InvokeAI

[!CAUTION]

⚠️ Please read this before you install

If you point v7 at your existing InvokeAI root directory, it will upgrade your database, and that database will no longer work with InvokeAI v6. The migrations only go one way, and v6 refuses to open a database that contains migrations it doesn't recognise.

To try v7, create a brand-new InvokeAI root directory and experiment there. In the Invoke Launcher, choose a new, empty install location. When prompted for the version, select Manual and enter version v7.0.0-beta.1. For a manual install, pass --root /path/to/new/folder or set INVOKEAI_ROOT. Keep your v6 install and its root directory exactly where they are.

Upgraded your v6 database by accident? Don't panic. Invoke makes a backup before it migrates anything, and the startup log names that backup before the upgrade begins. See Restoring your v6 database at the bottom of these notes, or the Upgrading to v7 guide.

[!WARNING] This is beta software. All the major features of 7.0 are in place, and we've spent four alphas shaking out bugs, but you will still find rough edges. Please keep backups of work you care about. When you hit a bug, please open an issue on GitHub and put v7 in the title, or tell us about it on our Discord. Screenshots, logs and the output of the Diagnostics panel all help a lot.

[!NOTE] Coming from a v7 alpha? You can install beta 1 over alpha 4 and keep using the same root directory. Beta 1 adds no database migrations of its own. If you're upgrading from alpha 3 or earlier, remember that alpha 4's migration is one-way, so once the beta has opened your root directory the older alphas won't start on it.

InvokeAI 7.0.0 (beta 1)

Okay. This is InvokeAI 7, and it's now in beta.

It's the biggest release we've ever made. Alpha 1 alone was about 320 pull requests and 2,600 commits, and four alphas later the count has grown a good deal more. Many of you are meeting v7 for the first time with this beta, so these notes start with the tour of what v7 is, then cover the major features added during the alphas, and finish with what's new in beta 1. The full documentation for v7 lives at v7.invoke.ai, which has itself been redesigned for this release (more on that below).

Before you start, two practical notes:

• v7 needs Python 3.12. Python 3.11 is no longer supported. The Launcher handles this for you.
• The new interface is the default. If you need the old one, start Invoke with --web-legacy, but be aware that the legacy front end does not support all of v7's new features, and some of the old features may no longer work as expected.

Contents: What's new in InvokeAI 7 · Added during the alphas · New in beta 1 · Contributors · Restoring your v6 database · Full changelog

What's new in InvokeAI 7

🗂️ Projects: wander off and come back

You can now start something new without the nagging feeling that you're about to lose what you were working on. Everything lives in a project: your canvas, your generation settings, your workflows, your queue history, and boards of its own for everything the project produces.

Keep several projects open as tabs. Close one and go do something else. Come back next week from the Launchpad and it's right where you left it.

Projects autosave. Edits go to your browser first and then sync to the server, so a dropped wifi connection, a crashed tab, or the same project open in two windows won

[!CAUTION]

⚠️ Please read this before you install

If you point v7 at your existing InvokeAI root directory, it will upgrade your database, and that database will no longer work with InvokeAI v6. The migrations only go one way, and v6 refuses to open a database that contains migrations it doesn't recognise.

To try v7, create a brand-new InvokeAI root directory and experiment there. In the Invoke Launcher , choose a new, empty install location. When prompted for the version, select Manual and enter version v7.0.0-alpha.4. For a manual install, pass --root /path/to/new/folder or set INVOKEAI_ROOT. Keep your v6 install and its root directory exactly where they are.

Upgraded your v6 database by accident? Don't panic. Invoke makes a backup before it migrates anything, and from this release on the startup log names that backup before the upgrade begins. See Restoring your v6 database at the bottom of these notes, or the new Upgrading to v7 guide.

[!WARNING] This is alpha software. Things will break, some features are half-finished, and a few corners still have cobwebs. Please don't trust it with work you can't afford to lose. When you hit a bug, and you will, please open an issue on GitHub and put v7 in the title, or tell us about it on our Discord. Screenshots, logs and the output of the Diagnostics panel all help a lot.

[!NOTE] Alpha 4 adds a database migration, so once alpha 4 has opened your root directory, alpha 3 and earlier will refuse to start on it. Canvases that use the new Noise, Clarity, Texture or Dehaze adjustments, or the new type-first control layers, are saved in a newer canvas format that alpha 3 can't open. Please stay on alpha 4 once you upgrade.

What's New

Alpha 4 brings three new image model families, character and edit references for Anima, Krea-2 and Qwen-Image-2.1, new ControlNets, much better live previews, faster int8 models, Windows on ARM64, and the return of more features from the legacy interface. A lot of this release is also the result of your feedback on the earlier alphas, so thank you to everyone who reported bugs.

Major Features

Major new features include:

New model families: FLUX.3 Klein and MOSS-Image

• FLUX.3 Image Klein from Black Forest Labs, in both the step-distilled Klein (16 steps, no CFG) and the undistilled Klein Base. It generates from text and edits or combines up to ten reference images, and Canvas regional guidance is placed as FLUX.3 layout boxes. Both checkpoints are under the FLUX Kommunity License. (@Pfannkuchensack)
• MOSS-Image from OpenMOSS, in Base and SFT versions (Apache 2.0). It works in Generate, on the Canvas (img2img, inpaint, outpaint and regional guidance as layout elements) and in workflows, can decode with PiD, and comes with a prompt enhancer that expands a short prompt into a full caption or a layout draft. (@Pfannkuchensack)

📖 FLUX.3 · MOSS-Image

Reference images and edits

• Anima character references. Anima now supports IP-Adapter character reference images. (@lstein)
• Krea-2 edit mode. Krea-2 can take up to three reference images, in Generate, on the Canvas and in workflows. This is what makes ai-toolkit edit LoRAs (the pose and depth "ControlNets" people have been asking for) actually work. (@Pfannkuchensack)
• Qwen-Image-2.1 edits from reference images, plus LoRA support for Qwen-Image-2.1. (@Pfannkuchensack)

📖 [Anima](https://v7.invoke.ai/users-guide/model

InvokeAI v6.14.3 is a patch release that enhances the Canvas with a vector graphics layer and corrects a download bug in the Model Manager.

New Feature: Editable vector layers

@DustyShoe contributed an enhancement to the Canvas that allows you to create a vector layer with editable shapes and splines. When you are satisfied with the vector shapes you can rasterize them and use them for img2img.

Bug Fix: Keep restored downloads restartable

@primorLee fixed an issue that prevented partial downloads from being restarted after a server crash or termination.

What's Changed

• fix(model-install): keep restored downloads restartable by @primorLee in https://github.com/invoke-ai/InvokeAI/pull/9521
• chore(prep): bump version by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9640
• ci(docs): deploy invoke.ai from v6-bugfixes by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9705
• chore(ui): back-port Weblate translations to v6 by @lstein in https://github.com/invoke-ai/InvokeAI/pull/9878
• feat(canvas): add editable vector layers and spline workflows by @DustyShoe in https://github.com/invoke-ai/InvokeAI/pull/9194

New Contributors

• @primorLee made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/9521

Full Changelog: https://github.com/invoke-ai/InvokeAI/compare/v6.14.2...v6.14.3

[!CAUTION]

⚠️ Please read this before you install

If you point v7 at your existing InvokeAI root directory, it will upgrade your database, and that database will no longer work with InvokeAI v6. The migrations only go one way, and v6 refuses to open a database that contains migrations it doesn't recognise.

To try v7, create a brand-new InvokeAI root directory and experiment there. In the Invoke Launcher , choose a new, empty install location. When prompted for the version, select Manual and enter version v7.0.0-alpha.3. For a manual install, pass --root /path/to/new/folder or set INVOKEAI_ROOT. Keep your v6 install and its root directory exactly where they are.

Upgraded your v6 database by accident? Don't panic. Invoke makes a backup before it migrates anything. See Restoring your v6 database at the bottom of these notes.

[!WARNING] This is alpha software. Things will break, some features are half-finished, and a few corners still have cobwebs. Please don't trust it with work you can't afford to lose. When you hit a bug, and you will, please open an issue on GitHub and put v7 in the title, or tell us about it on our Discord. Screenshots, logs and the output of the new Diagnostics panel all help a lot.

[!NOTE] Alpha 3 changes the project file format so that each member of a project keeps their own settings. Projects saved or exported by alpha 3 can't be opened by alpha 2, so once you upgrade, please stay on alpha 3.

What's New

Alpha 3 brings board sharing, a new image model, a faster attention backend for NVIDIA cards, and the return of a long list of features from the legacy interface. As usual, there's also a big pile of bug fixes.

Major Features

Major new features include:

Board sharing by role

Boards can now be shared with specific roles. Each board has an owner, and everyone else gets one of four roles on it: Viewer, Contributor, Editor or Owner. A board's general access can be Restricted, Everyone can view or Everyone can contribute. Boards that other people share with you show up under Shared with me in the Gallery's board list, along with who owns them and what you can do there, and board menus only offer the actions your role allows. Administrators also get an Other users' boards section.

Projects now keep each member's own settings (layout, widgets, generation settings, prompt history, selection and staging) separate from the project's shared content. When you export a project as an .invk file you can choose whether to Include my settings for this project. This is the groundwork for the project collaboration features coming later in 7.X. (@joshistoast)

See the Multi-User Mode user guide for details.

Qwen-Image-2.1

We now support Qwen-Image-2.1, both the Base model and the 8-step Turbo, for text-to-image and for canvas img2img, inpaint and outpaint. It loads as Diffusers folders, single-file transformers (bf16, ComfyUI scaled fp8 or int8_convrot) and GGUF transformers. You'll find the Base and Turbo models, a Q4_K_M GGUF and the ComfyUI VAE in the starter models. (@Pfannkuchensack)

📖 Qwen-Image-2.1

SageAttention for faster generation on NVIDIA GPUs

There's a new opt-in setting in invokeai.yaml, attention_backend: sage. It runs the attention inside the diffusion model on SageAttention 2.2, an 8-bit attention kernel. It works with FLUX.1, FLUX.2, Z-Image, Qwen-Image, Krea-2, SDXL, LTX-2 and Wan 2.2. The speedup