Add mask to l2l, MaskEdge and ColorCorrect nodes

.github/workflows/close-inactive-issues.yml

@@ -1,11 +1,11 @@
 name: Close inactive issues
 on:
   schedule:
-    - cron: "00 4 * * *"
+    - cron: "00 6 * * *"
 
 env:
-  DAYS_BEFORE_ISSUE_STALE: 30
-  DAYS_BEFORE_ISSUE_CLOSE: 14
+  DAYS_BEFORE_ISSUE_STALE: 14
+  DAYS_BEFORE_ISSUE_CLOSE: 28
 
 jobs:
   close-issues:
@@ -14,7 +14,7 @@ jobs:
       issues: write
       pull-requests: write
     steps:
-      - uses: actions/stale@v8
+      - uses: actions/stale@v5
         with:
           days-before-issue-stale: ${{ env.DAYS_BEFORE_ISSUE_STALE }}
           days-before-issue-close: ${{ env.DAYS_BEFORE_ISSUE_CLOSE }}
@@ -23,6 +23,5 @@ jobs:
           close-issue-message: "Due to inactivity, this issue was automatically closed. If you are still experiencing the issue, please recreate the issue."
           days-before-pr-stale: -1
           days-before-pr-close: -1
-          exempt-issue-labels: "Active Issue"
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           operations-per-run: 500

LICENSE-SDXL.txt

@@ -1,290 +0,0 @@
-Copyright (c) 2023 Stability AI
-CreativeML Open RAIL++-M License dated July 26, 2023
-
-Section I: PREAMBLE
-
-Multimodal generative models are being widely adopted and used, and
-have the potential to transform the way artists, among other
-individuals, conceive and benefit from AI or ML technologies as a tool
-for content creation.
-
-Notwithstanding the current and potential benefits that these
-artifacts can bring to society at large, there are also concerns about
-potential misuses of them, either due to their technical limitations
-or ethical considerations.
-
-In short, this license strives for both the open and responsible
-downstream use of the accompanying model. When it comes to the open
-character, we took inspiration from open source permissive licenses
-regarding the grant of IP rights. Referring to the downstream
-responsible use, we added use-based restrictions not permitting the
-use of the model in very specific scenarios, in order for the licensor
-to be able to enforce the license in case potential misuses of the
-Model may occur. At the same time, we strive to promote open and
-responsible research on generative models for art and content
-generation.
-
-Even though downstream derivative versions of the model could be
-released under different licensing terms, the latter will always have
-to include - at minimum - the same use-based restrictions as the ones
-in the original license (this license). We believe in the intersection
-between open and responsible AI development; thus, this agreement aims
-to strike a balance between both in order to enable responsible
-open-science in the field of AI.
-
-This CreativeML Open RAIL++-M License governs the use of the model
-(and its derivatives) and is informed by the model card associated
-with the model.
-
-NOW THEREFORE, You and Licensor agree as follows:
-
-Definitions
-
-"License" means the terms and conditions for use, reproduction, and
-Distribution as defined in this document.
-
-"Data" means a collection of information and/or content extracted from
-the dataset used with the Model, including to train, pretrain, or
-otherwise evaluate the Model. The Data is not licensed under this
-License.
-
-"Output" means the results of operating a Model as embodied in
-informational content resulting therefrom.
-
-"Model" means any accompanying machine-learning based assemblies
-(including checkpoints), consisting of learnt weights, parameters
-(including optimizer states), corresponding to the model architecture
-as embodied in the Complementary Material, that have been trained or
-tuned, in whole or in part on the Data, using the Complementary
-Material.
-
-"Derivatives of the Model" means all modifications to the Model, works
-based on the Model, or any other model which is created or initialized
-by transfer of patterns of the weights, parameters, activations or
-output of the Model, to the other model, in order to cause the other
-model to perform similarly to the Model, including - but not limited
-to - distillation methods entailing the use of intermediate data
-representations or methods based on the generation of synthetic data
-by the Model for training the other model.
-
-"Complementary Material" means the accompanying source code and
-scripts used to define, run, load, benchmark or evaluate the Model,
-and used to prepare data for training or evaluation, if any. This
-includes any accompanying documentation, tutorials, examples, etc, if
-any.
-
-"Distribution" means any transmission, reproduction, publication or
-other sharing of the Model or Derivatives of the Model to a third
-party, including providing the Model as a hosted service made
-available by electronic or other remote means - e.g. API-based or web
-access.
-
-"Licensor" means the copyright owner or entity authorized by the
-copyright owner that is granting the License, including the persons or
-entities that may have rights in the Model and/or distributing the
-Model.
-
-"You" (or "Your") means an individual or Legal Entity exercising
-permissions granted by this License and/or making use of the Model for
-whichever purpose and in any field of use, including usage of the
-Model in an end-use application - e.g. chatbot, translator, image
-generator.
-
-"Third Parties" means individuals or legal entities that are not under
-common control with Licensor or You.
-
-"Contribution" means any work of authorship, including the original
-version of the Model and any modifications or additions to that Model
-or Derivatives of the Model thereof, that is intentionally submitted
-to Licensor for inclusion in the Model by the copyright owner or by an
-individual or Legal Entity authorized to submit on behalf of the
-copyright owner. For the purposes of this definition, "submitted"
-means any form of electronic, verbal, or written communication sent to
-the Licensor or its representatives, including but not limited to
-communication on electronic mailing lists, source code control
-systems, and issue tracking systems that are managed by, or on behalf
-of, the Licensor for the purpose of discussing and improving the
-Model, but excluding communication that is conspicuously marked or
-otherwise designated in writing by the copyright owner as "Not a
-Contribution."
-
-"Contributor" means Licensor and any individual or Legal Entity on
-behalf of whom a Contribution has been received by Licensor and
-subsequently incorporated within the Model.
-
-Section II: INTELLECTUAL PROPERTY RIGHTS
-
-Both copyright and patent grants apply to the Model, Derivatives of
-the Model and Complementary Material. The Model and Derivatives of the
-Model are subject to additional terms as described in
-
-Section III.
-
-Grant of Copyright License. Subject to the terms and conditions of
-this License, each Contributor hereby grants to You a perpetual,
-worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-copyright license to reproduce, prepare, publicly display, publicly
-perform, sublicense, and distribute the Complementary Material, the
-Model, and Derivatives of the Model.
-
-Grant of Patent License. Subject to the terms and conditions of this
-License and where and as applicable, each Contributor hereby grants to
-You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
-irrevocable (except as stated in this paragraph) patent license to
-make, have made, use, offer to sell, sell, import, and otherwise
-transfer the Model and the Complementary Material, where such license
-applies only to those patent claims licensable by such Contributor
-that are necessarily infringed by their Contribution(s) alone or by
-combination of their Contribution(s) with the Model to which such
-Contribution(s) was submitted. If You institute patent litigation
-against any entity (including a cross-claim or counterclaim in a
-lawsuit) alleging that the Model and/or Complementary Material or a
-Contribution incorporated within the Model and/or Complementary
-Material constitutes direct or contributory patent infringement, then
-any patent licenses granted to You under this License for the Model
-and/or Work shall terminate as of the date such litigation is asserted
-or filed.
-
-Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
-
-Distribution and Redistribution. You may host for Third Party remote
-access purposes (e.g. software-as-a-service), reproduce and distribute
-copies of the Model or Derivatives of the Model thereof in any medium,
-with or without modifications, provided that You meet the following
-conditions: Use-based restrictions as referenced in paragraph 5 MUST
-be included as an enforceable provision by You in any type of legal
-agreement (e.g. a license) governing the use and/or distribution of
-the Model or Derivatives of the Model, and You shall give notice to
-subsequent users You Distribute to, that the Model or Derivatives of
-the Model are subject to paragraph 5. This provision does not apply to
-the use of Complementary Material. You must give any Third Party
-recipients of the Model or Derivatives of the Model a copy of this
-License; You must cause any modified files to carry prominent notices
-stating that You changed the files; You must retain all copyright,
-patent, trademark, and attribution notices excluding those notices
-that do not pertain to any part of the Model, Derivatives of the
-Model. You may add Your own copyright statement to Your modifications
-and may provide additional or different license terms and conditions -
-respecting paragraph 4.a. - for use, reproduction, or Distribution of
-Your modifications, or for any such Derivatives of the Model as a
-whole, provided Your use, reproduction, and Distribution of the Model
-otherwise complies with the conditions stated in this License.
-
-Use-based restrictions. The restrictions set forth in Attachment A are
-considered Use-based restrictions. Therefore You cannot use the Model
-and the Derivatives of the Model for the specified restricted
-uses. You may use the Model subject to this License, including only
-for lawful purposes and in accordance with the License. Use may
-include creating any content with, finetuning, updating, running,
-training, evaluating and/or reparametrizing the Model. You shall
-require all of Your users who use the Model or a Derivative of the
-Model to comply with the terms of this paragraph (paragraph 5).
-
-The Output You Generate.  Except as set forth herein, Licensor claims
-no rights in the Output You generate using the Model. You are
-accountable for the Output you generate and its subsequent uses. No
-use of the output can contravene any provision as stated in the
-License.
-
-Section IV: OTHER PROVISIONS
-
-Updates and Runtime Restrictions. To the maximum extent permitted by
-law, Licensor reserves the right to restrict (remotely or otherwise)
-usage of the Model in violation of this License.
-
-Trademarks and related. Nothing in this License permits You to make
-use of Licensors’ trademarks, trade names, logos or to otherwise
-suggest endorsement or misrepresent the relationship between the
-parties; and any rights not expressly granted herein are reserved by
-the Licensors.
-
-Disclaimer of Warranty. Unless required by applicable law or agreed to
-in writing, Licensor provides the Model and the Complementary Material
-(and each Contributor provides its Contributions) on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-implied, including, without limitation, any warranties or conditions
-of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-PARTICULAR PURPOSE. You are solely responsible for determining the
-appropriateness of using or redistributing the Model, Derivatives of
-the Model, and the Complementary Material and assume any risks
-associated with Your exercise of permissions under this License.
-
-Limitation of Liability. In no event and under no legal theory,
-whether in tort (including negligence), contract, or otherwise, unless
-required by applicable law (such as deliberate and grossly negligent
-acts) or agreed to in writing, shall any Contributor be liable to You
-for damages, including any direct, indirect, special, incidental, or
-consequential damages of any character arising as a result of this
-License or out of the use or inability to use the Model and the
-Complementary Material (including but not limited to damages for loss
-of goodwill, work stoppage, computer failure or malfunction, or any
-and all other commercial damages or losses), even if such Contributor
-has been advised of the possibility of such damages.
-
-Accepting Warranty or Additional Liability. While redistributing the
-Model, Derivatives of the Model and the Complementary Material
-thereof, You may choose to offer, and charge a fee for, acceptance of
-support, warranty, indemnity, or other liability obligations and/or
-rights consistent with this License. However, in accepting such
-obligations, You may act only on Your own behalf and on Your sole
-responsibility, not on behalf of any other Contributor, and only if
-You agree to indemnify, defend, and hold each Contributor harmless for
-any liability incurred by, or claims asserted against, such
-Contributor by reason of your accepting any such warranty or
-additional liability.
-
-If any provision of this License is held to be invalid, illegal or
-unenforceable, the remaining provisions shall be unaffected thereby
-and remain valid as if such provision had not been set forth herein.
-
-
-END OF TERMS AND CONDITIONS
-
-Attachment A
-
-Use Restrictions
-
-You agree not to use the Model or Derivatives of the Model:
-
-* In any way that violates any applicable national, federal, state,
-local or international law or regulation;
-
-* For the purpose of exploiting, harming or attempting to exploit or
-harm minors in any way;
-
-* To generate or disseminate verifiably false information and/or
-  content with the purpose of harming others;
-
-* To generate or disseminate personal identifiable information that
-  can be used to harm an individual;
-
-* To defame, disparage or otherwise harass others;
-
-* For fully automated decision making that adversely impacts an
-  individual’s legal rights or otherwise creates or modifies a
-  binding, enforceable obligation;
-
-* For any use intended to or which has the effect of discriminating
-  against or harming individuals or groups based on online or offline
-  social behavior or known or predicted personal or personality
-  characteristics;
-
-* To exploit any of the vulnerabilities of a specific group of persons
-  based on their age, social, physical or mental characteristics, in
-  order to materially distort the behavior of a person pertaining to
-  that group in a manner that causes or is likely to cause that person
-  or another person physical or psychological harm;
-
-* For any use intended to or which has the effect of discriminating
-  against individuals or groups based on legally protected
-  characteristics or categories;
-
-* To provide medical advice and medical results interpretation;
-
-* To generate or disseminate information for the purpose to be used
-  for administration of justice, law enforcement, immigration or
-  asylum processes, such as predicting an individual will commit
-  fraud/crime commitment (e.g. by text profiling, drawing causal
-  relationships between assertions made in documents, indiscriminate
-  and arbitrarily-targeted use).
-

docs/features/CONFIGURATION.md

@@ -65,6 +65,7 @@ InvokeAI:
     esrgan: true
     internet_available: true
     log_tokenization: false
+    nsfw_checker: false
     patchmatch: true
     restore: true
 ...
@@ -135,16 +136,19 @@ command-line options by giving the `--help` argument:
 
 ```
 (.venv) > invokeai-web --help
-usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials] [--allow_methods [ALLOW_METHODS ...]]
-                [--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan] [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
-                [--patchmatch | --no-patchmatch] [--restore | --no-restore]
-                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_loaded_models MAX_LOADED_MODELS] [--max_cache_size MAX_CACHE_SIZE]
-                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--gpu_mem_reserved GPU_MEM_RESERVED] [--precision {auto,float16,float32,autocast}]
-                [--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled] [--tiled_decode | --no-tiled_decode] [--root ROOT]
-                [--autoimport_dir AUTOIMPORT_DIR] [--lora_dir LORA_DIR] [--embedding_dir EMBEDDING_DIR] [--controlnet_dir CONTROLNET_DIR] [--conf_path CONF_PATH]
-                [--models_dir MODELS_DIR] [--legacy_conf_dir LEGACY_CONF_DIR] [--db_dir DB_DIR] [--outdir OUTDIR] [--from_file FROM_FILE]
-                [--use_memory_db | --no-use_memory_db] [--model MODEL] [--log_handlers [LOG_HANDLERS ...]] [--log_format {plain,color,syslog,legacy}]
-                [--log_level {debug,info,warning,error,critical}] [--version | --no-version]
+usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials]
+                [--allow_methods [ALLOW_METHODS ...]] [--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan]
+                [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
+                [--nsfw_checker | --no-nsfw_checker] [--patchmatch | --no-patchmatch] [--restore | --no-restore]
+                [--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_cache_size MAX_CACHE_SIZE]
+                [--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--precision {auto,float16,float32,autocast}]
+                [--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled]
+                [--tiled_decode | --no-tiled_decode] [--root ROOT] [--autoimport_dir AUTOIMPORT_DIR] [--lora_dir LORA_DIR]
+                [--embedding_dir EMBEDDING_DIR] [--controlnet_dir CONTROLNET_DIR] [--conf_path CONF_PATH] [--models_dir MODELS_DIR]
+                [--legacy_conf_dir LEGACY_CONF_DIR] [--db_dir DB_DIR] [--outdir OUTDIR] [--from_file FROM_FILE]
+                [--use_memory_db | --no-use_memory_db] [--model MODEL] [--log_handlers [LOG_HANDLERS ...]]
+                [--log_format {plain,color,syslog,legacy}] [--log_level {debug,info,warning,error,critical}]
+...
 ```
 
 ## The Configuration Settings
@@ -174,6 +178,7 @@ These configuration settings allow you to enable and disable various InvokeAI fe
 | `esrgan`     | `true`      | Activate the ESRGAN upscaling options|
 | `internet_available` | `true`     | When a resource is not available locally, try to fetch it via the internet |
 | `log_tokenization` | `false`      | Before each text2image generation, print a color-coded representation of the prompt to the console; this can help understand why a prompt is not working as expected |
+| `nsfw_checker` | `true`     | Activate the NSFW checker to blur out risque images |
 | `patchmatch` | `true`     | Activate the "patchmatch" algorithm for improved inpainting |
 | `restore`    | `true`     | Activate the facial restoration features (DEPRECATED; restoration features will be removed in 3.0.0) |
 

docs/features/NODES.md

@@ -61,13 +61,11 @@ A noise scheduler (eg. DPM++ 2M Karras) schedules the subtraction of noise from
 | ImageInverseLerp                   | Inverse linear interpolation of all pixels of an image |
 | ImageLerp                          | Linear interpolation of all pixels of an image |
 | ImageMultiply                      | Multiplies two images together using `PIL.ImageChops.Multiply()` |
-| ImageNSFWBlurInvocation            | Detects and blurs images that may contain sexually explicit content |
 | ImagePaste                         | Pastes an image into another image |
 | ImageProcessor                     | Base class for invocations that reprocess images for ControlNet |
 | ImageResize                        | Resizes an image to specific dimensions |
 | ImageScale                         | Scales an image by a factor |
 | ImageToLatents                     | Scales latents by a given factor |
-| ImageWatermarkInvocation           | Adds an invisible watermark to images |
 | InfillColor                        | Infills transparent areas of an image with a solid color |
 | InfillPatchMatch                   | Infills transparent areas of an image using the PatchMatch algorithm |
 | InfillTile                         | Infills transparent areas of an image with tiles of the image |
@@ -118,49 +116,49 @@ There are several node grouping concepts that can be examined with a narrow focu
 
 As described, an initial noise tensor is necessary for the latent diffusion process. As a result, all non-image *ToLatents nodes require a noise node input.  
 
-![groupsnoise](../assets/nodes/groupsnoise.png)
+<img width="654" alt="groupsnoise" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/2e8d297e-ad55-4d27-bc93-c119dad2a2c5">
 
 ### Conditioning
 
 As described, conditioning is necessary for the latent diffusion process, whether empty or not. As a result, all non-image *ToLatents nodes require positive and negative conditioning inputs. Conditioning is reliant on a CLIP tokenizer provided by the Model Loader node.
 
-![groupsconditioning](../assets/nodes/groupsconditioning.png)
+<img width="1024" alt="groupsconditioning" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/f8f7ad8a-8d9c-418e-b5ad-1437b774b27e">
 
 ### Image Space & VAE
 
 The ImageToLatents node doesn't require a noise node input, but requires a VAE input to convert the image from image space into latent space. In reverse, the LatentsToImage node requires a VAE input to convert from latent space back into image space.
 
-![groupsimgvae](../assets/nodes/groupsimgvae.png)
+<img width="637" alt="groupsimgvae" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/dd99969c-e0a8-4f78-9b17-3ffe179cef9a">
 
 ### Defined & Random Seeds
 
 It is common to want to use both the same seed (for continuity) and random seeds (for variance). To define a seed, simply enter it into the 'Seed' field on a noise node. Conversely, the RandomInt node generates a random integer between 'Low' and 'High', and can be used as input to the 'Seed' edge point on a noise node to randomize your seed.
 
-![groupsrandseed](../assets/nodes/groupsrandseed.png)
+<img width="922" alt="groupsrandseed" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/af55bc20-60f6-438e-aba5-3ec871443710">
 
 ### Control
 
 Control means to guide the diffusion process to adhere to a defined input or structure. Control can be provided as input to non-image *ToLatents nodes from ControlNet nodes. ControlNet nodes usually require an image processor which converts an input image for use with ControlNet.
 
-![groupscontrol](../assets/nodes/groupscontrol.png)
+<img width="805" alt="groupscontrol" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/cc9c5de7-23a7-46c8-bbad-1f3609d999a6">
 
 ### LoRA
 
 The Lora Loader node lets you load a LoRA (say that ten times fast) and pass it as output to both the Prompt (Compel) and non-image *ToLatents nodes. A model's CLIP tokenizer is passed through the LoRA into Prompt (Compel), where it affects conditioning. A model's U-Net is also passed through the LoRA into a non-image *ToLatents node, where it affects noise prediction.
 
-![groupslora](../assets/nodes/groupslora.png)
+<img width="993" alt="groupslora" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/630962b0-d914-4505-b3ea-ccae9b0269da">
 
 ### Scaling
 
 Use the ImageScale, ScaleLatents, and Upscale nodes to upscale images and/or latent images. The chosen method differs across contexts. However, be aware that latents are already noisy and compressed at their original resolution; scaling an image could produce more detailed results.
 
-![groupsallscale](../assets/nodes/groupsallscale.png)
+<img width="644" alt="groupsallscale" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/99314f05-dd9f-4b6d-b378-31de55346a13">
 
 ### Iteration + Multiple Images as Input
 
 Iteration is a common concept in any processing, and means to repeat a process with given input. In nodes, you're able to use the Iterate node to iterate through collections usually gathered by the Collect node. The Iterate node has many potential uses, from processing a collection of images one after another, to varying seeds across multiple image generations and more. This screenshot demonstrates how to collect several images and pass them out one at a time.
 
-![groupsiterate](../assets/nodes/groupsiterate.png)
+<img width="788" alt="groupsiterate" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/4af5ca27-82c9-4018-8c5b-024d3ee0a121">
 
 ### Multiple Image Generation + Random Seeds
 
@@ -168,7 +166,7 @@ Multiple image generation in the node editor is done using the RandomRange node.
 
 To control seeds across generations takes some care. The first row in the screenshot will generate multiple images with different seeds, but using the same RandomRange parameters across invocations will result in the same group of random seeds being used across the images, producing repeatable results. In the second row, adding the RandomInt node as input to RandomRange's 'Seed' edge point will ensure that seeds are varied across all images across invocations, producing varied results.
 
-![groupsmultigenseeding](../assets/nodes/groupsmultigenseeding.png)
+<img width="1027" alt="groupsmultigenseeding" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/518d1b2b-fed1-416b-a052-ab06552521b3">
 
 ## Examples
 
@@ -176,7 +174,7 @@ With our knowledge of node grouping and the diffusion process, let’s break dow
 
 ### Basic text-to-image Node Graph
 
-![nodest2i](../assets/nodes/nodest2i.png)
+<img width="875" alt="nodest2i" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/17c67720-c376-4db8-94f0-5e00381a61ee">
 
 - Model Loader: A necessity to generating images (as we’ve read above). We choose our model from the dropdown. It outputs a U-Net, CLIP tokenizer, and VAE.
 - Prompt (Compel): Another necessity. Two prompt nodes are created. One will output positive conditioning (what you want, ‘dog’), one will output negative (what you don’t want, ‘cat’). They both input the CLIP tokenizer that the Model Loader node outputs.
@@ -186,7 +184,7 @@ With our knowledge of node grouping and the diffusion process, let’s break dow
 
 ### Basic image-to-image Node Graph
 
-![nodesi2i](../assets/nodes/nodesi2i.png)
+<img width="998" alt="nodesi2i" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/3f2c95d5-cee7-4415-9b79-b46ee60a92fe">
 
 - Model Loader: Choose a model from the dropdown.
 - Prompt (Compel): Two prompt nodes. One positive (dog), one negative (dog). Same CLIP inputs from the Model Loader node as before.
@@ -197,7 +195,7 @@ With our knowledge of node grouping and the diffusion process, let’s break dow
 
 ### Basic ControlNet Node Graph
 
-![nodescontrol](../assets/nodes/nodescontrol.png)
+<img width="703" alt="nodescontrol" src="https://github.com/ymgenesis/InvokeAI/assets/25252829/b02ded86-ceb4-44a2-9910-e19ad184d471">
 
 - Model Loader
 - Prompt (Compel)

docs/features/NSFW.md

@@ -1,40 +1,12 @@
 ---
-title: Watermarking, NSFW Image Checking
+title: The NSFW Checker
 ---
 
-# :material-image-off: Invisible Watermark and the NSFW Checker
-
-## Watermarking
-
-InvokeAI does not apply watermarking to images by default. However,
-many computer scientists working in the field of generative AI worry
-that a flood of computer-generated imagery will contaminate the image
-data sets needed to train future generations of generative models.
-
-InvokeAI offers an optional watermarking mode that writes a small bit
-of text, **InvokeAI**, into each image that it generates using an
-"invisible" watermarking library that spreads the information
-throughout the image in a way that is not perceptible to the human
-eye. If you are planning to share your generated images on
-internet-accessible services, we encourage you to activate the
-invisible watermark mode in order to help preserve the digital image
-environment.
-
-The downside of watermarking is that it increases the size of the
-image moderately, and has been reported by some individuals to degrade
-image quality. Your mileage may vary.
-
-To read the watermark in an image, activate the InvokeAI virtual
-environment (called the "developer's console" in the launcher) and run
-the command:
-
-```
-invisible-watermark -a decode -t bytes -m dwtDct -l 64 /path/to/image.png
-```
+# :material-image-off: NSFW Checker
 
 ## The NSFW ("Safety") Checker
 
-Stable Diffusion 1.5-based image generation models will produce sexual
+The Stable Diffusion image generation models will produce sexual
 imagery if deliberately prompted, and will occasionally produce such
 images when this is not intended. Such images are colloquially known
 as "Not Safe for Work" (NSFW). This behavior is due to the nature of
@@ -46,17 +18,35 @@ jurisdictions it may be illegal to publicly distribute such imagery,
 including mounting a publicly-available server that provides
 unfiltered images to the public. Furthermore, the [Stable Diffusion
 weights
-License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-SD1+SD2.txt),
-and the [Stable Diffusion XL
-License][https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-SDXL.txt]
-both forbid the models from being used to "exploit any of the
+License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-ModelWeights.txt)
+forbids the model from being used to "exploit any of the
 vulnerabilities of a specific group of persons."
 
 For these reasons Stable Diffusion offers a "safety checker," a
 machine learning model trained to recognize potentially disturbing
 imagery. When a potentially NSFW image is detected, the checker will
 blur the image and paste a warning icon on top. The checker can be
-turned on and off in the Web interface under Settings.
+turned on and off on the command line using `--nsfw_checker` and
+`--no-nsfw_checker`.
+
+At installation time, InvokeAI will ask whether the checker should be
+activated by default (neither argument given on the command line). The
+response is stored in the InvokeAI initialization file
+(`invokeai.yaml` in the InvokeAI root directory).  You can change the
+default at any time by opening this file in a text editor and
+changing the line `nsfw_checker:` from true to false or vice-versa:
+
+
+```
+...
+  Features:
+    esrgan: true
+    internet_available: true
+    log_tokenization: false
+    nsfw_checker: true
+    patchmatch: true
+    restore: true
+```
 
 ## Caveats
 
@@ -94,3 +84,10 @@ are encouraged to turn **off** intermediate image rendering when you
 are using the checker. Future versions of InvokeAI will apply
 additional blurring to intermediate images when the checker is active.
 
+### Watermarking
+
+InvokeAI does not apply any sort of watermark to images it
+generates. However, it does write metadata into the PNG data area,
+including the prompt used to generate the image and relevant parameter
+settings. These fields can be examined using the `sd-metadata.py`
+script that comes with the InvokeAI package.

docs/features/OTHER.md

@@ -16,24 +16,21 @@ Output Example:
 
 ---
 
-## **Invisible Watermark**
+## **Seamless Tiling**
 
-In keeping with the principles for responsible AI generation, and to
-help AI researchers avoid synthetic images contaminating their
-training sets, InvokeAI adds an invisible watermark to each of the
-final images it generates. The watermark consists of the text
-"InvokeAI" and can be viewed using the
-[invisible-watermarks](https://github.com/ShieldMnt/invisible-watermark)
-tool.
+The seamless tiling mode causes generated images to seamlessly tile
+with itself creating repetitive wallpaper-like patterns. To use it,
+activate the Seamless Tiling option in the Web GUI and then select
+whether to tile on the X (horizontal) and/or Y (vertical) axes. Tiling
+will then be active for the next set of generations.
 
-Watermarking is controlled using the `invisible-watermark` setting in
-`invokeai.yaml`. To turn it off, add the following line under the `Features`
-category.
+A nice prompt to test seamless tiling with is:
 
 ```
-invisible_watermark: false
+pond garden with lotus by claude monet"
 ```
 
+---
 
 ## **Weighted Prompts**
 
@@ -42,10 +39,34 @@ priority to them, by adding `:<percent>` to the end of the section you wish to u
 example consider this prompt:
 
 ```bash
-(tabby cat):0.25 (white duck):0.75 hybrid
+tabby cat:0.25 white duck:0.75 hybrid
 ```
 
 This will tell the sampler to invest 25% of its effort on the tabby cat aspect of the image and 75%
 on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
 combination of integers and floating point numbers, and they do not need to add up to 1.
 
+## **Thresholding and Perlin Noise Initialization Options**
+
+Under the Noise section of the Web UI, you will find two options named
+Perlin Noise and Noise Threshold. [Perlin
+noise](https://en.wikipedia.org/wiki/Perlin_noise) is a type of
+structured noise used to simulate terrain and other natural
+textures. The slider controls the percentage of perlin noise that will
+be mixed into the image at the beginning of generation. Adding a little
+perlin noise to a generation will alter the image substantially.
+
+The noise threshold limits the range of the latent values during
+sampling and helps combat the oversharpening seem with higher CFG
+scale values.
+
+For better intuition into what these options do in practice:
+
+![here is a graphic demonstrating them both](../assets/truncation_comparison.jpg)
+
+In generating this graphic, perlin noise at initialization was
+programmatically varied going across on the diagram by values 0.0,
+0.1, 0.2, 0.4, 0.5, 0.6, 0.8, 0.9, 1.0; and the threshold was varied
+going down from 0, 1, 2, 3, 4, 5, 10, 20, 100. The other options are
+fixed using the prompt "a portrait of a beautiful young lady" a CFG of
+20, 100 steps, and a seed of 1950357039.

docs/index.md

@@ -148,7 +148,7 @@ images in full-precision mode:
 - [Model Merging](features/MODEL_MERGING.md)
 - [ControlNet Models](features/CONTROLNET.md)
 - [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
-- [Watermarking and the Not Safe for Work (NSFW) Checker](features/WATERMARK+NSFW.md)
+- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
 <!-- seperator -->
 ### Prompt Engineering
 - [Prompt Syntax](features/PROMPTS.md)

docs/installation/010_INSTALL_AUTOMATED.md

@@ -215,6 +215,17 @@ experimental versions later.
     Generally the defaults are fine, and you can come back to this screen at
     any time to tweak your system. Here are the options you can adjust:
 
+    - ***Output directory for images***
+      This is the path to a directory in which InvokeAI will store all its
+      generated images.
+
+    - ***NSFW checker***
+      If checked, InvokeAI will test images for potential sexual content
+      and blur them out if found. Note that the NSFW checker consumes
+      an additional 0.6 GB of VRAM on top of the 2-3 GB of VRAM used
+      by most image models. If you have a low VRAM GPU (4-6 GB), you
+      can reduce out of memory errors by disabling the checker.
+
     - ***HuggingFace Access Token***
       InvokeAI has the ability to download embedded styles and subjects
       from the HuggingFace Concept Library on-demand. However, some of
@@ -246,30 +257,20 @@ experimental versions later.
 	and graphics cards. The "autocast" option is deprecated and
 	shouldn't be used unless you are asked to by a member of the team.
 
-    - **Size of the RAM cache used for fast model switching***
+    - ***Number of models to cache in CPU memory***
         This allows you to keep models in memory and switch rapidly among
 	them rather than having them load from disk each time. This slider
-	controls how many models to keep loaded at once. A typical SD-1 or SD-2 model
-	uses 2-3 GB of memory. A typical SDXL model uses 6-7 GB. Providing more
-	RAM will allow more models to be co-resident.
+	controls how many models to keep loaded at once. Each
+	model will use 2-4 GB of RAM, so use this cautiously
 
-    - ***Output directory for images***
-      This is the path to a directory in which InvokeAI will store all its
-      generated images.
-
-    - ***Autoimport Folder***
-      This is the directory in which you can place models you have
-	  downloaded and wish to load into InvokeAI. You can place a variety
-	  of models in this directory, including diffusers folders, .ckpt files,
-	  .safetensors files, as well as LoRAs, ControlNet and Textual Inversion
-	  files (both folder and file versions). To help organize this folder,
-	  you can create several levels of subfolders and drop your models into
-      whichever ones you want.
-	
-    - ***Autoimport FolderLICENSE***     
+    - ***Directory containing embedding/textual inversion files***
+        This is the directory in which you can place custom embedding
+	files (.pt or .bin). During startup, this directory will be
+	scanned and InvokeAI will print out the text terms that
+	are available to trigger the embeddings.
 
     At the bottom of the screen you will see a checkbox for accepting
-    the CreativeML Responsible AI Licenses. You need to accept the license
+    the CreativeML Responsible AI License. You need to accept the license
     in order to download Stable Diffusion models from the next screen.
 
     _You can come back to the startup options form_ as many times as you like.

invokeai/app/api/routers/app_info.py

@@ -1,15 +1,9 @@
-import typing
 from enum import Enum
 from fastapi import Body
 from fastapi.routing import APIRouter
-from pathlib import Path
 from pydantic import BaseModel, Field
 
 from invokeai.backend.image_util.patchmatch import PatchMatch
-from invokeai.backend.image_util.safety_checker import SafetyChecker
-from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
-from invokeai.app.invocations.upscale import ESRGAN_MODELS
-
 from invokeai.version import __version__
 
 from ..dependencies import ApiDependencies
@@ -22,10 +16,6 @@ class LogLevel(int, Enum):
     Warning = logging.WARNING
     Error = logging.ERROR
     Critical = logging.CRITICAL
-
-class Upscaler(BaseModel):
-    upscaling_method: str = Field(description="Name of upscaling method")
-    upscaling_models: list[str] = Field(description="List of upscaling models for this method")
     
 app_router = APIRouter(prefix="/v1/app", tags=["app"])
 
@@ -40,9 +30,6 @@ class AppConfig(BaseModel):
     """App Config Response"""
 
     infill_methods: list[str] = Field(description="List of available infill methods")
-    upscaling_methods: list[Upscaler] = Field(description="List of upscaling methods")
-    nsfw_methods: list[str] = Field(description="List of NSFW checking methods")
-    watermarking_methods: list[str] = Field(description="List of invisible watermark methods")
 
 
 @app_router.get(
@@ -59,30 +46,7 @@ async def get_config() -> AppConfig:
     infill_methods = ['tile']
     if PatchMatch.patchmatch_available():
         infill_methods.append('patchmatch')
-        
-
-    upscaling_models = []
-    for model in typing.get_args(ESRGAN_MODELS):
-        upscaling_models.append(str(Path(model).stem))
-    upscaler = Upscaler(
-        upscaling_method = 'esrgan',
-        upscaling_models = upscaling_models
-    )
-    
-    nsfw_methods = []
-    if SafetyChecker.safety_checker_available():
-        nsfw_methods.append('nsfw_checker')
-
-    watermarking_methods = []
-    if InvisibleWatermark.invisible_watermark_available():
-        watermarking_methods.append('invisible_watermark')
-        
-    return AppConfig(
-        infill_methods=infill_methods,
-        upscaling_methods=[upscaler],
-        nsfw_methods=nsfw_methods,
-        watermarking_methods=watermarking_methods,
-    )
+    return AppConfig(infill_methods=infill_methods)
 
 @app_router.get(
     "/logging",

invokeai/app/api/routers/models.py

@@ -298,7 +298,7 @@ async def search_for_models(
 )->List[pathlib.Path]:
     if not search_path.is_dir():
         raise HTTPException(status_code=404, detail=f"The search path '{search_path}' does not exist or is not directory")
-    return ApiDependencies.invoker.services.model_manager.search_for_models(search_path)
+    return ApiDependencies.invoker.services.model_manager.search_for_models([search_path])
 
 @models_router.get(
     "/ckpt_confs",

invokeai/app/api_app.py

@@ -203,10 +203,7 @@ def invoke_api():
                 return find_port(port=port + 1)
             else:
                 return port
-            
-    from invokeai.backend.install.check_root import check_invokeai_root
-    check_invokeai_root(app_config)  # note, may exit with an exception if root not set up
-    
+
     port = find_port(app_config.port)
     if port != app_config.port:
         logger.warn(f"Port {app_config.port} in use, using port {port}")

invokeai/app/invocations/compel.py

@@ -95,7 +95,7 @@ class CompelInvocation(BaseInvocation):
         def _lora_loader():
             for lora in self.clip.loras:
                 lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}), context=context)
+                    **lora.dict(exclude={"weight"}))
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
@@ -171,16 +171,16 @@ class CompelInvocation(BaseInvocation):
 class SDXLPromptInvocationBase:
     def run_clip_raw(self, context, clip_field, prompt, get_pooled):
         tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.dict(), context=context,
+            **clip_field.tokenizer.dict(),
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.dict(), context=context,
+            **clip_field.text_encoder.dict(),
         )
 
         def _lora_loader():
             for lora in clip_field.loras:
                 lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}), context=context)
+                    **lora.dict(exclude={"weight"}))
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
@@ -196,7 +196,6 @@ class SDXLPromptInvocationBase:
                         model_name=name,
                         base_model=clip_field.text_encoder.base_model,
                         model_type=ModelType.TextualInversion,
-                        context=context,
                     ).context.model
                 )
             except ModelNotFoundException:
@@ -241,16 +240,16 @@ class SDXLPromptInvocationBase:
 
     def run_clip_compel(self, context, clip_field, prompt, get_pooled):
         tokenizer_info = context.services.model_manager.get_model(
-            **clip_field.tokenizer.dict(), context=context,
+            **clip_field.tokenizer.dict(),
         )
         text_encoder_info = context.services.model_manager.get_model(
-            **clip_field.text_encoder.dict(), context=context,
+            **clip_field.text_encoder.dict(),
         )
 
         def _lora_loader():
             for lora in clip_field.loras:
                 lora_info = context.services.model_manager.get_model(
-                    **lora.dict(exclude={"weight"}), context=context)
+                    **lora.dict(exclude={"weight"}))
                 yield (lora_info.context.model, lora.weight)
                 del lora_info
             return
@@ -266,7 +265,6 @@ class SDXLPromptInvocationBase:
                         model_name=name,
                         base_model=clip_field.text_encoder.base_model,
                         model_type=ModelType.TextualInversion,
-                        context=context,
                     ).context.model
                 )
             except ModelNotFoundException:

invokeai/app/invocations/controlnet_image_processors.py

@@ -20,7 +20,7 @@ from ...backend.model_management import BaseModelType, ModelType
 from ..models.image import ImageCategory, ImageField, ResourceOrigin
 from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
                              InvocationConfig, InvocationContext)
-from ..models.image import ImageOutput, PILInvocationConfig
+from .image import ImageOutput, PILInvocationConfig
 
 CONTROLNET_DEFAULT_MODELS = [
     ###########################################

invokeai/app/invocations/image.py

@@ -2,23 +2,64 @@
 
 from typing import Literal, Optional
 
+import cv2
 import numpy
 from PIL import Image, ImageFilter, ImageOps, ImageChops
-from pydantic import Field
-from pathlib import Path
+from pydantic import BaseModel, Field
 from typing import Union
-from invokeai.app.invocations.metadata import CoreMetadata
-from ..models.image import (
-    ImageCategory, ImageField, ResourceOrigin,
-    PILInvocationConfig, ImageOutput, MaskOutput,
-)    
+
+from ..models.image import ImageCategory, ImageField, ResourceOrigin
 from .baseinvocation import (
     BaseInvocation,
+    BaseInvocationOutput,
     InvocationContext,
     InvocationConfig,
 )
-from invokeai.backend.image_util.safety_checker import SafetyChecker
-from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
+
+
+class PILInvocationConfig(BaseModel):
+    """Helper class to provide all PIL invocations with additional config"""
+
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["PIL", "image"],
+            },
+        }
+
+
+class ImageOutput(BaseInvocationOutput):
+    """Base class for invocations that output an image"""
+
+    # fmt: off
+    type: Literal["image_output"] = "image_output"
+    image:      ImageField = Field(default=None, description="The output image")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {"required": ["type", "image", "width", "height"]}
+
+
+class MaskOutput(BaseInvocationOutput):
+    """Base class for invocations that output a mask"""
+
+    # fmt: off
+    type: Literal["mask"] = "mask"
+    mask:      ImageField = Field(default=None, description="The output mask")
+    width:            int = Field(description="The width of the mask in pixels")
+    height:           int = Field(description="The height of the mask in pixels")
+    # fmt: on
+
+    class Config:
+        schema_extra = {
+            "required": [
+                "type",
+                "mask",
+            ]
+        }
+
 
 class LoadImageInvocation(BaseInvocation):
     """Load an image and provide it as output."""
@@ -153,13 +194,10 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         base_image = context.services.images.get_pil_image(self.base_image.image_name)
         image = context.services.images.get_pil_image(self.image.image_name)
-        mask = (
-            None
-            if self.mask is None
-            else ImageOps.invert(
-                context.services.images.get_pil_image(self.mask.image_name)
-            )
-        )
+        mask = None
+        if self.mask is not None:
+            mask = context.services.images.get_pil_image(self.mask.image_name)
+            mask =  ImageOps.invert(mask.convert("L"))
         # TODO: probably shouldn't invert mask here... should user be required to do it?
 
         min_x = min(0, self.x)
@@ -357,6 +395,7 @@ class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
             height=image_dto.height,
         )
 
+
 class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
     """Blurs an image"""
 
@@ -561,6 +600,7 @@ class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
             height=image_dto.height,
         )
 
+
 class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
     """Inverse linear interpolation of all pixels of an image"""
 
@@ -609,89 +649,162 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
             height=image_dto.height,
         )
 
-class ImageNSFWBlurInvocation(BaseInvocation, PILInvocationConfig):
-    """Add blur to NSFW-flagged images"""
+class MaskEdgeInvocation(BaseInvocation, PILInvocationConfig):
+    """Applies an edge mask to an image"""
 
     # fmt: off
-    type: Literal["img_nsfw"] = "img_nsfw"
+    type: Literal["mask_edge"] = "mask_edge"
 
     # Inputs
-    image: Optional[ImageField]  = Field(default=None, description="The image to check")
-    metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")    
+    image: Optional[ImageField] = Field(default=None, description="The image to apply the mask to")
+    edge_size: int = Field(description="The size of the edge")
+    edge_blur: int = Field(description="The amount of blur on the edge")
+    low_threshold: int = Field(description="First threshold for the hysteresis procedure in Canny edge detection")
+    high_threshold: int = Field(description="Second threshold for the hysteresis procedure in Canny edge detection")
     # fmt: on
 
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "title": "Blur NSFW Images",
-                "tags": ["image", "nsfw", "checker"]
-            },
-        }
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        mask = context.services.images.get_pil_image(self.image.image_name)
 
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        
-        logger = context.services.logger
-        logger.debug("Running NSFW checker")
-        if SafetyChecker.has_nsfw_concept(image):
-            logger.info("A potentially NSFW image has been detected. Image will be blurred.")
-            blurry_image = image.filter(filter=ImageFilter.GaussianBlur(radius=32))
-            caution = self._get_caution_img()
-            blurry_image.paste(caution,(0,0),caution)
-            image = blurry_image
+        npimg = numpy.asarray(mask, dtype=numpy.uint8)
+        npgradient = numpy.uint8(
+            255 * (1.0 - numpy.floor(numpy.abs(0.5 - numpy.float32(npimg) / 255.0) * 2.0))
+        )
+        npedge = cv2.Canny(npimg, threshold1=self.low_threshold, threshold2=self.high_threshold)
+        npmask = npgradient + npedge
+        npmask = cv2.dilate(
+            npmask, numpy.ones((3, 3), numpy.uint8), iterations=int(self.edge_size / 2)
+        )
+
+        new_mask = Image.fromarray(npmask)
+
+        if self.edge_blur > 0:
+            new_mask = new_mask.filter(ImageFilter.BoxBlur(self.edge_blur))
+
+        new_mask = ImageOps.invert(new_mask)
 
         image_dto = context.services.images.create(
-            image=image,
+            image=new_mask,
             image_origin=ResourceOrigin.INTERNAL,
-            image_category=ImageCategory.GENERAL,
+            image_category=ImageCategory.MASK,
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
         )
-                
-        return ImageOutput(
-            image=ImageField(image_name=image_dto.image_name),
+
+        return MaskOutput(
+            mask=ImageField(image_name=image_dto.image_name),
             width=image_dto.width,
             height=image_dto.height,
         )
-    
-    def _get_caution_img(self)->Image:
-        import invokeai.app.assets.images as image_assets
-        caution = Image.open(Path(image_assets.__path__[0]) / 'caution.png')
-        return caution.resize((caution.width // 2, caution.height //2))
 
-class ImageWatermarkInvocation(BaseInvocation, PILInvocationConfig):
-    """ Add an invisible watermark to an image """
+class ColorCorrectInvocation(BaseInvocation, PILInvocationConfig):
 
-    # fmt: off
-    type: Literal["img_watermark"] = "img_watermark"
+    type: Literal["color_correct"] = "color_correct"
 
-    # Inputs
-    image: Optional[ImageField]  = Field(default=None, description="The image to check")
-    text: str = Field(default='InvokeAI', description="Watermark text")
-    metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")    
-    # fmt: on
-
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "title": "Add Invisible Watermark",
-                "tags": ["image", "watermark", "invisible"]
-            },
-        }
+    init: Optional[ImageField] = Field(default=None, description="Initial image")
+    result: Optional[ImageField] = Field(default=None, description="Resulted image")
+    mask: Optional[ImageField] = Field(default=None, description="Mask image")
+    mask_blur_radius: float = Field(default=8, description="Mask blur radius")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        image = context.services.images.get_pil_image(self.image.image_name)
-        new_image = InvisibleWatermark.add_watermark(image, self.text)
+        pil_init_mask = None
+        if self.mask is not None:
+            pil_init_mask = context.services.images.get_pil_image(
+                self.mask.image_name
+            ).convert("L")
+
+        init_image = context.services.images.get_pil_image(
+            self.init.image_name
+        )
+
+        result = context.services.images.get_pil_image(
+            self.result.image_name
+        ).convert("RGBA")
+
+
+        #if init_image is None or init_mask is None:
+        #    return result
+
+        # Get the original alpha channel of the mask if there is one.
+        # Otherwise it is some other black/white image format ('1', 'L' or 'RGB')
+        #pil_init_mask = (
+        #    init_mask.getchannel("A")
+        #    if init_mask.mode == "RGBA"
+        #    else init_mask.convert("L")
+        #)
+        pil_init_image = init_image.convert(
+            "RGBA"
+        )  # Add an alpha channel if one doesn't exist
+
+        # Build an image with only visible pixels from source to use as reference for color-matching.
+        init_rgb_pixels = numpy.asarray(init_image.convert("RGB"), dtype=numpy.uint8)
+        init_a_pixels = numpy.asarray(pil_init_image.getchannel("A"), dtype=numpy.uint8)
+        init_mask_pixels = numpy.asarray(pil_init_mask, dtype=numpy.uint8)
+
+        # Get numpy version of result
+        np_image = numpy.asarray(result.convert("RGB"), dtype=numpy.uint8)
+
+        # Mask and calculate mean and standard deviation
+        mask_pixels = init_a_pixels * init_mask_pixels > 0
+        np_init_rgb_pixels_masked = init_rgb_pixels[mask_pixels, :]
+        np_image_masked = np_image[mask_pixels, :]
+
+        if np_init_rgb_pixels_masked.size > 0:
+            init_means = np_init_rgb_pixels_masked.mean(axis=0)
+            init_std = np_init_rgb_pixels_masked.std(axis=0)
+            gen_means = np_image_masked.mean(axis=0)
+            gen_std = np_image_masked.std(axis=0)
+
+            # Color correct
+            np_matched_result = np_image.copy()
+            np_matched_result[:, :, :] = (
+                (
+                    (
+                        (
+                            np_matched_result[:, :, :].astype(numpy.float32)
+                            - gen_means[None, None, :]
+                        )
+                        / gen_std[None, None, :]
+                    )
+                    * init_std[None, None, :]
+                    + init_means[None, None, :]
+                )
+                .clip(0, 255)
+                .astype(numpy.uint8)
+            )
+            matched_result = Image.fromarray(np_matched_result, mode="RGB")
+        else:
+            matched_result = Image.fromarray(np_image, mode="RGB")
+
+        # Blur the mask out (into init image) by specified amount
+        if self.mask_blur_radius > 0:
+            nm = numpy.asarray(pil_init_mask, dtype=numpy.uint8)
+            nmd = cv2.erode(
+                nm,
+                kernel=numpy.ones((3, 3), dtype=numpy.uint8),
+                iterations=int(self.mask_blur_radius / 2),
+            )
+            pmd = Image.fromarray(nmd, mode="L")
+            blurred_init_mask = pmd.filter(ImageFilter.BoxBlur(self.mask_blur_radius))
+        else:
+            blurred_init_mask = pil_init_mask
+
+
+        multiplied_blurred_init_mask = ImageChops.multiply(
+            blurred_init_mask, result.split()[-1]
+        )
+
+        # Paste original on color-corrected generation (using blurred mask)
+        matched_result.paste(init_image, (0, 0), mask=multiplied_blurred_init_mask)
+
         image_dto = context.services.images.create(
-            image=new_image,
+            image=matched_result,
             image_origin=ResourceOrigin.INTERNAL,
             image_category=ImageCategory.GENERAL,
             node_id=self.id,
             session_id=context.graph_execution_state_id,
             is_intermediate=self.is_intermediate,
-            metadata=self.metadata.dict() if self.metadata else None,
         )
 
         return ImageOutput(
@@ -699,6 +812,3 @@ class ImageWatermarkInvocation(BaseInvocation, PILInvocationConfig):
             width=image_dto.width,
             height=image_dto.height,
         )
-
-
-

invokeai/app/invocations/latent.py

@@ -3,6 +3,8 @@
 from contextlib import ExitStack
 from typing import List, Literal, Optional, Union
 
+import torchvision.transforms as T
+from torchvision.transforms.functional import resize as tv_resize
 import einops
 import torch
 from diffusers import ControlNetModel
@@ -394,6 +396,9 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
     strength: float = Field(
         default=0.7, ge=0, le=1,
         description="The strength of the latents to use")
+    mask: Optional[ImageField] = Field(
+        None, description="Mask",
+    )
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -409,10 +414,25 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             },
         }
 
+    def prep_mask_tensor(self, context, lantents):
+        if self.mask is None:
+            return None
+
+        mask_image = context.services.images.get_pil_image(self.mask.image_name)
+        if mask_image.mode != "L":
+            # FIXME: why do we get passed an RGB image here? We can only use single-channel.
+            mask_image = mask_image.convert("L")
+        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        mask_tensor = tv_resize(
+            mask_tensor, lantents.shape[-2:], T.InterpolationMode.BILINEAR
+        )
+        return mask_tensor
+
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         noise = context.services.latents.get(self.noise.latents_name)
         latent = context.services.latents.get(self.latents.latents_name)
+        mask = self.prep_mask_tensor(context, latent)
 
         # Get the source node id (we are invoking the prepared node)
         graph_execution_state = context.services.graph_execution_manager.get(
@@ -441,6 +461,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
 
             noise = noise.to(device=unet.device, dtype=unet.dtype)
             latent = latent.to(device=unet.device, dtype=unet.dtype)
+            mask = mask.to(device=unet.device, dtype=unet.dtype)
 
             scheduler = get_scheduler(
                 context=context,
@@ -470,6 +491,15 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
                 device=unet.device,
             )
 
+            def _apply_mask_on_step(step_output, timestep, conditioning_data):
+                noised_init = scheduler.add_noise(initial_latents, noise, timestep.unsqueeze(0))
+                step_output.prev_sample = step_output.prev_sample * (1 - mask) + noised_init * mask
+                return step_output
+
+            additional_guidance = []
+            if mask is not None:
+                additional_guidance.append(_apply_mask_on_step)
+
             result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
                 latents=initial_latents,
                 timesteps=timesteps,
@@ -477,7 +507,8 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
                 num_inference_steps=self.steps,
                 conditioning_data=conditioning_data,
                 control_data=control_data,  # list[ControlNetData]
-                callback=step_callback
+                callback=step_callback,
+                additional_guidance=additional_guidance,
             )
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
@@ -501,7 +532,7 @@ class LatentsToImageInvocation(BaseInvocation):
     vae: VaeField = Field(default=None, description="Vae submodel")
     tiled: bool = Field(
         default=False,
-        description="Decode latents by overlapping tiles(less memory consumption)")
+        description="Decode latents by overlaping tiles(less memory consumption)")
     fp32: bool = Field(DEFAULT_PRECISION=='float32', description="Decode in full precision")
     metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")
 

invokeai/app/invocations/metadata.py

@@ -2,18 +2,16 @@ from typing import Literal, Optional, Union
 
 from pydantic import BaseModel, Field
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    InvocationConfig,
-    InvocationContext,
-)
+from invokeai.app.invocations.baseinvocation import (BaseInvocation,
+                                                     BaseInvocationOutput, InvocationConfig,
+                                                     InvocationContext)
 from invokeai.app.invocations.controlnet_image_processors import ControlField
-from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
+from invokeai.app.invocations.model import (LoRAModelField, MainModelField,
+                                            VAEModelField)
+
 
 class LoRAMetadataField(BaseModel):
     """LoRA metadata for an image generated in InvokeAI."""
-
     lora: LoRAModelField = Field(description="The LoRA model")
     weight: float = Field(description="The weight of the LoRA model")
 
@@ -21,9 +19,7 @@ class LoRAMetadataField(BaseModel):
 class CoreMetadata(BaseModel):
     """Core generation metadata for an image generated in InvokeAI."""
 
-    generation_mode: str = Field(
-        description="The generation mode that output this image",
-    )
+    generation_mode: str = Field(description="The generation mode that output this image",)
     positive_prompt: str = Field(description="The positive prompt parameter")
     negative_prompt: str = Field(description="The negative prompt parameter")
     width: int = Field(description="The width parameter")
@@ -33,20 +29,10 @@ class CoreMetadata(BaseModel):
     cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
     steps: int = Field(description="The number of steps used for inference")
     scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: int = Field(
-        description="The number of skipped CLIP layers",
-    )
+    clip_skip: int = Field(description="The number of skipped CLIP layers",)
     model: MainModelField = Field(description="The main model used for inference")
-    controlnets: list[ControlField] = Field(
-        description="The ControlNets used for inference"
-    )
+    controlnets: list[ControlField]= Field(description="The ControlNets used for inference")
     loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
-    vae: Union[VAEModelField, None] = Field(
-        default=None,
-        description="The VAE used for decoding, if the main model's default was not used",
-    )
-
-    # Latents-to-Latents
     strength: Union[float, None] = Field(
         default=None,
         description="The strength used for latents-to-latents",
@@ -54,34 +40,9 @@ class CoreMetadata(BaseModel):
     init_image: Union[str, None] = Field(
         default=None, description="The name of the initial image"
     )
-
-    # SDXL
-    positive_style_prompt: Union[str, None] = Field(
-        default=None, description="The positive style prompt parameter"
-    )
-    negative_style_prompt: Union[str, None] = Field(
-        default=None, description="The negative style prompt parameter"
-    )
-
-    # SDXL Refiner
-    refiner_model: Union[MainModelField, None] = Field(
-        default=None, description="The SDXL Refiner model used"
-    )
-    refiner_cfg_scale: Union[float, None] = Field(
+    vae: Union[VAEModelField, None] = Field(
         default=None,
-        description="The classifier-free guidance scale parameter used for the refiner",
-    )
-    refiner_steps: Union[int, None] = Field(
-        default=None, description="The number of steps used for the refiner"
-    )
-    refiner_scheduler: Union[str, None] = Field(
-        default=None, description="The scheduler used for the refiner"
-    )
-    refiner_aesthetic_store: Union[float, None] = Field(
-        default=None, description="The aesthetic score used for the refiner"
-    )
-    refiner_start: Union[float, None] = Field(
-        default=None, description="The start value used for refiner denoising"
+        description="The VAE used for decoding, if the main model's default was not used",
     )
 
 
@@ -110,9 +71,7 @@ class MetadataAccumulatorInvocation(BaseInvocation):
 
     type: Literal["metadata_accumulator"] = "metadata_accumulator"
 
-    generation_mode: str = Field(
-        description="The generation mode that output this image",
-    )
+    generation_mode: str = Field(description="The generation mode that output this image",)
     positive_prompt: str = Field(description="The positive prompt parameter")
     negative_prompt: str = Field(description="The negative prompt parameter")
     width: int = Field(description="The width parameter")
@@ -122,13 +81,9 @@ class MetadataAccumulatorInvocation(BaseInvocation):
     cfg_scale: float = Field(description="The classifier-free guidance scale parameter")
     steps: int = Field(description="The number of steps used for inference")
     scheduler: str = Field(description="The scheduler used for inference")
-    clip_skip: int = Field(
-        description="The number of skipped CLIP layers",
-    )
+    clip_skip: int = Field(description="The number of skipped CLIP layers",)
     model: MainModelField = Field(description="The main model used for inference")
-    controlnets: list[ControlField] = Field(
-        description="The ControlNets used for inference"
-    )
+    controlnets: list[ControlField]= Field(description="The ControlNets used for inference")
     loras: list[LoRAMetadataField] = Field(description="The LoRAs used for inference")
     strength: Union[float, None] = Field(
         default=None,
@@ -142,44 +97,36 @@ class MetadataAccumulatorInvocation(BaseInvocation):
         description="The VAE used for decoding, if the main model's default was not used",
     )
 
-    # SDXL
-    positive_style_prompt: Union[str, None] = Field(
-        default=None, description="The positive style prompt parameter"
-    )
-    negative_style_prompt: Union[str, None] = Field(
-        default=None, description="The negative style prompt parameter"
-    )
-
-    # SDXL Refiner
-    refiner_model: Union[MainModelField, None] = Field(
-        default=None, description="The SDXL Refiner model used"
-    )
-    refiner_cfg_scale: Union[float, None] = Field(
-        default=None,
-        description="The classifier-free guidance scale parameter used for the refiner",
-    )
-    refiner_steps: Union[int, None] = Field(
-        default=None, description="The number of steps used for the refiner"
-    )
-    refiner_scheduler: Union[str, None] = Field(
-        default=None, description="The scheduler used for the refiner"
-    )
-    refiner_aesthetic_store: Union[float, None] = Field(
-        default=None, description="The aesthetic score used for the refiner"
-    )
-    refiner_start: Union[float, None] = Field(
-        default=None, description="The start value used for refiner denoising"
-    )
-
     class Config(InvocationConfig):
         schema_extra = {
             "ui": {
                 "title": "Metadata Accumulator",
-                "tags": ["image", "metadata", "generation"],
+                "tags": ["image", "metadata", "generation"]
             },
         }
 
+
     def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
         """Collects and outputs a CoreMetadata object"""
 
-        return MetadataAccumulatorOutput(metadata=CoreMetadata(**self.dict()))
+        return MetadataAccumulatorOutput(
+            metadata=CoreMetadata(
+                generation_mode=self.generation_mode,
+                positive_prompt=self.positive_prompt,
+                negative_prompt=self.negative_prompt,
+                width=self.width,
+                height=self.height,
+                seed=self.seed,
+                rand_device=self.rand_device,
+                cfg_scale=self.cfg_scale,
+                steps=self.steps,
+                scheduler=self.scheduler,
+                model=self.model,
+                strength=self.strength,
+                init_image=self.init_image,
+                vae=self.vae,
+                controlnets=self.controlnets,
+                loras=self.loras,
+                clip_skip=self.clip_skip,
+            )
+        )

invokeai/app/invocations/noise.py

@@ -119,8 +119,8 @@ class NoiseInvocation(BaseInvocation):
 
     @validator("seed", pre=True)
     def modulo_seed(cls, v):
-        """Returns the seed modulo (SEED_MAX + 1) to ensure it is within the valid range."""
-        return v % (SEED_MAX + 1)
+        """Returns the seed modulo SEED_MAX to ensure it is within the valid range."""
+        return v % SEED_MAX
 
     def invoke(self, context: InvocationContext) -> NoiseOutput:
         noise = get_noise(

invokeai/app/invocations/sdxl.py

@@ -138,7 +138,7 @@ class SDXLRefinerModelLoaderInvocation(BaseInvocation):
             "ui": {
                 "title": "SDXL Refiner Model Loader",
                 "tags": ["model", "loader", "sdxl_refiner"],
-                "type_hints": {"model": "refiner_model"},
+                "type_hints": {"model": "model"},
             },
         }
 
@@ -295,7 +295,7 @@ class SDXLTextToLatentsInvocation(BaseInvocation):
 
 
         unet_info = context.services.model_manager.get_model(
-            **self.unet.unet.dict(), context=context
+            **self.unet.unet.dict()
         )
         do_classifier_free_guidance = True
         cross_attention_kwargs = None
@@ -463,8 +463,8 @@ class SDXLLatentsToLatentsInvocation(BaseInvocation):
     unet: UNetField = Field(default=None, description="UNet submodel")
     latents: Optional[LatentsField] = Field(description="Initial latents")
 
-    denoising_start: float = Field(default=0.0, ge=0, le=1, description="")
-    denoising_end: float = Field(default=1.0, ge=0, le=1, description="")
+    denoising_start: float = Field(default=0.0, ge=0, lt=1, description="")
+    denoising_end: float = Field(default=1.0, gt=0, le=1, description="")
 
     #control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
     #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
@@ -549,13 +549,13 @@ class SDXLLatentsToLatentsInvocation(BaseInvocation):
         num_inference_steps = num_inference_steps - t_start
 
         # apply noise(if provided)
-        if self.noise is not None and timesteps.shape[0] > 0:
+        if self.noise is not None:
             noise = context.services.latents.get(self.noise.latents_name)
             latents = scheduler.add_noise(latents, noise, timesteps[:1])
             del noise
 
         unet_info = context.services.model_manager.get_model(
-            **self.unet.unet.dict(), context=context,
+            **self.unet.unet.dict()
         )
         do_classifier_free_guidance = True
         cross_attention_kwargs = None

invokeai/app/models/image.py

@@ -1,80 +1,9 @@
 from enum import Enum
-from typing import Optional, Tuple, Literal
+from typing import Optional, Tuple
 from pydantic import BaseModel, Field
 
 from invokeai.app.util.metaenum import MetaEnum
-from ..invocations.baseinvocation import (
-    BaseInvocationOutput,
-    InvocationConfig,
-)
 
-class ImageField(BaseModel):
-    """An image field used for passing image objects between invocations"""
-
-    image_name: Optional[str] = Field(default=None, description="The name of the image")
-
-    class Config:
-        schema_extra = {"required": ["image_name"]}
-
-
-class ColorField(BaseModel):
-    r: int = Field(ge=0, le=255, description="The red component")
-    g: int = Field(ge=0, le=255, description="The green component")
-    b: int = Field(ge=0, le=255, description="The blue component")
-    a: int = Field(ge=0, le=255, description="The alpha component")
-
-    def tuple(self) -> Tuple[int, int, int, int]:
-        return (self.r, self.g, self.b, self.a)
-
-
-class ProgressImage(BaseModel):
-    """The progress image sent intermittently during processing"""
-
-    width: int = Field(description="The effective width of the image in pixels")
-    height: int = Field(description="The effective height of the image in pixels")
-    dataURL: str = Field(description="The image data as a b64 data URL")
-
-class PILInvocationConfig(BaseModel):
-    """Helper class to provide all PIL invocations with additional config"""
-
-    class Config(InvocationConfig):
-        schema_extra = {
-            "ui": {
-                "tags": ["PIL", "image"],
-            },
-        }
-
-class ImageOutput(BaseInvocationOutput):
-    """Base class for invocations that output an image"""
-
-    # fmt: off
-    type: Literal["image_output"] = "image_output"
-    image:      ImageField = Field(default=None, description="The output image")
-    width:             int = Field(description="The width of the image in pixels")
-    height:            int = Field(description="The height of the image in pixels")
-    # fmt: on
-
-    class Config:
-        schema_extra = {"required": ["type", "image", "width", "height"]}
-
-
-class MaskOutput(BaseInvocationOutput):
-    """Base class for invocations that output a mask"""
-
-    # fmt: off
-    type: Literal["mask"] = "mask"
-    mask:      ImageField = Field(default=None, description="The output mask")
-    width:            int = Field(description="The width of the mask in pixels")
-    height:           int = Field(description="The height of the mask in pixels")
-    # fmt: on
-
-    class Config:
-        schema_extra = {
-            "required": [
-                "type",
-                "mask",
-            ]
-        }
 
 class ResourceOrigin(str, Enum, metaclass=MetaEnum):
     """The origin of a resource (eg image).
@@ -134,3 +63,28 @@ class InvalidImageCategoryException(ValueError):
         super().__init__(message)
 
 
+class ImageField(BaseModel):
+    """An image field used for passing image objects between invocations"""
+
+    image_name: Optional[str] = Field(default=None, description="The name of the image")
+
+    class Config:
+        schema_extra = {"required": ["image_name"]}
+
+
+class ColorField(BaseModel):
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)
+
+
+class ProgressImage(BaseModel):
+    """The progress image sent intermittently during processing"""
+
+    width: int = Field(description="The effective width of the image in pixels")
+    height: int = Field(description="The effective height of the image in pixels")
+    dataURL: str = Field(description="The image data as a b64 data URL")

invokeai/app/services/config.py

@@ -28,6 +28,7 @@ InvokeAI:
     always_use_cpu: false
     free_gpu_mem: false
   Features:
+    nsfw_checker: true
     restore: true
     esrgan: true
     patchmatch: true
@@ -91,18 +92,18 @@ Typical usage at the top level file:
 
  from invokeai.app.services.config import InvokeAIAppConfig
 
- # get global configuration and print its cache size
+ # get global configuration and print its nsfw_checker value
  conf = InvokeAIAppConfig.get_config()
  conf.parse_args()
- print(conf.max_cache_size)
+ print(conf.nsfw_checker)
 
 Typical usage in a backend module:
 
  from invokeai.app.services.config import InvokeAIAppConfig
 
- # get global configuration and print its cache size value
+ # get global configuration and print its nsfw_checker value
  conf = InvokeAIAppConfig.get_config()
- print(conf.max_cache_size)
+ print(conf.nsfw_checker)
 
 
 Computed properties:
@@ -276,7 +277,7 @@ class InvokeAISettings(BaseSettings):
     @classmethod
     def _excluded_from_yaml(self)->List[str]:
         # combination of deprecated parameters and internal ones that shouldn't be exposed as invokeai.yaml options
-        return ['type','initconf', 'gpu_mem_reserved', 'max_loaded_models', 'version', 'from_file', 'model', 'restore', 'root', 'nsfw_checker']
+        return ['type','initconf', 'gpu_mem_reserved', 'max_loaded_models', 'version', 'from_file', 'model', 'restore', 'root']
 
     class Config:
         env_file_encoding = 'utf-8'
@@ -363,6 +364,7 @@ setting environment variables INVOKEAI_<setting>.
     esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
     internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
     log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
+    nsfw_checker        : bool = Field(default=True, description="Enable/disable the NSFW checker", category='Features')
     patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
     restore             : bool = Field(default=True, description="Enable/disable face restoration code (DEPRECATED)", category='DEPRECATED')
 
@@ -372,7 +374,6 @@ setting environment variables INVOKEAI_<setting>.
     max_cache_size      : float = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
     max_vram_cache_size : float = Field(default=2.75, ge=0, description="Amount of VRAM reserved for model storage", category='Memory/Performance')
     gpu_mem_reserved    : float = Field(default=2.75, ge=0, description="DEPRECATED: use max_vram_cache_size. Amount of VRAM reserved for model storage", category='DEPRECATED')
-    nsfw_checker        : bool = Field(default=True, description="DEPRECATED: use Web settings to enable/disable", category='DEPRECATED')
     precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='auto',description='Floating point precision', category='Memory/Performance')
     sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
     xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
@@ -524,16 +525,6 @@ setting environment variables INVOKEAI_<setting>.
         """Return true if patchmatch true"""
         return self.patchmatch
 
-    @property
-    def nsfw_checker(self)->bool:
-        """ NSFW node is always active and disabled from Web UIe"""
-        return True
-
-    @property
-    def invisible_watermark(self)->bool:
-        """ invisible watermark node is always active and disabled from Web UIe"""
-        return True
-    
     @staticmethod
     def find_root()->Path:
         '''

invokeai/app/services/default_graphs.py

@@ -1,5 +1,4 @@
 from ..invocations.latent import LatentsToImageInvocation, TextToLatentsInvocation
-from ..invocations.image import ImageNSFWBlurInvocation
 from ..invocations.noise import NoiseInvocation
 from ..invocations.compel import CompelInvocation
 from ..invocations.params import ParamIntInvocation
@@ -25,7 +24,6 @@ def create_text_to_image() -> LibraryGraph:
                 '5': CompelInvocation(id='5'),
                 '6': TextToLatentsInvocation(id='6'),
                 '7': LatentsToImageInvocation(id='7'),
-                '8': ImageNSFWBlurInvocation(id='8'),
             },
             edges=[
                 Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='3', field='width')),
@@ -35,7 +33,6 @@ def create_text_to_image() -> LibraryGraph:
                 Edge(source=EdgeConnection(node_id='6', field='latents'), destination=EdgeConnection(node_id='7', field='latents')),
                 Edge(source=EdgeConnection(node_id='4', field='conditioning'), destination=EdgeConnection(node_id='6', field='positive_conditioning')),
                 Edge(source=EdgeConnection(node_id='5', field='conditioning'), destination=EdgeConnection(node_id='6', field='negative_conditioning')),
-                Edge(source=EdgeConnection(node_id='7', field='image'), destination=EdgeConnection(node_id='8', field='image')),
             ]
         ),
         exposed_inputs=[
@@ -46,7 +43,7 @@ def create_text_to_image() -> LibraryGraph:
             ExposedNodeInput(node_path='seed', field='a', alias='seed'),
         ],
         exposed_outputs=[
-            ExposedNodeOutput(node_path='8', field='image', alias='image')
+            ExposedNodeOutput(node_path='7', field='image', alias='image')
         ])
 
 

invokeai/app/services/events.py

@@ -3,13 +3,7 @@
 from typing import Any, Optional
 from invokeai.app.models.image import ProgressImage
 from invokeai.app.util.misc import get_timestamp
-from invokeai.app.services.model_manager_service import (
-    BaseModelType,
-    ModelType,
-    SubModelType,
-    ModelInfo,
-)
-
+from invokeai.app.services.model_manager_service import BaseModelType, ModelType, SubModelType, ModelInfo
 
 class EventServiceBase:
     session_event: str = "session_event"
@@ -44,9 +38,7 @@ class EventServiceBase:
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
-                progress_image=progress_image.dict()
-                if progress_image is not None
-                else None,
+                progress_image=progress_image.dict() if progress_image is not None else None,
                 step=step,
                 total_steps=total_steps,
             ),
@@ -75,7 +67,6 @@ class EventServiceBase:
         graph_execution_state_id: str,
         node: dict,
         source_node_id: str,
-        error_type: str,
         error: str,
     ) -> None:
         """Emitted when an invocation has completed"""
@@ -85,7 +76,6 @@ class EventServiceBase:
                 graph_execution_state_id=graph_execution_state_id,
                 node=node,
                 source_node_id=source_node_id,
-                error_type=error_type,
                 error=error,
             ),
         )
@@ -112,13 +102,13 @@ class EventServiceBase:
             ),
         )
 
-    def emit_model_load_started(
-        self,
-        graph_execution_state_id: str,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: SubModelType,
+    def emit_model_load_started (
+            self,
+            graph_execution_state_id: str,
+            model_name: str,
+            base_model: BaseModelType,
+            model_type: ModelType,
+            submodel: SubModelType,
     ) -> None:
         """Emitted when a model is requested"""
         self.__emit_session_event(
@@ -133,13 +123,13 @@ class EventServiceBase:
         )
 
     def emit_model_load_completed(
-        self,
-        graph_execution_state_id: str,
-        model_name: str,
-        base_model: BaseModelType,
-        model_type: ModelType,
-        submodel: SubModelType,
-        model_info: ModelInfo,
+            self,
+            graph_execution_state_id: str,
+            model_name: str,
+            base_model: BaseModelType,
+            model_type: ModelType,
+            submodel: SubModelType,
+            model_info: ModelInfo,
     ) -> None:
         """Emitted when a model is correctly loaded (returns model info)"""
         self.__emit_session_event(
@@ -155,37 +145,3 @@ class EventServiceBase:
                 precision=str(model_info.precision),
             ),
         )
-
-    def emit_session_retrieval_error(
-        self,
-        graph_execution_state_id: str,
-        error_type: str,
-        error: str,
-    ) -> None:
-        """Emitted when session retrieval fails"""
-        self.__emit_session_event(
-            event_name="session_retrieval_error",
-            payload=dict(
-                graph_execution_state_id=graph_execution_state_id,
-                error_type=error_type,
-                error=error,
-            ),
-        )
-
-    def emit_invocation_retrieval_error(
-        self,
-        graph_execution_state_id: str,
-        node_id: str,
-        error_type: str,
-        error: str,
-    ) -> None:
-        """Emitted when invocation retrieval fails"""
-        self.__emit_session_event(
-            event_name="invocation_retrieval_error",
-            payload=dict(
-                graph_execution_state_id=graph_execution_state_id,
-                node_id=node_id,
-                error_type=error_type,
-                error=error,
-            ),
-        )

invokeai/app/services/images.py

@@ -216,13 +216,16 @@ class ImageService(ImageServiceABC):
                 metadata=metadata,
                 session_id=session_id,
             )
+
             if board_id is not None:
                 self._services.board_image_records.add_image_to_board(
                     board_id=board_id, image_name=image_name
                 )
+
             self._services.image_files.save(
                 image_name=image_name, image=image, metadata=metadata, graph=graph
             )
+
             image_dto = self.get_dto(image_name)
 
             return image_dto
@@ -233,7 +236,7 @@ class ImageService(ImageServiceABC):
             self._services.logger.error("Failed to save image file")
             raise
         except Exception as e:
-            self._services.logger.error(f"Problem saving image record and file: {str(e)}")
+            self._services.logger.error("Problem saving image record and file")
             raise e
 
     def update(

invokeai/app/services/model_manager_service.py

@@ -600,7 +600,7 @@ class ModelManagerService(ModelManagerServiceBase):
         """
         Return list of all models found in the designated directory.
         """
-        search = FindModels([directory], self.logger)
+        search = FindModels(directory,self.logger)
         return search.list_models()
 
     def sync_to_config(self):

invokeai/app/services/processor.py

@@ -39,41 +39,21 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 try:
                     queue_item: InvocationQueueItem = self.__invoker.services.queue.get()
                 except Exception as e:
-                    self.__invoker.services.logger.error("Exception while getting from queue:\n%s" % e)
+                    logger.debug("Exception while getting from queue: %s" % e)
 
                 if not queue_item:  # Probably stopping
                     # do not hammer the queue
                     time.sleep(0.5)
                     continue
 
-                try:
-                    graph_execution_state = (
-                        self.__invoker.services.graph_execution_manager.get(
-                            queue_item.graph_execution_state_id
-                        )
+                graph_execution_state = (
+                    self.__invoker.services.graph_execution_manager.get(
+                        queue_item.graph_execution_state_id
                     )
-                except Exception as e:
-                    self.__invoker.services.logger.error("Exception while retrieving session:\n%s" % e)
-                    self.__invoker.services.events.emit_session_retrieval_error(
-                        graph_execution_state_id=queue_item.graph_execution_state_id,
-                        error_type=e.__class__.__name__,
-                        error=traceback.format_exc(),
-                    )
-                    continue
-                
-                try:
-                    invocation = graph_execution_state.execution_graph.get_node(
-                        queue_item.invocation_id
-                    )
-                except Exception as e:
-                    self.__invoker.services.logger.error("Exception while retrieving invocation:\n%s" % e)
-                    self.__invoker.services.events.emit_invocation_retrieval_error(
-                        graph_execution_state_id=queue_item.graph_execution_state_id,
-                        node_id=queue_item.invocation_id,
-                        error_type=e.__class__.__name__,
-                        error=traceback.format_exc(),
-                    )
-                    continue
+                )
+                invocation = graph_execution_state.execution_graph.get_node(
+                    queue_item.invocation_id
+                )
 
                 # get the source node id to provide to clients (the prepared node id is not as useful)
                 source_node_id = graph_execution_state.prepared_source_mapping[invocation.id]
@@ -134,13 +114,11 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                         graph_execution_state
                     )
 
-                    self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
                     # Send error event
                     self.__invoker.services.events.emit_invocation_error(
                         graph_execution_state_id=graph_execution_state.id,
                         node=invocation.dict(),
                         source_node_id=source_node_id,
-                        error_type=e.__class__.__name__,
                         error=error,
                     )
 
@@ -158,12 +136,11 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     try:
                         self.__invoker.invoke(graph_execution_state, invoke_all=True)
                     except Exception as e:
-                        self.__invoker.services.logger.error("Error while invoking:\n%s" % e)
+                        logger.error("Error while invoking: %s" % e)
                         self.__invoker.services.events.emit_invocation_error(
                             graph_execution_state_id=graph_execution_state.id,
                             node=invocation.dict(),
                             source_node_id=source_node_id,
-                            error_type=e.__class__.__name__,
                             error=traceback.format_exc()
                         )
                 elif is_complete:

invokeai/app/util/misc.py

@@ -14,9 +14,8 @@ def get_datetime_from_iso_timestamp(iso_timestamp: str) -> datetime.datetime:
     return datetime.datetime.fromisoformat(iso_timestamp)
 
 
-SEED_MAX = np.iinfo(np.uint32).max
+SEED_MAX = np.iinfo(np.int32).max
 
 
 def get_random_seed():
-    rng = np.random.default_rng(seed=0)
-    return int(rng.integers(0, SEED_MAX))
+    return np.random.randint(0, SEED_MAX)

invokeai/backend/__init__.py

@@ -12,4 +12,4 @@ from .model_management import (
     ModelManager, ModelCache, BaseModelType,
     ModelType, SubModelType, ModelInfo
     )
-from .model_management.models import SilenceWarnings
+from .safety_checker import SafetyChecker

invokeai/backend/generator/base.py

@@ -28,6 +28,7 @@ from diffusers.schedulers import SchedulerMixin as Scheduler
 import invokeai.backend.util.logging as logger
 from ..image_util import configure_model_padding
 from ..util.util import rand_perlin_2d
+from ..safety_checker import SafetyChecker
 from ..stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
 from ..stable_diffusion.schedulers import SCHEDULER_MAP
 
@@ -51,6 +52,7 @@ class InvokeAIGeneratorBasicParams:
     v_symmetry_time_pct: Optional[float]=None
     variation_amount: float = 0.0
     with_variations: list=field(default_factory=list)
+    safety_checker: Optional[SafetyChecker]=None
 
 @dataclass
 class InvokeAIGeneratorOutput:
@@ -238,6 +240,7 @@ class Generator:
         self.seed = None
         self.latent_channels = model.unet.config.in_channels
         self.downsampling_factor = downsampling  # BUG: should come from model or config
+        self.safety_checker = None
         self.perlin = 0.0
         self.threshold = 0
         self.variation_amount = 0
@@ -274,10 +277,12 @@ class Generator:
         perlin=0.0,
         h_symmetry_time_pct=None,
         v_symmetry_time_pct=None,
+        safety_checker: SafetyChecker=None,
         free_gpu_mem: bool = False,
         **kwargs,
     ):
         scope = nullcontext
+        self.safety_checker = safety_checker
         self.free_gpu_mem = free_gpu_mem
         attention_maps_images = []
         attention_maps_callback = lambda saver: attention_maps_images.append(
@@ -324,6 +329,9 @@ class Generator:
                 # Pass on the seed in case a layer beneath us needs to generate noise on its own.
                 image = make_image(x_T, seed)
 
+                if self.safety_checker is not None:
+                    image = self.safety_checker.check(image)
+
                 results.append([image, seed, attention_maps_images])
 
                 if image_callback is not None:

invokeai/backend/image_util/invisible_watermark.py

@@ -1,34 +0,0 @@
-"""
-This module defines a singleton object, "invisible_watermark" that
-wraps the invisible watermark model. It respects the global "invisible_watermark"
-configuration variable, that allows the watermarking to be supressed.
-"""
-import numpy as np
-import cv2
-from PIL import Image
-from imwatermark import WatermarkEncoder
-from invokeai.app.services.config import InvokeAIAppConfig
-import invokeai.backend.util.logging as logger
-config = InvokeAIAppConfig.get_config()
-
-class InvisibleWatermark:
-    """
-    Wrapper around InvisibleWatermark module.
-    """
-    
-    @classmethod
-    def invisible_watermark_available(self) -> bool:
-        return config.invisible_watermark
-
-    @classmethod
-    def add_watermark(self, image: Image, watermark_text:str) -> Image:
-        if not self.invisible_watermark_available():
-            return image
-        logger.debug(f'Applying invisible watermark "{watermark_text}"')
-        bgr = cv2.cvtColor(np.array(image.convert("RGB")), cv2.COLOR_RGB2BGR)
-        encoder = WatermarkEncoder()
-        encoder.set_watermark('bytes', watermark_text.encode('utf-8'))
-        bgr_encoded = encoder.encode(bgr, 'dwtDct')
-        return Image.fromarray(
-            cv2.cvtColor(bgr_encoded, cv2.COLOR_BGR2RGB)
-        ).convert("RGBA")

invokeai/backend/image_util/safety_checker.py

@@ -1,63 +0,0 @@
-"""
-This module defines a singleton object, "safety_checker" that
-wraps the safety_checker model. It respects the global "nsfw_checker"
-configuration variable, that allows the checker to be supressed.
-"""
-import numpy as np
-from PIL import Image
-from invokeai.backend import SilenceWarnings
-from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.backend.util.devices import choose_torch_device
-import invokeai.backend.util.logging as logger
-config = InvokeAIAppConfig.get_config()
-
-CHECKER_PATH = 'core/convert/stable-diffusion-safety-checker'
-
-class SafetyChecker:
-    """
-    Wrapper around SafetyChecker model.
-    """
-    safety_checker = None
-    feature_extractor = None
-    tried_load: bool = False
-
-    @classmethod
-    def _load_safety_checker(self):
-        if self.tried_load:
-            return
-        
-        if config.nsfw_checker:
-            try:
-                from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
-                from transformers import AutoFeatureExtractor
-                self.safety_checker = StableDiffusionSafetyChecker.from_pretrained(
-                    config.models_path / CHECKER_PATH
-                )
-                self.feature_extractor = AutoFeatureExtractor.from_pretrained(
-                    config.models_path / CHECKER_PATH)
-                logger.info('NSFW checker initialized')
-            except Exception as e:
-                logger.warning(f'Could not load NSFW checker: {str(e)}')
-        else:
-            logger.info('NSFW checker loading disabled')
-        self.tried_load = True
-
-    @classmethod
-    def safety_checker_available(self) -> bool:
-        self._load_safety_checker()
-        return self.safety_checker is not None
-
-    @classmethod
-    def has_nsfw_concept(self, image: Image) -> bool:
-        if not self.safety_checker_available():
-            return False
-        
-        device = choose_torch_device()
-        features = self.feature_extractor([image], return_tensors="pt")
-        features.to(device)
-        self.safety_checker.to(device)
-        x_image = np.array(image).astype(np.float32) / 255.0
-        x_image = x_image[None].transpose(0, 3, 1, 2)
-        with SilenceWarnings():
-            checked_image, has_nsfw_concept = self.safety_checker(images=x_image, clip_input=features.pixel_values)
-        return has_nsfw_concept[0]

invokeai/backend/install/check_root.py

@@ -1,31 +0,0 @@
-"""
-Check that the invokeai_root is correctly configured and exit if not.
-"""
-import sys
-from invokeai.app.services.config import (
-    InvokeAIAppConfig,
-)
-
-def check_invokeai_root(config: InvokeAIAppConfig):
-    try:
-        assert config.model_conf_path.exists()
-        assert config.db_path.exists()
-        assert config.models_path.exists()
-        for model in [
-                'CLIP-ViT-bigG-14-laion2B-39B-b160k',
-                'bert-base-uncased',
-                'clip-vit-large-patch14',
-                'sd-vae-ft-mse',
-                'stable-diffusion-2-clip',
-                'stable-diffusion-safety-checker']:
-            assert (config.models_path / f'core/convert/{model}').exists()
-    except:
-        print()
-        print('== STARTUP ABORTED ==')
-        print('** One or more necessary files is missing from your InvokeAI root directory **')
-        print('** Please rerun the configuration script to fix this problem. **')
-        print('** From the launcher, selection option [7]. **')
-        print('** From the command line, activate the virtual environment and run "invokeai-configure --yes --skip-sd-weights" **')
-        input('Press any key to continue...')
-        sys.exit(0)
-

invokeai/backend/install/invokeai_configure.py

@@ -13,8 +13,8 @@ import os
 import shutil
 import textwrap
 import traceback
-import yaml
 import warnings
+import yaml
 from argparse import Namespace
 from pathlib import Path
 from shutil import get_terminal_size
@@ -32,7 +32,6 @@ from omegaconf import OmegaConf
 from tqdm import tqdm
 from transformers import (
     CLIPTextModel,
-    CLIPTextConfig,
     CLIPTokenizer,
     AutoFeatureExtractor,
     BertTokenizerFast,
@@ -45,7 +44,6 @@ from invokeai.app.services.config import (
 from invokeai.backend.util.logging import InvokeAILogger
 from invokeai.frontend.install.model_install import addModelsForm, process_and_execute
 from invokeai.frontend.install.widgets import (
-    SingleSelectColumns,
     CenteredButtonPress,
     FileBox,
     IntTitleSlider,
@@ -206,15 +204,6 @@ def download_conversion_models():
         pipeline = CLIPTextModel.from_pretrained(repo_id, subfolder="text_encoder", **kwargs)
         pipeline.save_pretrained(target_dir / 'stable-diffusion-2-clip' / 'text_encoder', safe_serialization=True)
 
-        # sd-xl - tokenizer_2
-        repo_id = "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k"
-        _, model_name = repo_id.split('/')
-        pipeline = CLIPTokenizer.from_pretrained(repo_id, **kwargs)
-        pipeline.save_pretrained(target_dir / model_name, safe_serialization=True)
-        
-        pipeline = CLIPTextConfig.from_pretrained(repo_id, **kwargs)
-        pipeline.save_pretrained(target_dir / model_name, safe_serialization=True)
-        
         # VAE
         logger.info('Downloading stable diffusion VAE')
         vae = AutoencoderKL.from_pretrained('stabilityai/sd-vae-ft-mse', **kwargs)
@@ -298,6 +287,47 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
                 color="CONTROL",
             )
 
+        self.nextrely += 1
+        self.add_widget_intelligent(
+            npyscreen.TitleFixedText,
+            name="== BASIC OPTIONS ==",
+            begin_entry_at=0,
+            editable=False,
+            color="CONTROL",
+            scroll_exit=True,
+        )
+        self.nextrely -= 1
+        self.add_widget_intelligent(
+            npyscreen.FixedText,
+            value="Select an output directory for images:",
+            editable=False,
+            color="CONTROL",
+        )
+        self.outdir = self.add_widget_intelligent(
+            npyscreen.TitleFilename,
+            name="(<tab> autocompletes, ctrl-N advances):",
+            value=str(default_output_dir()),
+            select_dir=True,
+            must_exist=False,
+            use_two_lines=False,
+            labelColor="GOOD",
+            begin_entry_at=40,
+            scroll_exit=True,
+        )
+        self.nextrely += 1
+        self.add_widget_intelligent(
+            npyscreen.FixedText,
+            value="Activate the NSFW checker to blur images showing potential sexual imagery:",
+            editable=False,
+            color="CONTROL",
+        )
+        self.nsfw_checker = self.add_widget_intelligent(
+            npyscreen.Checkbox,
+            name="NSFW checker",
+            value=old_opts.nsfw_checker,
+            relx=5,
+            scroll_exit=True,
+        )
         self.nextrely += 1
         label = """HuggingFace access token (OPTIONAL) for automatic model downloads. See https://huggingface.co/settings/tokens."""
         for line in textwrap.wrap(label,width=window_width-6):
@@ -317,6 +347,15 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
             scroll_exit=True,
         )
         self.nextrely += 1
+        self.add_widget_intelligent(
+            npyscreen.TitleFixedText,
+            name="== ADVANCED OPTIONS ==",
+            begin_entry_at=0,
+            editable=False,
+            color="CONTROL",
+            scroll_exit=True,
+        )
+        self.nextrely -= 1
         self.add_widget_intelligent(
             npyscreen.TitleFixedText,
             name="GPU Management",
@@ -330,49 +369,34 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
             npyscreen.Checkbox,
             name="Free GPU memory after each generation",
             value=old_opts.free_gpu_mem,
-            max_width=45,
             relx=5,
             scroll_exit=True,
         )
-        self.nextrely -= 1
         self.xformers_enabled = self.add_widget_intelligent(
             npyscreen.Checkbox,
-            name="Enable xformers support",
+            name="Enable xformers support if available",
             value=old_opts.xformers_enabled,
-            max_width=30,
-            relx=50,
+            relx=5,
             scroll_exit=True,
         )
-        self.nextrely -=1
         self.always_use_cpu = self.add_widget_intelligent(
             npyscreen.Checkbox,
             name="Force CPU to be used on GPU systems",
             value=old_opts.always_use_cpu,
-            relx=80,
+            relx=5,
             scroll_exit=True,
         )
         precision = old_opts.precision or (
             "float32" if program_opts.full_precision else "auto"
         )
-        self.nextrely +=1
-        self.add_widget_intelligent(
-            npyscreen.TitleFixedText,
-            name="Floating Point Precision",
-            begin_entry_at=0,
-            editable=False,
-            color="CONTROL",
-            scroll_exit=True,
-        )
-        self.nextrely -=1
         self.precision = self.add_widget_intelligent(
-            SingleSelectColumns,
-            columns = 3,
+            npyscreen.TitleSelectOne,
+            columns = 2,
             name="Precision",
             values=PRECISION_CHOICES,
             value=PRECISION_CHOICES.index(precision),
             begin_entry_at=3,
-            max_height=2,
-            max_width=80,
+            max_height=len(PRECISION_CHOICES) + 1,
             scroll_exit=True,
         )
         self.max_cache_size = self.add_widget_intelligent(
@@ -385,22 +409,16 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
             scroll_exit=True,
         )
         self.nextrely += 1
-        self.outdir = self.add_widget_intelligent(
-            FileBox,
-            name="Output directory for images (<tab> autocompletes, ctrl-N advances):",
-            value=str(default_output_dir()),
-            select_dir=True,
-            must_exist=False,
-            use_two_lines=False,
-            labelColor="GOOD",
-            begin_entry_at=40,
-            max_height=3,
-            scroll_exit=True,
+        self.add_widget_intelligent(
+            npyscreen.FixedText,
+            value="Folder to recursively scan for new checkpoints, ControlNets, LoRAs and TI models (<tab> autocompletes, ctrl-N advances):",
+            editable=False,
+            color="CONTROL",
         )
         self.autoimport_dirs = {}
         self.autoimport_dirs['autoimport_dir'] = self.add_widget_intelligent(
                 FileBox,
-                name=f'Folder to recursively scan for new checkpoints, ControlNets, LoRAs and TI models',
+                name=f'Autoimport Folder',
                 value=str(config.root_path / config.autoimport_dir),
                 select_dir=True,
                 must_exist=False,
@@ -411,10 +429,18 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
                 scroll_exit=True
             )
         self.nextrely += 1
+        self.add_widget_intelligent(
+            npyscreen.TitleFixedText,
+            name="== LICENSE ==",
+            begin_entry_at=0,
+            editable=False,
+            color="CONTROL",
+            scroll_exit=True,
+        )
+        self.nextrely -= 1
         label = """BY DOWNLOADING THE STABLE DIFFUSION WEIGHT FILES, YOU AGREE TO HAVE READ
-AND ACCEPTED THE CREATIVEML RESPONSIBLE AI LICENSES LOCATED AT
-https://huggingface.co/spaces/CompVis/stable-diffusion-license and
-https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md
+AND ACCEPTED THE CREATIVEML RESPONSIBLE AI LICENSE LOCATED AT
+https://huggingface.co/spaces/CompVis/stable-diffusion-license
 """
         for i in textwrap.wrap(label,width=window_width-6):
             self.add_widget_intelligent(
@@ -425,7 +451,7 @@ https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENS
             )
         self.license_acceptance = self.add_widget_intelligent(
             npyscreen.Checkbox,
-            name="I accept the CreativeML Responsible AI Licenses",
+            name="I accept the CreativeML Responsible AI License",
             value=not first_time,
             relx=2,
             scroll_exit=True,
@@ -440,6 +466,7 @@ https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENS
             CenteredButtonPress,
             name=label,
             relx=(window_width - len(label)) // 2,
+            rely=-3,
             when_pressed_function=self.on_ok,
         )
 
@@ -479,6 +506,7 @@ https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENS
 
         for attr in [
                 "outdir",
+                "nsfw_checker",
                 "free_gpu_mem",
                 "max_cache_size",
                 "xformers_enabled",
@@ -514,7 +542,7 @@ class EditOptApplication(npyscreen.NPSAppManaged):
             "MAIN",
             editOptsForm,
             name="InvokeAI Startup Options",
-            cycle_widgets=False,
+            cycle_widgets=True,
         )
         if not (self.program_opts.skip_sd_weights or self.program_opts.default_only):
             self.model_select = self.addForm(
@@ -522,7 +550,7 @@ class EditOptApplication(npyscreen.NPSAppManaged):
                 addModelsForm,
                 name="Install Stable Diffusion Models",
                 multipage=True,
-                cycle_widgets=False,
+                cycle_widgets=True,
             )
 
     def new_opts(self):
@@ -536,6 +564,8 @@ def edit_opts(program_opts: Namespace, invokeai_opts: Namespace) -> argparse.Nam
 
 def default_startup_options(init_file: Path) -> Namespace:
     opts = InvokeAIAppConfig.get_config()
+    if not init_file.exists():
+        opts.nsfw_checker = True
     return opts
 
 def default_user_selections(program_opts: Namespace) -> InstallSelections:
@@ -558,7 +588,7 @@ def default_user_selections(program_opts: Namespace) -> InstallSelections:
 
 # -------------------------------------
 def initialize_rootdir(root: Path, yes_to_all: bool = False):
-    logger.info("Initializing InvokeAI runtime directory")
+    logger.info("** INITIALIZING INVOKEAI RUNTIME DIRECTORY **")
     for name in (
             "models",
             "databases",
@@ -583,18 +613,7 @@ def initialize_rootdir(root: Path, yes_to_all: bool = False):
     path = dest / 'core'
     path.mkdir(parents=True, exist_ok=True)
 
-    maybe_create_models_yaml(root)
-
-def maybe_create_models_yaml(root: Path):
-    models_yaml = root / 'configs' / 'models.yaml'
-    if models_yaml.exists():
-        if OmegaConf.load(models_yaml).get('__metadata__'):  # up to date
-            return
-        else:
-            logger.info('Creating new models.yaml, original saved as models.yaml.orig')
-            models_yaml.rename(models_yaml.parent / 'models.yaml.orig')
-    
-    with open(models_yaml,'w') as yaml_file:
+    with open(root / 'configs' / 'models.yaml','w') as yaml_file:
         yaml_file.write(yaml.dump({'__metadata__':
                                    {'version':'3.0.0'}
                                    }
@@ -670,6 +689,7 @@ def migrate_init_file(legacy_format:Path):
 
     # a few places where the field names have changed and we have to
     # manually add in the new names/values
+    new.nsfw_checker = old.safety_checker
     new.xformers_enabled = old.xformers
     new.conf_path = old.conf
     new.root = legacy_format.parent.resolve()
@@ -778,8 +798,8 @@ def main():
         if migrate_if_needed(opt, config.root_path):
             sys.exit(0)
 
-        # run this unconditionally in case new directories need to be added
-        initialize_rootdir(config.root_path, opt.yes_to_all)
+        if not config.model_conf_path.exists():
+            initialize_rootdir(config.root_path, opt.yes_to_all)
 
         models_to_download = default_user_selections(opt)
         new_init_file = config.root_path / 'invokeai.yaml'
@@ -799,14 +819,15 @@ def main():
                 sys.exit(0)
                 
         if opt.skip_support_models:
-            logger.info("Skipping support models at user's request")
+            logger.info("SKIPPING SUPPORT MODEL DOWNLOADS PER USER REQUEST")
         else:
-            logger.info("Installing support models")
+            logger.info("CHECKING/UPDATING SUPPORT MODELS")
             download_support_models()
 
         if opt.skip_sd_weights:
-            logger.warning("Skipping diffusion weights download per user request")
+            logger.warning("SKIPPING DIFFUSION WEIGHTS DOWNLOAD PER USER REQUEST")
         elif models_to_download:
+            logger.info("DOWNLOADING DIFFUSION WEIGHTS")
             process_and_execute(opt, models_to_download)
 
         postscript(errors=errors)

invokeai/backend/install/model_install_backend.py

@@ -58,15 +58,7 @@ LEGACY_CONFIGS = {
             SchedulerPredictionType.Epsilon: 'v2-inpainting-inference.yaml',
             SchedulerPredictionType.VPrediction: 'v2-inpainting-inference-v.yaml',
         }
-    },
-    
-    BaseModelType.StableDiffusionXL: {
-        ModelVariantType.Normal: 'sd_xl_base.yaml',
-    },
-    
-    BaseModelType.StableDiffusionXLRefiner: {
-        ModelVariantType.Normal: 'sd_xl_refiner.yaml',
-    },
+    }
 }
 
 @dataclass
@@ -149,17 +141,16 @@ class ModelInstall(object):
         for i in installed:
             print(f"{i['model_name']}\t{i['base_model']}\t{i['path']}")
 
-    # logic here a little reversed to maintain backward compatibility
-    def starter_models(self, all_models: bool=False)->Set[str]:
+    def starter_models(self)->Set[str]:
         models = set()
         for key, value in self.datasets.items():
             name,base,model_type = ModelManager.parse_key(key)
-            if all_models or model_type in [ModelType.Main, ModelType.Vae]:
+            if model_type==ModelType.Main:
                 models.add(key)
         return models
 
     def recommended_models(self)->Set[str]:
-        starters = self.starter_models(all_models=True)
+        starters = self.starter_models()
         return set([x for x in starters if self.datasets[x].get('recommended',False)])
     
     def default_model(self)->str:
@@ -338,7 +329,6 @@ class ModelInstall(object):
             description = str(description),
             model_format = info.format,
             )
-        legacy_conf = None
         if info.model_type == ModelType.Main:
             attributes.update(dict(variant = info.variant_type,))
             if info.format=="checkpoint":
@@ -353,17 +343,11 @@ class ModelInstall(object):
                 except KeyError:
                     legacy_conf = Path(self.config.legacy_conf_dir, 'v1-inference.yaml')  # best guess
                     
-        if info.model_type == ModelType.ControlNet and info.format=="checkpoint":
-            possible_conf = path.with_suffix('.yaml')
-            if possible_conf.exists():
-                legacy_conf = str(self.relative_to_root(possible_conf))
-
-        if legacy_conf:
-            attributes.update(
-                dict(
-                    config = str(legacy_conf)
+                attributes.update(
+                    dict(
+                        config = str(legacy_conf)
+                    )
                 )
-            )
         return attributes
 
     def relative_to_root(self, path: Path)->Path:

invokeai/backend/model_management/lora.py

@@ -474,7 +474,7 @@ class ModelPatcher:
 
     @staticmethod
     def _lora_forward_hook(
-        applied_loras: List[Tuple[LoRAModel, float]],
+        applied_loras: List[Tuple[LoraModel, float]],
         layer_name: str,
     ):
 
@@ -519,7 +519,7 @@ class ModelPatcher:
     def apply_lora(
         cls,
         model: torch.nn.Module,
-        loras: List[Tuple[LoRAModel, float]],
+        loras: List[Tuple[LoraModel, float]],
         prefix: str,
     ):
         original_weights = dict()

invokeai/backend/model_management/model_manager.py

@@ -673,7 +673,6 @@ class ModelManager(object):
 
         self.models[model_key] = model_config
         self.commit()
-
         return AddModelResult(
             name = model_name,
             model_type = model_type,
@@ -841,7 +840,7 @@ class ModelManager(object):
         Returns the preamble for the config file.
         """
         return textwrap.dedent(
-            """
+            """\
             # This file describes the alternative machine learning models
             # available to InvokeAI script.
             #

invokeai/backend/model_management/model_probe.py

@@ -253,13 +253,10 @@ class PipelineCheckpointProbe(CheckpointProbeBase):
             return BaseModelType.StableDiffusion1
         if key_name in state_dict and state_dict[key_name].shape[-1] == 1024:
             return BaseModelType.StableDiffusion2
-        key_name = 'model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight'
+        # TODO: Verify that this is correct! Need an XL checkpoint file for this.
         if key_name in state_dict and state_dict[key_name].shape[-1] == 2048:
             return BaseModelType.StableDiffusionXL
-        elif key_name in state_dict and state_dict[key_name].shape[-1] == 1280:
-            return BaseModelType.StableDiffusionXLRefiner
-        else:
-            raise InvalidModelException("Cannot determine base type")
+        raise InvalidModelException("Cannot determine base type")
 
     def get_scheduler_prediction_type(self)->SchedulerPredictionType:
         type = self.get_base_type()
@@ -416,14 +413,7 @@ class PipelineFolderProbe(FolderProbeBase):
 
 class VaeFolderProbe(FolderProbeBase):
     def get_base_type(self)->BaseModelType:
-        config_file = self.folder_path / 'config.json'
-        if not config_file.exists():
-            raise InvalidModelException(f"Cannot determine base type for {self.folder_path}")
-        with open(config_file,'r') as file:
-            config = json.load(file)
-        return BaseModelType.StableDiffusionXL \
-            if config.get('scaling_factor',0)==0.13025 and config.get('sample_size') in [512, 1024] \
-            else BaseModelType.StableDiffusion1
+        return BaseModelType.StableDiffusion1
 
 class TextualInversionFolderProbe(FolderProbeBase):
     def get_format(self)->str:

invokeai/backend/model_management/model_search.py

@@ -98,6 +98,6 @@ class FindModels(ModelSearch):
 
     def list_models(self) -> List[Path]:
         self.search()
-        return list(self.models_found)
+        return self.models_found
 
     

invokeai/backend/model_management/models/controlnet.py

@@ -1,8 +1,7 @@
 import os
 import torch
 from enum import Enum
-from pathlib import Path
-from typing import Optional, Literal
+from typing import Optional
 from .base import (
     ModelBase,
     ModelConfigBase,
@@ -16,7 +15,6 @@ from .base import (
     InvalidModelException,
     ModelNotFoundException,
 )
-from invokeai.app.services.config import InvokeAIAppConfig
 
 class ControlNetModelFormat(str, Enum):
     Checkpoint = "checkpoint"
@@ -26,12 +24,8 @@ class ControlNetModel(ModelBase):
     #model_class: Type
     #model_size: int
 
-    class DiffusersConfig(ModelConfigBase):
-        model_format: Literal[ControlNetModelFormat.Diffusers]
-
-    class CheckpointConfig(ModelConfigBase):
-        model_format: Literal[ControlNetModelFormat.Checkpoint]
-        config: str
+    class Config(ModelConfigBase):
+        model_format: ControlNetModelFormat
 
     def __init__(self, model_path: str, base_model: BaseModelType, model_type: ModelType):
         assert model_type == ModelType.ControlNet
@@ -105,51 +99,13 @@ class ControlNetModel(ModelBase):
 
     @classmethod
     def convert_if_required(
-            cls,
-            model_path: str,
-            output_path: str,
-            config: ModelConfigBase,
-            base_model: BaseModelType,
-    ) -> str:
-        if cls.detect_format(model_path) == ControlNetModelFormat.Checkpoint:
-            return _convert_controlnet_ckpt_and_cache(
-                model_path = model_path,
-                model_config = config.config,
-                output_path = output_path,
-                base_model = base_model,
-                )
-        else:
-            return model_path
-
-@classmethod
-def _convert_controlnet_ckpt_and_cache(
         cls,
         model_path: str,
         output_path: str,
+        config: ModelConfigBase, # empty config or config of parent model
         base_model: BaseModelType,
-        model_config: ControlNetModel.CheckpointConfig,
-) -> str:
-    """
-    Convert the controlnet from checkpoint format to diffusers format,
-    cache it to disk, and return Path to converted
-    file. If already on disk then just returns Path.
-    """
-    app_config = InvokeAIAppConfig.get_config()
-    weights = app_config.root_path / model_path
-    output_path = Path(output_path)
-
-    # return cached version if it exists
-    if output_path.exists():
-        return output_path
-
-    # to avoid circular import errors
-    from ..convert_ckpt_to_diffusers import convert_controlnet_to_diffusers
-    convert_controlnet_to_diffusers(
-        weights,
-        output_path,
-        original_config_file = app_config.root_path / model_config,
-        image_size = 512,
-        scan_needed = True,
-        from_safetensors = weights.suffix == ".safetensors"
-    )
-    return output_path
+    ) -> str:
+        if cls.detect_format(model_path) != ControlNetModelFormat.Diffusers:
+            raise NotImplementedError("Checkpoint controlnet models currently unsupported")
+        else:
+            return model_path

invokeai/backend/model_management/models/lora.py

@@ -10,7 +10,6 @@ from .base import (
     SubModelType,
     classproperty,
     InvalidModelException,
-    ModelNotFoundException,
 )
 # TODO: naming
 from ..lora import LoRAModel as LoRAModelRaw

invokeai/backend/model_management/models/sdxl.py

@@ -1,6 +1,5 @@
 import os
 import json
-import invokeai.backend.util.logging as logger
 from enum import Enum
 from pydantic import Field
 from typing import Literal, Optional
@@ -49,7 +48,7 @@ class StableDiffusionXLModel(DiffusersModel):
         if model_format == StableDiffusionXLModelFormat.Checkpoint:
             if ckpt_config_path:
                 ckpt_config = OmegaConf.load(ckpt_config_path)
-                in_channels = ckpt_config["model"]["params"]["unet_config"]["params"]["in_channels"]
+                ckpt_config["model"]["params"]["unet_config"]["params"]["in_channels"]
 
             else:
                 checkpoint = read_checkpoint_meta(path)
@@ -109,20 +108,7 @@ class StableDiffusionXLModel(DiffusersModel):
         config: ModelConfigBase,
         base_model: BaseModelType,
     ) -> str:
-        # The convert script adapted from the diffusers package uses
-        # strings for the base model type. To avoid making too many
-        # source code changes, we simply translate here
-        model_base_to_model_type = {BaseModelType.StableDiffusionXL: 'SDXL',
-                                    BaseModelType.StableDiffusionXLRefiner: 'SDXL-Refiner',
-                                    }
         if isinstance(config, cls.CheckpointConfig):
-            from invokeai.backend.model_management.models.stable_diffusion import _convert_ckpt_and_cache
-            return _convert_ckpt_and_cache(
-                version=base_model,
-                model_config=config,
-                output_path=output_path,
-                model_type=model_base_to_model_type[base_model],
-                use_safetensors=False, # corrupts sdxl models for some reason
-            )
+            raise NotImplementedError('conversion of SDXL checkpoint models to diffusers format is not yet supported')
         else:
             return model_path

invokeai/backend/model_management/models/stable_diffusion.py

@@ -14,14 +14,10 @@ from .base import (
     read_checkpoint_meta,
     classproperty,
     InvalidModelException,
-    ModelNotFoundException,
 )
-from .sdxl import StableDiffusionXLModel
-import invokeai.backend.util.logging as logger
 from invokeai.app.services.config import InvokeAIAppConfig
 from omegaconf import OmegaConf
 
-
 class StableDiffusion1ModelFormat(str, Enum):
     Checkpoint = "checkpoint"
     Diffusers = "diffusers"
@@ -239,17 +235,42 @@ class StableDiffusion2Model(DiffusersModel):
         else:
             return model_path
 
+def _select_ckpt_config(version: BaseModelType, variant: ModelVariantType):
+    ckpt_configs = {
+        BaseModelType.StableDiffusion1: {
+            ModelVariantType.Normal: "v1-inference.yaml",
+            ModelVariantType.Inpaint: "v1-inpainting-inference.yaml",
+        },
+        BaseModelType.StableDiffusion2: {
+            ModelVariantType.Normal: "v2-inference-v.yaml", # best guess, as we can't differentiate with base(512)
+            ModelVariantType.Inpaint: "v2-inpainting-inference.yaml",
+            ModelVariantType.Depth: "v2-midas-inference.yaml",
+        },
+        # note that these .yaml files don't yet exist!
+        BaseModelType.StableDiffusionXL: {
+            ModelVariantType.Normal: "xl-inference-v.yaml",
+            ModelVariantType.Inpaint: "xl-inpainting-inference.yaml",
+            ModelVariantType.Depth: "xl-midas-inference.yaml",
+        }
+    }
+
+    app_config = InvokeAIAppConfig.get_config()
+    try:
+        config_path = app_config.legacy_conf_path / ckpt_configs[version][variant]
+        if config_path.is_relative_to(app_config.root_path):
+            config_path = config_path.relative_to(app_config.root_path)
+        return str(config_path)
+            
+    except:
+        return None
+
+
 # TODO: rework
-# pass precision - currently defaulting to fp16
+# Note that convert_ckpt_to_diffuses does not currently support conversion of SDXL models
 def _convert_ckpt_and_cache(
-        version: BaseModelType,
-        model_config: Union[StableDiffusion1Model.CheckpointConfig,
-                            StableDiffusion2Model.CheckpointConfig,
-                            StableDiffusionXLModel.CheckpointConfig,
-                            ],
-        output_path: str,
-        use_save_model: bool=False,
-        **kwargs,
+    version: BaseModelType,
+    model_config: Union[StableDiffusion1Model.CheckpointConfig, StableDiffusion2Model.CheckpointConfig],
+    output_path: str,
 ) -> str:
     """
     Convert the checkpoint model indicated in mconfig into a
@@ -268,60 +289,14 @@ def _convert_ckpt_and_cache(
 
     # to avoid circular import errors
     from ..convert_ckpt_to_diffusers import convert_ckpt_to_diffusers
-    from ...util.devices import choose_torch_device, torch_dtype
-
-    model_base_to_model_type = {BaseModelType.StableDiffusion1: 'FrozenCLIPEmbedder',
-                                BaseModelType.StableDiffusion2: 'FrozenOpenCLIPEmbedder',
-                                }
-
-    logger.info(f'Converting {weights} to diffusers format')
     with SilenceWarnings():        
         convert_ckpt_to_diffusers(
             weights,
             output_path,
-            model_type=model_base_to_model_type[version],
             model_version=version,
             model_variant=model_config.variant,
             original_config_file=config_file,
             extract_ema=True,
             scan_needed=True,
-            from_safetensors = weights.suffix == ".safetensors",
-            precision = torch_dtype(choose_torch_device()),
-            **kwargs,
         )
     return output_path
-
-def _select_ckpt_config(version: BaseModelType, variant: ModelVariantType):
-    ckpt_configs = {
-        BaseModelType.StableDiffusion1: {
-            ModelVariantType.Normal: "v1-inference.yaml",
-            ModelVariantType.Inpaint: "v1-inpainting-inference.yaml",
-        },
-        BaseModelType.StableDiffusion2: {
-            ModelVariantType.Normal: "v2-inference-v.yaml", # best guess, as we can't differentiate with base(512)
-            ModelVariantType.Inpaint: "v2-inpainting-inference.yaml",
-            ModelVariantType.Depth: "v2-midas-inference.yaml",
-        },
-        BaseModelType.StableDiffusionXL: {
-            ModelVariantType.Normal: "sd_xl_base.yaml",
-            ModelVariantType.Inpaint: None,
-            ModelVariantType.Depth: None,
-        },
-        BaseModelType.StableDiffusionXLRefiner: {
-            ModelVariantType.Normal: "sd_xl_refiner.yaml",
-            ModelVariantType.Inpaint: None,
-            ModelVariantType.Depth: None,
-        },
-    }
-
-    app_config = InvokeAIAppConfig.get_config()
-    try:
-        config_path = app_config.legacy_conf_path / ckpt_configs[version][variant]
-        if config_path.is_relative_to(app_config.root_path):
-            config_path = config_path.relative_to(app_config.root_path)
-        return str(config_path)
-            
-    except:
-        return None
-
-

invokeai/backend/safety_checker.py

@@ -0,0 +1,77 @@
+'''
+SafetyChecker class - checks images against the StabilityAI NSFW filter
+and blurs images that contain potential NSFW content.
+'''
+import diffusers
+import numpy as np
+import torch
+import traceback
+from diffusers.pipelines.stable_diffusion.safety_checker import (
+    StableDiffusionSafetyChecker,
+)
+from pathlib import Path
+from PIL import Image, ImageFilter
+from transformers import AutoFeatureExtractor
+
+import invokeai.assets.web as web_assets
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import InvokeAIAppConfig
+from .util import CPU_DEVICE
+
+config = InvokeAIAppConfig.get_config()
+
+class SafetyChecker(object):
+    CAUTION_IMG = "caution.png"
+    
+    def __init__(self, device: torch.device):
+        path = Path(web_assets.__path__[0]) / self.CAUTION_IMG
+        caution = Image.open(path)
+        self.caution_img = caution.resize((caution.width // 2, caution.height // 2))
+        self.device = device
+
+        try:
+            safety_model_id = config.models_path / 'core/convert/stable-diffusion-safety-checker'
+            feature_extractor_id = config.models_path / 'core/convert/stable-diffusion-safety-checker-extractor'
+            self.safety_checker = StableDiffusionSafetyChecker.from_pretrained(safety_model_id)
+            self.safety_feature_extractor = AutoFeatureExtractor.from_pretrained(feature_extractor_id)
+        except Exception:
+            logger.error(
+                "An error was encountered while installing the safety checker:"
+            )
+            print(traceback.format_exc())
+
+    def check(self, image: Image.Image):
+        """
+        Check provided image against the StabilityAI safety checker and return
+
+        """
+
+        self.safety_checker.to(self.device)
+        features = self.safety_feature_extractor([image], return_tensors="pt")
+        features.to(self.device)
+        
+        # unfortunately checker requires the numpy version, so we have to convert back
+        x_image = np.array(image).astype(np.float32) / 255.0
+        x_image = x_image[None].transpose(0, 3, 1, 2)
+
+        diffusers.logging.set_verbosity_error()
+        checked_image, has_nsfw_concept = self.safety_checker(
+            images=x_image, clip_input=features.pixel_values
+        )
+        self.safety_checker.to(CPU_DEVICE) # offload
+        if has_nsfw_concept[0]:
+            logger.warning(
+                "An image with potential non-safe content has been detected. A blurred image will be returned."
+            )
+            return self.blur(image)
+        else:
+            return image
+
+    def blur(self, input):
+        blurry = input.filter(filter=ImageFilter.GaussianBlur(radius=32))
+        try:
+            if caution := self.caution_img:
+                blurry.paste(caution, (0, 0), caution)
+        except FileNotFoundError:
+            pass
+        return blurry

invokeai/backend/util/logging.py

@@ -1,7 +1,7 @@
 # Copyright (c) 2023 Lincoln D. Stein and The InvokeAI Development Team
 
 """
-invokeai.backend.util.logging
+invokeai.util.logging
 
 Logging class for InvokeAI that produces console messages
 

invokeai/configs/INITIAL_MODELS.yaml

@@ -16,18 +16,14 @@ sd-2/main/stable-diffusion-2-inpainting:
    description: Stable Diffusion version 2.0 inpainting model (5.21 GB)
    repo_id: stabilityai/stable-diffusion-2-inpainting
    recommended: False
-sdxl/main/stable-diffusion-xl-base-1-0:
-   description: Stable Diffusion XL base model (12 GB)
-   repo_id: stabilityai/stable-diffusion-xl-base-1.0
+sdxl/main/stable-diffusion-xl-base-0-9:
+   description: Stable Diffusion XL base model (12 GB; access token required)
+   repo_id: stabilityai/stable-diffusion-xl-base-0.9
    recommended: False
-sdxl-refiner/main/stable-diffusion-xl-refiner-1-0:
-   description: Stable Diffusion XL refiner model (12 GB)
-   repo_id: stabilityai/stable-diffusion-xl-refiner-1.0
+sdxl-refiner/main/stable-diffusion-xl-refiner-0-9:
+   description: Stable Diffusion XL refiner model (12 GB; access token required)
+   repo_id: stabilityai/stable-diffusion-xl-refiner-0.9
    recommended: False
-sdxl/vae/sdxl-1-0-vae-fix:
-   description: Fine tuned version of the SDXL-1.0 VAE
-   repo_id: madebyollin/sdxl-vae-fp16-fix
-   recommended: true
 sd-1/main/Analog-Diffusion:
    description: An SD-1.5 model trained on diverse analog photographs (2.13 GB)
    repo_id: wavymulder/Analog-Diffusion
@@ -52,6 +48,10 @@ sd-1/main/openjourney:
    description: An SD 1.5 model fine tuned on Midjourney; prompt with "mdjrny-v4 style" (2.13 GB)
    repo_id: prompthero/openjourney
    recommended: False
+sd-1/main/portraitplus:
+   description: An SD-1.5 model trained on close range portraits of people; prompt with "portrait+" (2.13 GB)
+   repo_id: wavymulder/portraitplus
+   recommended: False
 sd-1/main/seek.art_MEGA:
    repo_id: coreco/seek.art_MEGA
    description: A general use SD-1.5 "anything" model that supports multiple styles (2.1 GB)
@@ -60,6 +60,10 @@ sd-1/main/trinart_stable_diffusion_v2:
    description: An SD-1.5 model finetuned with ~40K assorted high resolution manga/anime-style images (2.13 GB)
    repo_id: naclbit/trinart_stable_diffusion_v2
    recommended: False
+sd-1/main/waifu-diffusion:
+   description: An SD-1.5 model trained on 680k anime/manga-style images (2.13 GB)
+   repo_id: hakurei/waifu-diffusion
+   recommended: False
 sd-1/controlnet/canny:
    repo_id: lllyasviel/control_v11p_sd15_canny
    recommended: True

invokeai/configs/stable-diffusion/sd_xl_base.yaml

@@ -1,98 +0,0 @@
-model:
-  target: sgm.models.diffusion.DiffusionEngine
-  params:
-    scale_factor: 0.13025
-    disable_first_stage_autocast: True
-
-    denoiser_config:
-      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
-      params:
-        num_idx: 1000
-
-        weighting_config:
-          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
-        scaling_config:
-          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
-        discretization_config:
-          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
-
-    network_config:
-      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        adm_in_channels: 2816
-        num_classes: sequential
-        use_checkpoint: True
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [4, 2]
-        num_res_blocks: 2
-        channel_mult: [1, 2, 4]
-        num_head_channels: 64
-        use_spatial_transformer: True
-        use_linear_in_transformer: True
-        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
-        context_dim: 2048
-        spatial_transformer_attn_type: softmax-xformers
-        legacy: False
-
-    conditioner_config:
-      target: sgm.modules.GeneralConditioner
-      params:
-        emb_models:
-          # crossattn cond
-          - is_trainable: False
-            input_key: txt
-            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
-            params:
-              layer: hidden
-              layer_idx: 11
-          # crossattn and vector cond
-          - is_trainable: False
-            input_key: txt
-            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
-            params:
-              arch: ViT-bigG-14
-              version: laion2b_s39b_b160k
-              freeze: True
-              layer: penultimate
-              always_return_pooled: True
-              legacy: False
-          # vector cond
-          - is_trainable: False
-            input_key: original_size_as_tuple
-            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
-            params:
-              outdim: 256  # multiplied by two
-          # vector cond
-          - is_trainable: False
-            input_key: crop_coords_top_left
-            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
-            params:
-              outdim: 256  # multiplied by two
-          # vector cond
-          - is_trainable: False
-            input_key: target_size_as_tuple
-            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
-            params:
-              outdim: 256  # multiplied by two
-
-    first_stage_config:
-      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          attn_type: vanilla-xformers
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult: [1, 2, 4, 4]
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity

invokeai/configs/stable-diffusion/sd_xl_refiner.yaml

@@ -1,91 +0,0 @@
-model:
-  target: sgm.models.diffusion.DiffusionEngine
-  params:
-    scale_factor: 0.13025
-    disable_first_stage_autocast: True
-
-    denoiser_config:
-      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
-      params:
-        num_idx: 1000
-
-        weighting_config:
-          target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
-        scaling_config:
-          target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
-        discretization_config:
-          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
-
-    network_config:
-      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        adm_in_channels: 2560
-        num_classes: sequential
-        use_checkpoint: True
-        in_channels: 4
-        out_channels: 4
-        model_channels: 384
-        attention_resolutions: [4, 2]
-        num_res_blocks: 2
-        channel_mult: [1, 2, 4, 4]
-        num_head_channels: 64
-        use_spatial_transformer: True
-        use_linear_in_transformer: True
-        transformer_depth: 4
-        context_dim: [1280, 1280, 1280, 1280]  # 1280
-        spatial_transformer_attn_type: softmax-xformers
-        legacy: False
-
-    conditioner_config:
-      target: sgm.modules.GeneralConditioner
-      params:
-        emb_models:
-          # crossattn and vector cond
-          - is_trainable: False
-            input_key: txt
-            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
-            params:
-              arch: ViT-bigG-14
-              version: laion2b_s39b_b160k
-              legacy: False
-              freeze: True
-              layer: penultimate
-              always_return_pooled: True
-          # vector cond
-          - is_trainable: False
-            input_key: original_size_as_tuple
-            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
-            params:
-              outdim: 256  # multiplied by two
-          # vector cond
-          - is_trainable: False
-            input_key: crop_coords_top_left
-            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
-            params:
-              outdim: 256  # multiplied by two
-          # vector cond
-          - is_trainable: False
-            input_key: aesthetic_score
-            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
-            params:
-              outdim: 256  # multiplied by one
-
-    first_stage_config:
-      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          attn_type: vanilla-xformers
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult: [1, 2, 4, 4]
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity

invokeai/frontend/install/model_install.py

@@ -93,7 +93,13 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
         self.nextrely -= 1
         self.add_widget_intelligent(
             npyscreen.FixedText,
-            value="Use ctrl-N and ctrl-P to move to the <N>ext and <P>revious fields. Cursor keys navigate, and <space> selects.",
+            value="Use ctrl-N and ctrl-P to move to the <N>ext and <P>revious fields,",
+            editable=False,
+            color="CAUTION",
+        )
+        self.add_widget_intelligent(
+            npyscreen.FixedText,
+            value="Use cursor arrows to make a selection, and space to toggle checkboxes.",
             editable=False,
             color="CAUTION",
         )
@@ -155,40 +161,33 @@ class addModelsForm(CyclingForm, npyscreen.FormMultiPage):
             BufferBox,
             name='Log Messages',
             editable=False,
-            max_height = 8,
+            max_height = 10,
         )
         
         self.nextrely += 1
         done_label = "APPLY CHANGES"
         back_label = "BACK"
-        cancel_label = "CANCEL"
-        current_position = self.nextrely
         if self.multipage:
             self.back_button = self.add_widget_intelligent(
                 npyscreen.ButtonPress,
                 name=back_label,
+                rely=-3,
                 when_pressed_function=self.on_back,
             )
         else:
-            self.nextrely = current_position
-            self.cancel_button = self.add_widget_intelligent(
-                npyscreen.ButtonPress,
-                name=cancel_label,
-                when_pressed_function=self.on_cancel
-            )
-            self.nextrely = current_position
             self.ok_button = self.add_widget_intelligent(
                 npyscreen.ButtonPress,
                 name=done_label,
                 relx=(window_width - len(done_label)) // 2,
-                 when_pressed_function=self.on_execute
+                rely=-3,
+                when_pressed_function=self.on_execute
             )
 
         label = "APPLY CHANGES & EXIT"
-        self.nextrely = current_position
         self.done = self.add_widget_intelligent(
             npyscreen.ButtonPress,
             name=label,
+            rely=-3,
             relx=window_width-len(label)-15,
             when_pressed_function=self.on_done,
         )
@@ -554,7 +553,7 @@ class AddModelApplication(npyscreen.NPSAppManaged):
     def onStart(self):
         npyscreen.setTheme(npyscreen.Themes.DefaultTheme)
         self.main_form = self.addForm(
-            "MAIN", addModelsForm, name="Install Stable Diffusion Models", cycle_widgets=False,
+            "MAIN", addModelsForm, name="Install Stable Diffusion Models", cycle_widgets=True,
         )
 
 class StderrToMessage():

invokeai/frontend/install/widgets.py

@@ -17,8 +17,8 @@ from shutil import get_terminal_size
 from curses import BUTTON2_CLICKED,BUTTON3_CLICKED
 
 # minimum size for UIs
-MIN_COLS = 130
-MIN_LINES = 38
+MIN_COLS = 136
+MIN_LINES = 45
 
 # -------------------------------------
 def set_terminal_size(columns: int, lines: int):
@@ -38,13 +38,13 @@ def set_terminal_size(columns: int, lines: int):
     ts = get_terminal_size()
     pause = False
     if ts.columns < columns:
-        print('\033[1mThis window is too narrow for the user interface.\033[0m')
+        print('\033[1mThis window is too narrow for the user interface. Please make it wider.\033[0m')
         pause = True
     if ts.lines < lines:
-        print('\033[1mThis window is too short for the user interface.\033[0m')
+        print('\033[1mThis window is too short for the user interface. Please make it taller.\033[0m')
         pause = True
     if pause:
-        input('Maximize the window then press any key to continue..')
+        input('Press any key to continue..')
 
 def _set_terminal_size_powershell(width: int, height: int):
     script=f'''

invokeai/frontend/web/dist/index.html

@@ -12,7 +12,7 @@
         margin: 0;
       }
     </style>
-    <script type="module" crossorigin src="./assets/index-e45bf5a6.js"></script>
+    <script type="module" crossorigin src="./assets/index-e2437518.js"></script>
   </head>
 
   <body dir="ltr">

invokeai/frontend/web/dist/locales/en.json

@@ -102,7 +102,8 @@
         "openInNewTab": "Open in New Tab",
         "dontAskMeAgain": "Don't ask me again",
         "areYouSure": "Are you sure?",
-        "imagePrompt": "Image Prompt"
+        "imagePrompt": "Image Prompt",
+        "clearNodes": "Are you sure you want to clear all nodes?"
     },
     "gallery": {
         "generations": "Generations",
@@ -614,11 +615,6 @@
         "initialImageNotSetDesc": "Could not load initial image",
         "nodesSaved": "Nodes Saved",
         "nodesLoaded": "Nodes Loaded",
-        "nodesNotValidGraph": "Not a valid InvokeAI Node Graph",
-        "nodesNotValidJSON": "Not a valid JSON",
-        "nodesCorruptedGraph": "Cannot load. Graph seems to be corrupted.",
-        "nodesUnrecognizedTypes": "Cannot load. Graph has unrecognized types",
-        "nodesBrokenConnections": "Cannot load. Some connections are broken.",
         "nodesLoadedFailed": "Failed To Load Nodes",
         "nodesCleared": "Nodes Cleared"
     },
@@ -704,10 +700,9 @@
     },
     "nodes": {
         "reloadSchema": "Reload Schema",
-        "saveGraph": "Save Graph",
-        "loadGraph": "Load Graph (saved from Node Editor) (Do not copy-paste metadata)",
-        "clearGraph": "Clear Graph",
-        "clearGraphDesc": "Are you sure you want to clear all nodes?",
+        "saveNodes": "Save Nodes",
+        "loadNodes": "Load Nodes",
+        "clearNodes": "Clear Nodes",
         "zoomInNodes": "Zoom In",
         "zoomOutNodes": "Zoom Out",
         "fitViewportNodes": "Fit View",

invokeai/frontend/web/package.json

@@ -53,11 +53,11 @@
     ]
   },
   "dependencies": {
-    "@chakra-ui/anatomy": "^2.2.0",
+    "@chakra-ui/anatomy": "^2.1.1",
     "@chakra-ui/icons": "^2.0.19",
-    "@chakra-ui/react": "^2.8.0",
+    "@chakra-ui/react": "^2.7.1",
     "@chakra-ui/styled-system": "^2.9.1",
-    "@chakra-ui/theme-tools": "^2.1.0",
+    "@chakra-ui/theme-tools": "^2.0.18",
     "@dagrejs/graphlib": "^2.1.13",
     "@dnd-kit/core": "^6.0.8",
     "@dnd-kit/modifiers": "^6.0.1",

invokeai/frontend/web/public/locales/en.json

@@ -23,7 +23,6 @@
         "menu": "Menu"
     },
     "common": {
-        "communityLabel": "Community",
         "hotkeysLabel": "Hotkeys",
         "darkMode": "Dark Mode",
         "lightMode": "Light Mode",

invokeai/frontend/web/src/app/constants.ts

@@ -1,2 +1,2 @@
 export const NUMPY_RAND_MIN = 0;
-export const NUMPY_RAND_MAX = 4294967295;
+export const NUMPY_RAND_MAX = 2147483647;

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/index.ts

@@ -65,14 +65,11 @@ import { addGeneratorProgressEventListener as addGeneratorProgressListener } fro
 import { addGraphExecutionStateCompleteEventListener as addGraphExecutionStateCompleteListener } from './listeners/socketio/socketGraphExecutionStateComplete';
 import { addInvocationCompleteEventListener as addInvocationCompleteListener } from './listeners/socketio/socketInvocationComplete';
 import { addInvocationErrorEventListener as addInvocationErrorListener } from './listeners/socketio/socketInvocationError';
-import { addInvocationRetrievalErrorEventListener } from './listeners/socketio/socketInvocationRetrievalError';
 import { addInvocationStartedEventListener as addInvocationStartedListener } from './listeners/socketio/socketInvocationStarted';
 import { addModelLoadEventListener } from './listeners/socketio/socketModelLoad';
-import { addSessionRetrievalErrorEventListener } from './listeners/socketio/socketSessionRetrievalError';
 import { addSocketSubscribedEventListener as addSocketSubscribedListener } from './listeners/socketio/socketSubscribed';
 import { addSocketUnsubscribedEventListener as addSocketUnsubscribedListener } from './listeners/socketio/socketUnsubscribed';
 import { addStagingAreaImageSavedListener } from './listeners/stagingAreaImageSaved';
-import { addTabChangedListener } from './listeners/tabChanged';
 import { addUpscaleRequestedListener } from './listeners/upscaleRequested';
 import { addUserInvokedCanvasListener } from './listeners/userInvokedCanvas';
 import { addUserInvokedImageToImageListener } from './listeners/userInvokedImageToImage';
@@ -156,8 +153,6 @@ addSocketDisconnectedListener();
 addSocketSubscribedListener();
 addSocketUnsubscribedListener();
 addModelLoadEventListener();
-addSessionRetrievalErrorEventListener();
-addInvocationRetrievalErrorEventListener();
 
 // Session Created
 addSessionCreatedPendingListener();
@@ -202,6 +197,3 @@ addFirstListImagesListener();
 
 // Ad-hoc upscale workflwo
 addUpscaleRequestedListener();
-
-// Tab Change
-addTabChangedListener();

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/appConfigReceived.ts

@@ -1,8 +1,4 @@
 import { setInfillMethod } from 'features/parameters/store/generationSlice';
-import {
-  shouldUseNSFWCheckerChanged,
-  shouldUseWatermarkerChanged,
-} from 'features/system/store/systemSlice';
 import { appInfoApi } from 'services/api/endpoints/appInfo';
 import { startAppListening } from '..';
 
@@ -10,21 +6,12 @@ export const addAppConfigReceivedListener = () => {
   startAppListening({
     matcher: appInfoApi.endpoints.getAppConfig.matchFulfilled,
     effect: async (action, { getState, dispatch }) => {
-      const { infill_methods, nsfw_methods, watermarking_methods } =
-        action.payload;
+      const { infill_methods } = action.payload;
       const infillMethod = getState().generation.infillMethod;
 
       if (!infill_methods.includes(infillMethod)) {
         dispatch(setInfillMethod(infill_methods[0]));
       }
-
-      if (!nsfw_methods.includes('nsfw_checker')) {
-        dispatch(shouldUseNSFWCheckerChanged(false));
-      }
-
-      if (!watermarking_methods.includes('invisible_watermark')) {
-        dispatch(shouldUseWatermarkerChanged(false));
-      }
     },
   });
 };

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/modelsLoaded.ts

@@ -9,19 +9,13 @@ import {
   zMainModel,
   zVaeModel,
 } from 'features/parameters/types/parameterSchemas';
-import {
-  refinerModelChanged,
-  setShouldUseSDXLRefiner,
-} from 'features/sdxl/store/sdxlSlice';
 import { forEach, some } from 'lodash-es';
 import { modelsApi } from 'services/api/endpoints/models';
 import { startAppListening } from '..';
 
 export const addModelsLoadedListener = () => {
   startAppListening({
-    predicate: (state, action) =>
-      modelsApi.endpoints.getMainModels.matchFulfilled(action) &&
-      !action.meta.arg.originalArgs.includes('sdxl-refiner'),
+    matcher: modelsApi.endpoints.getMainModels.matchFulfilled,
     effect: async (action, { getState, dispatch }) => {
       // models loaded, we need to ensure the selected model is available and if not, select the first one
       const log = logger('models');
@@ -65,54 +59,6 @@ export const addModelsLoadedListener = () => {
       dispatch(modelChanged(result.data));
     },
   });
-  startAppListening({
-    predicate: (state, action) =>
-      modelsApi.endpoints.getMainModels.matchFulfilled(action) &&
-      action.meta.arg.originalArgs.includes('sdxl-refiner'),
-    effect: async (action, { getState, dispatch }) => {
-      // models loaded, we need to ensure the selected model is available and if not, select the first one
-      const log = logger('models');
-      log.info(
-        { models: action.payload.entities },
-        `SDXL Refiner models loaded (${action.payload.ids.length})`
-      );
-
-      const currentModel = getState().sdxl.refinerModel;
-
-      const isCurrentModelAvailable = some(
-        action.payload.entities,
-        (m) =>
-          m?.model_name === currentModel?.model_name &&
-          m?.base_model === currentModel?.base_model
-      );
-
-      if (isCurrentModelAvailable) {
-        return;
-      }
-
-      const firstModelId = action.payload.ids[0];
-      const firstModel = action.payload.entities[firstModelId];
-
-      if (!firstModel) {
-        // No models loaded at all
-        dispatch(refinerModelChanged(null));
-        dispatch(setShouldUseSDXLRefiner(false));
-        return;
-      }
-
-      const result = zMainModel.safeParse(firstModel);
-
-      if (!result.success) {
-        log.error(
-          { error: result.error.format() },
-          'Failed to parse SDXL Refiner Model'
-        );
-        return;
-      }
-
-      dispatch(refinerModelChanged(result.data));
-    },
-  });
   startAppListening({
     matcher: modelsApi.endpoints.getVaeModels.matchFulfilled,
     effect: async (action, { getState, dispatch }) => {

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/sessionCreated.ts

@@ -33,11 +33,12 @@ export const addSessionCreatedRejectedListener = () => {
     effect: (action) => {
       const log = logger('session');
       if (action.payload) {
-        const { error, status } = action.payload;
+        const { error } = action.payload;
         const graph = parseify(action.meta.arg);
+        const stringifiedError = JSON.stringify(error);
         log.error(
-          { graph, status, error: serializeError(error) },
-          `Problem creating session`
+          { graph, error: serializeError(error) },
+          `Problem creating session: ${stringifiedError}`
         );
       }
     },

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/sessionInvoked.ts

@@ -31,12 +31,13 @@ export const addSessionInvokedRejectedListener = () => {
       const { session_id } = action.meta.arg;
       if (action.payload) {
         const { error } = action.payload;
+        const stringifiedError = JSON.stringify(error);
         log.error(
           {
             session_id,
             error: serializeError(error),
           },
-          `Problem invoking session`
+          `Problem invoking session: ${stringifiedError}`
         );
       }
     },

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/socketio/socketConnected.ts

@@ -1,6 +1,4 @@
 import { logger } from 'app/logging/logger';
-import { LIST_TAG } from 'services/api';
-import { appInfoApi } from 'services/api/endpoints/appInfo';
 import { modelsApi } from 'services/api/endpoints/models';
 import { receivedOpenAPISchema } from 'services/api/thunks/schema';
 import { appSocketConnected, socketConnected } from 'services/events/actions';
@@ -26,18 +24,11 @@ export const addSocketConnectedEventListener = () => {
       dispatch(appSocketConnected(action.payload));
 
       // update all server state
-      dispatch(
-        modelsApi.util.invalidateTags([
-          { type: 'MainModel', id: LIST_TAG },
-          { type: 'SDXLRefinerModel', id: LIST_TAG },
-          { type: 'LoRAModel', id: LIST_TAG },
-          { type: 'ControlNetModel', id: LIST_TAG },
-          { type: 'VaeModel', id: LIST_TAG },
-          { type: 'TextualInversionModel', id: LIST_TAG },
-          { type: 'ScannedModels', id: LIST_TAG },
-        ])
-      );
-      dispatch(appInfoApi.util.invalidateTags(['AppConfig', 'AppVersion']));
+      dispatch(modelsApi.endpoints.getMainModels.initiate());
+      dispatch(modelsApi.endpoints.getControlNetModels.initiate());
+      dispatch(modelsApi.endpoints.getLoRAModels.initiate());
+      dispatch(modelsApi.endpoints.getTextualInversionModels.initiate());
+      dispatch(modelsApi.endpoints.getVaeModels.initiate());
     },
   });
 };

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/socketio/socketInvocationRetrievalError.ts

@@ -1,20 +0,0 @@
-import { logger } from 'app/logging/logger';
-import {
-  appSocketInvocationRetrievalError,
-  socketInvocationRetrievalError,
-} from 'services/events/actions';
-import { startAppListening } from '../..';
-
-export const addInvocationRetrievalErrorEventListener = () => {
-  startAppListening({
-    actionCreator: socketInvocationRetrievalError,
-    effect: (action, { dispatch }) => {
-      const log = logger('socketio');
-      log.error(
-        action.payload,
-        `Invocation retrieval error (${action.payload.data.graph_execution_state_id})`
-      );
-      dispatch(appSocketInvocationRetrievalError(action.payload));
-    },
-  });
-};

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/socketio/socketInvocationStarted.ts

@@ -21,10 +21,7 @@ export const addInvocationStartedEventListener = () => {
         return;
       }
 
-      log.debug(
-        action.payload,
-        `Invocation started (${action.payload.data.node.type})`
-      );
+      log.debug(action.payload, 'Invocation started');
       dispatch(appSocketInvocationStarted(action.payload));
     },
   });

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/socketio/socketSessionRetrievalError.ts

@@ -1,20 +0,0 @@
-import { logger } from 'app/logging/logger';
-import {
-  appSocketSessionRetrievalError,
-  socketSessionRetrievalError,
-} from 'services/events/actions';
-import { startAppListening } from '../..';
-
-export const addSessionRetrievalErrorEventListener = () => {
-  startAppListening({
-    actionCreator: socketSessionRetrievalError,
-    effect: (action, { dispatch }) => {
-      const log = logger('socketio');
-      log.error(
-        action.payload,
-        `Session retrieval error (${action.payload.data.graph_execution_state_id})`
-      );
-      dispatch(appSocketSessionRetrievalError(action.payload));
-    },
-  });
-};

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/tabChanged.ts

@@ -1,56 +0,0 @@
-import { modelChanged } from 'features/parameters/store/generationSlice';
-import { setActiveTab } from 'features/ui/store/uiSlice';
-import { forEach } from 'lodash-es';
-import { NON_REFINER_BASE_MODELS } from 'services/api/constants';
-import {
-  MainModelConfigEntity,
-  modelsApi,
-} from 'services/api/endpoints/models';
-import { startAppListening } from '..';
-
-export const addTabChangedListener = () => {
-  startAppListening({
-    actionCreator: setActiveTab,
-    effect: (action, { getState, dispatch }) => {
-      const activeTabName = action.payload;
-      if (activeTabName === 'unifiedCanvas') {
-        // grab the models from RTK Query cache
-        const { data } = modelsApi.endpoints.getMainModels.select(
-          NON_REFINER_BASE_MODELS
-        )(getState());
-
-        if (!data) {
-          // no models yet, so we can't do anything
-          dispatch(modelChanged(null));
-          return;
-        }
-
-        // need to filter out all the invalid canvas models (currently, this is just sdxl)
-        const validCanvasModels: MainModelConfigEntity[] = [];
-
-        forEach(data.entities, (entity) => {
-          if (!entity) {
-            return;
-          }
-          if (['sd-1', 'sd-2'].includes(entity.base_model)) {
-            validCanvasModels.push(entity);
-          }
-        });
-
-        // this could still be undefined even tho TS doesn't say so
-        const firstValidCanvasModel = validCanvasModels[0];
-
-        if (!firstValidCanvasModel) {
-          // uh oh, we have no models that are valid for canvas
-          dispatch(modelChanged(null));
-          return;
-        }
-
-        // only store the model name and base model in redux
-        const { base_model, model_name } = firstValidCanvasModel;
-
-        dispatch(modelChanged({ base_model, model_name }));
-      }
-    },
-  });
-};

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/userInvokedCanvas.ts

@@ -39,22 +39,8 @@ export const addUserInvokedCanvasListener = () => {
 
       const state = getState();
 
-      const {
-        layerState,
-        boundingBoxCoordinates,
-        boundingBoxDimensions,
-        isMaskEnabled,
-        shouldPreserveMaskedArea,
-      } = state.canvas;
-
       // Build canvas blobs
-      const canvasBlobsAndImageData = await getCanvasData(
-        layerState,
-        boundingBoxCoordinates,
-        boundingBoxDimensions,
-        isMaskEnabled,
-        shouldPreserveMaskedArea
-      );
+      const canvasBlobsAndImageData = await getCanvasData(state);
 
       if (!canvasBlobsAndImageData) {
         log.error('Unable to create canvas data');

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/userInvokedImageToImage.ts

@@ -3,7 +3,6 @@ import { userInvoked } from 'app/store/actions';
 import { parseify } from 'common/util/serialize';
 import { imageToImageGraphBuilt } from 'features/nodes/store/actions';
 import { buildLinearImageToImageGraph } from 'features/nodes/util/graphBuilders/buildLinearImageToImageGraph';
-import { buildLinearSDXLImageToImageGraph } from 'features/nodes/util/graphBuilders/buildLinearSDXLImageToImageGraph';
 import { sessionReadyToInvoke } from 'features/system/store/actions';
 import { sessionCreated } from 'services/api/thunks/session';
 import { startAppListening } from '..';
@@ -15,16 +14,8 @@ export const addUserInvokedImageToImageListener = () => {
     effect: async (action, { getState, dispatch, take }) => {
       const log = logger('session');
       const state = getState();
-      const model = state.generation.model;
-
-      let graph;
-
-      if (model && model.base_model === 'sdxl') {
-        graph = buildLinearSDXLImageToImageGraph(state);
-      } else {
-        graph = buildLinearImageToImageGraph(state);
-      }
 
+      const graph = buildLinearImageToImageGraph(state);
       dispatch(imageToImageGraphBuilt(graph));
       log.debug({ graph: parseify(graph) }, 'Image to Image graph built');
 

invokeai/frontend/web/src/app/store/middleware/listenerMiddleware/listeners/userInvokedTextToImage.ts

@@ -2,7 +2,6 @@ import { logger } from 'app/logging/logger';
 import { userInvoked } from 'app/store/actions';
 import { parseify } from 'common/util/serialize';
 import { textToImageGraphBuilt } from 'features/nodes/store/actions';
-import { buildLinearSDXLTextToImageGraph } from 'features/nodes/util/graphBuilders/buildLinearSDXLTextToImageGraph';
 import { buildLinearTextToImageGraph } from 'features/nodes/util/graphBuilders/buildLinearTextToImageGraph';
 import { sessionReadyToInvoke } from 'features/system/store/actions';
 import { sessionCreated } from 'services/api/thunks/session';
@@ -15,15 +14,8 @@ export const addUserInvokedTextToImageListener = () => {
     effect: async (action, { getState, dispatch, take }) => {
       const log = logger('session');
       const state = getState();
-      const model = state.generation.model;
 
-      let graph;
-
-      if (model && model.base_model === 'sdxl') {
-        graph = buildLinearSDXLTextToImageGraph(state);
-      } else {
-        graph = buildLinearTextToImageGraph(state);
-      }
+      const graph = buildLinearTextToImageGraph(state);
 
       dispatch(textToImageGraphBuilt(graph));
 

invokeai/frontend/web/src/app/store/store.ts

@@ -15,7 +15,6 @@ import loraReducer from 'features/lora/store/loraSlice';
 import nodesReducer from 'features/nodes/store/nodesSlice';
 import generationReducer from 'features/parameters/store/generationSlice';
 import postprocessingReducer from 'features/parameters/store/postprocessingSlice';
-import sdxlReducer from 'features/sdxl/store/sdxlSlice';
 import configReducer from 'features/system/store/configSlice';
 import systemReducer from 'features/system/store/systemSlice';
 import modelmanagerReducer from 'features/ui/components/tabs/ModelManager/store/modelManagerSlice';
@@ -48,7 +47,6 @@ const allReducers = {
   imageDeletion: imageDeletionReducer,
   lora: loraReducer,
   modelmanager: modelmanagerReducer,
-  sdxl: sdxlReducer,
   [api.reducerPath]: api.reducer,
 };
 
@@ -60,7 +58,6 @@ const rememberedKeys: (keyof typeof allReducers)[] = [
   'canvas',
   'gallery',
   'generation',
-  'sdxl',
   'nodes',
   'postprocessing',
   'system',

invokeai/frontend/web/src/app/types/invokeai.ts

@@ -95,8 +95,7 @@ export type AppFeature =
   | 'localization'
   | 'consoleLogging'
   | 'dynamicPrompting'
-  | 'batches'
-  | 'syncModels';
+  | 'batches';
 
 /**
  * A disable-able Stable Diffusion feature

invokeai/frontend/web/src/common/components/IAISlider.tsx

@@ -114,11 +114,6 @@ const IAISlider = (props: IAIFullSliderProps) => {
     setLocalInputValue(value);
   }, [value]);
 
-  const numberInputMin = useMemo(
-    () => (sliderNumberInputProps?.min ? sliderNumberInputProps.min : min),
-    [min, sliderNumberInputProps?.min]
-  );
-
   const numberInputMax = useMemo(
     () => (sliderNumberInputProps?.max ? sliderNumberInputProps.max : max),
     [max, sliderNumberInputProps?.max]
@@ -134,23 +129,24 @@ const IAISlider = (props: IAIFullSliderProps) => {
   const handleInputBlur = useCallback(
     (e: FocusEvent<HTMLInputElement>) => {
       if (e.target.value === '') {
-        e.target.value = String(numberInputMin);
+        e.target.value = String(min);
       }
       const clamped = clamp(
         isInteger
           ? Math.floor(Number(e.target.value))
           : Number(localInputValue),
-        numberInputMin,
+        min,
         numberInputMax
       );
       const quantized = roundDownToMultiple(clamped, step);
       onChange(quantized);
       setLocalInputValue(quantized);
     },
-    [isInteger, localInputValue, numberInputMin, numberInputMax, onChange, step]
+    [isInteger, localInputValue, min, numberInputMax, onChange, step]
   );
 
   const handleInputChange = useCallback((v: number | string) => {
+    console.log('input');
     setLocalInputValue(v);
   }, []);
 
@@ -314,7 +310,7 @@ const IAISlider = (props: IAIFullSliderProps) => {
 
         {withInput && (
           <NumberInput
-            min={numberInputMin}
+            min={min}
             max={numberInputMax}
             step={step}
             value={localInputValue}

invokeai/frontend/web/src/common/hooks/useIsReadyToInvoke.ts

@@ -5,7 +5,6 @@ import { defaultSelectorOptions } from 'app/store/util/defaultMemoizeOptions';
 // import { validateSeedWeights } from 'common/util/seedWeightPairs';
 import { activeTabNameSelector } from 'features/ui/store/uiSelectors';
 import { forEach } from 'lodash-es';
-import { NON_REFINER_BASE_MODELS } from 'services/api/constants';
 import { modelsApi } from '../../services/api/endpoints/models';
 
 const readinessSelector = createSelector(
@@ -25,7 +24,7 @@ const readinessSelector = createSelector(
     }
 
     const { isSuccess: mainModelsSuccessfullyLoaded } =
-      modelsApi.endpoints.getMainModels.select(NON_REFINER_BASE_MODELS)(state);
+      modelsApi.endpoints.getMainModels.select()(state);
     if (!mainModelsSuccessfullyLoaded) {
       isReady = false;
       reasonsWhyNotReady.push('Models are not loaded');

invokeai/frontend/web/src/features/canvas/components/IAICanvasStatusText.tsx

@@ -2,8 +2,8 @@ import { Box, Flex } from '@chakra-ui/react';
 import { createSelector } from '@reduxjs/toolkit';
 import { useAppSelector } from 'app/store/storeHooks';
 import { canvasSelector } from 'features/canvas/store/canvasSelectors';
-import GenerationModeStatusText from 'features/parameters/components/Parameters/Canvas/GenerationModeStatusText';
 import { isEqual } from 'lodash-es';
+
 import { useTranslation } from 'react-i18next';
 import roundToHundreth from '../util/roundToHundreth';
 import IAICanvasStatusTextCursorPos from './IAICanvasStatusText/IAICanvasStatusTextCursorPos';
@@ -110,7 +110,6 @@ const IAICanvasStatusText = () => {
         },
       }}
     >
-      <GenerationModeStatusText />
       <Box
         style={{
           color: activeLayerColor,

invokeai/frontend/web/src/features/canvas/components/IAICanvasToolbar/IAICanvasToolbar.tsx

@@ -2,15 +2,7 @@ import { Box, ButtonGroup, Flex } from '@chakra-ui/react';
 import { createSelector } from '@reduxjs/toolkit';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import IAIIconButton from 'common/components/IAIIconButton';
-import IAIMantineSelect from 'common/components/IAIMantineSelect';
-import { useImageUploadButton } from 'common/hooks/useImageUploadButton';
 import { useSingleAndDoubleClick } from 'common/hooks/useSingleAndDoubleClick';
-import {
-  canvasCopiedToClipboard,
-  canvasDownloadedAsImage,
-  canvasMerged,
-  canvasSavedToGallery,
-} from 'features/canvas/store/actions';
 import {
   canvasSelector,
   isStagingSelector,
@@ -29,8 +21,16 @@ import {
 } from 'features/canvas/store/canvasTypes';
 import { getCanvasBaseLayer } from 'features/canvas/util/konvaInstanceProvider';
 import { systemSelector } from 'features/system/store/systemSelectors';
-import { useCopyImageToClipboard } from 'features/ui/hooks/useCopyImageToClipboard';
 import { isEqual } from 'lodash-es';
+
+import IAIMantineSearchableSelect from 'common/components/IAIMantineSearchableSelect';
+import { useImageUploadButton } from 'common/hooks/useImageUploadButton';
+import {
+  canvasCopiedToClipboard,
+  canvasDownloadedAsImage,
+  canvasMerged,
+  canvasSavedToGallery,
+} from 'features/canvas/store/actions';
 import { useHotkeys } from 'react-hotkeys-hook';
 import { useTranslation } from 'react-i18next';
 import {
@@ -48,6 +48,7 @@ import IAICanvasRedoButton from './IAICanvasRedoButton';
 import IAICanvasSettingsButtonPopover from './IAICanvasSettingsButtonPopover';
 import IAICanvasToolChooserOptions from './IAICanvasToolChooserOptions';
 import IAICanvasUndoButton from './IAICanvasUndoButton';
+import { useCopyImageToClipboard } from 'features/ui/hooks/useCopyImageToClipboard';
 
 export const selector = createSelector(
   [systemSelector, canvasSelector, isStagingSelector],
@@ -219,7 +220,7 @@ const IAICanvasToolbar = () => {
       }}
     >
       <Box w={24}>
-        <IAIMantineSelect
+        <IAIMantineSearchableSelect
           tooltip={`${t('unifiedCanvas.layer')} (Q)`}
           value={layer}
           data={LAYER_NAMES_DICT}

invokeai/frontend/web/src/features/canvas/hooks/useCanvasGenerationMode.ts

@@ -1,72 +0,0 @@
-import { useAppSelector } from 'app/store/storeHooks';
-import { GenerationMode } from 'features/canvas/store/canvasTypes';
-import { getCanvasData } from 'features/canvas/util/getCanvasData';
-import { getCanvasGenerationMode } from 'features/canvas/util/getCanvasGenerationMode';
-import { useEffect, useState } from 'react';
-import { useDebounce } from 'react-use';
-
-export const useCanvasGenerationMode = () => {
-  const layerState = useAppSelector((state) => state.canvas.layerState);
-
-  const boundingBoxCoordinates = useAppSelector(
-    (state) => state.canvas.boundingBoxCoordinates
-  );
-  const boundingBoxDimensions = useAppSelector(
-    (state) => state.canvas.boundingBoxDimensions
-  );
-  const isMaskEnabled = useAppSelector((state) => state.canvas.isMaskEnabled);
-
-  const shouldPreserveMaskedArea = useAppSelector(
-    (state) => state.canvas.shouldPreserveMaskedArea
-  );
-  const [generationMode, setGenerationMode] = useState<
-    GenerationMode | undefined
-  >();
-
-  useEffect(() => {
-    setGenerationMode(undefined);
-  }, [
-    layerState,
-    boundingBoxCoordinates,
-    boundingBoxDimensions,
-    isMaskEnabled,
-    shouldPreserveMaskedArea,
-  ]);
-
-  useDebounce(
-    async () => {
-      // Build canvas blobs
-      const canvasBlobsAndImageData = await getCanvasData(
-        layerState,
-        boundingBoxCoordinates,
-        boundingBoxDimensions,
-        isMaskEnabled,
-        shouldPreserveMaskedArea
-      );
-
-      if (!canvasBlobsAndImageData) {
-        return;
-      }
-
-      const { baseImageData, maskImageData } = canvasBlobsAndImageData;
-
-      // Determine the generation mode
-      const generationMode = getCanvasGenerationMode(
-        baseImageData,
-        maskImageData
-      );
-
-      setGenerationMode(generationMode);
-    },
-    1000,
-    [
-      layerState,
-      boundingBoxCoordinates,
-      boundingBoxDimensions,
-      isMaskEnabled,
-      shouldPreserveMaskedArea,
-    ]
-  );
-
-  return generationMode;
-};

invokeai/frontend/web/src/features/canvas/store/canvasTypes.ts

@@ -168,7 +168,4 @@ export interface CanvasState {
   stageDimensions: Dimensions;
   stageScale: number;
   tool: CanvasTool;
-  generationMode?: GenerationMode;
 }
-
-export type GenerationMode = 'txt2img' | 'img2img' | 'inpaint' | 'outpaint';

invokeai/frontend/web/src/features/canvas/util/getCanvasData.ts

@@ -1,10 +1,6 @@
 import { logger } from 'app/logging/logger';
-import { Vector2d } from 'konva/lib/types';
-import {
-  CanvasLayerState,
-  Dimensions,
-  isCanvasMaskLine,
-} from '../store/canvasTypes';
+import { RootState } from 'app/store/store';
+import { isCanvasMaskLine } from '../store/canvasTypes';
 import createMaskStage from './createMaskStage';
 import { getCanvasBaseLayer, getCanvasStage } from './konvaInstanceProvider';
 import { konvaNodeToBlob } from './konvaNodeToBlob';
@@ -13,13 +9,7 @@ import { konvaNodeToImageData } from './konvaNodeToImageData';
 /**
  * Gets Blob and ImageData objects for the base and mask layers
  */
-export const getCanvasData = async (
-  layerState: CanvasLayerState,
-  boundingBoxCoordinates: Vector2d,
-  boundingBoxDimensions: Dimensions,
-  isMaskEnabled: boolean,
-  shouldPreserveMaskedArea: boolean
-) => {
+export const getCanvasData = async (state: RootState) => {
   const log = logger('canvas');
 
   const canvasBaseLayer = getCanvasBaseLayer();
@@ -30,6 +20,14 @@ export const getCanvasData = async (
     return;
   }
 
+  const {
+    layerState: { objects },
+    boundingBoxCoordinates,
+    boundingBoxDimensions,
+    isMaskEnabled,
+    shouldPreserveMaskedArea,
+  } = state.canvas;
+
   const boundingBox = {
     ...boundingBoxCoordinates,
     ...boundingBoxDimensions,
@@ -60,7 +58,7 @@ export const getCanvasData = async (
 
   // For the mask layer, use the normal boundingBox
   const maskStage = await createMaskStage(
-    isMaskEnabled ? layerState.objects.filter(isCanvasMaskLine) : [], // only include mask lines, and only if mask is enabled
+    isMaskEnabled ? objects.filter(isCanvasMaskLine) : [], // only include mask lines, and only if mask is enabled
     boundingBox,
     shouldPreserveMaskedArea
   );

invokeai/frontend/web/src/features/canvas/util/getCanvasGenerationMode.ts

@@ -2,12 +2,11 @@ import {
   areAnyPixelsBlack,
   getImageDataTransparency,
 } from 'common/util/arrayBuffer';
-import { GenerationMode } from '../store/canvasTypes';
 
 export const getCanvasGenerationMode = (
   baseImageData: ImageData,
   maskImageData: ImageData
-): GenerationMode => {
+) => {
   const {
     isPartiallyTransparent: baseIsPartiallyTransparent,
     isFullyTransparent: baseIsFullyTransparent,

invokeai/frontend/web/src/features/embedding/components/ParamEmbeddingPopover.tsx

@@ -57,11 +57,6 @@ const ParamEmbeddingPopover = (props: Props) => {
       });
     });
 
-    // Sort Alphabetically
-    data.sort((a, b) =>
-      a.label && b.label ? (a.label?.localeCompare(b.label) ? -1 : 1) : -1
-    );
-
     return data.sort((a, b) => (a.disabled && !b.disabled ? 1 : -1));
   }, [embeddingQueryData, currentMainModel?.base_model]);
 

invokeai/frontend/web/src/features/gallery/components/ImageContextMenu/SingleSelectionMenuItems.tsx

@@ -1,6 +1,5 @@
-import { MenuItem } from '@chakra-ui/react';
+import { Link, MenuItem } from '@chakra-ui/react';
 import { createSelector } from '@reduxjs/toolkit';
-import { skipToken } from '@reduxjs/toolkit/dist/query';
 import { useAppToaster } from 'app/components/Toaster';
 import { stateSelector } from 'app/store/store';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
@@ -34,9 +33,10 @@ import {
   useRemoveImageFromBoardMutation,
 } from 'services/api/endpoints/images';
 import { ImageDTO } from 'services/api/types';
-import { useDebounce } from 'use-debounce';
 import { AddImageToBoardContext } from '../../../../app/contexts/AddImageToBoardContext';
 import { sentImageToCanvas, sentImageToImg2Img } from '../../store/actions';
+import { useDebounce } from 'use-debounce';
+import { skipToken } from '@reduxjs/toolkit/dist/query';
 
 type SingleSelectionMenuItemsProps = {
   imageDTO: ImageDTO;
@@ -154,29 +154,21 @@ const SingleSelectionMenuItems = (props: SingleSelectionMenuItemsProps) => {
 
   return (
     <>
-      <MenuItem
-        as="a"
-        href={imageDTO.image_url}
-        target="_blank"
-        icon={<FaExternalLinkAlt />}
-      >
-        {t('common.openInNewTab')}
-      </MenuItem>
+      <Link href={imageDTO.image_url} target="_blank">
+        <MenuItem icon={<FaExternalLinkAlt />}>
+          {t('common.openInNewTab')}
+        </MenuItem>
+      </Link>
       {isClipboardAPIAvailable && (
         <MenuItem icon={<FaCopy />} onClickCapture={handleCopyImage}>
           {t('parameters.copyImage')}
         </MenuItem>
       )}
-      <MenuItem
-        as="a"
-        download={true}
-        href={imageDTO.image_url}
-        target="_blank"
-        icon={<FaDownload />}
-        w="100%"
-      >
-        {t('parameters.downloadImage')}
-      </MenuItem>
+      <Link download={true} href={imageDTO.image_url} target="_blank">
+        <MenuItem icon={<FaDownload />} w="100%">
+          {t('parameters.downloadImage')}
+        </MenuItem>
+      </Link>
       <MenuItem
         icon={<FaQuoteRight />}
         onClickCapture={handleRecallPrompt}

invokeai/frontend/web/src/features/lora/components/ParamLora.tsx

@@ -48,7 +48,6 @@ const ParamLora = (props: Props) => {
         handleReset={handleReset}
         withSliderMarks
         sliderMarks={[-1, 0, 1, 2]}
-        sliderNumberInputProps={{ min: -50, max: 50 }}
       />
       <IAIIconButton
         size="sm"

invokeai/frontend/web/src/features/lora/components/ParamLoraSelect.tsx

@@ -54,12 +54,7 @@ const ParamLoRASelect = () => {
       });
     });
 
-    // Sort Alphabetically
-    data.sort((a, b) =>
-      a.label && b.label ? (a.label?.localeCompare(b.label) ? 1 : -1) : -1
-    );
-
-    return data.sort((a, b) => (a.disabled && !b.disabled ? -1 : 1));
+    return data.sort((a, b) => (a.disabled && !b.disabled ? 1 : -1));
   }, [loras, loraModels, currentMainModel?.base_model]);
 
   const handleChange = useCallback(

invokeai/frontend/web/src/features/nodes/components/InputFieldComponent.tsx

@@ -20,7 +20,6 @@ import StringInputFieldComponent from './fields/StringInputFieldComponent';
 import UnetInputFieldComponent from './fields/UnetInputFieldComponent';
 import VaeInputFieldComponent from './fields/VaeInputFieldComponent';
 import VaeModelInputFieldComponent from './fields/VaeModelInputFieldComponent';
-import RefinerModelInputFieldComponent from './fields/RefinerModelInputFieldComponent';
 
 type InputFieldComponentProps = {
   nodeId: string;
@@ -156,16 +155,6 @@ const InputFieldComponent = (props: InputFieldComponentProps) => {
     );
   }
 
-  if (type === 'refiner_model' && template.type === 'refiner_model') {
-    return (
-      <RefinerModelInputFieldComponent
-        nodeId={nodeId}
-        field={field}
-        template={template}
-      />
-    );
-  }
-
   if (type === 'vae_model' && template.type === 'vae_model') {
     return (
       <VaeModelInputFieldComponent