Since the very beginning, Invoke has been innovating where it matters for creatives. Today, we're excited to do it again with Control Layers.

Invoke 4.2 brings a number of enhancements and fixes, with the addition of a major new feature - Control Layers.

🧪 Control Layers

Integrating some of the latest in open-source research, creatives can use Control Adapters, Image Prompts, and regional guidance to articulate and control the generation process from a single panel. With regional guidance, you can compose specific regions to apply a positive prompt, negative prompt, or any number of IP Adapters to be applied to the masked region. Control Adapters (ControlNet & T2I Adapters) and an Initial Image are visualized on the new Control Layers canvas.

You can read more about how to use Control Layers here - Control Layers

📈 Patch Nodes for v4.2.0

Enhancements

• Control Layers
• Add TCD scheduler @l0stl0rd
• Image Viewer updates -- You can easily switch to the Image Viewer on the Generations tab by tapping the Z hotkey, or double clicking on any image in the gallery.

Major Changes

Also known as the "who moved my 🧀?" section, this list details where certain features have moved.

• Image to Image: The Image to Image pipeline can be executed using Control Layers by adding an Initial Image layer.
• Control Adapters and IP Adapters: These have been moved to the Control Layers tab -- with the added benefit of being able to visualize your control adapter's processed images easily!

Fixes

• Fixed inpainting models on canvas @dunkeroni
• Fixed IP Adapter starter models
• Fixed bug where temp files (tensors, conditioning) aren't cleaned up properly
• Fixed trigger phrase form submit @joshistoast
• Fixed SDXL checkpoint inpainting models not installing
• Fixed installing models on external SSDs on macOS
• Fixed Control Adapter processors' image size constraints being overly restrictive

💾 Installation and Updating

To install or update to v4.2.0, download the installer and follow the installation instructions.

To update, select the same installation location. Your user data will not be touched.

Missing models after updating from v3 to v4

See this FAQ.

What's Changed

• fix: IP Adapter Method having incorrect informational popover by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/6238
• Re-enable app shutdown actions by @lstein in https://github.com/invoke-ai/InvokeAI/pull/6244
• feat(ui): regional prompting by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6182
• feat(ui): regional prompting followups by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6247
• feat(ui): regional prompting followups 2 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6249
• feat(ui): regional prompting followups 3 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6256
• chore: v4.2.0a1 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6254
• feat(ui): regional prompting followups 4 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6257
• fix(ui): disabled ip adapters applied to regional control by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6258
• fix: :bug: handle trigger phrase form submit events by @joshistoast in https://github.com/invoke-ai/InvokeAI/pull/6253
• Remove dangling temporary directories from outputs/tensors at startup time by @lstein in https://github.com/invoke-ai/InvokeAI/pull/6246
• Fix Gradient Mask (Canvas) Inpaint Model Support by @dunkeroni in https://github.com/invoke-ai/InvokeAI/pull/6205
• fix: update ip adapter starter models path by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/6262
• fix: update SDXL IP Adpater starter model to be ViT-H by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/6263
• feat(ui): regional control canvas feedback by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6266
• chore: v4.2.0a3 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6269
• feat: controlnet util refresh by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6271
• Update README.md by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/6270
• docs: remove references to config script in CONFIGURATION.md by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6275
• feat(mm): support sdxl ckpt inpainting models by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6281
• fix(nodes): denoise latents accepts and validates CFG lists as input by @dunkeroni in https://github.com/invoke-ai/InvokeAI/pull/6283
• feat(mm): handle PC_PATH_MAX on external drives on macOS by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6292
• feat: control adapters in control layers canvas by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6287
• chore: v4.2.0a4 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6295
• Add TCD scheduler by @l0stl0rd in https://github.com/invoke-ai/InvokeAI/pull/6086
• feat(ui): refactor Control Adapters in Control Layers by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6298
• fix(nodes): fix constraints in cnet processors by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6299
• feat(ui): CL metadata, viewer, img2img by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6300
• chore: v4.2.0b1 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6303
• Update TRAINING.md by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/6294
• Update Installation Docs by @hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/6296
• feat(ui): cache mask images, fix viewer getting stuck bug by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6304
• feat: improve the switch states of the control layers / viewer area by @blessedcoolant in https://github.com/invoke-ai/InvokeAI/pull/6305
• feat(ui): control layers fixes/enhancements by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6307
• feat(ui): more control layers enhancements by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6311
• feat(ui): control layers styling, floating image viewer by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6316
• fix(ui): stuck viewer, remover floating viewer, viewer switching logic, layer count by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6320
• chore: v4.2.0b2 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6317
• feat(ui): move img2img strength out of advanced on canvas by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6321
• feat(ui): layers metadata recall by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6322
• switch to generation tab when someone sends to img2img by @maryhipp in https://github.com/invoke-ai/InvokeAI/pull/6323
• feat(ui): add data-testids, fix canvas toolbar align, add invert scroll checkbox to CL settings by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6324
• fix(ui): last-minute CL fixes by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6326
• chore: v4.2.0 by @psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/6328

New Contributors

• @l0stl0rd made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/6086

Full Changelog: https://github.com/invoke-ai/InvokeAI/compare/v4.1.0...v4.2.0