions.
- Ability to apply custom workflows directly to a Canvas image via a right-click context menu.
- New Custom Node Manager tab for installing and managing node packs (groups of related nodes).
- Nodes in the workflow picker are now organized by function.
- Introduced the workflow connector, a new edge type for flexible connection of multiple input/output fields.
- New generation nodes for running external models.
- New denoising nodes for Qwen Image and Anima local models.
- Added a node for decoding invisible watermarks in images.
- The Collect node now supports chaining for deterministic iteration.
- A new 'If' mode in workflows allows for conditional branching.
- In Multiuser Mode, users can create private, shared, and public image boards, and private/shared workflows.
🐛 Bug Fixes
- Corrected many small bugs and performance bottlenecks in image generation.