Invokeai

Latest version: v5.4.2

Safety actively analyzes 685525 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 25

12.0

5.4.3rc2

This minor release adds initial support for FLUX Regional Guidance, arrow key nudge on Canvas, plus an assortment of fixes and enhancements.

Changes

Enhancements
- Add 1-pixel `nudge` to the move tool on Canvas. Use the arrow keys to make fine adjustments to a layer's position. Thanks hippalectryon-0!
- Change the default infill method from `patchmatch` to `lama`. You can use `patchmatch`.
- Add empty state for Global Reference Images and Regional Guidance Reference Images, similar to the empty state for Control Layers. A blurb directs users to upload an image or drag an image from gallery to set the image.
- FLUX performance improvements (~10% speed-up).
- Added `ImagePanelLayoutInvocation` to facilitate FLUX IC-LoRA workflows.
- FLUX Regional Guidance support (beta). Only positive prompts are supported; negative prompts, reference images and auto-negative are not supported for FLUX Regional Guidance.
- Canvas layers now have a warning indicator that indicates issues with the layer that could prevent invoking or cause a problem.
- `New Layer from Image` functions added to Canvas Staging Area Toolbar. These create a new layer without dismissing the rest of the staged images.
- Improved empty state for Regional Guidance Reference Images.
- Added missing `New from...` image context menu actions: `Reference Image (Regional)` and `Reference Image (Global)`
- Added Vietnamese to language picker in Settings.

Fixes
- Soft Edge (Lineart, Lineart Anime) Control Layers default to the Soft Edge filter correctly.
- Remove the nonfunctional `width` and `height` outputs from the `Image Batch` node. If you want to use `width` and `height` in a batch, route the `image` from `Image Batch` to an `Image Primitive` node, which outputs `width` and `height`.
- Ensure invocation templates have fully parsed before running studio init actions.
- Bumped `transformers` to get a fix for Depth Anything artifacts.
- False negative edge case with `picklescan`.
- Invoke queue actions menu's Cancel Current action erroneously cleared the entire queue. Thanks rikublock!
- New Reference Images could inadvertently have the last-used Reference Image populated on creation.
- Error when importing GGUF models. Thanks JPPhoto!
- Canceling any queue item from the Queue tab _also_ erroneously canceled the currently-executing queue item.

Internal
- Add redux actions for support video modal.
- Tidied various things related to the queue. Thanks rikublock!

Docs
- General tidy across many docs pages. Thanks magnusviri!
- Fixed a few broken links. Thanks emmanuel-ferdman!

Translations
- Updated Italian translations. Thanks Harvester62!

Installation and Updating

To install or update, [download the latest installer](https://github.com/invoke-ai/InvokeAI/releases/download/v5.4.3rc2/InvokeAI-installer-v5.4.3rc2.zip) and follow the [installation instructions](https://invoke-ai.github.io/InvokeAI/installation/installer/)

To update, select the same installation location. Your user data (images, models, etc) will be retained.

What's Changed
* fix(api): make sure Soft Edge Detection has preprocessor applied by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7360
* fix(ui): disable width and height output on image batch output by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7361
* feat(ui): set default infill method to lama by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7362
* fix(ui): make sure schema has loaded before trying to load any workflows by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7364
* feat(ui): add actions for video modal clicks by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7365
* feat(ui): add empty state for regional guidance ref image by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7363
* feat(ui): nudge on canvas by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7368
* chore: bump version to v5.4.3rc1 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7369
* fix(ui): use token for download if its in store by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7373
* Create SECURITY.md by hipsterusername in https://github.com/invoke-ai/InvokeAI/pull/7376
* misc(ui): various copy updates by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7382
* fix: Fail scan on InvalidMagicError in picklescan, update default for… by brandonrising in https://github.com/invoke-ai/InvokeAI/pull/7381
* Add `ImagePanelLayoutInvocation` utility to facilitate In-Context LoRA workflows by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7374
* Bump transformers to ingest a DepthAnything post-processing fix by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7386
* docs: update code of conduct reference by emmanuel-ferdman in https://github.com/invoke-ai/InvokeAI/pull/7380
* FLUX Regional Prompting by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7388
* FLUX Speed Improvements (~10% speedup) by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7399
* Update node vers by JPPhoto in https://github.com/invoke-ai/InvokeAI/pull/7403
* feat(ui): add `New Layer from Image` menu to staging area toolbar by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7389
* refactor(ui): move clear queue hook to separate file by rikublock in https://github.com/invoke-ai/InvokeAI/pull/7391
* fix(ui): call cancel instead of clear queue by rikublock in https://github.com/invoke-ai/InvokeAI/pull/7392
* chore(ui): update typegen schema by rikublock in https://github.com/invoke-ai/InvokeAI/pull/7394
* fix(app): adjust session queue api type by rikublock in https://github.com/invoke-ai/InvokeAI/pull/7393
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7397
* feat(ui): less confusing empty state for rg ref images by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7407
* fix(ui): ref image defaults to prev ref image's image selection by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7408
* feat(ui): add gallery image ctx menu items to create ref image from image by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7409
* fix(ui): allow invoke when inpaint/raster layers are empty by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7410
* fix(ui): remove "adding to" text on Invoke tooltip on Workflows/Upscaling tabs by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7411
* feat(ui): add vietnamese to language picker by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7412
* fix(worker): only apply processor cancel logic if cancel event is for current item by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7416
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7415
* Fix gguf importing by JPPhoto in https://github.com/invoke-ai/InvokeAI/pull/7405
* [docs] Fix documentation broken links and remove whitespace at end of lines by magnusviri in https://github.com/invoke-ai/InvokeAI/pull/7402
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7418
* chore: bump version to v5.4.3rc2 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7413

New Contributors
* emmanuel-ferdman made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/7380

**Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v5.4.2...v5.4.3rc2

5.4.3rc1

This minor release adds arrow key nudge on Canvas, plus a handful of fixes and enhancements.

Changes

Enhancements
- Add 1-pixel `nudge` to the move tool on Canvas. Use the arrow keys to make fine adjustments to a layer's position. Thanks hippalectryon-0!
- Change the default infill method from `patchmatch` to `lama`. You can use `patchmatch`.
- Add empty state for Global Reference Images and Regional Guidance Reference Images, similar to the empty state for Control Layers. A blurb directs users to upload an image or drag an image from gallery to set the image.

Fixes
- Soft Edge (Lineart, Lineart Anime) Control Layers default to the Soft Edge filter correctly.
- Remove the nonfunctional `width` and `height` outputs from the `Image Batch` node. If you want to use `width` and `height` in a batch, route the `image` from `Image Batch` to an `Image Primitive` node, which outputs `width` and `height`.
- Ensure invocation templates have fully parsed before running studio init actions.

Internal
- Add redux actions for support video modal.

Installation and Updating

To install or update, [download the latest installer](https://github.com/invoke-ai/InvokeAI/releases/download/v5.4.3rc1/InvokeAI-installer-v5.4.3rc1.zip) and follow the [installation instructions](https://invoke-ai.github.io/InvokeAI/installation/installer/)

To update, select the same installation location. Your user data (images, models, etc) will be retained.

What's Changed
* fix(api): make sure Soft Edge Detection has preprocessor applied by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7360
* fix(ui): disable width and height output on image batch output by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7361
* feat(ui): set default infill method to lama by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7362
* fix(ui): make sure schema has loaded before trying to load any workflows by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7364
* feat(ui): add actions for video modal clicks by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7365
* feat(ui): add empty state for regional guidance ref image by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7363
* feat(ui): nudge on canvas by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7368
* chore: bump version to v5.4.3rc1 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7369


**Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v5.4.2...v5.4.3rc1

5.4.2

This release includes support for FLUX IP Adapter v2 and image "batching" for Workflows.

Image Batching for Workflows

The Workflow Editor now supports running a given workflow for each image in a collection of images.

Add an `Image Batch` node, drag some images into its image collection, and connect its output to any other node(s). Invoke will run the workflow once for each image in the collection.

Here are a few examples to help build intuition for the feature. Click the arrow to expand each example.

<details>

<summary>Example 1 - Single Batch -> Single Node</summary>

The simplest case is using a batch image output with a single node. Here's a workflow that resizes 5 images to 200x200 thumbnails.

Workflow

<img width="538" alt="image" src="https://github.com/user-attachments/assets/04c92e39-1743-4239-9e47-e8d7d6973f70">

Results

<img width="493" alt="image" src="https://github.com/user-attachments/assets/693feb96-ab9f-4f2e-b40a-b3f654e015e8">

This batch queues 5 graphs, each containing a single resize node with one of the 5 images in the batch list. Note the images are 200x200 pixels.

</details>


<details>

<summary>Example 2 - Single Batch -> Multiple Nodes</summary>

You can also use a batch image output with multiple nodes. This contrived workflow resizes the image to a 200x200 thumbnail, like the previous example, the pastes the thumbnail on the full size image.

Workflow

<img width="805" alt="image" src="https://github.com/user-attachments/assets/3ee76c97-95a0-43fd-b1e1-939449c2427b">

Results

<img width="495" alt="image" src="https://github.com/user-attachments/assets/b4e5449e-b614-4378-b4a0-1b6eb8cf0606">

This batch also queues 5 graphs, each of which contains one resize and one paste node. In each graph, the nodes get the image of the 5 images in the batch collection. The batch node can connect to any number of other nodes. For each queued graph, all connected nodes will get the same image.

</details>

<details>

<summary>Example 3 - Multiple Batches (Product Batching)</summary>

When multiple batches are used, they are combined such that all permutations are queued (e.g. the product of batches is taken).

Workflow

<img width="929" alt="image" src="https://github.com/user-attachments/assets/85665851-3c77-4680-a002-1eed785d78dc">

Results

<img width="492" alt="image" src="https://github.com/user-attachments/assets/2f28f18e-cf39-4afe-8d20-a5911e61a6ce">

In this case, the product of the two batches is 15 graphs. Each image of the 3-image batch is used as the base image, and a thumbnail of each tiger is pasted on top of it. We'll call this "product" batching.

Zipped Batching

The batching API supports "zipped" batches, where the batch collections are merged into a single batch.

For example, imagine two batches of 5 images. As described in the "product" example above, you'd get 5 images * 5 images = 25 graphs. Zipped batching would instead take the first image from each of the two batches and use them together in the first graph, then take the second two images for the second graph, and so on.

Zipped batching is not supported in the UI at this time.

</details>

Versus `Iterate` Nodes

We support similar functionality to batching with `Iterate` nodes, so why add batching? In short, `Iterate` nodes have some technical issues which are addressed by batching.

<details>

<summary>Why `Iterate` Nodes are Scary</summary>

They result in unbounded graph complexity and size. If you don't know what these words mean, but they sound kinda scary, congrats! You are on the right track. They are indeed scary words.

- When using `Iterate` nodes, the graph is expanded with new nodes and edges _during execution_. Pretty scary.
- We cannot know ahead of time how much the graph will expand, because iterate nodes' collections are dynamic. Terrifying.
- Multiple iterate nodes combine via Cartesian product, resulting in combinatorial explosion. Your graph could be running at the heat death of the universe. Existential dread.

Batch collections are defined up front and don't expand the graph. We know exactly the complexity we are getting into before the graph executes. Sanity restored!

</details>

Batching also more intuitive - we run exactly this graph, once for each image.

Unlike `Iterate` nodes, `Image Batch` nodes' collections cannot be provided by other nodes in the graph. The collection must be defined up-front, so you cannot replace `Iterate` with `Image Batch` for all use-cases.

Nevertheless, we suggest using batching where possible.

Other Notes

- We've added `Image Batch` nodes first because it images are the highest-impact field type, but the batching API supports arbitrary field types. In fact, the Canvas uses both `int` and `str` fields internally. We'll save nodes for other field types for a future enhancement.
- If you want to batch over a board, you'll need to drag all images from the board into the batch collection. We'll explore a simpler way to use a board's images for a batch in a future enhancement.
- It is not possible to combine all outputs from a batch within the same workflow.

Other Changes

Enhancements
- Support for FLUX IP Adapter v2. **We've optimized internal handling for v2, and you may find FLUX IP Adapter v1 results are degraded. Update to v2 to fix this.**
- Updated image collection inputs for nodes. You may now drag images into collections directly.
- Brought some of dwringer's often-requested [composition nodes](https://github.com/dwringer/composition-nodes) into Invoke's core nodes. They have been renamed to not conflict with your existing install of the node pack. Thanks for your work on these very useful nodes dwringer!
- Show tab-specific info in the Invoke button's tooltip.
- Update the `New from Image` context menu actions. The actions that resize the image after creating a new Canvas are clearly named.
- Change the `Reset Canvas` button, which was too similar to the `Delete Image` button, into a menu with more options:
- New Canvas Session: Resets all generation settings, resets all layers, and enables Send to Canvas.
- New Gallery Session: Resets all generation settings, resets all layers, and enables Send to Gallery.
- Reset Generation Settings: Resets all generation settings, leaving layers alone.
- Reset Canvas Layers: Resets all layers, leaving generation settings alone.
- New Support Videos button in the bottom-left corner of the app, which lists and links to videos on our YouTube channel.

Fixes
- Added padding to the metadata recall buttons in the metadata viewer, so they aren't cut off by other UI elements.
- The progress bar stopped throbbing in the last release. We apologize for this oversight. Throbbing has been restored.
- Addressed some edge cases that could cause the UI to crash with an error about an entity not found.
- Updated grid size for SD3.5 models to 16px. Thanks for the heads up dunkeroni.

Internal
- Removed a node with a GPL-3 dependency (`easing-functions`), which had been contributed in the `step_param_easing` node that used it. While this node has been deprecated, please let us know if you were using this node, and the use-cases, so that we can better design inputs where these are found helpful.

Translations

> We have had some issues communicating with "walk-in" translators on Weblate, resulting in translations being changed when they are already correct. To mitigate this, we are trying a more restricted Weblate translation setup. Access to contribute translations must be granted by Harvester62. Please them in the [translators channel on discord](https://discord.com/channels/1020123559063990373/1054129386447716433) to get access.

> Our Weblate also has an account issue and is currently locked. This is unrelated to the access restriction changes.

We apologize for any inconvenience this change may cause. Thanks to all our translators for their continued efforts!

- Updated Chinese (Simplified). Thanks youo0o0!
- Updated Italian. Thanks Harvester62!
- Updated Spanish. Thanks gallegonovato (weblate user)!

Installation and Updating

To install or update, [download the latest installer](https://github.com/invoke-ai/InvokeAI/releases/download/v5.4.2/InvokeAI-installer-v5.4.2.zip) and follow the [installation instructions](https://invoke-ai.github.io/InvokeAI/installation/installer/)

To update, select the same installation location. Your user data (images, models, etc) will be retained.

What's Changed
* feat(ui): deferred invocation progress details for model loading by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7320
* fix(ui): add padding to the metadata recall section so buttons are not blocked by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7326
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7323
* remove GPL-3 licensed package easing-functions by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7337
* fix(ui): progress bar not throbbing when it should by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7332
* fix(ui): prevent entity not found errors by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7340
* XLabs FLUX IP-Adapter v2 by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7338
* feat(ui): image batching in workflows by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7343
* fix(ui): add sd-3 grid size of 16px to grid util by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7346
* chore: bump version to v5.4.2rc1 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7344
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7331
* feat: ingest composition nodes into core by brandonrising in https://github.com/invoke-ai/InvokeAI/pull/7341
* fix(ui): simplify logic for non-local invocation progress alerts by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7353
* feat(ui): update invoke button tooltip for batching by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7350
* feat(ui): change reset canvas icon to "empty" by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7351
* feat(ui): clarified new from image menu items by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7352
* feat(ui): change reset canvas button to new session menu by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7356
* feat(ui): support videos modal by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7300
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7355
* chore: bump version to v5.4.2 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7354


**Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v5.4.1...v5.4.2

5.4.2rc1

This release candidate includes support for FLUX IP Adapter v2 and image "batching" for Workflows.

Image Batching for Workflows

Invoke's Workflow Editor now supports running a given workflow for each image in a collection of images.

Add an `Image Batch` node, drag some images into its image collection, and connect its output to any other node(s). Invoke will run the workflow once for each image in the collection.

Here are a few examples to help build intuition for the feature.

<details>

<summary>Example 1 - Single Batch -> Single Node</summary>

The simplest case is using a batch image output with a single node. Here's a workflow that resizes 5 images to 200x200 thumbnails.

Workflow

<img width="538" alt="image" src="https://github.com/user-attachments/assets/04c92e39-1743-4239-9e47-e8d7d6973f70">

Results

<img width="493" alt="image" src="https://github.com/user-attachments/assets/693feb96-ab9f-4f2e-b40a-b3f654e015e8">

This batch queues 5 graphs, each containing a single resize node with one of the 5 images in the batch list. Note the images are 200x200 pixels.

</details>


<details>

<summary>Example 2 - Single Batch -> Multiple Nodes</summary>

You can also use a batch image output with multiple nodes. This contrived workflow resizes the image to a 200x200 thumbnail, like the previous example, the pastes the thumbnail on the full size image.

Workflow

<img width="805" alt="image" src="https://github.com/user-attachments/assets/3ee76c97-95a0-43fd-b1e1-939449c2427b">

Results

<img width="495" alt="image" src="https://github.com/user-attachments/assets/b4e5449e-b614-4378-b4a0-1b6eb8cf0606">

This batch also queues 5 graphs, each of which contains one resize and one paste node. In each graph, the nodes get the image of the 5 images in the batch collection. The batch node can connect to any number of other nodes. For each queued graph, all connected nodes will get the same image.

</details>

<details>

<summary>Example 3 - Multiple Batches (Product Batching)</summary>

When multiple batches are used, they are combined such that all permutations are queued (e.g. the product of batches is taken).

Workflow

<img width="929" alt="image" src="https://github.com/user-attachments/assets/85665851-3c77-4680-a002-1eed785d78dc">

Results

<img width="492" alt="image" src="https://github.com/user-attachments/assets/2f28f18e-cf39-4afe-8d20-a5911e61a6ce">

In this case, the product of the two batches is 15 graphs. Each image of the 3-image batch is used as the base image, and a thumbnail of each tiger is pasted on top of it. We'll call this "product" batching.

Zipped Batching

The batching API supports "zipped" batches, where the batch collections are merged into a single batch.

For example, imagine two batches of 5 images. As described in the "product" example above, you'd get 5 images * 5 images = 25 graphs. Zipped batching would instead take the first image from each of the two batches and use them together in the first graph, then take the second two images for the second graph, and so on.

Zipped batching is not supported in the UI at this time.

</details>

Versus `Iterate` Nodes

We support similar functionality to batching with `Iterate` nodes, so why add batching? In short, `Iterate` nodes have some technical issues avoided by batching.

<details>

<summary>Why `Iterate` Nodes are Scary</summary>

They result in unbounded graph complexity and size. If you don't know what these words mean, but they sound kinda scary, congrats! You are on the right track. They are indeed scary words.

- When using `Iterate` nodes, the graph is expanded with new nodes and edges _during execution_. Pretty scary.
- We cannot know ahead of time how much the graph will expand, because iterate nodes' collections are dynamic. Terrifying.
- Multiple iterate nodes combine via Cartesian product, resulting in combinatorial explosion. Your graph could be running at the heat death of the universe. Existential dread.

Batch collections are defined up front and don't expand the graph. We know exactly the complexity we are getting into before the graph executes. Sanity restored!

</details>

Batching also more intuitive - we run exactly this graph, once for each image.

Unlike `Iterate` nodes, `Image Batch` nodes' collections cannot be provided by other nodes in the graph. The collection must be defined up-front, so you cannot replace `Iterate` with `Image Batch` for all use-cases.

Nevertheless, we suggest using batching where possible.

Other Notes

- We've added `Image Batch` nodes first because it images are the highest-impact field type, but the batching API supports arbitrary field types. In fact, the Canvas uses both `int` and `str` fields internally. We'll save nodes for other field types for a future enhancement.
- If you want to batch over a board, you'll need to drag all images from the board into the batch collection. We'll explore a simpler way to use a board's images for a batch in a future enhancement.
- It is not possible to combine all outputs from a batch within the same workflow.

Other Changes

Enhancements
- Support for FLUX IP Adapter v2. **We've optimized internal handling for v2, and you may find FLUX IP Adapter v1 results are degraded. Update to v2 to fix this.**
- Updated image collection inputs for nodes. You may now drag images into collections directly.

Fixes
- Added padding to the metadata recall buttons in the metadata viewer, so they aren't cut off by other UI elements.
- The progress bar stopped throbbing in the last release. We apologize for this oversight. Throbbing has been restored.
- Addressed some edge cases that could cause the UI to crash with an error about an entity not found.
- Updated grid size for SD3.5 models to 16px. Thanks for the heads up dunkeroni.

Internal
- Removed a node with a GPL-3 dependency (`easing-functions`), which had been contributed in the `step_param_easing` node that used it. While this node has been deprecated, please let us know if you were using this node, and the use-cases, so that we can better design inputs where these are found helpful.

Translations

> We have had some issues communicating with "walk-in" translators on Weblate, resulting in translations being changed when they are already correct. To mitigate this, we are trying a more restricted Weblate translation setup. Access to contribute translations must be granted by Harvester62. Please them in the [translators channel on discord](https://discord.com/channels/1020123559063990373/1054129386447716433) to get access.

We apologize for any inconvenience this change may cause. Thanks to all our translators for their continued efforts!

- Updated Chinese (Simplified). Thanks youo0o0!
- Updated Italian. Thanks Harvester62!
- Updated Spanish. Thanks gallegonovato (weblate user)!

Installation and Updating

To install or update, [download the latest installer](https://github.com/invoke-ai/InvokeAI/releases/download/v5.4.2rc1/InvokeAI-installer-v5.4.2rc1.zip) and follow the [installation instructions](https://invoke-ai.github.io/InvokeAI/installation/installer/)

To update, select the same installation location. Your user data (images, models, etc) will be retained.

What's Changed
* feat(ui): deferred invocation progress details for model loading by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7320
* fix(ui): add padding to the metadata recall section so buttons are not blocked by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7326
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7323
* remove GPL-3 licensed package easing-functions by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7337
* fix(ui): progress bar not throbbing when it should by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7332
* fix(ui): prevent entity not found errors by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7340
* XLabs FLUX IP-Adapter v2 by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7338
* feat(ui): image batching in workflows by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7343
* fix(ui): add sd-3 grid size of 16px to grid util by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7346
* chore: bump version to v5.4.2rc1 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7344
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7331


**Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v5.4.1...v5.4.2rc1

5.4.1

This release includes support for SD 3.5, plus a number of fixes and improvements.

> We pulled v5.4.0 due to issues with model installation and loading. This release (v5.4.1) resolves those issues and includes all changes from v5.4.0.

Enhancements

- Support for SD 3.5 Medium and Large. You can download them in the starter models.
- Moved `Denoising Strength` slider to top of Layers panel with updated UI and info popover.
- Update viewer styling to have a menubar-ish header. Also used for image comparison.
- Layer preview tooltip with larger sized preview.
- Empty state for Control Layers, guiding user to upload an image, drag an image from gallery or start drawing.
- "Simple" mode for control layers filtering, triggered when you select a control model. This automatically selects and processes the default filter for that model, if a default exists. If the user clicks `Advanced`, they get the full filter settings UI. Control Layers now start with no model selected, implicitly directing users into this flow.
- Updated default control weight to 0.75 and end step % to 0.75. Updated label for the `Balanced` control mode, indicating it is the recommended setting.
- The FLUX Denoise node now has a flag to skip adding noise to input latents. This is useful for switching models mid-generation and other fancy denoising techniques. Thanks JPPhoto!
- Migrated the UI's drag-and-drop functionality to a new library, improving the overall performance of dnd. It also allows us to support external dnd. For example, dragging images from the OS directly into the canvas is now possible (not implemented in this release).
- Canvas layers may be sorted via drag-and-drop.
- When graph building fails, you will see an error toast. Previously, it only logged a message to the browser's JS console.
- Updated model warnings on Upscaling tab to not be misleading.
- More FLUX LoRA format support.
- Show alert over canvas/viewer with invocation progress event messages.
- Tweak gallery image selection styles to better differentiate between hovered and selected.
- `Output Only Masked Regions` renamed to `Output only Generated Regions` and now enabled by default.

Fixes

- Canvas progress images do not clear when canceling generation after at least one image has been staged.
- Tooltips on boards list stay open when scrolling, potentially causing the whole app to scroll.
- Saving canvas to gallery does not create a new image in gallery.
- Applying a filter could erase or otherwise change a layer's data unexpectedly, causing a range of user-facing generation issues.
- Unable to queue graphs with the Segment Anything node when its inputs were provided by connection.
- Unable to load a workflow from file when using the three-dots menu.
- `pip` downloads `torch` twice. This didn't cause any application issues - just a waste of time and bandwidth. We pinned `torch` to `<2.5.0` to prevent `pip`'s dependency resolver from getting confused.
- `mediapipe` install issue on Windows, related to its latest release. We pinned `mediapipe` to a known working version.
- CLIP Vision error when using FLUX IP Adapter.
- Fit bbox to layers math could result in a slightly-too-large bbox.
- Outdated link to FLUX IP Adapter. Thanks RadTechDad!
- Force a compatible precision for FLUX VAEs to prevent black outputs.

Translations

We have had some issues communicating with "walk-in" translators on Weblate, resulting in translations being changed when they are already correct. To mitigate this, we are trying a more restricted Weblate translation setup. Access to contribute translations must be granted by Harvester62. Please them in the [translators channel on discord](https://discord.com/channels/1020123559063990373/1054129386447716433) to get access.

We apologize for any inconvenience this change may cause. Thanks to all our translators for their continued efforts!

- Updated German. Thanks rikublock!
- Updated Chinese (Simplified). Thanks youo0o0!
- Updated Italian. Thanks Harvester62 & dakota2472!
- Updated Spanish. Thanks gallegonovato (weblate user)!
- Updated Vietnamese. Thanks Linos (weblate user)!
- Updated Japanese. Thanks GGSSKK!

Internal

- Simplified parameter schema declarations. Thanks rikublock!
- Simplified dnd image and gallery rendering, resulting in improved performance.

Installation and Updating

To install or update, [download the latest installer](https://github.com/invoke-ai/InvokeAI/releases/download/v5.4.1/InvokeAI-installer-v5.4.1.zip) and follow the [installation instructions](https://invoke-ai.github.io/InvokeAI/installation/installer/)

To update, select the same installation location. Your user data (images, models, etc) will be retained.

What's Changed
* Pin torch to <2.5.0 to prevent unnecessary downloads by ebr in https://github.com/invoke-ai/InvokeAI/pull/7247
* fix(ui): misc fixes by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7252
* fix(nodes): relaxed validation for segment anything by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7253
* fix(ui): load workflow from file by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7254
* fix(deps): pin mediapipe strictly to a known working version by ebr in https://github.com/invoke-ai/InvokeAI/pull/7258
* Ryan/sd3 diffusers by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7222
* chore: bump version to v5.4.0 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7259
* fix: Never throw an exception when finding the clip variant type by brandonrising in https://github.com/invoke-ai/InvokeAI/pull/7263
* fix(ui): add some feedback while layers are merging by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7265
* feat(api,ui): allow Whats New module to get content from back-end by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7268
* fix(ui): fix link for infill method popover by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7269
* update Whats New for 5.3.1 by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7272
* fix(ui): bad merge conflict by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7273
* fix: get_clip_variant_type should never return None by brandonrising in https://github.com/invoke-ai/InvokeAI/pull/7275
* feat(ui): denoising strength UI by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7262
* chore(gh): update pr template w/ reminder for what's new copy by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7274
* feat(ui): simplify parameter schema declaration by rikublock in https://github.com/invoke-ai/InvokeAI/pull/7281
* feat(ui): new user ux improvements by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7279
* fix: Avoid downloading unsafe .bin files if a safetensors file is ava… by brandonrising in https://github.com/invoke-ai/InvokeAI/pull/7282
* fix: Look in known subfolders for configs for clip variants by brandonrising in https://github.com/invoke-ai/InvokeAI/pull/7283
* chore: release v5.4.1rc1 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7285
* Update flux_denoise.py by JPPhoto in https://github.com/invoke-ai/InvokeAI/pull/7270
* fix(app): silence pydantic protected namespace warning by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7291
* chore(ui): migrate dnd library by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7288
* chore: bump version to v5.4.1rc2 by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7293
* fix(ui): FLUX IP adapter clip vision model error by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7292
* fix(ui): excessive toasts when generating on canvas by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7294
* fix(ui): fit bbox to layers math by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7297
* fix(ui): restore missing image paste handler by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7298
* feat(ui): update warnings on upscaling tab based on model arch by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7299
* feat(ui): clarify denoising strength badge text by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7304
* Updated link to flux ip adapter model by RadTechDad in https://github.com/invoke-ai/InvokeAI/pull/7309
* Flux Vae broke for float16, force bfloat16 or float32 were compatible by Vargol in https://github.com/invoke-ai/InvokeAI/pull/7213
* Fix FLUX diffusers LoRA models with no `.proj_mlp` layers by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7313
* SD3 Image-to-Image and Inpainting by RyanJDick in https://github.com/invoke-ai/InvokeAI/pull/7295
* (ui): update en string for full IP adapter by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7312
* feat(ui, worker): add invocation progress events to model loading by maryhipp in https://github.com/invoke-ai/InvokeAI/pull/7286
* feat(ui): tweak image selection/hover styling by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7302
* feat(ui): update output only masked regions by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7303
* fix(ui): image uploading handling by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7315
* fix(ui): unable to use text inputs within draggable by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7316
* fix(ui): multiple selection dnd sometimes doesn't get full selection by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7317
* fix(ui): remove progress message condition for canvas destinations by psychedelicious in https://github.com/invoke-ai/InvokeAI/pull/7319
* ui: translations update from weblate by weblate in https://github.com/invoke-ai/InvokeAI/pull/7242

New Contributors
* RadTechDad made their first contribution in https://github.com/invoke-ai/InvokeAI/pull/7309

**Full Changelog**: https://github.com/invoke-ai/InvokeAI/compare/v5.3.1...v5.4.1

Page 1 of 25

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.