github invoke-ai/InvokeAI v6.13.0.rc1
v6.13.0rc1
on GitHub

pre-release7 hours ago

InvokeAI v6.13.0 (release candidate 1)

This release of InvokeAI offers support for a variety of new models, including those that are remotely hosted by external providers such as GPT Image. In addition, it provides a host of new and improved features as well as bug fixes.

New Locally-Hosted Models

We've added support for the popular Qwen Image models, both the txt2img and edit versions, as well as Anima.

Qwen Image 2.5

This is a high quality txt2img model that can be run either on your local hardware are on a remotely hosted service (see Hosted Models. We provide starters for the full model (~40 GB!) as well as multiple smaller quantized models. For best results, we recommend 30-40 steps and a CFG of 3-4. We also provide two "turbo" LoRA models, Qwen Image Lightning (4-steps) and Qwen_Image_Lightning (8-steps). These LoRAs provide fast rendering and high accuracy, but loss of diversity. Use a CFG of 1 and a Shift of 3 when applying either of these LoRAs.

Qwen Image Edit 2.5

This is a version of Qwen Image that is optimized for image editing. Add up to three reference images and tell the model on how to combine and alter them using declarative statements such as "Pose the duck on the table". We provide the full model as a starter, along with multiple quantized versions and two Qwen Image Edit Lightning LoRAs for turbo mode.

See Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency for tips on using Qwen Image Edit effectively.

Anima Preview 3

Anima is an anime-themed model created by a collaboration between CircleStone Labs and Comfy Org. It is able to produce a wide variety of illustration styles. There is also an Anima Turbo LoRA that can be used to speed up rendering using a CFG of 1 and 8-12 steps.

You'll find Anima and its support models in the Starter Models tab.

New Externally-Hosted Models

This version of InvokeAI offers the ability to generate using externally-hosted models, such as those provided by OpenAI, Google and cloud-based AI generation hosting services. You "install" these models by providing an API key provided by a service that you subscribe to. Typically image generation services will provide a number of generations for free and then start charging on a pay-as-you-go basis. We support externally-hosted models from OpenAI, and Gemini (Google).

The full release will add support for models from BytePlus, and Alibaba Cloud.

An externally-hosted model works much like a locally-hosted one but with restrictions. In general, you cannot adust steps, scheduler or CFG, and only a limited number of image dimensions are supported. Both txt2img and img2img modes are supported, and the models can be applied to the Canvas and Workflow editor. However inpainting, outpainting, controlnets, LoRAs, regional guidance, and the ability to apply different levels of denoising to img2img are not available. These are limitations imposed by the hosting service and not by InvokeAI.

To get started with externally-hosted models, go to the Models tab and select External Providers. Select the hosting service you wish to use and enter your API key. Click Save and the models supported by this provider will be added to your collection of models.

Models available from OpenAI

  • GPT Image 1
  • GPT Image 1.5
  • GPT Image 1 Mini
  • DALL-E 3

Models available from Gemini (Google)

  • Gemini 2.5 Flash Image
  • Gemini 3 Pro Image Preview
  • Gemini 3.1 Flash Image Preview

Model Manager Improvements

This version improves the Model Manager in several ways. When installing a new model, the installation queue display and progress bars have been completely rewritten to be more functional and attractive. A new bulk reidentify action has been implemented, and it is now possible to sort the model listing in multiple ways.

Image Generation Improvements

Users now have access to LLM-powered prompt expansion and image-to-prompt features. You will find two new buttons in the prompt textfield:

  • Expand Prompt uses a local TextLLM model to expand brief prompts into detailed image generation prompts. This button will replace a simple prompt with a complex one that is well-suited for producing high quality imagery.
  • Image to Prompt Generates descriptive prompts from uploaded images. Use it as a supplement to reference images.

To use these features, you must first install a causal LM model, such as Qwen/Qwen2.5-1.5B-Instruct via the Model Manager (enter this repo name into the HuggingFace tab). The LLaVA vision model needed for image to prompt should already be installed.

In addition, this release corrects many small bugs and performance bottlenecks in image generation.

Image Gallery Improvements

You can now automatically create "virtual" boards that group images according to their characteristics. Right now you can only create virtual boards that group images by their date, but more options are on their way.

Canvas Improvements

There have been several new features added to the Canvas. One frequently-requested feature is the ability to hide and show the preview stage thumbnails that can obscure the bottom of the canvas. Another feature is the addition of a Lasso Tool with freehand and polygon modes for creating inpaint masks and selecting raster image regions.

Also among multiple new features is the ability to apply custom workflows directly to a Canvas image. First create a workflow with an image input field in the Form Builder and a Canvas Output node. Right click on the canvas and select Run Workflow. The workflow will run on the input image and create a new layer containing the output of the Canvas Output node.

Workflow Editor and Nodes

There is now a Custom Node Manager tab in the left-hand panel which allows you to install and manage related groups of nodes called node packs. Node packs can be installed from local files or URLs.

When adding a node to a workflow, you will find that the nodes are now organized by function with an easy to navigate node picker. Another convenient new feature is the workflow connector, a new type of edge that can be used to connect two or more input/output fields in a highly flexible fashion. To start using this feature, right click on the canvas and select Add Connector.

Internally the workflow execution engine has been overhauled and optimized to improve performance and stability. In addition, there are a number of new user-visible features. There are new generation nodes for running external models, new denoising nodes for the Qwen Image and Anima local models, and a node for decoding invisible watermarks in images. The Collect node now supports chaining to enable deterministic iteration over the items in a collection. A new If mode allows for conditional branching of workflows.

Multiuser Features

When running in Multiuser Mode each logged-in user can create private (only visible to the owner), shared (writable by the owner, readable by everyone else) and public (read/write for everyone) image boards. Similarly, users can now create private and shared workflows.

Documentation

The Documentation Site has been completely redesigned and overhauled. However, be aware that the documentation for some of the newer features has not yet been ported over to the new site, and can be found here.

What's Changed in Detail

Below is a log of all changes from the previous version. Many thanks to all the authors who contributed to this release.

Models and Model Manager

Image Generation

  • Feat(UI): Add LLM-powered prompt expansion and image-to-prompt features by @Pfannkuchensack in #8899
  • Fix(frontend): Make ordering of multiple FLUX.2 reference images deterministic by @lstein in #8989
  • Upgrade spandrel version by @JPPhoto in #8996
  • fix: detect Z-Image LoRAs with transformer.layers prefix by @Pfannkuchensack in #8986
  • Fix partial-load device recovery across CLIP, T5, and Qwen text encoders by @JPPhoto in #9034
  • feat: add configurable shift parameter for Z-Image by @Pfannkuchensack in #9004
  • Feature: Add optional setting to prune queue on startup by @DustyShoe in #8861
  • Handle mixed-dtype mismatches in autocast linear and conv wrappers by @JPPhoto in #9006
  • fix(ui): FLUX.2 Klein VAE/Qwen3 readiness checks and diffusers source auto-detection by @lstein in #9041
  • Fix: Preserve reference image panel state and selection on recall by @ufuksarp in #9010
  • Fix: Z-Image LoRA detection for Kohya and ComfyUI formats by @Pfannkuchensack in #9007
  • [Fix] remove anima optimized denoise by @dunkeroni in #9072
  • fix: SDXL DoRA LoRA fails with enable_partial_loading=true by @Pfannkuchensack in #9063
  • fix(flux2): remove inert guidance UI, add Klein 4B Base variant, fix metadata recall by @Pfannkuchensack in #8995
  • Align DyPE with the paper as much as possible by @JPPhoto in #8980
  • feat(recall): support direct model reference images in recall API by @lstein in #9045

Image Gallery

Canvas

Workflow Editor and Nodes

  • feat: add Custom Node Manager by @Pfannkuchensack in #9047
  • Add chaining to Collect node by @JPPhoto in #8933
  • Feature (frontend): Add invisible watermark decoder node. by @lstein in #8967
  • Fix workflows info copy focus by @JPPhoto in #9015
  • Added If node and ability to link an Any output to a node input if cardinality matches by @JPPhoto in #8869
  • graph.py refactoring and If node optimization by @JPPhoto in #9030
  • Added workflow connectors by @JPPhoto in #9027
  • feat(ui): group nodes by category in add-node dialog by @Pfannkuchensack in #8912
  • Prevent stale queue snapshots from regressing workflow completion state by @JPPhoto in #9043
  • fix(ui): stabilize workflow node execution state updates by @JPPhoto in #9029
  • Fix graph execution state resume after JSON round-trip by @JPPhoto in #9042
  • Fix lazy If branch pruning and skipped-parent handling in graph runtime by @JPPhoto in #9079

Multiuser

  • Fix (multiuser): Ask user to log back in when security token has expired by @lstein in #9017
  • feat(multiuser): Shared/private workflows and image boards in multiuser mode by @lstein in #9018
  • fix(multiuser): make preexisting workflows visible after migration by @lstein in #9049

Internationalizaton

Thanks to Dmitry Warkentin and Riccardo Giovanetti (@Harvester62) for contributing Russian and Italian translations, respectively.

Documentation

Miscellaneous

  • chore: bump version to 6.12.0.post1 by @lstein in #8990
  • Fix SIGINT shutdown during active inference by @JPPhoto in #8993
  • Run vitest during frontend build by @JPPhoto in #9022
  • feat(frontend): suppress tooltips on touch devices by @lstein in #9001
  • fix: patch openapi-typescript enum generation to match OpenAPI schema by @lstein in #9037
  • Feat(UI): Replace prompt window resize handle with bottom edge drag handle. by @DustyShoe in #8975
  • Feat(UI): Reintroduce middle click to open image in new tab by @DustyShoe in #8998
  • chore(CI/CD): Prevent agents from running npm by @lstein in #8930

New Contributors

Full Changelog: v6.12.0...v6.13.0.rc1

Check out latest releases or
releases around invoke-ai/InvokeAI v6.13.0.rc1

Don't miss a new InvokeAI release

NewReleases is sending notifications on new releases.

Get notifications