[nodes] Add cancelation to the API

.coveragerc

@@ -0,0 +1,6 @@
+[run]
+omit='.env/*'
+source='.'
+
+[report]
+show_missing = true

.github/CODEOWNERS

@@ -1,16 +1,16 @@
 # continuous integration
-/.github/workflows/ @mauwii @lstein @blessedcoolant
+/.github/workflows/ @mauwii @lstein
 
 # documentation
-/docs/ @lstein @mauwii @tildebyte @blessedcoolant
-/mkdocs.yml @lstein @mauwii @blessedcoolant
+/docs/ @lstein @mauwii @tildebyte
+/mkdocs.yml @lstein @mauwii
 
 # nodes
 /invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
 /pyproject.toml @mauwii @lstein @blessedcoolant
-/docker/ @mauwii @lstein @blessedcoolant
+/docker/ @mauwii @lstein
 /scripts/ @ebr @lstein
 /installer/ @lstein @ebr
 /invokeai/assets @lstein @ebr

.github/workflows/build-container.yml

@@ -16,10 +16,6 @@ on:
       - 'v*.*.*'
   workflow_dispatch:
 
-permissions:
-  contents: write
-  packages: write
-
 jobs:
   docker:
     if: github.event.pull_request.draft == false

.github/workflows/mkdocs-material.yml

@@ -5,9 +5,6 @@ on:
       - 'main'
       - 'development'
 
-permissions:
-    contents: write
-
 jobs:
   mkdocs-material:
     if: github.event.pull_request.draft == false

.github/workflows/test-invoke-pip-skip.yml

@@ -6,6 +6,7 @@ on:
       - '!pyproject.toml'
       - '!invokeai/**'
       - 'invokeai/frontend/web/**'
+      - '!invokeai/frontend/web/dist/**'
   merge_group:
   workflow_dispatch:
 

.github/workflows/test-invoke-pip.yml

@@ -7,11 +7,13 @@ on:
       - 'pyproject.toml'
       - 'invokeai/**'
       - '!invokeai/frontend/web/**'
+      - 'invokeai/frontend/web/dist/**'
   pull_request:
     paths:
       - 'pyproject.toml'
       - 'invokeai/**'
       - '!invokeai/frontend/web/**'
+      - 'invokeai/frontend/web/dist/**'
     types:
       - 'ready_for_review'
       - 'opened'

.gitignore

@@ -63,7 +63,6 @@ pip-delete-this-directory.txt
 htmlcov/
 .tox/
 .nox/
-.coveragerc
 .coverage
 .coverage.*
 .cache
@@ -74,7 +73,6 @@ cov.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.pytest.ini
 cover/
 junit/
 

.pytest.ini

@@ -0,0 +1,5 @@
+[pytest]
+DJANGO_SETTINGS_MODULE = webtas.settings
+; python_files = tests.py test_*.py *_tests.py
+
+addopts = --cov=. --cov-config=.coveragerc --cov-report xml:cov.xml

README.md

@@ -139,13 +139,13 @@ not supported.
     _For Windows/Linux with an NVIDIA GPU:_
 
     ```terminal
-    pip install "InvokeAI[xformers]" --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
+    pip install InvokeAI[xformers] --use-pep517 --extra-index-url https://download.pytorch.org/whl/cu117
     ```
 
     _For Linux with an AMD GPU:_
 
     ```sh
-    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
     ```
 
     _For Macintoshes, either Intel or M1/M2:_

coverage/.gitignore

@@ -1,4 +0,0 @@
-# Ignore everything in this directory
-*
-# Except this file
-!.gitignore

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -1,83 +0,0 @@
-# Local Development
-
-If you are looking to contribute you will need to have a local development
-environment. See the
-[Developer Install](../installation/020_INSTALL_MANUAL.md#developer-install) for
-full details.
-
-Broadly this involves cloning the repository, installing the pre-reqs, and
-InvokeAI (in editable form). Assuming this is working, choose your area of
-focus.
-
-## Documentation
-
-We use [mkdocs](https://www.mkdocs.org) for our documentation with the
-[material theme](https://squidfunk.github.io/mkdocs-material/). Documentation is
-written in markdown files under the `./docs` folder and then built into a static
-website for hosting with GitHub Pages at
-[invoke-ai.github.io/InvokeAI](https://invoke-ai.github.io/InvokeAI).
-
-To contribute to the documentation you'll need to install the dependencies. Note
-the use of `"`.
-
-```zsh
-pip install ".[docs]"
-```
-
-Now, to run the documentation locally with hot-reloading for changes made.
-
-```zsh
-mkdocs serve
-```
-
-You'll then be prompted to connect to `http://127.0.0.1:8080` in order to
-access.
-
-## Backend
-
-The backend is contained within the `./invokeai/backend` folder structure. To
-get started however please install the development dependencies.
-
-From the root of the repository run the following command. Note the use of `"`.
-
-```zsh
-pip install ".[test]"
-```
-
-This in an optional group of packages which is defined within the
-`pyproject.toml` and will be required for testing the changes you make the the
-code.
-
-### Running Tests
-
-We use [pytest](https://docs.pytest.org/en/7.2.x/) for our test suite. Tests can
-be found under the `./tests` folder and can be run with a single `pytest`
-command. Optionally, to review test coverage you can append `--cov`.
-
-```zsh
-pytest --cov
-```
-
-Test outcomes and coverage will be reported in the terminal. In addition a more
-detailed report is created in both XML and HTML format in the `./coverage`
-folder. The HTML one in particular can help identify missing statements
-requiring tests to ensure coverage. This can be run by opening
-`./coverage/html/index.html`.
-
-For example.
-
-```zsh
-pytest --cov; open ./coverage/html/index.html
-```
-
-??? info "HTML coverage report output"
-
-    ![html-overview](../assets/contributing/html-overview.png)
-
-    ![html-detail](../assets/contributing/html-detail.png)
-
-## Front End
-
-<!--#TODO: get input from blessedcoolant here, for the moment inserted the frontend README via snippets extension.-->
-
---8<-- "invokeai/frontend/web/README.md"

docs/features/INPAINTING.md

@@ -168,15 +168,11 @@ used by Stable Diffusion 1.4 and 1.5.
 After installation, your `models.yaml` should contain an entry that looks like
 this one:
 
-```yml
-inpainting-1.5:
-  weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
-  description: SD inpainting v1.5
-  config: configs/stable-diffusion/v1-inpainting-inference.yaml
-  vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
-  width: 512
-  height: 512
-```
+inpainting-1.5: weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
+description: SD inpainting v1.5 config:
+configs/stable-diffusion/v1-inpainting-inference.yaml vae:
+models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt width: 512
+height: 512
 
 As shown in the example, you may include a VAE fine-tuning weights file as well.
 This is strongly recommended.

docs/features/PROMPTS.md

@@ -268,7 +268,7 @@ model is so good at inpainting, a good substitute is to use the `clipseg` text
 masking option:
 
 ```bash
-invoke> a fluffy cat eating a hotdog
+invoke> a fluffy cat eating a hotdot
 Outputs:
 [1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
 invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat

docs/features/TEXTUAL_INVERSION.md

@@ -17,7 +17,7 @@ notebooks.
 
 You will need a GPU to perform training in a reasonable length of
 time, and at least 12 GB of VRAM. We recommend using the [`xformers`
-library](../installation/070_INSTALL_XFORMERS.md) to accelerate the
+library](../installation/070_INSTALL_XFORMERS) to accelerate the
 training process further. During training, about ~8 GB is temporarily
 needed in order to store intermediate models, checkpoints and logs.
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -417,7 +417,7 @@ Then type the following commands:
 
 === "AMD System"
     ```bash
-    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+    pip install torch torchvision --force-reinstall --extra-index-url https://download.pytorch.org/whl/rocm5.2
     ```
 
 ### Corrupted configuration file

docs/installation/020_INSTALL_MANUAL.md

@@ -154,7 +154,7 @@ manager, please follow these steps:
     === "ROCm (AMD)"
 
         ```bash
-        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"
@@ -315,7 +315,7 @@ installation protocol (important!)
 
     === "ROCm (AMD)"
         ```bash
-        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
+        pip install -e . --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.2
         ```
 
     === "CPU (Intel Macs & non-GPU systems)"

docs/installation/030_INSTALL_CUDA_AND_ROCM.md

@@ -110,7 +110,7 @@ recipes are available
 
 When installing torch and torchvision manually with `pip`, remember to provide
 the argument `--extra-index-url
-https://download.pytorch.org/whl/rocm5.4.2` as described in the [Manual
+https://download.pytorch.org/whl/rocm5.2` as described in the [Manual
 Installation Guide](020_INSTALL_MANUAL.md).
 
 This will be done automatically for you if you use the installer

docs/installation/060_INSTALL_PATCHMATCH.md

@@ -24,7 +24,7 @@ You need to have opencv installed so that pypatchmatch can be built:
 brew install opencv
 ```
 
-The next time you start `invoke`, after successfully installing opencv, pypatchmatch will be built.
+The next time you start `invoke`, after sucesfully installing opencv, pypatchmatch will be built.
 
 ## Linux
 
@@ -56,7 +56,7 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 5. Confirm that pypatchmatch is installed. At the command-line prompt enter
    `python`, and then at the `>>>` line type
-   `from patchmatch import patch_match`: It should look like the following:
+   `from patchmatch import patch_match`: It should look like the follwing:
 
     ```py
     Python 3.9.5 (default, Nov 23 2021, 15:27:38)
@@ -108,4 +108,4 @@ Prior to installing PyPatchMatch, you need to take the following steps:
 
 [**Next, Follow Steps 4-6 from the Debian Section above**](#linux)
 
-If you see no errors you're ready to go!
+If you see no errors, then you're ready to go!

installer/lib/installer.py

@@ -456,12 +456,13 @@ def get_torch_source() -> (Union[str, None],str):
     optional_modules = None
     if OS == "Linux":
         if device == "rocm":
-            url = "https://download.pytorch.org/whl/rocm5.4.2"
+            url = "https://download.pytorch.org/whl/rocm5.2"
         elif device == "cpu":
             url = "https://download.pytorch.org/whl/cpu"
 
     if device == 'cuda':
-        url = 'https://download.pytorch.org/whl/cu118'
+        url = 'https://download.pytorch.org/whl/cu117'
+        optional_modules = '[xformers]'
 
     # in all other cases, Torch wheels should be coming from PyPi as of Torch 1.13
 

installer/templates/invoke.sh.in

@@ -24,9 +24,9 @@ if [ "$(uname -s)" == "Darwin" ]; then
     export PYTORCH_ENABLE_MPS_FALLBACK=1
 fi
 
+while true
+do
 if [ "$0" != "bash" ]; then
-  while true
-  do
     echo "Do you want to generate images using the"
     echo "1. command-line interface"
     echo "2. browser-based UI"
@@ -67,29 +67,29 @@ if [ "$0" != "bash" ]; then
             ;;
         7)
             invokeai-configure --root ${INVOKEAI_ROOT} --yes --default_only
-            ;;
-        8)
-            echo "Developer Console:"
+	    ;;
+	8)
+	    echo "Developer Console:"
             file_name=$(basename "${BASH_SOURCE[0]}")
             bash --init-file "$file_name"
             ;;
         9)
-            echo "Update:"
+	    echo "Update:"
             invokeai-update
             ;;
         10)
             invokeai --help
             ;;
-        [qQ])
+	[qQ])
             exit 0
             ;;
         *)
             echo "Invalid selection"
             exit;;
     esac
- done
 else # in developer console
     python --version
     echo "Press ^D to exit"
     export PS1="(InvokeAI) \u@\h \w> "
 fi
+done

invokeai/app/api/dependencies.py

@@ -3,8 +3,6 @@
 import os
 from argparse import Namespace
 
-from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-
 from ...backend import Globals
 from ..services.model_manager_initializer import get_model_manager
 from ..services.restoration_services import RestorationServices
@@ -56,9 +54,7 @@ class ApiDependencies:
             os.path.join(os.path.dirname(__file__), "../../../../outputs")
         )
 
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents'))
-
-        images = DiskImageStorage(f'{output_folder}/images')
+        images = DiskImageStorage(output_folder)
 
         # TODO: build a file/path manager?
         db_location = os.path.join(output_folder, "invokeai.db")
@@ -66,7 +62,6 @@ class ApiDependencies:
         services = InvocationServices(
             model_manager=get_model_manager(config),
             events=events,
-            latents=latents,
             images=images,
             queue=MemoryInvocationQueue(),
             graph_execution_manager=SqliteItemStorage[GraphExecutionState](

invokeai/app/api/routers/images.py

@@ -23,16 +23,6 @@ async def get_image(
     filename = ApiDependencies.invoker.services.images.get_path(image_type, image_name)
     return FileResponse(filename)
 
-@images_router.get("/{image_type}/thumbnails/{image_name}", operation_id="get_thumbnail")
-async def get_thumbnail(
-    image_type: ImageType = Path(description="The type of image to get"),
-    image_name: str = Path(description="The name of the image to get"),
-):
-    """Gets a thumbnail"""
-    # TODO: This is not really secure at all. At least make sure only output results are served
-    filename = ApiDependencies.invoker.services.images.get_path(image_type, 'thumbnails/' + image_name)
-    return FileResponse(filename)
-
 
 @images_router.post(
     "/uploads/",

invokeai/app/api/routers/models.py

@@ -1,279 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Annotated, Any, List, Literal, Optional, Union
-
-from fastapi.routing import APIRouter
-from pydantic import BaseModel, Field, parse_obj_as
-
-from ..dependencies import ApiDependencies
-
-models_router = APIRouter(prefix="/v1/models", tags=["models"])
-
-
-class VaeRepo(BaseModel):
-    repo_id: str = Field(description="The repo ID to use for this VAE")
-    path: Optional[str] = Field(description="The path to the VAE")
-    subfolder: Optional[str] = Field(description="The subfolder to use for this VAE")
-
-
-class ModelInfo(BaseModel):
-    description: Optional[str] = Field(description="A description of the model")
-    
-
-class CkptModelInfo(ModelInfo):
-    format: Literal['ckpt'] = 'ckpt'
-
-    config: str = Field(description="The path to the model config")
-    weights: str = Field(description="The path to the model weights")
-    vae: str = Field(description="The path to the model VAE")
-    width: Optional[int] = Field(description="The width of the model")
-    height: Optional[int] = Field(description="The height of the model")
-
-
-class DiffusersModelInfo(ModelInfo):
-    format: Literal['diffusers'] = 'diffusers'
-
-    vae: Optional[VaeRepo] = Field(description="The VAE repo to use for this model")
-    repo_id: Optional[str] = Field(description="The repo ID to use for this model")
-    path: Optional[str] = Field(description="The path to the model")
-
-
-class ModelsList(BaseModel):
-    models: dict[str, Annotated[Union[(CkptModelInfo,DiffusersModelInfo)], Field(discriminator="format")]]
-
-
-
-@models_router.get(
-    "/",
-    operation_id="list_models",
-    responses={200: {"model": ModelsList }},
-)
-async def list_models() -> ModelsList:
-    """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models()
-    models = parse_obj_as(ModelsList, { "models": models_raw })
-    return models
-
-        # @socketio.on("requestSystemConfig")
-        # def handle_request_capabilities():
-        #     print(">> System config requested")
-        #     config = self.get_system_config()
-        #     config["model_list"] = self.generate.model_manager.list_models()
-        #     config["infill_methods"] = infill_methods()
-        #     socketio.emit("systemConfig", config)
-
-        # @socketio.on("searchForModels")
-        # def handle_search_models(search_folder: str):
-        #     try:
-        #         if not search_folder:
-        #             socketio.emit(
-        #                 "foundModels",
-        #                 {"search_folder": None, "found_models": None},
-        #             )
-        #         else:
-        #             (
-        #                 search_folder,
-        #                 found_models,
-        #             ) = self.generate.model_manager.search_models(search_folder)
-        #             socketio.emit(
-        #                 "foundModels",
-        #                 {"search_folder": search_folder, "found_models": found_models},
-        #             )
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-        #         print("\n")
-
-        # @socketio.on("addNewModel")
-        # def handle_add_model(new_model_config: dict):
-        #     try:
-        #         model_name = new_model_config["name"]
-        #         del new_model_config["name"]
-        #         model_attributes = new_model_config
-        #         if len(model_attributes["vae"]) == 0:
-        #             del model_attributes["vae"]
-        #         update = False
-        #         current_model_list = self.generate.model_manager.list_models()
-        #         if model_name in current_model_list:
-        #             update = True
-
-        #         print(f">> Adding New Model: {model_name}")
-
-        #         self.generate.model_manager.add_model(
-        #             model_name=model_name,
-        #             model_attributes=model_attributes,
-        #             clobber=True,
-        #         )
-        #         self.generate.model_manager.commit(opt.conf)
-
-        #         new_model_list = self.generate.model_manager.list_models()
-        #         socketio.emit(
-        #             "newModelAdded",
-        #             {
-        #                 "new_model_name": model_name,
-        #                 "model_list": new_model_list,
-        #                 "update": update,
-        #             },
-        #         )
-        #         print(f">> New Model Added: {model_name}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("deleteModel")
-        # def handle_delete_model(model_name: str):
-        #     try:
-        #         print(f">> Deleting Model: {model_name}")
-        #         self.generate.model_manager.del_model(model_name)
-        #         self.generate.model_manager.commit(opt.conf)
-        #         updated_model_list = self.generate.model_manager.list_models()
-        #         socketio.emit(
-        #             "modelDeleted",
-        #             {
-        #                 "deleted_model_name": model_name,
-        #                 "model_list": updated_model_list,
-        #             },
-        #         )
-        #         print(f">> Model Deleted: {model_name}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("requestModelChange")
-        # def handle_set_model(model_name: str):
-        #     try:
-        #         print(f">> Model change requested: {model_name}")
-        #         model = self.generate.set_model(model_name)
-        #         model_list = self.generate.model_manager.list_models()
-        #         if model is None:
-        #             socketio.emit(
-        #                 "modelChangeFailed",
-        #                 {"model_name": model_name, "model_list": model_list},
-        #             )
-        #         else:
-        #             socketio.emit(
-        #                 "modelChanged",
-        #                 {"model_name": model_name, "model_list": model_list},
-        #             )
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("convertToDiffusers")
-        # def convert_to_diffusers(model_to_convert: dict):
-        #     try:
-        #         if model_info := self.generate.model_manager.model_info(
-        #             model_name=model_to_convert["model_name"]
-        #         ):
-        #             if "weights" in model_info:
-        #                 ckpt_path = Path(model_info["weights"])
-        #                 original_config_file = Path(model_info["config"])
-        #                 model_name = model_to_convert["model_name"]
-        #                 model_description = model_info["description"]
-        #             else:
-        #                 self.socketio.emit(
-        #                     "error", {"message": "Model is not a valid checkpoint file"}
-        #                 )
-        #         else:
-        #             self.socketio.emit(
-        #                 "error", {"message": "Could not retrieve model info."}
-        #             )
-
-        #         if not ckpt_path.is_absolute():
-        #             ckpt_path = Path(Globals.root, ckpt_path)
-
-        #         if original_config_file and not original_config_file.is_absolute():
-        #             original_config_file = Path(Globals.root, original_config_file)
-
-        #         diffusers_path = Path(
-        #             ckpt_path.parent.absolute(), f"{model_name}_diffusers"
-        #         )
-
-        #         if model_to_convert["save_location"] == "root":
-        #             diffusers_path = Path(
-        #                 global_converted_ckpts_dir(), f"{model_name}_diffusers"
-        #             )
-
-        #         if (
-        #             model_to_convert["save_location"] == "custom"
-        #             and model_to_convert["custom_location"] is not None
-        #         ):
-        #             diffusers_path = Path(
-        #                 model_to_convert["custom_location"], f"{model_name}_diffusers"
-        #             )
-
-        #         if diffusers_path.exists():
-        #             shutil.rmtree(diffusers_path)
-
-        #         self.generate.model_manager.convert_and_import(
-        #             ckpt_path,
-        #             diffusers_path,
-        #             model_name=model_name,
-        #             model_description=model_description,
-        #             vae=None,
-        #             original_config_file=original_config_file,
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         new_model_list = self.generate.model_manager.list_models()
-        #         socketio.emit(
-        #             "modelConverted",
-        #             {
-        #                 "new_model_name": model_name,
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Model Converted: {model_name}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)
-
-        # @socketio.on("mergeDiffusersModels")
-        # def merge_diffusers_models(model_merge_info: dict):
-        #     try:
-        #         models_to_merge = model_merge_info["models_to_merge"]
-        #         model_ids_or_paths = [
-        #             self.generate.model_manager.model_name_or_path(x)
-        #             for x in models_to_merge
-        #         ]
-        #         merged_pipe = merge_diffusion_models(
-        #             model_ids_or_paths,
-        #             model_merge_info["alpha"],
-        #             model_merge_info["interp"],
-        #             model_merge_info["force"],
-        #         )
-
-        #         dump_path = global_models_dir() / "merged_models"
-        #         if model_merge_info["model_merge_save_path"] is not None:
-        #             dump_path = Path(model_merge_info["model_merge_save_path"])
-
-        #         os.makedirs(dump_path, exist_ok=True)
-        #         dump_path = dump_path / model_merge_info["merged_model_name"]
-        #         merged_pipe.save_pretrained(dump_path, safe_serialization=1)
-
-        #         merged_model_config = dict(
-        #             model_name=model_merge_info["merged_model_name"],
-        #             description=f'Merge of models {", ".join(models_to_merge)}',
-        #             commit_to_conf=opt.conf,
-        #         )
-
-        #         if vae := self.generate.model_manager.config[models_to_merge[0]].get(
-        #             "vae", None
-        #         ):
-        #             print(f">> Using configured VAE assigned to {models_to_merge[0]}")
-        #             merged_model_config.update(vae=vae)
-
-        #         self.generate.model_manager.import_diffuser_model(
-        #             dump_path, **merged_model_config
-        #         )
-        #         new_model_list = self.generate.model_manager.list_models()
-
-        #         socketio.emit(
-        #             "modelsMerged",
-        #             {
-        #                 "merged_models": models_to_merge,
-        #                 "merged_model_name": model_merge_info["merged_model_name"],
-        #                 "model_list": new_model_list,
-        #                 "update": True,
-        #             },
-        #         )
-        #         print(f">> Models Merged: {models_to_merge}")
-        #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
-        #     except Exception as e:
-        #         self.handle_exceptions(e)

invokeai/app/api/routers/sessions.py

@@ -51,7 +51,7 @@ async def list_sessions(
     query: str = Query(default="", description="The query string to search for"),
 ) -> PaginatedResults[GraphExecutionState]:
     """Gets a list of sessions, optionally searching"""
-    if query == "":
+    if filter == "":
         result = ApiDependencies.invoker.services.graph_execution_manager.list(
             page, per_page
         )

invokeai/app/api_app.py

@@ -14,7 +14,7 @@ from pydantic.schema import schema
 
 from ..backend import Args
 from .api.dependencies import ApiDependencies
-from .api.routers import images, sessions, models
+from .api.routers import images, sessions
 from .api.sockets import SocketIO
 from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
@@ -76,8 +76,6 @@ app.include_router(sessions.session_router, prefix="/api")
 
 app.include_router(images.images_router, prefix="/api")
 
-app.include_router(models.models_router, prefix="/api")
-
 
 # Build a custom OpenAPI to include all outputs
 # TODO: can outputs be included on metadata of invocation schemas somehow?

invokeai/app/cli/commands.py

@@ -4,8 +4,7 @@ from abc import ABC, abstractmethod
 import argparse
 from typing import Any, Callable, Iterable, Literal, get_args, get_origin, get_type_hints
 from pydantic import BaseModel, Field
-import networkx as nx
-import matplotlib.pyplot as plt
+
 from ..invocations.image import ImageField
 from ..services.graph import GraphExecutionState
 from ..services.invoker import Invoker
@@ -47,7 +46,7 @@ def add_parsers(
                     f"--{name}",
                     dest=name,
                     type=field_type,
-                    default=field.default if field.default_factory is None else field.default_factory(),
+                    default=field.default,
                     choices=allowed_values,
                     help=field.field_info.description,
                 )
@@ -56,7 +55,7 @@ def add_parsers(
                     f"--{name}",
                     dest=name,
                     type=field.type_,
-                    default=field.default if field.default_factory is None else field.default_factory(),
+                    default=field.default,
                     help=field.field_info.description,
                 )
 
@@ -201,39 +200,3 @@ class SetDefaultCommand(BaseCommand):
                 del context.defaults[self.field]
         else:
             context.defaults[self.field] = self.value
-
-
-class DrawGraphCommand(BaseCommand):
-    """Debugs a graph"""
-    type: Literal['draw_graph'] = 'draw_graph'
-
-    def run(self, context: CliContext) -> None:
-        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
-        nxgraph = session.graph.nx_graph_flat()
-
-        # Draw the networkx graph
-        plt.figure(figsize=(20, 20))
-        pos = nx.spectral_layout(nxgraph)
-        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
-        nx.draw_networkx_edges(nxgraph, pos, width=2)
-        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
-        plt.axis("off")
-        plt.show()
-
-
-class DrawExecutionGraphCommand(BaseCommand):
-    """Debugs an execution graph"""
-    type: Literal['draw_xgraph'] = 'draw_xgraph'
-
-    def run(self, context: CliContext) -> None:
-        session: GraphExecutionState = context.invoker.services.graph_execution_manager.get(context.session.id)
-        nxgraph = session.execution_graph.nx_graph_flat()
-
-        # Draw the networkx graph
-        plt.figure(figsize=(20, 20))
-        pos = nx.spectral_layout(nxgraph)
-        nx.draw_networkx_nodes(nxgraph, pos, node_size=1000)
-        nx.draw_networkx_edges(nxgraph, pos, width=2)
-        nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
-        plt.axis("off")
-        plt.show()

invokeai/app/cli/completer.py

@@ -1,167 +0,0 @@
-"""
-Readline helper functions for cli_app.py
-You may import the global singleton `completer` to get access to the
-completer object.
-"""
-import atexit
-import readline
-import shlex
-
-from pathlib import Path
-from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
-
-from ...backend import ModelManager, Globals
-from ..invocations.baseinvocation import BaseInvocation
-from .commands import BaseCommand
-
-# singleton object, class variable
-completer = None
-
-class Completer(object):
-    
-    def __init__(self, model_manager: ModelManager):
-        self.commands = self.get_commands()
-        self.matches = None
-        self.linebuffer = None
-        self.manager = model_manager
-        return
-
-    def complete(self, text, state):
-        """
-        Complete commands and switches fromm the node CLI command line.
-        Switches are determined in a context-specific manner.
-        """
-
-        buffer = readline.get_line_buffer()
-        if state == 0:
-            options = None
-            try:
-                current_command, current_switch = self.get_current_command(buffer)
-                options = self.get_command_options(current_command, current_switch)
-            except IndexError:
-                pass
-            options = options or list(self.parse_commands().keys())
-            
-            if not text:  # first time
-                self.matches = options
-            else:
-                self.matches = [s for s in options if s and s.startswith(text)]
-
-        try:
-            match = self.matches[state]
-        except IndexError:
-            match = None
-        return match
-
-    @classmethod
-    def get_commands(self)->List[object]:
-        """
-        Return a list of all the client commands and invocations.
-        """
-        return BaseCommand.get_commands() + BaseInvocation.get_invocations()
-
-    def get_current_command(self, buffer: str)->tuple[str, str]:
-        """
-        Parse the readline buffer to find the most recent command and its switch.
-        """
-        if len(buffer)==0:
-            return None, None
-        tokens = shlex.split(buffer)
-        command = None
-        switch = None
-        for t in tokens:
-            if t[0].isalpha():
-                if switch is None:
-                    command = t
-            else:
-                switch = t
-        # don't try to autocomplete switches that are already complete
-        if switch and buffer.endswith(' '):
-            switch=None
-        return command or '', switch or ''
-
-    def parse_commands(self)->Dict[str, List[str]]:
-        """
-        Return a dict in which the keys are the command name
-        and the values are the parameters the command takes.
-        """
-        result = dict()
-        for command in self.commands:
-            hints = get_type_hints(command)
-            name = get_args(hints['type'])[0]
-            result.update({name:hints})
-        return result
-
-    def get_command_options(self, command: str, switch: str)->List[str]:
-        """
-        Return all the parameters that can be passed to the command as
-        command-line switches. Returns None if the command is unrecognized.
-        """
-        parsed_commands = self.parse_commands()
-        if command not in parsed_commands:
-            return None
-        
-        # handle switches in the format "-foo=bar"
-        argument = None
-        if switch and '=' in switch:
-            switch, argument = switch.split('=')
-            
-        parameter = switch.strip('-')
-        if parameter in parsed_commands[command]:
-            if argument is None:
-                return self.get_parameter_options(parameter, parsed_commands[command][parameter])
-            else:
-                return [f"--{parameter}={x}" for x in self.get_parameter_options(parameter, parsed_commands[command][parameter])]
-        else:
-            return [f"--{x}" for x in parsed_commands[command].keys()]
-
-    def get_parameter_options(self, parameter: str, typehint)->List[str]:
-        """
-        Given a parameter type (such as Literal), offers autocompletions.
-        """
-        if get_origin(typehint) == Literal:
-            return get_args(typehint)
-        if parameter == 'model':
-            return self.manager.model_names()
-        
-    def _pre_input_hook(self):
-        if self.linebuffer:
-            readline.insert_text(self.linebuffer)
-            readline.redisplay()
-            self.linebuffer = None
-    
-def set_autocompleter(model_manager: ModelManager) -> Completer:
-    global completer
-    
-    if completer:
-        return completer
-    
-    completer = Completer(model_manager)
-
-    readline.set_completer(completer.complete)
-    # pyreadline3 does not have a set_auto_history() method
-    try:
-        readline.set_auto_history(True)
-    except:
-        pass
-    readline.set_pre_input_hook(completer._pre_input_hook)
-    readline.set_completer_delims(" ")
-    readline.parse_and_bind("tab: complete")
-    readline.parse_and_bind("set print-completions-horizontally off")
-    readline.parse_and_bind("set page-completions on")
-    readline.parse_and_bind("set skip-completed-text on")
-    readline.parse_and_bind("set show-all-if-ambiguous on")
-
-    histfile = Path(Globals.root, ".invoke_history")
-    try:
-        readline.read_history_file(histfile)
-        readline.set_history_length(1000)
-    except FileNotFoundError:
-        pass
-    except OSError:  # file likely corrupted
-        newname = f"{histfile}.old"
-        print(
-            f"## Your history file {histfile} couldn't be loaded and may be corrupted. Renaming it to {newname}"
-        )
-        histfile.replace(Path(newname))
-    atexit.register(readline.write_history_file, histfile)

invokeai/app/cli_app.py

@@ -2,7 +2,6 @@
 
 import argparse
 import os
-import re
 import shlex
 import time
 from typing import (
@@ -13,17 +12,14 @@ from typing import (
 from pydantic import BaseModel
 from pydantic.fields import Field
 
-from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
-
 from ..backend import Args
 from .cli.commands import BaseCommand, CliContext, ExitCli, add_parsers, get_graph_execution_history
-from .cli.completer import set_autocompleter
 from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
 from .services.events import EventServiceBase
 from .services.model_manager_initializer import get_model_manager
 from .services.restoration_services import RestorationServices
-from .services.graph import Edge, EdgeConnection, GraphExecutionState, are_connection_types_compatible
+from .services.graph import Edge, EdgeConnection, GraphExecutionState
 from .services.image_storage import DiskImageStorage
 from .services.invocation_queue import MemoryInvocationQueue
 from .services.invocation_services import InvocationServices
@@ -47,7 +43,7 @@ def add_invocation_args(command_parser):
         "-l",
         action="append",
         nargs=3,
-        help="A link in the format 'source_node source_field dest_field'. source_node can be relative to history (e.g. -1)",
+        help="A link in the format 'dest_field source_node source_field'. source_node can be relative to history (e.g. -1)",
     )
 
     command_parser.add_argument(
@@ -97,9 +93,6 @@ def generate_matching_edges(
     invalid_fields = set(["type", "id"])
     matching_fields = matching_fields.difference(invalid_fields)
 
-    # Validate types
-    matching_fields = [f for f in matching_fields if are_connection_types_compatible(afields[f], bfields[f])]
-
     edges = [
         Edge(
             source=EdgeConnection(node_id=a.id, field=field),
@@ -137,12 +130,6 @@ def invoke_cli():
     config.parse_args()
     model_manager = get_model_manager(config)
 
-    # This initializes the autocompleter and returns it.
-    # Currently nothing is done with the returned Completer
-    # object, but the object can be used to change autocompletion
-    # behavior on the fly, if desired.
-    completer = set_autocompleter(model_manager)
-
     events = EventServiceBase()
 
     output_folder = os.path.abspath(
@@ -155,8 +142,7 @@ def invoke_cli():
     services = InvocationServices(
         model_manager=model_manager,
         events=events,
-        latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
-        images=DiskImageStorage(f'{output_folder}/images'),
+        images=DiskImageStorage(output_folder),
         queue=MemoryInvocationQueue(),
         graph_execution_manager=SqliteItemStorage[GraphExecutionState](
             filename=db_location, table_name="graph_executions"
@@ -169,8 +155,6 @@ def invoke_cli():
     session: GraphExecutionState = invoker.create_execution_state()
     parser = get_command_parser()
 
-    re_negid = re.compile('^-[0-9]+$')
-
     # Uncomment to print out previous sessions at startup
     # print(services.session_manager.list())
 
@@ -178,8 +162,8 @@ def invoke_cli():
 
     while True:
         try:
-            cmd_input = input("invoke> ")
-        except (KeyboardInterrupt, EOFError):
+            cmd_input = input("> ")
+        except KeyboardInterrupt:
             # Ctrl-c exits
             break
 
@@ -236,11 +220,7 @@ def invoke_cli():
                 # Parse provided links
                 if "link_node" in args and args["link_node"]:
                     for link in args["link_node"]:
-                        node_id = link
-                        if re_negid.match(node_id):
-                            node_id = str(current_id + int(node_id))
-
-                        link_node = context.session.graph.get_node(node_id)
+                        link_node = context.session.graph.get_node(link)
                         matching_edges = generate_matching_edges(
                             link_node, command.command
                         )
@@ -250,15 +230,10 @@ def invoke_cli():
 
                 if "link" in args and args["link"]:
                     for link in args["link"]:
-                        edges = [e for e in edges if e.destination.node_id != command.command.id or e.destination.field != link[2]]
-
-                        node_id = link[0]
-                        if re_negid.match(node_id):
-                            node_id = str(current_id + int(node_id))
-
+                        edges = [e for e in edges if e.destination.node_id != command.command.id and e.destination.field != link[2]]
                         edges.append(
                             Edge(
-                                source=EdgeConnection(node_id=node_id, field=link[1]),
+                                source=EdgeConnection(node_id=link[1], field=link[0]),
                                 destination=EdgeConnection(
                                     node_id=command.command.id, field=link[2]
                                 )

invokeai/app/invocations/collections.py

@@ -1,50 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Literal
-
-import cv2 as cv
-import numpy as np
-import numpy.random
-from PIL import Image, ImageOps
-from pydantic import Field
-
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext, BaseInvocationOutput
-from .image import ImageField, ImageOutput
-
-
-class IntCollectionOutput(BaseInvocationOutput):
-    """A collection of integers"""
-
-    type: Literal["int_collection"] = "int_collection"
-
-    # Outputs
-    collection: list[int] = Field(default=[], description="The int collection")
-
-
-class RangeInvocation(BaseInvocation):
-    """Creates a range"""
-
-    type: Literal["range"] = "range"
-
-    # Inputs
-    start: int = Field(default=0, description="The start of the range")
-    stop: int = Field(default=10, description="The stop of the range")
-    step: int = Field(default=1, description="The step of the range")
-
-    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(collection=list(range(self.start, self.stop, self.step)))
-
-
-class RandomRangeInvocation(BaseInvocation):
-    """Creates a collection of random numbers"""
-
-    type: Literal["random_range"] = "random_range"
-
-    # Inputs
-    low: int = Field(default=0, description="The inclusive low value")
-    high: int = Field(default=np.iinfo(np.int32).max, description="The exclusive high value")
-    size: int = Field(default=1, description="The number of values to generate")
-
-    def invoke(self, context: InvocationContext) -> IntCollectionOutput:
-        return IntCollectionOutput(collection=list(numpy.random.randint(self.low, self.high, size=self.size)))

invokeai/app/invocations/generate.py

@@ -1,19 +1,22 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-from functools import partial
-from typing import Literal, Optional, Union
+from datetime import datetime, timezone
+from typing import Any, Literal, Optional, Union
 
 import numpy as np
-from torch import Tensor
 
+from torch import Tensor
+from PIL import Image
 from pydantic import Field
+from skimage.exposure.histogram_matching import match_histograms
 
 from ..services.image_storage import ImageType
+from ..services.invocation_services import InvocationServices
 from .baseinvocation import BaseInvocation, InvocationContext
 from .image import ImageField, ImageOutput
-from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
+from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator, Generator
 from ...backend.stable_diffusion import PipelineIntermediateState
-from ..util.util import diffusers_step_callback_adapter, CanceledException
+from ...backend.util.util import image_to_dataURL
 
 SAMPLER_NAME_VALUES = Literal[
     tuple(InvokeAIGenerator.schedulers())
@@ -42,26 +45,32 @@ class TextToImageInvocation(BaseInvocation):
 
     # TODO: pass this an emitter method or something? or a session for dispatching?
     def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
+        self, context: InvocationContext, sample: Tensor, step: int
+    ) -> None:  
+        # TODO: only output a preview image when requested
+        image = Generator.sample_to_lowres_estimated_image(sample)
 
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-        
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
+        (width, height) = image.size
+        width *= 8
+        height *= 8
+
+        dataURL = image_to_dataURL(image, image_format="JPEG")
+
+        context.services.events.emit_generator_progress(
+            context.graph_execution_state_id,
+            self.id,
+            {
+                "width": width,
+                "height": height,
+                "dataURL": dataURL
+            },
+            step,
+            self.steps,
+        )
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
-        # def step_callback(state: PipelineIntermediateState):
-        #     if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-        #         raise CanceledException
-        #     self.dispatch_progress(context, state.latents, state.step)
+        def step_callback(state: PipelineIntermediateState):
+            self.dispatch_progress(context, state.latents, state.step)
 
         # Handle invalid model parameter
         # TODO: figure out if this can be done via a validator that uses the model_cache
@@ -70,7 +79,7 @@ class TextToImageInvocation(BaseInvocation):
         model= context.services.model_manager.get_model()
         outputs = Txt2Img(model).generate(
             prompt=self.prompt,
-            step_callback=partial(self.dispatch_progress, context),
+            step_callback=step_callback,
             **self.dict(
                 exclude={"prompt"}
             ),  # Shorthand for passing all of the parameters above manually
@@ -107,22 +116,6 @@ class ImageToImageInvocation(TextToImageInvocation):
         description="Whether or not the result should be fit to the aspect ratio of the input image",
     )
 
-    def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
@@ -133,23 +126,24 @@ class ImageToImageInvocation(TextToImageInvocation):
         )
         mask = None
 
+        def step_callback(sample, step=0):
+            self.dispatch_progress(context, sample, step)
+
         # Handle invalid model parameter
         # TODO: figure out if this can be done via a validator that uses the model_cache
         # TODO: How to get the default model name now?
         model = context.services.model_manager.get_model()
-        outputs = Img2Img(model).generate(
+        generator_output = next(
+            Img2Img(model).generate(
                 prompt=self.prompt,
                 init_image=image,
                 init_mask=mask,
-                step_callback=partial(self.dispatch_progress, context),
+                step_callback=step_callback,
                 **self.dict(
                     exclude={"prompt", "image", "mask"}
                 ),  # Shorthand for passing all of the parameters above manually
             )
-
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generator_output = next(outputs)
+        )
 
         result_image = generator_output.image
 
@@ -179,22 +173,6 @@ class InpaintInvocation(ImageToImageInvocation):
         description="The amount by which to replace masked areas with latent noise",
     )
 
-    def dispatch_progress(
-        self, context: InvocationContext, intermediate_state: PipelineIntermediateState
-    ) -> None:  
-        if (context.services.queue.is_canceled(context.graph_execution_state_id)):
-            raise CanceledException
-
-        step = intermediate_state.step
-        if intermediate_state.predicted_original is not None:
-            # Some schedulers report not only the noisy latents at the current timestep,
-            # but also their estimate so far of what the de-noised latents will be.
-            sample = intermediate_state.predicted_original
-        else:
-            sample = intermediate_state.latents
-
-        diffusers_step_callback_adapter(sample, step, steps=self.steps, id=self.id, context=context)
-
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = (
             None
@@ -209,23 +187,24 @@ class InpaintInvocation(ImageToImageInvocation):
             else context.services.images.get(self.mask.image_type, self.mask.image_name)
         )
 
+        def step_callback(sample, step=0):
+            self.dispatch_progress(context, sample, step)
+
         # Handle invalid model parameter
         # TODO: figure out if this can be done via a validator that uses the model_cache
         # TODO: How to get the default model name now?
-        model = context.services.model_manager.get_model()
-        outputs = Inpaint(model).generate(
+        manager = context.services.model_manager.get_model()
+        generator_output = next(
+            Inpaint(model).generate(
                 prompt=self.prompt,
-                init_img=image,
-                init_mask=mask,
-                step_callback=partial(self.dispatch_progress, context),
+                init_image=image,
+                mask_image=mask,
+                step_callback=step_callback,
                 **self.dict(
                     exclude={"prompt", "image", "mask"}
                 ),  # Shorthand for passing all of the parameters above manually
             )
-
-        # Outputs is an infinite iterator that will return a new InvokeAIGeneratorOutput object
-        # each time it is called. We only need the first one.
-        generator_output = next(outputs)
+        )
 
         result_image = generator_output.image
 

invokeai/app/invocations/image.py

@@ -28,28 +28,12 @@ class ImageOutput(BaseInvocationOutput):
     image:      ImageField = Field(default=None, description="The output image")
     #fmt: on
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'image',
-            ]
-        }
-
 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")
-    #fmt: on
-
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'mask',
-            ]
-        }
+    #fomt: on
 
 # TODO: this isn't really necessary anymore
 class LoadImageInvocation(BaseInvocation):

invokeai/app/invocations/latent.py

@@ -1,321 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from typing import Literal, Optional
-from pydantic import BaseModel, Field
-from torch import Tensor
-import torch
-
-from ...backend.model_management.model_manager import ModelManager
-from ...backend.util.devices import CUDA_DEVICE, torch_dtype
-from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import PostprocessingSettings
-from ...backend.image_util.seamless import configure_model_padding
-from ...backend.prompting.conditioning import get_uc_and_c_and_ec
-from ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
-import numpy as np
-from accelerate.utils import set_seed
-from ..services.image_storage import ImageType
-from .baseinvocation import BaseInvocation, InvocationContext
-from .image import ImageField, ImageOutput
-from ...backend.generator import Generator
-from ...backend.stable_diffusion import PipelineIntermediateState
-from ...backend.util.util import image_to_dataURL
-from diffusers.schedulers import SchedulerMixin as Scheduler
-import diffusers
-from diffusers import DiffusionPipeline
-
-
-class LatentsField(BaseModel):
-    """A latents field used for passing latents between invocations"""
-
-    latents_name: Optional[str] = Field(default=None, description="The name of the latents")
-
-
-class LatentsOutput(BaseInvocationOutput):
-    """Base class for invocations that output latents"""
-    #fmt: off
-    type: Literal["latent_output"] = "latent_output"
-    latents: LatentsField            = Field(default=None, description="The output latents")
-    #fmt: on
-
-class NoiseOutput(BaseInvocationOutput):
-    """Invocation noise output"""
-    #fmt: off
-    type: Literal["noise_output"] = "noise_output"
-    noise: LatentsField            = Field(default=None, description="The output noise")
-    #fmt: on
-
-
-# TODO: this seems like a hack
-scheduler_map = dict(
-    ddim=diffusers.DDIMScheduler,
-    dpmpp_2=diffusers.DPMSolverMultistepScheduler,
-    k_dpm_2=diffusers.KDPM2DiscreteScheduler,
-    k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
-    k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
-    k_euler=diffusers.EulerDiscreteScheduler,
-    k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
-    k_heun=diffusers.HeunDiscreteScheduler,
-    k_lms=diffusers.LMSDiscreteScheduler,
-    plms=diffusers.PNDMScheduler,
-)
-
-
-SAMPLER_NAME_VALUES = Literal[
-    tuple(list(scheduler_map.keys()))
-]
-
-
-def get_scheduler(scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
-    scheduler_class = scheduler_map.get(scheduler_name,'ddim')
-    scheduler = scheduler_class.from_config(model.scheduler.config)
-    # hack copied over from generate.py
-    if not hasattr(scheduler, 'uses_inpainting_model'):
-        scheduler.uses_inpainting_model = lambda: False
-    return scheduler
-
-
-def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_channels:int=4, use_mps_noise:bool=False, downsampling_factor:int = 8):
-    # limit noise to only the diffusion image channels, not the mask channels
-    input_channels = min(latent_channels, 4)
-    use_device = "cpu" if (use_mps_noise or device.type == "mps") else device
-    generator = torch.Generator(device=use_device).manual_seed(seed)
-    x = torch.randn(
-        [
-            1,
-            input_channels,
-            height // downsampling_factor,
-            width //  downsampling_factor,
-        ],
-        dtype=torch_dtype(device),
-        device=use_device,
-        generator=generator,
-    ).to(device)
-    # if self.perlin > 0.0:
-    #     perlin_noise = self.get_perlin_noise(
-    #         width // self.downsampling_factor, height // self.downsampling_factor
-    #     )
-    #     x = (1 - self.perlin) * x + self.perlin * perlin_noise
-    return x
-
-
-class NoiseInvocation(BaseInvocation):
-    """Generates latent noise."""
-
-    type: Literal["noise"] = "noise"
-
-    # Inputs
-    seed:        int = Field(default=0, ge=0, le=np.iinfo(np.uint32).max, description="The seed to use", )
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting noise", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting noise", )
-
-    def invoke(self, context: InvocationContext) -> NoiseOutput:
-        device = torch.device(CUDA_DEVICE)
-        noise = get_noise(self.width, self.height, device, self.seed)
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, noise)
-        return NoiseOutput(
-            noise=LatentsField(latents_name=name)
-        )
-
-
-# Text to image
-class TextToLatentsInvocation(BaseInvocation):
-    """Generates latents from a prompt."""
-
-    type: Literal["t2l"] = "t2l"
-
-    # Inputs
-    # TODO: consider making prompt optional to enable providing prompt through a link
-    # fmt: off
-    prompt: Optional[str] = Field(description="The prompt to generate an image from")
-    seed:        int = Field(default=-1,ge=-1, le=np.iinfo(np.uint32).max, description="The seed to use (-1 for a random seed)", )
-    noise: Optional[LatentsField] = Field(description="The noise to use")
-    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
-    width:       int = Field(default=512, multiple_of=64, gt=0, description="The width of the resulting image", )
-    height:      int = Field(default=512, multiple_of=64, gt=0, description="The height of the resulting image", )
-    cfg_scale: float = Field(default=7.5, gt=0, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
-    sampler_name: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The sampler to use" )
-    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
-    seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
-    model:       str = Field(default="", description="The model to use (currently ignored)")
-    progress_images: bool = Field(default=False, description="Whether or not to produce progress images during generation",  )
-    # fmt: on
-
-    # TODO: pass this an emitter method or something? or a session for dispatching?
-    def dispatch_progress(
-        self, context: InvocationContext, sample: Tensor, step: int
-    ) -> None:  
-        # TODO: only output a preview image when requested
-        image = Generator.sample_to_lowres_estimated_image(sample)
-
-        (width, height) = image.size
-        width *= 8
-        height *= 8
-
-        dataURL = image_to_dataURL(image, image_format="JPEG")
-
-        context.services.events.emit_generator_progress(
-            context.graph_execution_state_id,
-            self.id,
-            {
-                "width": width,
-                "height": height,
-                "dataURL": dataURL
-            },
-            step,
-            self.steps,
-        )
-    
-    def get_model(self, model_manager: ModelManager) -> StableDiffusionGeneratorPipeline:
-        model_info = model_manager.get_model(self.model)
-        model_name = model_info['model_name']
-        model_hash = model_info['hash']
-        model: StableDiffusionGeneratorPipeline = model_info['model']
-        model.scheduler = get_scheduler(
-            model=model,
-            scheduler_name=self.sampler_name
-        )
-        
-        if isinstance(model, DiffusionPipeline):
-            for component in [model.unet, model.vae]:
-                configure_model_padding(component,
-                                        self.seamless,
-                                        self.seamless_axes
-                                        )
-        else:
-            configure_model_padding(model,
-                                    self.seamless,
-                                    self.seamless_axes
-                                    )
-
-        return model
-
-
-    def get_conditioning_data(self, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
-        uc, c, extra_conditioning_info = get_uc_and_c_and_ec(self.prompt, model=model)
-        conditioning_data = ConditioningData(
-            uc,
-            c,
-            self.cfg_scale,
-            extra_conditioning_info,
-            postprocessing_settings=PostprocessingSettings(
-                threshold=0.0,#threshold,
-                warmup=0.2,#warmup,
-                h_symmetry_time_pct=None,#h_symmetry_time_pct,
-                v_symmetry_time_pct=None#v_symmetry_time_pct,
-            ),
-        ).add_scheduler_args_if_applicable(model.scheduler, eta=None)#ddim_eta)
-        return conditioning_data
-
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
-
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, state.latents, state.step)
-
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
-
-        # TODO: Verify the noise is the right size
-
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=torch.zeros_like(noise, dtype=torch_dtype(model.device)),
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            callback=step_callback
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
-
-
-class LatentsToLatentsInvocation(TextToLatentsInvocation):
-    """Generates latents using latents as base image."""
-
-    type: Literal["l2l"] = "l2l"
-
-    # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to use as a base image")
-    strength: float = Field(default=0.5, description="The strength of the latents to use")
-
-    def invoke(self, context: InvocationContext) -> LatentsOutput:
-        noise = context.services.latents.get(self.noise.latents_name)
-        latent = context.services.latents.get(self.latents.latents_name)
-
-        def step_callback(state: PipelineIntermediateState):
-            self.dispatch_progress(context, state.latents, state.step)
-
-        model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
-
-        # TODO: Verify the noise is the right size
-
-        initial_latents = latent if self.strength < 1.0 else torch.zeros_like(
-            latent, device=model.device, dtype=latent.dtype
-        )
-        
-        timesteps, _ = model.get_img2img_timesteps(
-            self.steps,
-            self.strength,
-            device=model.device,
-        )
-
-        result_latents, result_attention_map_saver = model.latents_from_embeddings(
-            latents=initial_latents,
-            timesteps=timesteps,
-            noise=noise,
-            num_inference_steps=self.steps,
-            conditioning_data=conditioning_data,
-            callback=step_callback
-        )
-
-        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
-        torch.cuda.empty_cache()
-
-        name = f'{context.graph_execution_state_id}__{self.id}'
-        context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
-
-
-# Latent to image
-class LatentsToImageInvocation(BaseInvocation):
-    """Generates an image from latents."""
-
-    type: Literal["l2i"] = "l2i"
-
-    # Inputs
-    latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
-    model: str = Field(default="", description="The model to use")
-
-    @torch.no_grad()
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        latents = context.services.latents.get(self.latents.latents_name)
-
-        # TODO: this only really needs the vae
-        model_info = context.services.model_manager.get_model(self.model)
-        model: StableDiffusionGeneratorPipeline = model_info['model']
-
-        with torch.inference_mode():
-            np_image = model.decode_latents(latents)
-            image = model.numpy_to_pil(np_image)[0]
-
-            image_type = ImageType.RESULT
-            image_name = context.services.images.create_name(
-                context.graph_execution_state_id, self.id
-            )
-            context.services.images.save(image_type, image_name, image)
-            return ImageOutput(
-                image=ImageField(image_type=image_type, image_name=image_name)
-            )

invokeai/app/invocations/math.py

@@ -1,68 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-from datetime import datetime, timezone
-from typing import Literal, Optional
-
-import numpy
-from PIL import Image, ImageFilter, ImageOps
-from pydantic import BaseModel, Field
-
-from ..services.image_storage import ImageType
-from ..services.invocation_services import InvocationServices
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
-
-
-class IntOutput(BaseInvocationOutput):
-    """An integer output"""
-    #fmt: off
-    type: Literal["int_output"] = "int_output"
-    a: int = Field(default=None, description="The output integer")
-    #fmt: on
-
-
-class AddInvocation(BaseInvocation):
-    """Adds two numbers"""
-    #fmt: off
-    type: Literal["add"] = "add"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=self.a + self.b)
-
-
-class SubtractInvocation(BaseInvocation):
-    """Subtracts two numbers"""
-    #fmt: off
-    type: Literal["sub"] = "sub"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=self.a - self.b)
-
-
-class MultiplyInvocation(BaseInvocation):
-    """Multiplies two numbers"""
-    #fmt: off
-    type: Literal["mul"] = "mul"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=self.a * self.b)
-
-
-class DivideInvocation(BaseInvocation):
-    """Divides two numbers"""
-    #fmt: off
-    type: Literal["div"] = "div"
-    a: int = Field(default=0, description="The first number")
-    b: int = Field(default=0, description="The second number")
-    #fmt: on
-
-    def invoke(self, context: InvocationContext) -> IntOutput:
-        return IntOutput(a=int(self.a / self.b))

invokeai/app/invocations/prompt.py

@@ -12,11 +12,3 @@ class PromptOutput(BaseInvocationOutput):
 
     prompt: str = Field(default=None, description="The output prompt")
     #fmt: on
-
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'prompt',
-            ]
-        }

invokeai/app/services/graph.py

@@ -127,13 +127,6 @@ class NodeAlreadyExecutedError(Exception):
 class GraphInvocationOutput(BaseInvocationOutput):
     type: Literal["graph_output"] = "graph_output"
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'image',
-            ]
-        }
 
 # TODO: Fill this out and move to invocations
 class GraphInvocation(BaseInvocation):
@@ -154,13 +147,6 @@ class IterateInvocationOutput(BaseInvocationOutput):
 
     item: Any = Field(description="The item being iterated over")
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'item',
-            ]
-        }
 
 # TODO: Fill this out and move to invocations
 class IterateInvocation(BaseInvocation):
@@ -183,13 +169,6 @@ class CollectInvocationOutput(BaseInvocationOutput):
 
     collection: list[Any] = Field(description="The collection of input items")
 
-    class Config:
-        schema_extra = {
-            'required': [
-                'type',
-                'collection',
-            ]
-        }
 
 class CollectInvocation(BaseInvocation):
     """Collects values into a collection"""
@@ -1069,8 +1048,9 @@ class GraphExecutionState(BaseModel):
                 n
                 for n in prepared_nodes
                 if all(
-                    nx.has_path(execution_graph, pit[0], n)
+                    pit
                     for pit in parent_iterators
+                    if nx.has_path(execution_graph, pit[0], n)
                 )
             ),
             None,

invokeai/app/services/image_storage.py

@@ -9,7 +9,6 @@ from queue import Queue
 from typing import Dict
 
 from PIL.Image import Image
-from invokeai.app.util.save_thumbnail import save_thumbnail
 
 from invokeai.backend.image_util import PngWriter
 
@@ -67,9 +66,6 @@ class DiskImageStorage(ImageStorageBase):
             Path(os.path.join(output_folder, image_type)).mkdir(
                 parents=True, exist_ok=True
             )
-            Path(os.path.join(output_folder, image_type, "thumbnails")).mkdir(
-                parents=True, exist_ok=True
-            )
 
     def get(self, image_type: ImageType, image_name: str) -> Image:
         image_path = self.get_path(image_type, image_name)
@@ -91,11 +87,7 @@ class DiskImageStorage(ImageStorageBase):
         self.__pngWriter.save_image_and_prompt_to_png(
             image, "", image_subpath, None
         )  # TODO: just pass full path to png writer
-        save_thumbnail(
-            image=image,
-            filename=image_name,
-            path=os.path.join(self.__output_folder, image_type, "thumbnails"),
-        )
+
         image_path = self.get_path(image_type, image_name)
         self.__set_cache(image_path, image)
 

invokeai/app/services/invocation_services.py

@@ -2,7 +2,6 @@
 from invokeai.backend import ModelManager
 
 from .events import EventServiceBase
-from .latent_storage import LatentsStorageBase
 from .image_storage import ImageStorageBase
 from .restoration_services import RestorationServices
 from .invocation_queue import InvocationQueueABC
@@ -12,7 +11,6 @@ class InvocationServices:
     """Services that can be used by invocations"""
 
     events: EventServiceBase
-    latents: LatentsStorageBase
     images: ImageStorageBase
     queue: InvocationQueueABC
     model_manager: ModelManager
@@ -26,7 +24,6 @@ class InvocationServices:
             self,
             model_manager: ModelManager,
             events: EventServiceBase,
-            latents: LatentsStorageBase,
             images: ImageStorageBase,
             queue: InvocationQueueABC,
             graph_execution_manager: ItemStorageABC["GraphExecutionState"],
@@ -35,7 +32,6 @@ class InvocationServices:
     ):
         self.model_manager = model_manager
         self.events = events
-        self.latents = latents
         self.images = images
         self.queue = queue
         self.graph_execution_manager = graph_execution_manager

invokeai/app/services/invoker.py

@@ -33,6 +33,7 @@ class Invoker:
         self.services.graph_execution_manager.set(graph_execution_state)
 
         # Queue the invocation
+        print(f"queueing item {invocation.id}")
         self.services.queue.put(
             InvocationQueueItem(
                 # session_id    = session.id,

invokeai/app/services/latent_storage.py

@@ -1,93 +0,0 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
-import os
-from abc import ABC, abstractmethod
-from pathlib import Path
-from queue import Queue
-from typing import Dict
-
-import torch
-
-class LatentsStorageBase(ABC):
-    """Responsible for storing and retrieving latents."""
-
-    @abstractmethod
-    def get(self, name: str) -> torch.Tensor:
-        pass
-
-    @abstractmethod
-    def set(self, name: str, data: torch.Tensor) -> None:
-        pass
-
-    @abstractmethod
-    def delete(self, name: str) -> None:
-        pass
-
-
-class ForwardCacheLatentsStorage(LatentsStorageBase):
-    """Caches the latest N latents in memory, writing-thorugh to and reading from underlying storage"""
-    
-    __cache: Dict[str, torch.Tensor]
-    __cache_ids: Queue
-    __max_cache_size: int
-    __underlying_storage: LatentsStorageBase
-
-    def __init__(self, underlying_storage: LatentsStorageBase, max_cache_size: int = 20):
-        self.__underlying_storage = underlying_storage
-        self.__cache = dict()
-        self.__cache_ids = Queue()
-        self.__max_cache_size = max_cache_size
-
-    def get(self, name: str) -> torch.Tensor:
-        cache_item = self.__get_cache(name)
-        if cache_item is not None:
-            return cache_item
-
-        latent = self.__underlying_storage.get(name)
-        self.__set_cache(name, latent)
-        return latent
-
-    def set(self, name: str, data: torch.Tensor) -> None:
-        self.__underlying_storage.set(name, data)
-        self.__set_cache(name, data)
-
-    def delete(self, name: str) -> None:
-        self.__underlying_storage.delete(name)
-        if name in self.__cache:
-            del self.__cache[name]
-
-    def __get_cache(self, name: str) -> torch.Tensor|None:
-        return None if name not in self.__cache else self.__cache[name]
-
-    def __set_cache(self, name: str, data: torch.Tensor):
-        if not name in self.__cache:
-            self.__cache[name] = data
-            self.__cache_ids.put(name)
-            if self.__cache_ids.qsize() > self.__max_cache_size:
-                self.__cache.pop(self.__cache_ids.get())
-
-
-class DiskLatentsStorage(LatentsStorageBase):
-    """Stores latents in a folder on disk without caching"""
-
-    __output_folder: str
-
-    def __init__(self, output_folder: str):
-        self.__output_folder = output_folder
-        Path(output_folder).mkdir(parents=True, exist_ok=True)
-
-    def get(self, name: str) -> torch.Tensor:
-        latent_path = self.get_path(name)
-        return torch.load(latent_path)
-
-    def set(self, name: str, data: torch.Tensor) -> None:
-        latent_path = self.get_path(name)
-        torch.save(data, latent_path)
-
-    def delete(self, name: str) -> None:
-        latent_path = self.get_path(name)
-        os.remove(latent_path)
-
-    def get_path(self, name: str) -> str:
-        return os.path.join(self.__output_folder, name)
-    

invokeai/app/services/processor.py

@@ -4,7 +4,7 @@ from threading import Event, Thread
 from ..invocations.baseinvocation import InvocationContext
 from .invocation_queue import InvocationQueueItem
 from .invoker import InvocationProcessorABC, Invoker
-from ..util.util import CanceledException
+
 
 class DefaultInvocationProcessor(InvocationProcessorABC):
     __invoker_thread: Thread
@@ -82,9 +82,6 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 except KeyboardInterrupt:
                     pass
 
-                except CanceledException:
-                    pass
-
                 except Exception as e:
                     error = traceback.format_exc()
 

invokeai/app/services/sqlite.py

@@ -59,7 +59,6 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
                 f"""INSERT OR REPLACE INTO {self._table_name} (item) VALUES (?);""",
                 (item.json(),),
             )
-            self._conn.commit()
         finally:
             self._lock.release()
         self._on_changed(item)
@@ -85,7 +84,6 @@ class SqliteItemStorage(ItemStorageABC, Generic[T]):
             self._cursor.execute(
                 f"""DELETE FROM {self._table_name} WHERE id = ?;""", (str(id),)
             )
-            self._conn.commit()
         finally:
             self._lock.release()
         self._on_deleted(id)

invokeai/app/util/save_thumbnail.py

@@ -1,25 +0,0 @@
-import os
-from PIL import Image
-
-
-def save_thumbnail(
-    image: Image.Image,
-    filename: str,
-    path: str,
-    size: int = 256,
-) -> str:
-    """
-    Saves a thumbnail of an image, returning its path.
-    """
-    base_filename = os.path.splitext(filename)[0]
-    thumbnail_path = os.path.join(path, base_filename + ".webp")
-
-    if os.path.exists(thumbnail_path):
-        return thumbnail_path
-
-    image_copy = image.copy()
-    image_copy.thumbnail(size=(size, size))
-
-    image_copy.save(thumbnail_path, "WEBP")
-
-    return thumbnail_path

invokeai/app/util/util.py

@@ -1,42 +0,0 @@
-import torch
-from PIL import Image
-from ..invocations.baseinvocation import InvocationContext
-from ...backend.util.util import image_to_dataURL
-from ...backend.generator.base import Generator
-from ...backend.stable_diffusion import PipelineIntermediateState
-
-class CanceledException(Exception):
-    pass
-
-def fast_latents_step_callback(sample: torch.Tensor, step: int, steps: int, id: str, context: InvocationContext, ):
-    # TODO: only output a preview image when requested
-    image = Generator.sample_to_lowres_estimated_image(sample)
-
-    (width, height) = image.size
-    width *= 8
-    height *= 8
-
-    dataURL = image_to_dataURL(image, image_format="JPEG")
-
-    context.services.events.emit_generator_progress(
-        context.graph_execution_state_id,
-        id,
-        {
-            "width": width,
-            "height": height,
-            "dataURL": dataURL
-        },
-        step,
-        steps,
-    )
-
-def diffusers_step_callback_adapter(*cb_args, **kwargs):
-    """
-    txt2img gives us a Tensor in the step_callbak, while img2img gives us a PipelineIntermediateState.
-    This adapter grabs the needed data and passes it along to the callback function.
-    """
-    if isinstance(cb_args[0], PipelineIntermediateState):
-        progress_state: PipelineIntermediateState = cb_args[0]
-        return fast_latents_step_callback(progress_state.latents, progress_state.step, **kwargs)
-    else:
-        return fast_latents_step_callback(*cb_args, **kwargs)

invokeai/backend/generator/base.py

@@ -21,7 +21,7 @@ from PIL import Image, ImageChops, ImageFilter
 from accelerate.utils import set_seed
 from diffusers import DiffusionPipeline
 from tqdm import trange
-from typing import Callable, List, Iterator, Optional, Type
+from typing import List, Iterator, Type
 from dataclasses import dataclass, field
 from diffusers.schedulers import SchedulerMixin as Scheduler
 
@@ -35,23 +35,23 @@ downsampling = 8
 
 @dataclass
 class InvokeAIGeneratorBasicParams:
-    seed: Optional[int]=None
+    seed: int=None
     width: int=512
     height: int=512
-    cfg_scale: float=7.5
+    cfg_scale: int=7.5
     steps: int=20
     ddim_eta: float=0.0
-    scheduler: str='ddim'
+    scheduler: int='ddim'
     precision: str='float16'
     perlin: float=0.0
-    threshold: float=0.0
+    threshold: int=0.0
     seamless: bool=False
     seamless_axes: List[str]=field(default_factory=lambda: ['x', 'y'])
-    h_symmetry_time_pct: Optional[float]=None
-    v_symmetry_time_pct: Optional[float]=None
+    h_symmetry_time_pct: float=None
+    v_symmetry_time_pct: float=None
     variation_amount: float = 0.0
     with_variations: list=field(default_factory=list)
-    safety_checker: Optional[SafetyChecker]=None
+    safety_checker: SafetyChecker=None
 
 @dataclass
 class InvokeAIGeneratorOutput:
@@ -61,10 +61,10 @@ class InvokeAIGeneratorOutput:
     and the model hash, as well as all the generate() parameters that went into
     generating the image (in .params, also available as attributes)
     '''
-    image: Image.Image
+    image: Image
     seed: int
     model_hash: str
-    attention_maps_images: List[Image.Image]
+    attention_maps_images: List[Image]
     params: Namespace
 
 # we are interposing a wrapper around the original Generator classes so that
@@ -92,8 +92,8 @@ class InvokeAIGenerator(metaclass=ABCMeta):
 
     def generate(self,
                  prompt: str='',
-                 callback: Optional[Callable]=None,
-                 step_callback: Optional[Callable]=None,
+                 callback: callable=None,
+                 step_callback: callable=None,
                  iterations: int=1,
                  **keyword_args,
                  )->Iterator[InvokeAIGeneratorOutput]:
@@ -154,7 +154,6 @@ class InvokeAIGenerator(metaclass=ABCMeta):
         for i in iteration_count:
             results = generator.generate(prompt,
                                          conditioning=(uc, c, extra_conditioning_info),
-                                         step_callback=step_callback,
                                          sampler=scheduler,
                                          **generator_args,
                                          )
@@ -206,10 +205,10 @@ class Txt2Img(InvokeAIGenerator):
 # ------------------------------------
 class Img2Img(InvokeAIGenerator):
     def generate(self,
-               init_image: Image.Image | torch.FloatTensor,
+               init_image: Image | torch.FloatTensor,
                strength: float=0.75,
                **keyword_args
-               )->Iterator[InvokeAIGeneratorOutput]:
+               )->List[InvokeAIGeneratorOutput]:
         return super().generate(init_image=init_image,
                                 strength=strength,
                                 **keyword_args
@@ -223,7 +222,7 @@ class Img2Img(InvokeAIGenerator):
 # Takes all the arguments of Img2Img and adds the mask image and the seam/infill stuff
 class Inpaint(Img2Img):
     def generate(self,
-                 mask_image: Image.Image | torch.FloatTensor,
+                 mask_image: Image | torch.FloatTensor,
                  # Seam settings - when 0, doesn't fill seam
                  seam_size: int = 0,
                  seam_blur: int = 0,
@@ -236,7 +235,7 @@ class Inpaint(Img2Img):
                  inpaint_height=None,
                  inpaint_fill: tuple(int) = (0x7F, 0x7F, 0x7F, 0xFF),
                  **keyword_args
-                 )->Iterator[InvokeAIGeneratorOutput]:
+                 )->List[InvokeAIGeneratorOutput]:
         return super().generate(
             mask_image=mask_image,
             seam_size=seam_size,
@@ -263,7 +262,7 @@ class Embiggen(Txt2Img):
             embiggen: list=None,
             embiggen_tiles: list = None,
             strength: float=0.75,
-            **kwargs)->Iterator[InvokeAIGeneratorOutput]:
+            **kwargs)->List[InvokeAIGeneratorOutput]:
         return super().generate(embiggen=embiggen,
                                 embiggen_tiles=embiggen_tiles,
                                 strength=strength,

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -372,32 +372,22 @@ def convert_ldm_unet_checkpoint(checkpoint, config, path=None, extract_ema=False
     unet_key = "model.diffusion_model."
     # at least a 100 parameters have to start with `model_ema` in order for the checkpoint to be EMA
     if sum(k.startswith("model_ema") for k in keys) > 100:
-        print(f"   | Checkpoint {path} has both EMA and non-EMA weights.")
+        print(f"  | Checkpoint {path} has both EMA and non-EMA weights.")
         if extract_ema:
-            print("   | Extracting EMA weights (usually better for inference)")
+            print("  | Extracting EMA weights (usually better for inference)")
             for key in keys:
                 if key.startswith("model.diffusion_model"):
                     flat_ema_key = "model_ema." + "".join(key.split(".")[1:])
-                    flat_ema_key_alt = "model_ema." + "".join(key.split(".")[2:])
-                    if flat_ema_key in checkpoint:
-                        unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
-                            flat_ema_key
-                        )
-                    elif flat_ema_key_alt in checkpoint:
-                        unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
-                            flat_ema_key_alt
-                        )
-                    else:
-                        unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
-                            key
-                        )
+                    unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(
+                        flat_ema_key
+                    )
         else:
             print(
-                "   | Extracting only the non-EMA weights (usually better for fine-tuning)"
+                "  | Extracting only the non-EMA weights (usually better for fine-tuning)"
             )
 
     for key in keys:
-        if key.startswith("model.diffusion_model") and key in checkpoint:
+        if key.startswith(unet_key):
             unet_state_dict[key.replace(unet_key, "")] = checkpoint.pop(key)
 
     new_checkpoint = {}
@@ -1036,15 +1026,6 @@ def convert_open_clip_checkpoint(checkpoint):
 
     return text_model
 
-def replace_checkpoint_vae(checkpoint, vae_path:str):
-    if vae_path.endswith(".safetensors"):
-        vae_ckpt = load_file(vae_path)
-    else:
-        vae_ckpt = torch.load(vae_path, map_location="cpu")
-    state_dict = vae_ckpt['state_dict'] if "state_dict" in vae_ckpt else vae_ckpt
-    for vae_key in state_dict:
-        new_key = f'first_stage_model.{vae_key}'
-        checkpoint[new_key] = state_dict[vae_key]
 
 def load_pipeline_from_original_stable_diffusion_ckpt(
     checkpoint_path: str,
@@ -1057,10 +1038,8 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     extract_ema: bool = True,
     upcast_attn: bool = False,
     vae: AutoencoderKL = None,
-    vae_path: str = None,
     precision: torch.dtype = torch.float32,
     return_generator_pipeline: bool = False,
-    scan_needed:bool=True,
 ) -> Union[StableDiffusionPipeline, StableDiffusionGeneratorPipeline]:
     """
     Load a Stable Diffusion pipeline object from a CompVis-style `.ckpt`/`.safetensors` file and (ideally) a `.yaml`
@@ -1088,8 +1067,6 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     :param precision: precision to use - torch.float16, torch.float32 or torch.autocast
     :param upcast_attention: Whether the attention computation should always be upcasted. This is necessary when
     running stable diffusion 2.1.
-    :param vae: A diffusers VAE to load into the pipeline.
-    :param vae_path: Path to a checkpoint VAE that will be converted into diffusers and loaded into the pipeline.
     """
 
     with warnings.catch_warnings():
@@ -1097,13 +1074,12 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         verbosity = dlogging.get_verbosity()
         dlogging.set_verbosity_error()
 
-        if Path(checkpoint_path).suffix == '.ckpt':
-            if scan_needed:
-                ModelManager.scan_model(checkpoint_path,checkpoint_path)
-            checkpoint = torch.load(checkpoint_path)
-        else:
-            checkpoint = load_file(checkpoint_path)
-
+        checkpoint = (
+            torch.load(checkpoint_path)
+            if Path(checkpoint_path).suffix == ".ckpt"
+            else load_file(checkpoint_path)
+            
+        )
         cache_dir = global_cache_dir("hub")
         pipeline_class = (
             StableDiffusionGeneratorPipeline
@@ -1115,7 +1091,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         if "global_step" in checkpoint:
             global_step = checkpoint["global_step"]
         else:
-            print("   | global_step key not found in model")
+            print("  | global_step key not found in model")
             global_step = None
 
         # sometimes there is a state_dict key and sometimes not
@@ -1226,19 +1202,9 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
         unet.load_state_dict(converted_unet_checkpoint)
 
-        # If a replacement VAE path was specified, we'll incorporate that into
-        # the checkpoint model and then convert it
-        if vae_path:
-            print(f"   | Converting VAE {vae_path}")
-            replace_checkpoint_vae(checkpoint,vae_path)
-        # otherwise we use the original VAE, provided that
-        # an externally loaded diffusers VAE was not passed
-        elif not vae:
-            print("   | Using checkpoint model's original VAE")
-
-        if vae:
-            print("   | Using replacement diffusers VAE")
-        else:  # convert the original or replacement VAE
+        # Convert the VAE model, or use the one passed
+        if not vae:
+            print("  | Using checkpoint model's original VAE")
             vae_config = create_vae_diffusers_config(
                 original_config, image_size=image_size
             )
@@ -1248,6 +1214,8 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
             vae = AutoencoderKL(**vae_config)
             vae.load_state_dict(converted_vae_checkpoint)
+        else:
+            print("  | Using external VAE specified in config")
 
         # Convert the text model.
         model_type = pipeline_type
@@ -1264,10 +1232,10 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
                 cache_dir=cache_dir,
             )
             pipe = pipeline_class(
-                vae=vae.to(precision),
-                text_encoder=text_model.to(precision),
+                vae=vae,
+                text_encoder=text_model,
                 tokenizer=tokenizer,
-                unet=unet.to(precision),
+                unet=unet,
                 scheduler=scheduler,
                 safety_checker=None,
                 feature_extractor=None,

invokeai/backend/model_management/model_manager.py

@@ -18,7 +18,7 @@ import warnings
 from enum import Enum
 from pathlib import Path
 from shutil import move, rmtree
-from typing import Any, Optional, Union, Callable
+from typing import Any, Optional, Union
 
 import safetensors
 import safetensors.torch
@@ -34,7 +34,7 @@ from picklescan.scanner import scan_file_path
 from invokeai.backend.globals import Globals, global_cache_dir
 
 from ..stable_diffusion import StableDiffusionGeneratorPipeline
-from ..util import CUDA_DEVICE, ask_user, download_with_resume
+from ..util import CUDA_DEVICE, CPU_DEVICE, ask_user, download_with_resume
 
 class SDLegacyType(Enum):
     V1 = 1
@@ -45,6 +45,9 @@ class SDLegacyType(Enum):
     UNKNOWN = 99
 
 DEFAULT_MAX_MODELS = 2
+VAE_TO_REPO_ID = {  # hack, see note in convert_and_import()
+    "vae-ft-mse-840000-ema-pruned": "stabilityai/sd-vae-ft-mse",
+}
 
 class ModelManager(object):
     '''
@@ -282,13 +285,13 @@ class ModelManager(object):
             self.stack.remove(model_name)
         if delete_files:
             if weights:
-                print(f"** Deleting file {weights}")
+                print(f"** deleting file {weights}")
                 Path(weights).unlink(missing_ok=True)
             elif path:
-                print(f"** Deleting directory {path}")
+                print(f"** deleting directory {path}")
                 rmtree(path, ignore_errors=True)
             elif repo_id:
-                print(f"** Deleting the cached model directory for {repo_id}")
+                print(f"** deleting the cached model directory for {repo_id}")
                 self._delete_model_from_cache(repo_id)
 
     def add_model(
@@ -359,7 +362,6 @@ class ModelManager(object):
             raise NotImplementedError(
                 f"Unknown model format {model_name}: {model_format}"
             )
-        self._add_embeddings_to_model(model)
         
         # usage statistics
         toc = time.time()
@@ -379,9 +381,9 @@ class ModelManager(object):
 
         print(f">> Loading diffusers model from {name_or_path}")
         if using_fp16:
-            print("   | Using faster float16 precision")
+            print("  | Using faster float16 precision")
         else:
-            print("   | Using more accurate float32 precision")
+            print("  | Using more accurate float32 precision")
 
         # TODO: scan weights maybe?
         pipeline_args: dict[str, Any] = dict(
@@ -432,8 +434,10 @@ class ModelManager(object):
         # square images???
         width = pipeline.unet.config.sample_size * pipeline.vae_scale_factor
         height = width
-        print(f"   | Default image dimensions = {width} x {height}")
-        
+
+        print(f"  | Default image dimensions = {width} x {height}")
+        self._add_embeddings_to_model(pipeline)
+
         return pipeline, width, height, model_hash
 
     def _load_ckpt_model(self, model_name, mconfig):
@@ -453,21 +457,15 @@ class ModelManager(object):
 
         from . import load_pipeline_from_original_stable_diffusion_ckpt
 
-        try:
-            if self.list_models()[self.current_model]['status'] == 'active':
-                self.offload_model(self.current_model)
-        except Exception as e:
-            pass
-        
-        vae_path = None
-        if vae:
-            vae_path = vae if os.path.isabs(vae) else os.path.normpath(os.path.join(Globals.root, vae))
+        self.offload_model(self.current_model)
+        if vae_config := self._choose_diffusers_vae(model_name):
+            vae = self._load_vae(vae_config)
         if self._has_cuda():
             torch.cuda.empty_cache()
         pipeline = load_pipeline_from_original_stable_diffusion_ckpt(
             checkpoint_path=weights,
             original_config_file=config,
-            vae_path=vae_path,
+            vae=vae,
             return_generator_pipeline=True,
             precision=torch.float16 if self.precision == "float16" else torch.float32,
         )
@@ -475,6 +473,7 @@ class ModelManager(object):
             pipeline.enable_offload_submodels(self.device)
         else:
             pipeline.to(self.device)
+
         return (
             pipeline,
             width,
@@ -513,20 +512,18 @@ class ModelManager(object):
         print(f">> Offloading {model_name} to CPU")
         model = self.models[model_name]["model"]
         model.offload_all()
-        self.current_model = None
 
         gc.collect()
         if self._has_cuda():
             torch.cuda.empty_cache()
 
-    @classmethod
     def scan_model(self, model_name, checkpoint):
         """
         Apply picklescanner to the indicated checkpoint and issue a warning
         and option to exit if an infected file is identified.
         """
         # scan model
-        print(f"   | Scanning Model: {model_name}")
+        print(f">> Scanning Model: {model_name}")
         scan_result = scan_file_path(checkpoint)
         if scan_result.infected_files != 0:
             if scan_result.infected_files == 1:
@@ -549,7 +546,7 @@ class ModelManager(object):
                     print("### Exiting InvokeAI")
                     sys.exit()
         else:
-            print("   | Model scanned ok")
+            print(">> Model scanned ok")
 
     def import_diffuser_model(
         self,
@@ -630,13 +627,14 @@ class ModelManager(object):
     def heuristic_import(
             self,
             path_url_or_repo: str,
+            convert: bool = True,
             model_name: str = None,
             description: str = None,
             model_config_file: Path = None,
             commit_to_conf: Path = None,
-            config_file_callback: Callable[[Path], Path] = None,
     ) -> str:
-        """Accept a string which could be:
+        """
+        Accept a string which could be:
            - a HF diffusers repo_id
            - a URL pointing to a legacy .ckpt or .safetensors file
            - a local path pointing to a legacy .ckpt or .safetensors file
@@ -650,20 +648,16 @@ class ModelManager(object):
         The model_name and/or description can be provided. If not, they will
         be generated automatically.
 
+        If convert is true, legacy models will be converted to diffusers
+        before importing.
+
         If commit_to_conf is provided, the newly loaded model will be written
         to the `models.yaml` file at the indicated path. Otherwise, the changes
         will only remain in memory.
 
-        The routine will do its best to figure out the config file
-        needed to convert legacy checkpoint file, but if it can't it
-        will call the config_file_callback routine, if provided. The
-        callback accepts a single argument, the Path to the checkpoint
-        file, and returns a Path to the config file to use.
-
-        The (potentially derived) name of the model is returned on
-        success, or None on failure. When multiple models are added
-        from a directory, only the last imported one is returned.
-
+        The (potentially derived) name of the model is returned on success, or None
+        on failure. When multiple models are added from a directory, only the last
+        imported one is returned.
         """
         model_path: Path = None
         thing = path_url_or_repo  # to save typing
@@ -671,7 +665,7 @@ class ModelManager(object):
         print(f">> Probing {thing} for import")
 
         if thing.startswith(("http:", "https:", "ftp:")):
-            print(f"   | {thing} appears to be a URL")
+            print(f"  | {thing} appears to be a URL")
             model_path = self._resolve_path(
                 thing, "models/ldm/stable-diffusion-v1"
             )  # _resolve_path does a download if needed
@@ -679,15 +673,15 @@ class ModelManager(object):
         elif Path(thing).is_file() and thing.endswith((".ckpt", ".safetensors")):
             if Path(thing).stem in ["model", "diffusion_pytorch_model"]:
                 print(
-                    f"   | {Path(thing).name} appears to be part of a diffusers model. Skipping import"
+                    f"  | {Path(thing).name} appears to be part of a diffusers model. Skipping import"
                 )
                 return
             else:
-                print(f"   | {thing} appears to be a checkpoint file on disk")
+                print(f"  | {thing} appears to be a checkpoint file on disk")
                 model_path = self._resolve_path(thing, "models/ldm/stable-diffusion-v1")
 
         elif Path(thing).is_dir() and Path(thing, "model_index.json").exists():
-            print(f"   | {thing} appears to be a diffusers file on disk")
+            print(f"  | {thing} appears to be a diffusers file on disk")
             model_name = self.import_diffuser_model(
                 thing,
                 vae=dict(repo_id="stabilityai/sd-vae-ft-mse"),
@@ -698,25 +692,25 @@ class ModelManager(object):
 
         elif Path(thing).is_dir():
             if (Path(thing) / "model_index.json").exists():
-                print(f"   | {thing} appears to be a diffusers model.")
+                print(f"  | {thing} appears to be a diffusers model.")
                 model_name = self.import_diffuser_model(
                     thing, commit_to_conf=commit_to_conf
                 )
             else:
                 print(
-                    f"   |{thing} appears to be a directory. Will scan for models to import"
+                    f"  |{thing} appears to be a directory. Will scan for models to import"
                 )
                 for m in list(Path(thing).rglob("*.ckpt")) + list(
                     Path(thing).rglob("*.safetensors")
                 ):
                     if model_name := self.heuristic_import(
-                        str(m), commit_to_conf=commit_to_conf
+                        str(m), convert, commit_to_conf=commit_to_conf
                     ):
                         print(f" >> {model_name} successfully imported")
                 return model_name
 
         elif re.match(r"^[\w.+-]+/[\w.+-]+$", thing):
-            print(f"   | {thing} appears to be a HuggingFace diffusers repo_id")
+            print(f"  | {thing} appears to be a HuggingFace diffusers repo_id")
             model_name = self.import_diffuser_model(
                 thing, commit_to_conf=commit_to_conf
             )
@@ -733,75 +727,55 @@ class ModelManager(object):
             return
 
         if model_path.stem in self.config:  # already imported
-            print("   | Already imported. Skipping")
+            print("  | Already imported. Skipping")
             return model_path.stem
 
         # another round of heuristics to guess the correct config file.
-        checkpoint = None
-        if model_path.suffix in [".ckpt",".pt"]:
-            self.scan_model(model_path,model_path)
-            checkpoint = torch.load(model_path)
-        else:
-            checkpoint = safetensors.torch.load_file(model_path)
+        checkpoint = (
+            torch.load(model_path)
+            if model_path.suffix == ".ckpt"
+            else safetensors.torch.load_file(model_path)
+        )
 
         # additional probing needed if no config file provided
         if model_config_file is None:
-            # look for a like-named .yaml file in same directory
-            if model_path.with_suffix(".yaml").exists():
-                model_config_file = model_path.with_suffix(".yaml")
-                print(f"   | Using config file {model_config_file.name}")
-
+            model_type = self.probe_model_type(checkpoint)
+            if model_type == SDLegacyType.V1:
+                print("  | SD-v1 model detected")
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v1-inference.yaml"
+                )
+            elif model_type == SDLegacyType.V1_INPAINT:
+                print("  | SD-v1 inpainting model detected")
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v1-inpainting-inference.yaml"
+                )
+            elif model_type == SDLegacyType.V2_v:
+                print(
+                    "  | SD-v2-v model detected; model will be converted to diffusers format"
+                )
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v2-inference-v.yaml"
+                )
+                convert = True
+            elif model_type == SDLegacyType.V2_e:
+                print(
+                    "  | SD-v2-e model detected; model will be converted to diffusers format"
+                )
+                model_config_file = Path(
+                    Globals.root, "configs/stable-diffusion/v2-inference.yaml"
+                )
+                convert = True
+            elif model_type == SDLegacyType.V2:
+                print(
+                    f"** {thing} is a V2 checkpoint file, but its parameterization cannot be determined. Please provide configuration file path."
+                )
+                return
             else:
-                model_type = self.probe_model_type(checkpoint)
-                if model_type == SDLegacyType.V1:
-                    print("   | SD-v1 model detected")
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v1-inference.yaml"
-                    )
-                elif model_type == SDLegacyType.V1_INPAINT:
-                    print("   | SD-v1 inpainting model detected")
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v1-inpainting-inference.yaml"
-                    )
-                elif model_type == SDLegacyType.V2_v:
-                    print(
-                        "   | SD-v2-v model detected"
-                    )
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v2-inference-v.yaml"
-                    )
-                elif model_type == SDLegacyType.V2_e:
-                    print(
-                        "   | SD-v2-e model detected"
-                    )
-                    model_config_file = Path(
-                        Globals.root, "configs/stable-diffusion/v2-inference.yaml"
-                    )
-                elif model_type == SDLegacyType.V2:
-                    print(
-                        f"** {thing} is a V2 checkpoint file, but its parameterization cannot be determined. Please provide configuration file path."
-                    )
-                    return
-                else:
-                    print(
-                        f"** {thing} is a legacy checkpoint file but not a known Stable Diffusion model. Please provide configuration file path."
-                    )
-                    return
-
-        if not model_config_file and config_file_callback:
-            model_config_file = config_file_callback(model_path)
-
-        # despite our best efforts, we could not find a model config file, so give up
-        if not model_config_file:
-            return
-
-        # look for a custom vae, a like-named file ending with .vae in the same directory
-        vae_path = None
-        for suffix in ["pt", "ckpt", "safetensors"]:
-            if (model_path.with_suffix(f".vae.{suffix}")).exists():
-                vae_path = model_path.with_suffix(f".vae.{suffix}")
-                print(f"   | Using VAE file {vae_path.name}")
-        vae = None if vae_path else dict(repo_id="stabilityai/sd-vae-ft-mse")
+                print(
+                    f"** {thing} is a legacy checkpoint file but not a known Stable Diffusion model. Please provide configuration file path."
+                )
+                return
 
         diffuser_path = Path(
             Globals.root, "models", Globals.converted_ckpts_dir, model_path.stem
@@ -809,27 +783,23 @@ class ModelManager(object):
         model_name = self.convert_and_import(
             model_path,
             diffusers_path=diffuser_path,
-            vae=vae,
-            vae_path=str(vae_path),
+            vae=dict(repo_id="stabilityai/sd-vae-ft-mse"),
             model_name=model_name,
             model_description=description,
             original_config_file=model_config_file,
             commit_to_conf=commit_to_conf,
-            scan_needed=False,
         )
         return model_name
 
     def convert_and_import(
-            self,
-            ckpt_path: Path,
-            diffusers_path: Path,
-            model_name=None,
-            model_description=None,
-            vae:dict=None,
-            vae_path:Path=None,
-            original_config_file: Path = None,
-            commit_to_conf: Path = None,
-            scan_needed: bool=True,
+        self,
+        ckpt_path: Path,
+        diffusers_path: Path,
+        model_name=None,
+        model_description=None,
+        vae=None,
+        original_config_file: Path = None,
+        commit_to_conf: Path = None,
     ) -> str:
         """
         Convert a legacy ckpt weights file to diffuser model and import
@@ -852,28 +822,23 @@ class ModelManager(object):
             return
 
         model_name = model_name or diffusers_path.name
-        model_description = model_description or f"Converted version of {model_name}"
-        print(f"   | Converting {model_name} to diffusers (30-60s)")
+        model_description = model_description or f"Optimized version of {model_name}"
+        print(f">> Optimizing {model_name} (30-60s)")
         try:
             # By passing the specified VAE to the conversion function, the autoencoder
             # will be built into the model rather than tacked on afterward via the config file
-            vae_model=None
-            if vae:
-                vae_model=self._load_vae(vae)
-                vae_path=None
+            vae_model = self._load_vae(vae) if vae else None
             convert_ckpt_to_diffusers(
                 ckpt_path,
                 diffusers_path,
                 extract_ema=True,
                 original_config_file=original_config_file,
                 vae=vae_model,
-                vae_path=vae_path,
-                scan_needed=scan_needed,
             )
             print(
-                f"   | Success. Converted model is now located at {str(diffusers_path)}"
+                f"  | Success. Optimized model is now located at {str(diffusers_path)}"
             )
-            print(f"   | Writing new config file entry for {model_name}")
+            print(f"  | Writing new config file entry for {model_name}")
             new_config = dict(
                 path=str(diffusers_path),
                 description=model_description,
@@ -884,7 +849,7 @@ class ModelManager(object):
             self.add_model(model_name, new_config, True)
             if commit_to_conf:
                 self.commit(commit_to_conf)
-            print("   | Conversion succeeded")
+            print(">> Conversion succeeded")
         except Exception as e:
             print(f"** Conversion failed: {str(e)}")
             print(
@@ -914,6 +879,36 @@ class ModelManager(object):
 
         return search_folder, found_models
 
+    def _choose_diffusers_vae(
+        self, model_name: str, vae: str = None
+    ) -> Union[dict, str]:
+        # In the event that the original entry is using a custom ckpt VAE, we try to
+        # map that VAE onto a diffuser VAE using a hard-coded dictionary.
+        # I would prefer to do this differently: We load the ckpt model into memory, swap the
+        # VAE in memory, and then pass that to convert_ckpt_to_diffuser() so that the swapped
+        # VAE is built into the model. However, when I tried this I got obscure key errors.
+        if vae:
+            return vae
+        if model_name in self.config and (
+            vae_ckpt_path := self.model_info(model_name).get("vae", None)
+        ):
+            vae_basename = Path(vae_ckpt_path).stem
+            diffusers_vae = None
+            if diffusers_vae := VAE_TO_REPO_ID.get(vae_basename, None):
+                print(
+                    f">> {vae_basename} VAE corresponds to known {diffusers_vae} diffusers version"
+                )
+                vae = {"repo_id": diffusers_vae}
+            else:
+                print(
+                    f'** Custom VAE "{vae_basename}" found, but corresponding diffusers model unknown'
+                )
+                print(
+                    '** Using "stabilityai/sd-vae-ft-mse"; If this isn\'t right, please edit the model config'
+                )
+                vae = {"repo_id": "stabilityai/sd-vae-ft-mse"}
+        return vae
+
     def _make_cache_room(self) -> None:
         num_loaded_models = len(self.models)
         if num_loaded_models >= self.max_loaded_models:
@@ -1110,7 +1105,7 @@ class ModelManager(object):
             with open(hashpath) as f:
                 hash = f.read()
             return hash
-        print("   | Calculating sha256 hash of model files")
+        print("  | Calculating sha256 hash of model files")
         tic = time.time()
         sha = hashlib.sha256()
         count = 0
@@ -1122,7 +1117,7 @@ class ModelManager(object):
                         sha.update(chunk)
         hash = sha.hexdigest()
         toc = time.time()
-        print(f"   | sha256 = {hash} ({count} files hashed in", "%4.2fs)" % (toc - tic))
+        print(f"  | sha256 = {hash} ({count} files hashed in", "%4.2fs)" % (toc - tic))
         with open(hashpath, "w") as f:
             f.write(hash)
         return hash
@@ -1167,12 +1162,12 @@ class ModelManager(object):
             local_files_only=not Globals.internet_available,
         )
 
-        print(f"   | Loading diffusers VAE from {name_or_path}")
+        print(f"  | Loading diffusers VAE from {name_or_path}")
         if using_fp16:
             vae_args.update(torch_dtype=torch.float16)
             fp_args_list = [{"revision": "fp16"}, {}]
         else:
-            print("   | Using more accurate float32 precision")
+            print("  | Using more accurate float32 precision")
             fp_args_list = [{}]
 
         vae = None
@@ -1213,7 +1208,7 @@ class ModelManager(object):
                     hashes_to_delete.add(revision.commit_hash)
         strategy = cache_info.delete_revisions(*hashes_to_delete)
         print(
-            f"** Deletion of this model is expected to free {strategy.expected_freed_size_str}"
+            f"** deletion of this model is expected to free {strategy.expected_freed_size_str}"
         )
         strategy.execute()
 

invokeai/backend/stable_diffusion/concepts_lib.py

@@ -6,6 +6,7 @@ The interface is through the Concepts() object.
 """
 import os
 import re
+import traceback
 from typing import Callable
 from urllib import error as ul_error
 from urllib import request
@@ -14,6 +15,7 @@ from huggingface_hub import (
     HfApi,
     HfFolder,
     ModelFilter,
+    ModelSearchArguments,
     hf_hub_url,
 )
 
@@ -82,7 +84,7 @@ class HuggingFaceConceptsLibrary(object):
         """
         if not concept_name in self.list_concepts():
             print(
-                f"{concept_name} is not a local embedding trigger, nor is it a HuggingFace concept. Generation will continue without the concept."
+                f"This concept is not a local embedding trigger, nor is it a HuggingFace concept. Generation will continue without the concept."
             )
             return None
         return self.get_concept_file(concept_name.lower(), "learned_embeds.bin")
@@ -234,7 +236,7 @@ class HuggingFaceConceptsLibrary(object):
         except ul_error.HTTPError as e:
             if e.code == 404:
                 print(
-                    f"Concept {concept_name} is not known to the Hugging Face library. Generation will continue without the concept."
+                    f"This concept is not known to the Hugging Face library. Generation will continue without the concept."
                 )
             else:
                 print(
@@ -244,7 +246,7 @@ class HuggingFaceConceptsLibrary(object):
             return False
         except ul_error.URLError as e:
             print(
-                f"ERROR while downloading {concept_name}: {str(e)}. This may reflect a network issue. Generation will continue without the concept."
+                f"ERROR: {str(e)}. This may reflect a network issue. Generation will continue without the concept."
             )
             os.rmdir(dest)
             return False

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -531,8 +531,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         run_id: str = None,
         additional_guidance: List[Callable] = None,
     ):
-        # FIXME: do we still use any slicing now that PyTorch 2.0 has scaled dot-product attention on all platforms?
-        #   self._adjust_memory_efficient_attention(latents)
+        self._adjust_memory_efficient_attention(latents)
         if run_id is None:
             run_id = secrets.token_urlsafe(self.ID_LENGTH)
         if additional_guidance is None:

invokeai/backend/stable_diffusion/textual_inversion_manager.py

@@ -1,26 +1,16 @@
+import os
 import traceback
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Optional, Union, List
+from typing import Optional, Union
 
-import safetensors.torch
 import torch
-
 from compel.embeddings_provider import BaseTextualInversionManager
 from picklescan.scanner import scan_file_path
 from transformers import CLIPTextModel, CLIPTokenizer
 
 from .concepts_lib import HuggingFaceConceptsLibrary
 
-@dataclass
-class EmbeddingInfo:
-    name: str
-    embedding: torch.Tensor
-    num_vectors_per_token: int
-    token_dim: int 
-    trained_steps: int = None
-    trained_model_name: str = None
-    trained_model_checksum: str = None
 
 @dataclass
 class TextualInversion:
@@ -82,46 +72,66 @@ class TextualInversionManager(BaseTextualInversionManager):
         if str(ckpt_path).endswith(".DS_Store"):
             return
 
-        embedding_list = self._parse_embedding(str(ckpt_path))
-        for embedding_info in embedding_list:
-            if (self.text_encoder.get_input_embeddings().weight.data[0].shape[0] != embedding_info.token_dim):
+        try:
+            scan_result = scan_file_path(str(ckpt_path))
+            if scan_result.infected_files == 1:
                 print(
-                    f"   ** Notice: {ckpt_path.parents[0].name}/{ckpt_path.name} was trained on a model with an incompatible token dimension: {self.text_encoder.get_input_embeddings().weight.data[0].shape[0]} vs {embedding_info.token_dim}."
+                    f"\n### Security Issues Found in Model: {scan_result.issues_count}"
                 )
-                continue
-
-            # Resolve the situation in which an earlier embedding has claimed the same
-            # trigger string. We replace the trigger with '<source_file>', as we used to.
-            trigger_str = embedding_info.name
-            sourcefile = (
-                f"{ckpt_path.parent.name}/{ckpt_path.name}"
-                if ckpt_path.name == "learned_embeds.bin"
-                else ckpt_path.name
+                print("### For your safety, InvokeAI will not load this embed.")
+                return
+        except Exception:
+            print(
+                f"### {ckpt_path.parents[0].name}/{ckpt_path.name} is damaged or corrupt."
             )
+            return
 
-            if trigger_str in self.trigger_to_sourcefile:
-                replacement_trigger_str = (
-                    f"<{ckpt_path.parent.name}>"
-                    if ckpt_path.name == "learned_embeds.bin"
-                    else f"<{ckpt_path.stem}>"
-                )
-                print(
-                    f">> {sourcefile}: Trigger token '{trigger_str}' is already claimed by '{self.trigger_to_sourcefile[trigger_str]}'. Trigger this concept with {replacement_trigger_str}"
-                )
-                trigger_str = replacement_trigger_str
+        embedding_info = self._parse_embedding(str(ckpt_path))
 
-            try:
-                self._add_textual_inversion(
-                    trigger_str,
-                    embedding_info.embedding,
-                    defer_injecting_tokens=defer_injecting_tokens,
-                )
-                # remember which source file claims this trigger
-                self.trigger_to_sourcefile[trigger_str] = sourcefile
+        if embedding_info is None:
+            # We've already put out an error message about the bad embedding in _parse_embedding, so just return.
+            return
+        elif (
+            self.text_encoder.get_input_embeddings().weight.data[0].shape[0]
+            != embedding_info["token_dim"]
+        ):
+            print(
+                f"** Notice: {ckpt_path.parents[0].name}/{ckpt_path.name} was trained on a model with an incompatible token dimension: {self.text_encoder.get_input_embeddings().weight.data[0].shape[0]} vs {embedding_info['token_dim']}."
+            )
+            return
 
-            except ValueError as e:
-                print(f'   | Ignoring incompatible embedding {embedding_info["name"]}')
-                print(f"   | The error was {str(e)}")
+        # Resolve the situation in which an earlier embedding has claimed the same
+        # trigger string. We replace the trigger with '<source_file>', as we used to.
+        trigger_str = embedding_info["name"]
+        sourcefile = (
+            f"{ckpt_path.parent.name}/{ckpt_path.name}"
+            if ckpt_path.name == "learned_embeds.bin"
+            else ckpt_path.name
+        )
+
+        if trigger_str in self.trigger_to_sourcefile:
+            replacement_trigger_str = (
+                f"<{ckpt_path.parent.name}>"
+                if ckpt_path.name == "learned_embeds.bin"
+                else f"<{ckpt_path.stem}>"
+            )
+            print(
+                f">> {sourcefile}: Trigger token '{trigger_str}' is already claimed by '{self.trigger_to_sourcefile[trigger_str]}'. Trigger this concept with {replacement_trigger_str}"
+            )
+            trigger_str = replacement_trigger_str
+
+        try:
+            self._add_textual_inversion(
+                trigger_str,
+                embedding_info["embedding"],
+                defer_injecting_tokens=defer_injecting_tokens,
+            )
+            # remember which source file claims this trigger
+            self.trigger_to_sourcefile[trigger_str] = sourcefile
+
+        except ValueError as e:
+            print(f'   | Ignoring incompatible embedding {embedding_info["name"]}')
+            print(f"   | The error was {str(e)}")
 
     def _add_textual_inversion(
         self, trigger_str, embedding, defer_injecting_tokens=False
@@ -299,130 +309,111 @@ class TextualInversionManager(BaseTextualInversionManager):
 
         return token_id
 
-
-    def _parse_embedding(self, embedding_file: str)->List[EmbeddingInfo]:
-        suffix = Path(embedding_file).suffix
-        try:
-            if suffix in [".pt",".ckpt",".bin"]:
-                scan_result = scan_file_path(embedding_file)
-                if scan_result.infected_files > 0:
-                    print(
-                        f"   ** Security Issues Found in Model: {scan_result.issues_count}"
-                    )
-                    print("   ** For your safety, InvokeAI will not load this embed.")
-                    return list()
-                ckpt = torch.load(embedding_file,map_location="cpu")
-            else:
-                ckpt = safetensors.torch.load_file(embedding_file)
-        except Exception as e:
-            print(f"   ** Notice: unrecognized embedding file format: {embedding_file}: {e}")
-            return list()
-        
-        # try to figure out what kind of embedding file it is and parse accordingly
-        keys = list(ckpt.keys())
-        if all(x in keys for x in ['string_to_token','string_to_param','name','step']):
-            return self._parse_embedding_v1(ckpt, embedding_file)     # example rem_rezero.pt
-        
-        elif all(x in keys for x in ['string_to_token','string_to_param']):
-            return self._parse_embedding_v2(ckpt, embedding_file)     # example midj-strong.pt
-        
-        elif 'emb_params' in keys:
-            return self._parse_embedding_v3(ckpt, embedding_file)     # example easynegative.safetensors
-        
+    def _parse_embedding(self, embedding_file: str):
+        file_type = embedding_file.split(".")[-1]
+        if file_type == "pt":
+            return self._parse_embedding_pt(embedding_file)
+        elif file_type == "bin":
+            return self._parse_embedding_bin(embedding_file)
         else:
-            return self._parse_embedding_v4(ckpt, embedding_file)     # usually a '.bin' file
+            print(f"** Notice: unrecognized embedding file format: {embedding_file}")
+            return None
 
-    def _parse_embedding_v1(self, embedding_ckpt: dict, file_path: str)->List[EmbeddingInfo]:
-        basename = Path(file_path).stem
-        print(f'   | Loading v1 embedding file: {basename}')
+    def _parse_embedding_pt(self, embedding_file):
+        embedding_ckpt = torch.load(embedding_file, map_location="cpu")
+        embedding_info = {}
 
-        embeddings = list()
-        token_counter = -1
-        for token,embedding in embedding_ckpt["string_to_param"].items():
-            if token_counter < 0:
-                trigger = embedding_ckpt["name"]
-            elif token_counter == 0:
-                trigger = f'<basename>'
-            else:
-                trigger = f'<{basename}-{int(token_counter:=token_counter)}>'
-            token_counter += 1
-            embedding_info = EmbeddingInfo(
-                name = trigger,
-                embedding = embedding,
-                num_vectors_per_token = embedding.size()[0],
-                token_dim = embedding.size()[1],
-                trained_steps = embedding_ckpt["step"],
-                trained_model_name = embedding_ckpt["sd_checkpoint_name"],
-                trained_model_checksum = embedding_ckpt["sd_checkpoint"]
-            )
-            embeddings.append(embedding_info)
-        return embeddings
+        # Check if valid embedding file
+        if "string_to_token" and "string_to_param" in embedding_ckpt:
+            # Catch variants that do not have the expected keys or values.
+            try:
+                embedding_info["name"] = embedding_ckpt["name"] or os.path.basename(
+                    os.path.splitext(embedding_file)[0]
+                )
 
-    def _parse_embedding_v2 (
-        self, embedding_ckpt: dict, file_path: str
-    ) -> List[EmbeddingInfo]:
+                # Check num of embeddings and warn user only the first will be used
+                embedding_info["num_of_embeddings"] = len(
+                    embedding_ckpt["string_to_token"]
+                )
+                if embedding_info["num_of_embeddings"] > 1:
+                    print(">> More than 1 embedding found. Will use the first one")
+
+                embedding = list(embedding_ckpt["string_to_param"].values())[0]
+            except (AttributeError, KeyError):
+                return self._handle_broken_pt_variants(embedding_ckpt, embedding_file)
+
+            embedding_info["embedding"] = embedding
+            embedding_info["num_vectors_per_token"] = embedding.size()[0]
+            embedding_info["token_dim"] = embedding.size()[1]
+
+            try:
+                embedding_info["trained_steps"] = embedding_ckpt["step"]
+                embedding_info["trained_model_name"] = embedding_ckpt[
+                    "sd_checkpoint_name"
+                ]
+                embedding_info["trained_model_checksum"] = embedding_ckpt[
+                    "sd_checkpoint"
+                ]
+            except AttributeError:
+                print(">> No Training Details Found. Passing ...")
+
+        # .pt files found at https://cyberes.github.io/stable-diffusion-textual-inversion-models/
+        # They are actually .bin files
+        elif len(embedding_ckpt.keys()) == 1:
+            embedding_info = self._parse_embedding_bin(embedding_file)
+
+        else:
+            print(">> Invalid embedding format")
+            embedding_info = None
+
+        return embedding_info
+
+    def _parse_embedding_bin(self, embedding_file):
+        embedding_ckpt = torch.load(embedding_file, map_location="cpu")
+        embedding_info = {}
+
+        if list(embedding_ckpt.keys()) == 0:
+            print(">> Invalid concepts file")
+            embedding_info = None
+        else:
+            for token in list(embedding_ckpt.keys()):
+                embedding_info["name"] = (
+                    token
+                    or f"<{os.path.basename(os.path.splitext(embedding_file)[0])}>"
+                )
+                embedding_info["embedding"] = embedding_ckpt[token]
+                embedding_info[
+                    "num_vectors_per_token"
+                ] = 1  # All Concepts seem to default to 1
+                embedding_info["token_dim"] = embedding_info["embedding"].size()[0]
+
+        return embedding_info
+
+    def _handle_broken_pt_variants(
+        self, embedding_ckpt: dict, embedding_file: str
+    ) -> dict:
         """
-        This handles embedding .pt file variant #2.
+        This handles the broken .pt file variants. We only know of one at present.
         """
-        basename = Path(file_path).stem
-        print(f'   | Loading v2 embedding file: {basename}')
-        embeddings = list()
-        
+        embedding_info = {}
         if isinstance(
             list(embedding_ckpt["string_to_token"].values())[0], torch.Tensor
         ):
-            token_counter = 0
-            for token,embedding in embedding_ckpt["string_to_param"].items():
-                trigger = token if token != '*' \
-                    else f'<{basename}>' if token_counter == 0 \
-                         else f'<{basename}-{int(token_counter:=token_counter+1)}>'
-                embedding_info = EmbeddingInfo(
-                    name = trigger,
-                    embedding = embedding,
-                    num_vectors_per_token = embedding.size()[0],
-                    token_dim = embedding.size()[1],
+            for token in list(embedding_ckpt["string_to_token"].keys()):
+                embedding_info["name"] = (
+                    token
+                    if token != "*"
+                    else f"<{os.path.basename(os.path.splitext(embedding_file)[0])}>"
                 )
-                embeddings.append(embedding_info)
+                embedding_info["embedding"] = embedding_ckpt[
+                    "string_to_param"
+                ].state_dict()[token]
+                embedding_info["num_vectors_per_token"] = embedding_info[
+                    "embedding"
+                ].shape[0]
+                embedding_info["token_dim"] = embedding_info["embedding"].size()[1]
         else:
-            print(f"   ** {basename}: Unrecognized embedding format")
+            print(">> Invalid embedding format")
+            embedding_info = None
 
-        return embeddings
-
-    def _parse_embedding_v3(self, embedding_ckpt: dict, file_path: str)->List[EmbeddingInfo]:
-        """
-        Parse 'version 3' of the .pt textual inversion embedding files.
-        """
-        basename = Path(file_path).stem
-        print(f'   | Loading v3 embedding file: {basename}')
-        embedding = embedding_ckpt['emb_params']
-        embedding_info = EmbeddingInfo(
-            name = f'<{basename}>',
-            embedding = embedding,
-            num_vectors_per_token = embedding.size()[0],
-            token_dim = embedding.size()[1],
-        )
-        return [embedding_info]
-    
-    def _parse_embedding_v4(self, embedding_ckpt: dict, filepath: str)->List[EmbeddingInfo]:
-        """
-        Parse 'version 4' of the textual inversion embedding files. This one
-        is usually associated with .bin files trained by HuggingFace diffusers.
-        """
-        basename = Path(filepath).stem
-        short_path = Path(filepath).parents[0].name+'/'+Path(filepath).name
-        
-        print(f'   | Loading v4 embedding file: {short_path}')
-        
-        embeddings = list()
-        if list(embedding_ckpt.keys()) == 0:
-            print(f"   ** Invalid embeddings file: {short_path}")
-        else:
-            for token,embedding in embedding_ckpt.items():
-                embedding_info = EmbeddingInfo(
-                    name = token or f"<{basename}>",
-                    embedding = embedding,
-                    num_vectors_per_token = 1,  # All Concepts seem to default to 1
-                    token_dim = embedding.size()[0],
-                )
-                embeddings.append(embedding_info)
-        return embeddings
+        return embedding_info

invokeai/backend/web/invoke_ai_web_server.py

@@ -1022,7 +1022,7 @@ class InvokeAIWebServer:
                     "RGB"
                 )
 
-            def image_progress(intermediate_state: PipelineIntermediateState):
+            def image_progress(sample, step):
                 if self.canceled.is_set():
                     raise CanceledException
 
@@ -1030,14 +1030,6 @@ class InvokeAIWebServer:
                 nonlocal generation_parameters
                 nonlocal progress
 
-                step = intermediate_state.step
-                if intermediate_state.predicted_original is not None:
-                    # Some schedulers report not only the noisy latents at the current timestep,
-                    # but also their estimate so far of what the de-noised latents will be.
-                    sample = intermediate_state.predicted_original
-                else:
-                    sample = intermediate_state.latents
-
                 generation_messages = {
                     "txt2img": "common.statusGeneratingTextToImage",
                     "img2img": "common.statusGeneratingImageToImage",
@@ -1310,9 +1302,16 @@ class InvokeAIWebServer:
 
                 progress.set_current_iteration(progress.current_iteration + 1)
 
+            def diffusers_step_callback_adapter(*cb_args, **kwargs):
+                if isinstance(cb_args[0], PipelineIntermediateState):
+                    progress_state: PipelineIntermediateState = cb_args[0]
+                    return image_progress(progress_state.latents, progress_state.step)
+                else:
+                    return image_progress(*cb_args, **kwargs)
+
             self.generate.prompt2image(
                 **generation_parameters,
-                step_callback=image_progress,
+                step_callback=diffusers_step_callback_adapter,
                 image_callback=image_done,
             )
 

invokeai/frontend/CLI/CLI.py

@@ -626,7 +626,7 @@ def set_default_output_dir(opt: Args, completer: Completer):
     completer.set_default_dir(opt.outdir)
 
 
-def import_model(model_path: str, gen, opt, completer):
+def import_model(model_path: str, gen, opt, completer, convert=False):
     """
     model_path can be (1) a URL to a .ckpt file; (2) a local .ckpt file path;
     (3) a huggingface repository id; or (4) a local directory containing a
@@ -657,6 +657,7 @@ def import_model(model_path: str, gen, opt, completer):
         model_path,
         model_name=model_name,
         description=model_desc,
+        convert=convert,
     )
 
     if not imported_name:
@@ -665,6 +666,7 @@ def import_model(model_path: str, gen, opt, completer):
                 model_path,
                 model_name=model_name,
                 description=model_desc,
+                convert=convert,
                 model_config_file=config_file,
             )
     if not imported_name:
@@ -755,6 +757,7 @@ def _get_model_name_and_desc(
     )
     return model_name, model_description
 
+
 def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
     model_name_or_path = model_name_or_path.replace("\\", "/")  # windows
     manager = gen.model_manager
@@ -769,10 +772,16 @@ def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
             original_config_file = Path(model_info["config"])
             model_name = model_name_or_path
             model_description = model_info["description"]
-            vae_path = model_info.get("vae")
+            vae = model_info["vae"]
         else:
             print(f"** {model_name_or_path} is not a legacy .ckpt weights file")
             return
+        if vae_repo := invokeai.backend.model_management.model_manager.VAE_TO_REPO_ID.get(
+            Path(vae).stem
+        ):
+            vae_repo = dict(repo_id=vae_repo)
+        else:
+            vae_repo = None
         model_name = manager.convert_and_import(
             ckpt_path,
             diffusers_path=Path(
@@ -781,11 +790,11 @@ def convert_model(model_name_or_path: Union[Path, str], gen, opt, completer):
             model_name=model_name,
             model_description=model_description,
             original_config_file=original_config_file,
-            vae_path=vae_path,
+            vae=vae_repo,
         )
     else:
         try:
-            import_model(model_name_or_path, gen, opt, completer)
+            import_model(model_name_or_path, gen, opt, completer, convert=True)
         except KeyboardInterrupt:
             return
 

invokeai/frontend/web/dist/assets/ThemeLocaleProvider-51f66919.js

@@ -1,4 +1,4 @@
-import{j as y,cN as Ie,r as _,cO as bt,q as Lr,cP as o,cQ as b,cR as v,cS as S,cT as Vr,cU as ut,cV as vt,cM as ft,cW as mt,n as gt,cX as ht,E as pt}from"./index-f7f41e1f.js";import{d as yt,i as St,T as xt,j as $t,h as kt}from"./storeHooks-eaf47ae3.js";var Or=`
+import{j as y,cN as Ie,r as _,cO as bt,q as Lr,cP as o,cQ as b,cR as v,cS as S,cT as Vr,cU as ut,cV as vt,cM as ft,cW as mt,n as gt,cX as ht,E as pt}from"./index-d64f4654.js";import{d as yt,i as St,T as xt,j as $t,h as kt}from"./storeHooks-0eed8e9f.js";var Or=`
   :root {
     --chakra-vh: 100vh;
   }

invokeai/frontend/web/dist/index.html

@@ -12,7 +12,7 @@
         margin: 0;
       }
     </style>
-    <script type="module" crossorigin src="./assets/index-f7f41e1f.js"></script>
+    <script type="module" crossorigin src="./assets/index-d64f4654.js"></script>
     <link rel="stylesheet" href="./assets/index-5483945c.css">
   </head>
 

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

@@ -64,8 +64,6 @@
         "trainingDesc2": "InvokeAI already supports training custom embeddings using Textual Inversion using the main script.",
         "upload": "Upload",
         "close": "Close",
-        "cancel": "Cancel",
-        "accept": "Accept",
         "load": "Load",
         "back": "Back",
         "statusConnected": "Connected",
@@ -335,7 +333,6 @@
         "addNewModel": "Add New Model",
         "addCheckpointModel": "Add Checkpoint / Safetensor Model",
         "addDiffuserModel": "Add Diffusers",
-        "scanForModels": "Scan For Models",
         "addManually": "Add Manually",
         "manual": "Manual",
         "name": "Name",

invokeai/frontend/web/index.d.ts

@@ -1,6 +1,4 @@
 import React, { PropsWithChildren } from 'react';
-import { IAIPopoverProps } from '../web/src/common/components/IAIPopover';
-import { IAIIconButtonProps } from '../web/src/common/components/IAIIconButton';
 
 export {};
 
@@ -52,27 +50,9 @@ declare module '@invoke-ai/invoke-ai-ui' {
   declare class InvokeAiLogoComponent extends React.Component<InvokeAILogoComponentProps> {
     public constructor(props: InvokeAILogoComponentProps);
   }
-
-  declare class IAIPopover extends React.Component<IAIPopoverProps> {
-    public constructor(props: IAIPopoverProps);
-  }
-
-  declare class IAIIconButton extends React.Component<IAIIconButtonProps> {
-    public constructor(props: IAIIconButtonProps);
-  }
-
-  declare class SettingsModal extends React.Component<SettingsModalProps> {
-    public constructor(props: SettingsModalProps);
-  }
 }
 
 declare function Invoke(props: PropsWithChildren): JSX.Element;
 
-export {
-  ThemeChanger,
-  InvokeAiLogoComponent,
-  IAIPopover,
-  IAIIconButton,
-  SettingsModal,
-};
+export { ThemeChanger, InvokeAiLogoComponent };
 export = Invoke;

invokeai/frontend/web/package.json

@@ -6,6 +6,7 @@
     "prepare": "cd ../../../ && husky install invokeai/frontend/web/.husky",
     "dev": "concurrently \"vite dev\" \"yarn run theme:watch\"",
     "build": "yarn run lint && vite build",
+    "build:package": "vite build --mode=package",
     "preview": "vite preview",
     "lint:madge": "madge --circular src/main.tsx",
     "lint:eslint": "eslint --max-warnings=0 .",

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

@@ -8,6 +8,7 @@
         "darkTheme": "داكن",
         "lightTheme": "فاتح",
         "greenTheme": "أخضر",
+        "text2img": "نص إلى صورة",
         "img2img": "صورة إلى صورة",
         "unifiedCanvas": "لوحة موحدة",
         "nodes": "عقد",

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

@@ -7,6 +7,7 @@
         "darkTheme": "Dunkel",
         "lightTheme": "Hell",
         "greenTheme": "Grün",
+        "text2img": "Text zu Bild",
         "img2img": "Bild zu Bild",
         "nodes": "Knoten",
         "langGerman": "Deutsch",

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

@@ -64,8 +64,6 @@
         "trainingDesc2": "InvokeAI already supports training custom embeddings using Textual Inversion using the main script.",
         "upload": "Upload",
         "close": "Close",
-        "cancel": "Cancel",
-        "accept": "Accept",
         "load": "Load",
         "back": "Back",
         "statusConnected": "Connected",
@@ -335,7 +333,6 @@
         "addNewModel": "Add New Model",
         "addCheckpointModel": "Add Checkpoint / Safetensor Model",
         "addDiffuserModel": "Add Diffusers",
-        "scanForModels": "Scan For Models",
         "addManually": "Add Manually",
         "manual": "Manual",
         "name": "Name",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Oscuro",
         "lightTheme": "Claro",
         "greenTheme": "Verde",
+        "text2img": "Texto a Imagen",
         "img2img": "Imagen a Imagen",
         "unifiedCanvas": "Lienzo Unificado",
         "nodes": "Nodos",
@@ -69,11 +70,7 @@
         "langHebrew": "Hebreo",
         "pinOptionsPanel": "Pin del panel de opciones",
         "loading": "Cargando",
-        "loadingInvokeAI": "Cargando invocar a la IA",
-        "postprocessing": "Tratamiento posterior",
-        "txt2img": "De texto a imagen",
-        "accept": "Aceptar",
-        "cancel": "Cancelar"
+        "loadingInvokeAI": "Cargando invocar a la IA"
     },
     "gallery": {
         "generations": "Generaciones",
@@ -407,8 +404,7 @@
         "none": "ninguno",
         "pickModelType": "Elige el tipo de modelo",
         "v2_768": "v2 (768px)",
-        "addDifference": "Añadir una diferencia",
-        "scanForModels": "Buscar modelos"
+        "addDifference": "Añadir una diferencia"
     },
     "parameters": {
         "images": "Imágenes",
@@ -578,7 +574,7 @@
         "autoSaveToGallery": "Guardar automáticamente en galería",
         "saveBoxRegionOnly": "Guardar solo región dentro de la caja",
         "limitStrokesToBox": "Limitar trazos a la caja",
-        "showCanvasDebugInfo": "Mostrar la información adicional del lienzo",
+        "showCanvasDebugInfo": "Mostrar información de depuración de lienzo",
         "clearCanvasHistory": "Limpiar historial de lienzo",
         "clearHistory": "Limpiar historial",
         "clearCanvasHistoryMessage": "Limpiar el historial de lienzo también restablece completamente el lienzo unificado. Esto incluye todo el historial de deshacer/rehacer, las imágenes en el área de preparación y la capa base del lienzo.",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Sombre",
         "lightTheme": "Clair",
         "greenTheme": "Vert",
+        "text2img": "Texte en image",
         "img2img": "Image en image",
         "unifiedCanvas": "Canvas unifié",
         "nodes": "Nœuds",
@@ -46,19 +47,7 @@
         "statusLoadingModel": "Chargement du modèle",
         "statusModelChanged": "Modèle changé",
         "discordLabel": "Discord",
-        "githubLabel": "Github",
-        "accept": "Accepter",
-        "statusMergingModels": "Mélange des modèles",
-        "loadingInvokeAI": "Chargement de Invoke AI",
-        "cancel": "Annuler",
-        "langEnglish": "Anglais",
-        "statusConvertingModel": "Conversion du modèle",
-        "statusModelConverted": "Modèle converti",
-        "loading": "Chargement",
-        "pinOptionsPanel": "Épingler la page d'options",
-        "statusMergedModels": "Modèles mélangés",
-        "txt2img": "Texte vers image",
-        "postprocessing": "Post-Traitement"
+        "githubLabel": "Github"
     },
     "gallery": {
         "generations": "Générations",
@@ -529,15 +518,5 @@
         "betaDarkenOutside": "Assombrir à l'extérieur",
         "betaLimitToBox": "Limiter à la boîte",
         "betaPreserveMasked": "Conserver masqué"
-    },
-    "accessibility": {
-        "uploadImage": "Charger une image",
-        "reset": "Réinitialiser",
-        "nextImage": "Image suivante",
-        "previousImage": "Image précédente",
-        "useThisParameter": "Utiliser ce paramètre",
-        "zoomIn": "Zoom avant",
-        "zoomOut": "Zoom arrière",
-        "showOptionsPanel": "Montrer la page d'options"
     }
 }

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

@@ -125,6 +125,7 @@
         "langSimplifiedChinese": "סינית",
         "langUkranian": "אוקראינית",
         "langSpanish": "ספרדית",
+        "text2img": "טקסט לתמונה",
         "img2img": "תמונה לתמונה",
         "unifiedCanvas": "קנבס מאוחד",
         "nodes": "צמתים",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Scuro",
         "lightTheme": "Chiaro",
         "greenTheme": "Verde",
+        "text2img": "Testo a Immagine",
         "img2img": "Immagine a Immagine",
         "unifiedCanvas": "Tela unificata",
         "nodes": "Nodi",
@@ -69,11 +70,7 @@
         "loading": "Caricamento in corso",
         "oceanTheme": "Oceano",
         "langHebrew": "Ebraico",
-        "loadingInvokeAI": "Caricamento Invoke AI",
-        "postprocessing": "Post Elaborazione",
-        "txt2img": "Testo a Immagine",
-        "accept": "Accetta",
-        "cancel": "Annulla"
+        "loadingInvokeAI": "Caricamento Invoke AI"
     },
     "gallery": {
         "generations": "Generazioni",
@@ -407,8 +404,7 @@
         "v2_768": "v2 (768px)",
         "none": "niente",
         "addDifference": "Aggiungi differenza",
-        "pickModelType": "Scegli il tipo di modello",
-        "scanForModels": "Cerca modelli"
+        "pickModelType": "Scegli il tipo di modello"
     },
     "parameters": {
         "images": "Immagini",
@@ -578,7 +574,7 @@
         "autoSaveToGallery": "Salvataggio automatico nella Galleria",
         "saveBoxRegionOnly": "Salva solo l'area di selezione",
         "limitStrokesToBox": "Limita i tratti all'area di selezione",
-        "showCanvasDebugInfo": "Mostra ulteriori informazioni sulla Tela",
+        "showCanvasDebugInfo": "Mostra informazioni di debug della Tela",
         "clearCanvasHistory": "Cancella cronologia Tela",
         "clearHistory": "Cancella la cronologia",
         "clearCanvasHistoryMessage": "La cancellazione della cronologia della tela lascia intatta la tela corrente, ma cancella in modo irreversibile la cronologia degli annullamenti e dei ripristini.",
@@ -616,7 +612,7 @@
         "copyMetadataJson": "Copia i metadati JSON",
         "exitViewer": "Esci dal visualizzatore",
         "zoomIn": "Zoom avanti",
-        "zoomOut": "Zoom indietro",
+        "zoomOut": "Zoom Indietro",
         "rotateCounterClockwise": "Ruotare in senso antiorario",
         "rotateClockwise": "Ruotare in senso orario",
         "flipHorizontally": "Capovolgi orizzontalmente",

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

@@ -11,6 +11,7 @@
         "langArabic": "العربية",
         "langEnglish": "English",
         "langDutch": "Nederlands",
+        "text2img": "텍스트->이미지",
         "unifiedCanvas": "통합 캔버스",
         "langFrench": "Français",
         "langGerman": "Deutsch",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Donker",
         "lightTheme": "Licht",
         "greenTheme": "Groen",
+        "text2img": "Tekst naar afbeelding",
         "img2img": "Afbeelding naar afbeelding",
         "unifiedCanvas": "Centraal canvas",
         "nodes": "Knooppunten",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Ciemny",
         "lightTheme": "Jasny",
         "greenTheme": "Zielony",
+        "text2img": "Tekst na obraz",
         "img2img": "Obraz na obraz",
         "unifiedCanvas": "Tryb uniwersalny",
         "nodes": "Węzły",

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

@@ -20,6 +20,7 @@
         "langSpanish": "Espanhol",
         "langRussian": "Русский",
         "langUkranian": "Украї́нська",
+        "text2img": "Texto para Imagem",
         "img2img": "Imagem para Imagem",
         "unifiedCanvas": "Tela Unificada",
         "nodes": "Nós",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Noite",
         "lightTheme": "Dia",
         "greenTheme": "Verde",
+        "text2img": "Texto Para Imagem",
         "img2img": "Imagem Para Imagem",
         "unifiedCanvas": "Tela Unificada",
         "nodes": "Nódulos",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Темная",
         "lightTheme": "Светлая",
         "greenTheme": "Зеленая",
+        "text2img": "Изображение из текста (text2img)",
         "img2img": "Изображение в изображение (img2img)",
         "unifiedCanvas": "Универсальный холст",
         "nodes": "Ноды",

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

@@ -8,6 +8,7 @@
         "darkTheme": "Темна",
         "lightTheme": "Світла",
         "greenTheme": "Зелена",
+        "text2img": "Зображення із тексту (text2img)",
         "img2img": "Зображення із зображення (img2img)",
         "unifiedCanvas": "Універсальне полотно",
         "nodes": "Вузли",

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

@@ -8,6 +8,7 @@
         "darkTheme": "暗色",
         "lightTheme": "亮色",
         "greenTheme": "绿色",
+        "text2img": "文字到图像",
         "img2img": "图像到图像",
         "unifiedCanvas": "统一画布",
         "nodes": "节点",

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

@@ -33,6 +33,7 @@
         "langBrPortuguese": "巴西葡萄牙語",
         "langRussian": "俄語",
         "langSpanish": "西班牙語",
+        "text2img": "文字到圖像",
         "unifiedCanvas": "統一畫布"
     }
 }

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

@@ -31,14 +31,18 @@ export const DIFFUSERS_SAMPLERS: Array<string> = [
 ];
 
 // Valid image widths
-export const WIDTHS: Array<number> = Array.from(Array(65)).map(
-  (_x, i) => i * 64
-);
+export const WIDTHS: Array<number> = [
+  64, 128, 192, 256, 320, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960,
+  1024, 1088, 1152, 1216, 1280, 1344, 1408, 1472, 1536, 1600, 1664, 1728, 1792,
+  1856, 1920, 1984, 2048,
+];
 
 // Valid image heights
-export const HEIGHTS: Array<number> = Array.from(Array(65)).map(
-  (_x, i) => i * 64
-);
+export const HEIGHTS: Array<number> = [
+  64, 128, 192, 256, 320, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960,
+  1024, 1088, 1152, 1216, 1280, 1344, 1408, 1472, 1536, 1600, 1664, 1728, 1792,
+  1856, 1920, 1984, 2048,
+];
 
 // Valid upscaling levels
 export const UPSCALING_LEVELS: Array<{ key: string; value: number }> = [

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

@@ -9,7 +9,6 @@ import {
   useDisclosure,
 } from '@chakra-ui/react';
 import { cloneElement, memo, ReactElement, ReactNode, useRef } from 'react';
-import { useTranslation } from 'react-i18next';
 import IAIButton from './IAIButton';
 
 type Props = {
@@ -23,12 +22,10 @@ type Props = {
 };
 
 const IAIAlertDialog = forwardRef((props: Props, ref) => {
-  const { t } = useTranslation();
-
   const {
-    acceptButtonText = t('common.accept'),
+    acceptButtonText = 'Accept',
     acceptCallback,
-    cancelButtonText = t('common.cancel'),
+    cancelButtonText = 'Cancel',
     cancelCallback,
     children,
     title,
@@ -59,7 +56,6 @@ const IAIAlertDialog = forwardRef((props: Props, ref) => {
         isOpen={isOpen}
         leastDestructiveRef={cancelRef}
         onClose={onClose}
-        isCentered
       >
         <AlertDialogOverlay>
           <AlertDialogContent>

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

@@ -1,8 +0,0 @@
-import { chakra } from '@chakra-ui/react';
-
-/**
- * Chakra-enabled <form />
- */
-const IAIForm = chakra.form;
-
-export default IAIForm;

invokeai/frontend/web/src/common/components/IAIForms/IAIFormItemWrapper.tsx

@@ -1,23 +0,0 @@
-import { Flex } from '@chakra-ui/react';
-import { ReactElement } from 'react';
-
-export function IAIFormItemWrapper({
-  children,
-}: {
-  children: ReactElement | ReactElement[];
-}) {
-  return (
-    <Flex
-      sx={{
-        flexDirection: 'column',
-        padding: 4,
-        rowGap: 4,
-        borderRadius: 'base',
-        width: 'full',
-        bg: 'base.900',
-      }}
-    >
-      {children}
-    </Flex>
-  );
-}

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

@@ -8,7 +8,7 @@ import {
 } from '@chakra-ui/react';
 import { memo, ReactNode } from 'react';
 
-export type IAIPopoverProps = PopoverProps & {
+type IAIPopoverProps = PopoverProps & {
   triggerComponent: ReactNode;
   triggerContainerProps?: BoxProps;
   children: ReactNode;

invokeai/frontend/web/src/exports.tsx

@@ -2,15 +2,6 @@ import Component from './component';
 
 import InvokeAiLogoComponent from './features/system/components/InvokeAILogoComponent';
 import ThemeChanger from './features/system/components/ThemeChanger';
-import IAIPopover from './common/components/IAIPopover';
-import IAIIconButton from './common/components/IAIIconButton';
-import SettingsModal from './features/system/components/SettingsModal/SettingsModal';
 
 export default Component;
-export {
-  InvokeAiLogoComponent,
-  ThemeChanger,
-  IAIPopover,
-  IAIIconButton,
-  SettingsModal,
-};
+export { InvokeAiLogoComponent, ThemeChanger };

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

@@ -104,6 +104,7 @@ const IAICanvasMaskOptions = () => {
 
   return (
     <IAIPopover
+      trigger="hover"
       triggerComponent={
         <ButtonGroup>
           <IAIIconButton

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

@@ -88,7 +88,7 @@ const IAICanvasSettingsButtonPopover = () => {
 
   return (
     <IAIPopover
-      isLazy={false}
+      trigger="hover"
       triggerComponent={
         <IAIIconButton
           tooltip={t('unifiedCanvas.canvasSettings')}

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

@@ -219,6 +219,7 @@ const IAICanvasToolChooserOptions = () => {
         onClick={handleSelectColorPickerTool}
       />
       <IAIPopover
+        trigger="hover"
         triggerComponent={
           <IAIIconButton
             aria-label={t('unifiedCanvas.brushOptions')}

invokeai/frontend/web/src/features/gallery/components/CurrentImageButtons.tsx

@@ -405,6 +405,7 @@ const CurrentImageButtons = (props: CurrentImageButtonsProps) => {
     >
       <ButtonGroup isAttached={true}>
         <IAIPopover
+          trigger="hover"
           triggerComponent={
             <IAIIconButton
               aria-label={`${t('parameters.sendTo')}...`}
@@ -504,6 +505,7 @@ const CurrentImageButtons = (props: CurrentImageButtonsProps) => {
 
       <ButtonGroup isAttached={true}>
         <IAIPopover
+          trigger="hover"
           triggerComponent={
             <IAIIconButton
               icon={<FaGrinStars />}
@@ -533,6 +535,7 @@ const CurrentImageButtons = (props: CurrentImageButtonsProps) => {
         </IAIPopover>
 
         <IAIPopover
+          trigger="hover"
           triggerComponent={
             <IAIIconButton
               icon={<FaExpandArrowsAlt />}

invokeai/frontend/web/src/features/gallery/components/CurrentImageFallback.tsx

@@ -1,24 +0,0 @@
-import { Flex, Spinner, SpinnerProps } from '@chakra-ui/react';
-
-type CurrentImageFallbackProps = SpinnerProps;
-
-const CurrentImageFallback = (props: CurrentImageFallbackProps) => {
-  const { size = 'xl', ...rest } = props;
-
-  return (
-    <Flex
-      sx={{
-        w: 'full',
-        h: 'full',
-        alignItems: 'center',
-        justifyContent: 'center',
-        position: 'absolute',
-        color: 'base.400',
-      }}
-    >
-      <Spinner size={size} {...rest} />
-    </Flex>
-  );
-};
-
-export default CurrentImageFallback;

invokeai/frontend/web/src/features/gallery/components/CurrentImagePreview.tsx

@@ -7,7 +7,6 @@ import { isEqual } from 'lodash';
 import { APP_METADATA_HEIGHT } from 'theme/util/constants';
 
 import { gallerySelector } from '../store/gallerySelectors';
-import CurrentImageFallback from './CurrentImageFallback';
 import ImageMetadataViewer from './ImageMetaDataViewer/ImageMetadataViewer';
 import NextPrevImageButtons from './NextPrevImageButtons';
 
@@ -49,7 +48,6 @@ export default function CurrentImagePreview() {
           src={imageToDisplay.url}
           width={imageToDisplay.width}
           height={imageToDisplay.height}
-          fallback={!isIntermediate ? <CurrentImageFallback /> : undefined}
           sx={{
             objectFit: 'contain',
             maxWidth: '100%',

invokeai/frontend/web/src/features/lightbox/components/ReactPanZoomButtons.tsx

@@ -34,7 +34,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<BiZoomIn />}
         aria-label={t('accessibility.zoomIn')}
-        tooltip={t('accessibility.zoomIn')}
+        tooltip="Zoom In"
         onClick={() => zoomIn()}
         fontSize={20}
       />
@@ -42,7 +42,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<BiZoomOut />}
         aria-label={t('accessibility.zoomOut')}
-        tooltip={t('accessibility.zoomOut')}
+        tooltip="Zoom Out"
         onClick={() => zoomOut()}
         fontSize={20}
       />
@@ -50,7 +50,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<BiRotateLeft />}
         aria-label={t('accessibility.rotateCounterClockwise')}
-        tooltip={t('accessibility.rotateCounterClockwise')}
+        tooltip="Rotate Counter-Clockwise"
         onClick={rotateCounterClockwise}
         fontSize={20}
       />
@@ -58,7 +58,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<BiRotateRight />}
         aria-label={t('accessibility.rotateClockwise')}
-        tooltip={t('accessibility.rotateClockwise')}
+        tooltip="Rotate Clockwise"
         onClick={rotateClockwise}
         fontSize={20}
       />
@@ -66,7 +66,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<MdFlip />}
         aria-label={t('accessibility.flipHorizontally')}
-        tooltip={t('accessibility.flipHorizontally')}
+        tooltip="Flip Horizontally"
         onClick={flipHorizontally}
         fontSize={20}
       />
@@ -74,7 +74,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<MdFlip style={{ transform: 'rotate(90deg)' }} />}
         aria-label={t('accessibility.flipVertically')}
-        tooltip={t('accessibility.flipVertically')}
+        tooltip="Flip Vertically"
         onClick={flipVertically}
         fontSize={20}
       />
@@ -82,7 +82,7 @@ const ReactPanZoomButtons = ({
       <IAIIconButton
         icon={<BiReset />}
         aria-label={t('accessibility.reset')}
-        tooltip={t('accessibility.reset')}
+        tooltip="Reset"
         onClick={() => {
           resetTransform();
           reset();

invokeai/frontend/web/src/features/system/components/LanguagePicker.tsx

@@ -55,6 +55,7 @@ export default function LanguagePicker() {
 
   return (
     <IAIPopover
+      trigger="hover"
       triggerComponent={
         <IAIIconButton
           aria-label={t('common.languagePickerLabel')}

invokeai/frontend/web/src/features/system/components/ModelManager/AddCheckpointModel.tsx

@@ -1,5 +1,4 @@
 import {
-  Flex,
   FormControl,
   FormErrorMessage,
   FormHelperText,
@@ -26,10 +25,10 @@ import { useTranslation } from 'react-i18next';
 
 import type { InvokeModelConfigProps } from 'app/invokeai';
 import type { RootState } from 'app/store';
+import IAIIconButton from 'common/components/IAIIconButton';
 import { setAddNewModelUIOption } from 'features/ui/store/uiSlice';
 import type { FieldInputProps, FormikProps } from 'formik';
-import IAIForm from 'common/components/IAIForm';
-import { IAIFormItemWrapper } from 'common/components/IAIForms/IAIFormItemWrapper';
+import { BiArrowBack } from 'react-icons/bi';
 
 const MIN_MODEL_SIZE = 64;
 const MAX_MODEL_SIZE = 2048;
@@ -73,250 +72,243 @@ export default function AddCheckpointModel() {
 
   return (
     <VStack gap={2} alignItems="flex-start">
-      <Flex columnGap={4}>
-        <IAICheckbox
-          isChecked={!addManually}
-          label={t('modelManager.scanForModels')}
-          onChange={() => setAddmanually(!addManually)}
-        />
-        <IAICheckbox
-          label={t('modelManager.addManually')}
-          isChecked={addManually}
-          onChange={() => setAddmanually(!addManually)}
-        />
-      </Flex>
+      <IAIIconButton
+        aria-label={t('common.back')}
+        tooltip={t('common.back')}
+        onClick={() => dispatch(setAddNewModelUIOption(null))}
+        width="max-content"
+        position="absolute"
+        zIndex={1}
+        size="sm"
+        insetInlineEnd={12}
+        top={3}
+        icon={<BiArrowBack />}
+      />
 
-      {addManually ? (
+      <SearchModels />
+      <IAICheckbox
+        label={t('modelManager.addManually')}
+        isChecked={addManually}
+        onChange={() => setAddmanually(!addManually)}
+      />
+
+      {addManually && (
         <Formik
           initialValues={addModelFormValues}
           onSubmit={addModelFormSubmitHandler}
         >
           {({ handleSubmit, errors, touched }) => (
-            <IAIForm onSubmit={handleSubmit} sx={{ w: 'full' }}>
+            <form onSubmit={handleSubmit}>
               <VStack rowGap={2}>
                 <Text fontSize={20} fontWeight="bold" alignSelf="start">
                   {t('modelManager.manual')}
                 </Text>
                 {/* Name */}
-                <IAIFormItemWrapper>
-                  <FormControl
-                    isInvalid={!!errors.name && touched.name}
-                    isRequired
-                  >
-                    <FormLabel htmlFor="name" fontSize="sm">
-                      {t('modelManager.name')}
-                    </FormLabel>
-                    <VStack alignItems="start">
-                      <Field
-                        as={IAIInput}
-                        id="name"
-                        name="name"
-                        type="text"
-                        validate={baseValidation}
-                        width="full"
-                      />
-                      {!!errors.name && touched.name ? (
-                        <FormErrorMessage>{errors.name}</FormErrorMessage>
-                      ) : (
-                        <FormHelperText margin={0}>
-                          {t('modelManager.nameValidationMsg')}
-                        </FormHelperText>
-                      )}
-                    </VStack>
-                  </FormControl>
-                </IAIFormItemWrapper>
+                <FormControl
+                  isInvalid={!!errors.name && touched.name}
+                  isRequired
+                >
+                  <FormLabel htmlFor="name" fontSize="sm">
+                    {t('modelManager.name')}
+                  </FormLabel>
+                  <VStack alignItems="start">
+                    <Field
+                      as={IAIInput}
+                      id="name"
+                      name="name"
+                      type="text"
+                      validate={baseValidation}
+                      width="2xl"
+                    />
+                    {!!errors.name && touched.name ? (
+                      <FormErrorMessage>{errors.name}</FormErrorMessage>
+                    ) : (
+                      <FormHelperText margin={0}>
+                        {t('modelManager.nameValidationMsg')}
+                      </FormHelperText>
+                    )}
+                  </VStack>
+                </FormControl>
 
                 {/* Description */}
-                <IAIFormItemWrapper>
-                  <FormControl
-                    isInvalid={!!errors.description && touched.description}
-                    isRequired
-                  >
-                    <FormLabel htmlFor="description" fontSize="sm">
-                      {t('modelManager.description')}
-                    </FormLabel>
-                    <VStack alignItems="start">
-                      <Field
-                        as={IAIInput}
-                        id="description"
-                        name="description"
-                        type="text"
-                        width="full"
-                      />
-                      {!!errors.description && touched.description ? (
-                        <FormErrorMessage>
-                          {errors.description}
-                        </FormErrorMessage>
-                      ) : (
-                        <FormHelperText margin={0}>
-                          {t('modelManager.descriptionValidationMsg')}
-                        </FormHelperText>
-                      )}
-                    </VStack>
-                  </FormControl>
-                </IAIFormItemWrapper>
+                <FormControl
+                  isInvalid={!!errors.description && touched.description}
+                  isRequired
+                >
+                  <FormLabel htmlFor="description" fontSize="sm">
+                    {t('modelManager.description')}
+                  </FormLabel>
+                  <VStack alignItems="start">
+                    <Field
+                      as={IAIInput}
+                      id="description"
+                      name="description"
+                      type="text"
+                      width="2xl"
+                    />
+                    {!!errors.description && touched.description ? (
+                      <FormErrorMessage>{errors.description}</FormErrorMessage>
+                    ) : (
+                      <FormHelperText margin={0}>
+                        {t('modelManager.descriptionValidationMsg')}
+                      </FormHelperText>
+                    )}
+                  </VStack>
+                </FormControl>
 
                 {/* Config */}
-                <IAIFormItemWrapper>
-                  <FormControl
-                    isInvalid={!!errors.config && touched.config}
-                    isRequired
-                  >
-                    <FormLabel htmlFor="config" fontSize="sm">
-                      {t('modelManager.config')}
-                    </FormLabel>
-                    <VStack alignItems="start">
-                      <Field
-                        as={IAIInput}
-                        id="config"
-                        name="config"
-                        type="text"
-                        width="full"
-                      />
-                      {!!errors.config && touched.config ? (
-                        <FormErrorMessage>{errors.config}</FormErrorMessage>
-                      ) : (
-                        <FormHelperText margin={0}>
-                          {t('modelManager.configValidationMsg')}
-                        </FormHelperText>
-                      )}
-                    </VStack>
-                  </FormControl>
-                </IAIFormItemWrapper>
+                <FormControl
+                  isInvalid={!!errors.config && touched.config}
+                  isRequired
+                >
+                  <FormLabel htmlFor="config" fontSize="sm">
+                    {t('modelManager.config')}
+                  </FormLabel>
+                  <VStack alignItems="start">
+                    <Field
+                      as={IAIInput}
+                      id="config"
+                      name="config"
+                      type="text"
+                      width="2xl"
+                    />
+                    {!!errors.config && touched.config ? (
+                      <FormErrorMessage>{errors.config}</FormErrorMessage>
+                    ) : (
+                      <FormHelperText margin={0}>
+                        {t('modelManager.configValidationMsg')}
+                      </FormHelperText>
+                    )}
+                  </VStack>
+                </FormControl>
 
                 {/* Weights */}
-                <IAIFormItemWrapper>
-                  <FormControl
-                    isInvalid={!!errors.weights && touched.weights}
-                    isRequired
-                  >
-                    <FormLabel htmlFor="config" fontSize="sm">
-                      {t('modelManager.modelLocation')}
-                    </FormLabel>
-                    <VStack alignItems="start">
-                      <Field
-                        as={IAIInput}
-                        id="weights"
-                        name="weights"
-                        type="text"
-                        width="full"
-                      />
-                      {!!errors.weights && touched.weights ? (
-                        <FormErrorMessage>{errors.weights}</FormErrorMessage>
-                      ) : (
-                        <FormHelperText margin={0}>
-                          {t('modelManager.modelLocationValidationMsg')}
-                        </FormHelperText>
-                      )}
-                    </VStack>
-                  </FormControl>
-                </IAIFormItemWrapper>
+                <FormControl
+                  isInvalid={!!errors.weights && touched.weights}
+                  isRequired
+                >
+                  <FormLabel htmlFor="config" fontSize="sm">
+                    {t('modelManager.modelLocation')}
+                  </FormLabel>
+                  <VStack alignItems="start">
+                    <Field
+                      as={IAIInput}
+                      id="weights"
+                      name="weights"
+                      type="text"
+                      width="2xl"
+                    />
+                    {!!errors.weights && touched.weights ? (
+                      <FormErrorMessage>{errors.weights}</FormErrorMessage>
+                    ) : (
+                      <FormHelperText margin={0}>
+                        {t('modelManager.modelLocationValidationMsg')}
+                      </FormHelperText>
+                    )}
+                  </VStack>
+                </FormControl>
 
                 {/* VAE */}
-                <IAIFormItemWrapper>
-                  <FormControl isInvalid={!!errors.vae && touched.vae}>
-                    <FormLabel htmlFor="vae" fontSize="sm">
-                      {t('modelManager.vaeLocation')}
-                    </FormLabel>
-                    <VStack alignItems="start">
-                      <Field
-                        as={IAIInput}
-                        id="vae"
-                        name="vae"
-                        type="text"
-                        width="full"
-                      />
-                      {!!errors.vae && touched.vae ? (
-                        <FormErrorMessage>{errors.vae}</FormErrorMessage>
-                      ) : (
-                        <FormHelperText margin={0}>
-                          {t('modelManager.vaeLocationValidationMsg')}
-                        </FormHelperText>
-                      )}
-                    </VStack>
-                  </FormControl>
-                </IAIFormItemWrapper>
+                <FormControl isInvalid={!!errors.vae && touched.vae}>
+                  <FormLabel htmlFor="vae" fontSize="sm">
+                    {t('modelManager.vaeLocation')}
+                  </FormLabel>
+                  <VStack alignItems="start">
+                    <Field
+                      as={IAIInput}
+                      id="vae"
+                      name="vae"
+                      type="text"
+                      width="2xl"
+                    />
+                    {!!errors.vae && touched.vae ? (
+                      <FormErrorMessage>{errors.vae}</FormErrorMessage>
+                    ) : (
+                      <FormHelperText margin={0}>
+                        {t('modelManager.vaeLocationValidationMsg')}
+                      </FormHelperText>
+                    )}
+                  </VStack>
+                </FormControl>
 
                 <HStack width="100%">
                   {/* Width */}
-                  <IAIFormItemWrapper>
-                    <FormControl isInvalid={!!errors.width && touched.width}>
-                      <FormLabel htmlFor="width" fontSize="sm">
-                        {t('modelManager.width')}
-                      </FormLabel>
-                      <VStack alignItems="start">
-                        <Field id="width" name="width">
-                          {({
-                            field,
-                            form,
-                          }: {
-                            field: FieldInputProps<number>;
-                            form: FormikProps<InvokeModelConfigProps>;
-                          }) => (
-                            <IAINumberInput
-                              id="width"
-                              name="width"
-                              min={MIN_MODEL_SIZE}
-                              max={MAX_MODEL_SIZE}
-                              step={64}
-                              value={form.values.width}
-                              onChange={(value) =>
-                                form.setFieldValue(field.name, Number(value))
-                              }
-                            />
-                          )}
-                        </Field>
-
-                        {!!errors.width && touched.width ? (
-                          <FormErrorMessage>{errors.width}</FormErrorMessage>
-                        ) : (
-                          <FormHelperText margin={0}>
-                            {t('modelManager.widthValidationMsg')}
-                          </FormHelperText>
+                  <FormControl isInvalid={!!errors.width && touched.width}>
+                    <FormLabel htmlFor="width" fontSize="sm">
+                      {t('modelManager.width')}
+                    </FormLabel>
+                    <VStack alignItems="start">
+                      <Field id="width" name="width">
+                        {({
+                          field,
+                          form,
+                        }: {
+                          field: FieldInputProps<number>;
+                          form: FormikProps<InvokeModelConfigProps>;
+                        }) => (
+                          <IAINumberInput
+                            id="width"
+                            name="width"
+                            min={MIN_MODEL_SIZE}
+                            max={MAX_MODEL_SIZE}
+                            step={64}
+                            width="90%"
+                            value={form.values.width}
+                            onChange={(value) =>
+                              form.setFieldValue(field.name, Number(value))
+                            }
+                          />
                         )}
-                      </VStack>
-                    </FormControl>
-                  </IAIFormItemWrapper>
+                      </Field>
+
+                      {!!errors.width && touched.width ? (
+                        <FormErrorMessage>{errors.width}</FormErrorMessage>
+                      ) : (
+                        <FormHelperText margin={0}>
+                          {t('modelManager.widthValidationMsg')}
+                        </FormHelperText>
+                      )}
+                    </VStack>
+                  </FormControl>
 
                   {/* Height */}
-                  <IAIFormItemWrapper>
-                    <FormControl isInvalid={!!errors.height && touched.height}>
-                      <FormLabel htmlFor="height" fontSize="sm">
-                        {t('modelManager.height')}
-                      </FormLabel>
-                      <VStack alignItems="start">
-                        <Field id="height" name="height">
-                          {({
-                            field,
-                            form,
-                          }: {
-                            field: FieldInputProps<number>;
-                            form: FormikProps<InvokeModelConfigProps>;
-                          }) => (
-                            <IAINumberInput
-                              id="height"
-                              name="height"
-                              min={MIN_MODEL_SIZE}
-                              max={MAX_MODEL_SIZE}
-                              step={64}
-                              value={form.values.height}
-                              onChange={(value) =>
-                                form.setFieldValue(field.name, Number(value))
-                              }
-                            />
-                          )}
-                        </Field>
-
-                        {!!errors.height && touched.height ? (
-                          <FormErrorMessage>{errors.height}</FormErrorMessage>
-                        ) : (
-                          <FormHelperText margin={0}>
-                            {t('modelManager.heightValidationMsg')}
-                          </FormHelperText>
+                  <FormControl isInvalid={!!errors.height && touched.height}>
+                    <FormLabel htmlFor="height" fontSize="sm">
+                      {t('modelManager.height')}
+                    </FormLabel>
+                    <VStack alignItems="start">
+                      <Field id="height" name="height">
+                        {({
+                          field,
+                          form,
+                        }: {
+                          field: FieldInputProps<number>;
+                          form: FormikProps<InvokeModelConfigProps>;
+                        }) => (
+                          <IAINumberInput
+                            id="height"
+                            name="height"
+                            min={MIN_MODEL_SIZE}
+                            max={MAX_MODEL_SIZE}
+                            width="90%"
+                            step={64}
+                            value={form.values.height}
+                            onChange={(value) =>
+                              form.setFieldValue(field.name, Number(value))
+                            }
+                          />
                         )}
-                      </VStack>
-                    </FormControl>
-                  </IAIFormItemWrapper>
+                      </Field>
+
+                      {!!errors.height && touched.height ? (
+                        <FormErrorMessage>{errors.height}</FormErrorMessage>
+                      ) : (
+                        <FormHelperText margin={0}>
+                          {t('modelManager.heightValidationMsg')}
+                        </FormHelperText>
+                      )}
+                    </VStack>
+                  </FormControl>
                 </HStack>
 
                 <IAIButton
@@ -327,11 +319,9 @@ export default function AddCheckpointModel() {
                   {t('modelManager.addModel')}
                 </IAIButton>
               </VStack>
-            </IAIForm>
+            </form>
           )}
         </Formik>
-      ) : (
-        <SearchModels />
       )}
     </VStack>
   );

invokeai/frontend/web/src/features/system/components/ModelManager/AddDiffusersModel.tsx

@@ -11,14 +11,36 @@ import { InvokeDiffusersModelConfigProps } from 'app/invokeai';
 import { addNewModel } from 'app/socketio/actions';
 import { useAppDispatch, useAppSelector } from 'app/storeHooks';
 import IAIButton from 'common/components/IAIButton';
+import IAIIconButton from 'common/components/IAIIconButton';
 import IAIInput from 'common/components/IAIInput';
 import { setAddNewModelUIOption } from 'features/ui/store/uiSlice';
 import { Field, Formik } from 'formik';
 import { useTranslation } from 'react-i18next';
+import { BiArrowBack } from 'react-icons/bi';
 
 import type { RootState } from 'app/store';
-import IAIForm from 'common/components/IAIForm';
-import { IAIFormItemWrapper } from 'common/components/IAIForms/IAIFormItemWrapper';
+import type { ReactElement } from 'react';
+
+function FormItemWrapper({
+  children,
+}: {
+  children: ReactElement | ReactElement[];
+}) {
+  return (
+    <Flex
+      sx={{
+        flexDirection: 'column',
+        padding: 4,
+        rowGap: 4,
+        borderRadius: 'base',
+        width: 'full',
+        bg: 'base.900',
+      }}
+    >
+      {children}
+    </Flex>
+  );
+}
 
 export default function AddDiffusersModel() {
   const dispatch = useAppDispatch();
@@ -67,14 +89,26 @@ export default function AddDiffusersModel() {
 
   return (
     <Flex>
+      <IAIIconButton
+        aria-label={t('common.back')}
+        tooltip={t('common.back')}
+        onClick={() => dispatch(setAddNewModelUIOption(null))}
+        width="max-content"
+        position="absolute"
+        zIndex={1}
+        size="sm"
+        insetInlineEnd={12}
+        top={3}
+        icon={<BiArrowBack />}
+      />
       <Formik
         initialValues={addModelFormValues}
         onSubmit={addModelFormSubmitHandler}
       >
         {({ handleSubmit, errors, touched }) => (
-          <IAIForm onSubmit={handleSubmit}>
+          <form onSubmit={handleSubmit}>
             <VStack rowGap={2}>
-              <IAIFormItemWrapper>
+              <FormItemWrapper>
                 {/* Name */}
                 <FormControl
                   isInvalid={!!errors.name && touched.name}
@@ -102,9 +136,9 @@ export default function AddDiffusersModel() {
                     )}
                   </VStack>
                 </FormControl>
-              </IAIFormItemWrapper>
+              </FormItemWrapper>
 
-              <IAIFormItemWrapper>
+              <FormItemWrapper>
                 {/* Description */}
                 <FormControl
                   isInvalid={!!errors.description && touched.description}
@@ -131,9 +165,9 @@ export default function AddDiffusersModel() {
                     )}
                   </VStack>
                 </FormControl>
-              </IAIFormItemWrapper>
+              </FormItemWrapper>
 
-              <IAIFormItemWrapper>
+              <FormItemWrapper>
                 <Text fontWeight="bold" fontSize="sm">
                   {t('modelManager.formMessageDiffusersModelLocation')}
                 </Text>
@@ -192,9 +226,9 @@ export default function AddDiffusersModel() {
                     )}
                   </VStack>
                 </FormControl>
-              </IAIFormItemWrapper>
+              </FormItemWrapper>
 
-              <IAIFormItemWrapper>
+              <FormItemWrapper>
                 {/* VAE Path */}
                 <Text fontWeight="bold">
                   {t('modelManager.formMessageDiffusersVAELocation')}
@@ -256,13 +290,13 @@ export default function AddDiffusersModel() {
                     )}
                   </VStack>
                 </FormControl>
-              </IAIFormItemWrapper>
+              </FormItemWrapper>
 
               <IAIButton type="submit" isLoading={isProcessing}>
                 {t('modelManager.addModel')}
               </IAIButton>
             </VStack>
-          </IAIForm>
+          </form>
         )}
       </Formik>
     </Flex>

invokeai/frontend/web/src/features/system/components/ModelManager/AddModel.tsx

@@ -14,7 +14,7 @@ import {
 
 import IAIButton from 'common/components/IAIButton';
 
-import { FaArrowLeft, FaPlus } from 'react-icons/fa';
+import { FaPlus } from 'react-icons/fa';
 
 import { useAppDispatch, useAppSelector } from 'app/storeHooks';
 import { useTranslation } from 'react-i18next';
@@ -23,7 +23,6 @@ import type { RootState } from 'app/store';
 import { setAddNewModelUIOption } from 'features/ui/store/uiSlice';
 import AddCheckpointModel from './AddCheckpointModel';
 import AddDiffusersModel from './AddDiffusersModel';
-import IAIIconButton from 'common/components/IAIIconButton';
 
 function AddModelBox({
   text,
@@ -84,22 +83,8 @@ export default function AddModel() {
         closeOnOverlayClick={false}
       >
         <ModalOverlay />
-        <ModalContent margin="auto">
-          <ModalHeader>{t('modelManager.addNewModel')} </ModalHeader>
-          {addNewModelUIOption !== null && (
-            <IAIIconButton
-              aria-label={t('common.back')}
-              tooltip={t('common.back')}
-              onClick={() => dispatch(setAddNewModelUIOption(null))}
-              position="absolute"
-              variant="ghost"
-              zIndex={1}
-              size="sm"
-              insetInlineEnd={12}
-              top={2}
-              icon={<FaArrowLeft />}
-            />
-          )}
+        <ModalContent margin="auto" paddingInlineEnd={4}>
+          <ModalHeader>{t('modelManager.addNewModel')}</ModalHeader>
           <ModalCloseButton />
           <ModalBody>
             {addNewModelUIOption == null && (

invokeai/frontend/web/src/features/system/components/ModelManager/CheckpointModelEdit.tsx

@@ -28,7 +28,6 @@ import { isEqual, pickBy } from 'lodash';
 import ModelConvert from './ModelConvert';
 import IAIFormHelperText from 'common/components/IAIForms/IAIFormHelperText';
 import IAIFormErrorMessage from 'common/components/IAIForms/IAIFormErrorMessage';
-import IAIForm from 'common/components/IAIForm';
 
 const selector = createSelector(
   [systemSelector],
@@ -121,7 +120,7 @@ export default function CheckpointModelEdit() {
           onSubmit={editModelFormSubmitHandler}
         >
           {({ handleSubmit, errors, touched }) => (
-            <IAIForm onSubmit={handleSubmit}>
+            <form onSubmit={handleSubmit}>
               <VStack rowGap={2} alignItems="start">
                 {/* Description */}
                 <FormControl
@@ -318,7 +317,7 @@ export default function CheckpointModelEdit() {
                   {t('modelManager.updateModel')}
                 </IAIButton>
               </VStack>
-            </IAIForm>
+            </form>
           )}
         </Formik>
       </Flex>

invokeai/frontend/web/src/features/system/components/ModelManager/DiffusersModelEdit.tsx

@@ -18,7 +18,6 @@ import type { RootState } from 'app/store';
 import { isEqual, pickBy } from 'lodash';
 import IAIFormHelperText from 'common/components/IAIForms/IAIFormHelperText';
 import IAIFormErrorMessage from 'common/components/IAIForms/IAIFormErrorMessage';
-import IAIForm from 'common/components/IAIForm';
 
 const selector = createSelector(
   [systemSelector],
@@ -117,7 +116,7 @@ export default function DiffusersModelEdit() {
           onSubmit={editModelFormSubmitHandler}
         >
           {({ handleSubmit, errors, touched }) => (
-            <IAIForm onSubmit={handleSubmit}>
+            <form onSubmit={handleSubmit}>
               <VStack rowGap={2} alignItems="start">
                 {/* Description */}
                 <FormControl
@@ -260,7 +259,7 @@ export default function DiffusersModelEdit() {
                   {t('modelManager.updateModel')}
                 </IAIButton>
               </VStack>
-            </IAIForm>
+            </form>
           )}
         </Formik>
       </Flex>

invokeai/frontend/web/src/features/system/components/ModelManager/SearchModels.tsx

@@ -12,13 +12,14 @@ import {
   RadioGroup,
   Spacer,
   Text,
+  VStack,
 } from '@chakra-ui/react';
 import { createSelector } from '@reduxjs/toolkit';
 import { useAppDispatch, useAppSelector } from 'app/storeHooks';
 import { systemSelector } from 'features/system/store/systemSelectors';
 import { useTranslation } from 'react-i18next';
 
-import { FaSearch, FaTrash } from 'react-icons/fa';
+import { FaPlus, FaSearch } from 'react-icons/fa';
 
 import { addNewModel, searchForModels } from 'app/socketio/actions';
 import {
@@ -33,7 +34,7 @@ import IAIInput from 'common/components/IAIInput';
 import { Field, Formik } from 'formik';
 import { forEach, remove } from 'lodash';
 import type { ChangeEvent, ReactNode } from 'react';
-import IAIForm from 'common/components/IAIForm';
+import { BiReset } from 'react-icons/bi';
 
 const existingModelsSelector = createSelector([systemSelector], (system) => {
   const { model_list } = system;
@@ -70,32 +71,34 @@ function SearchModelEntry({
   };
 
   return (
-    <Flex
-      flexDirection="column"
-      gap={2}
-      backgroundColor={
-        modelsToAdd.includes(model.name) ? 'accent.650' : 'base.800'
-      }
-      paddingX={4}
-      paddingY={2}
-      borderRadius={4}
-    >
-      <Flex gap={4} alignItems="center" justifyContent="space-between">
-        <IAICheckbox
-          value={model.name}
-          label={<Text fontWeight={500}>{model.name}</Text>}
-          isChecked={modelsToAdd.includes(model.name)}
-          isDisabled={existingModels.includes(model.location)}
-          onChange={foundModelsChangeHandler}
-        ></IAICheckbox>
-        {existingModels.includes(model.location) && (
-          <Badge colorScheme="accent">{t('modelManager.modelExists')}</Badge>
-        )}
+    <VStack>
+      <Flex
+        flexDirection="column"
+        gap={2}
+        backgroundColor={
+          modelsToAdd.includes(model.name) ? 'accent.650' : 'base.800'
+        }
+        paddingX={4}
+        paddingY={2}
+        borderRadius={4}
+      >
+        <Flex gap={4}>
+          <IAICheckbox
+            value={model.name}
+            label={<Text fontWeight={500}>{model.name}</Text>}
+            isChecked={modelsToAdd.includes(model.name)}
+            isDisabled={existingModels.includes(model.location)}
+            onChange={foundModelsChangeHandler}
+          ></IAICheckbox>
+          {existingModels.includes(model.location) && (
+            <Badge colorScheme="accent">{t('modelManager.modelExists')}</Badge>
+          )}
+        </Flex>
+        <Text fontStyle="italic" variant="subtext">
+          {model.location}
+        </Text>
       </Flex>
-      <Text fontStyle="italic" variant="subtext">
-        {model.location}
-      </Text>
-    </Flex>
+    </VStack>
   );
 }
 
@@ -212,10 +215,10 @@ export default function SearchModels() {
     }
 
     return (
-      <Flex flexDirection="column" rowGap={4}>
+      <>
         {newFoundModels}
         {shouldShowExistingModelsInSearch && existingFoundModels}
-      </Flex>
+      </>
     );
   };
 
@@ -242,26 +245,26 @@ export default function SearchModels() {
             <Text
               sx={{
                 fontWeight: 500,
+                fontSize: 'sm',
               }}
               variant="subtext"
             >
               {t('modelManager.checkpointFolder')}
             </Text>
-            <Text sx={{ fontWeight: 500 }}>{searchFolder}</Text>
+            <Text sx={{ fontWeight: 500, fontSize: 'sm' }}>{searchFolder}</Text>
           </Flex>
           <Spacer />
           <IAIIconButton
             aria-label={t('modelManager.scanAgain')}
             tooltip={t('modelManager.scanAgain')}
-            icon={<FaSearch />}
+            icon={<BiReset />}
             fontSize={18}
             disabled={isProcessing}
             onClick={() => dispatch(searchForModels(searchFolder))}
           />
           <IAIIconButton
             aria-label={t('modelManager.clearCheckpointFolder')}
-            tooltip={t('modelManager.clearCheckpointFolder')}
-            icon={<FaTrash />}
+            icon={<FaPlus style={{ transform: 'rotate(45deg)' }} />}
             onClick={resetSearchModelHandler}
           />
         </Flex>
@@ -273,9 +276,9 @@ export default function SearchModels() {
           }}
         >
           {({ handleSubmit }) => (
-            <IAIForm onSubmit={handleSubmit} width="100%">
-              <HStack columnGap={2} alignItems="flex-end">
-                <FormControl flexGrow={1}>
+            <form onSubmit={handleSubmit}>
+              <HStack columnGap={2} alignItems="flex-end" width="100%">
+                <FormControl isRequired width="lg">
                   <Field
                     as={IAIInput}
                     id="checkpointFolder"
@@ -291,12 +294,12 @@ export default function SearchModels() {
                   tooltip={t('modelManager.findModels')}
                   type="submit"
                   disabled={isProcessing}
-                  px={8}
+                  paddingX={10}
                 >
                   {t('modelManager.findModels')}
                 </IAIButton>
               </HStack>
-            </IAIForm>
+            </form>
           )}
         </Formik>
       )}
@@ -407,6 +410,7 @@ export default function SearchModels() {
             maxHeight={72}
             overflowY="scroll"
             borderRadius="sm"
+            paddingInlineEnd={4}
             gap={2}
           >
             {foundModels.length > 0 ? (

invokeai/frontend/web/src/features/system/components/ThemeChanger.tsx

@@ -50,6 +50,7 @@ export default function ThemeChanger() {
 
   return (
     <IAIPopover
+      trigger="hover"
       triggerComponent={
         <IAIIconButton
           aria-label={t('common.themeLabel')}

invokeai/frontend/web/src/features/ui/components/InvokeTabs.tsx

@@ -166,8 +166,20 @@ export default function InvokeTabs() {
     []
   );
 
+  /**
+   * isLazy means the tabs are mounted and unmounted when changing them. There is a tradeoff here,
+   * as mounting is expensive, but so is retaining all tabs in the DOM at all times.
+   *
+   * Removing isLazy messes with the outside click watcher, which is used by ResizableDrawer.
+   * Because you have multiple handlers listening for an outside click, any click anywhere triggers
+   * the watcher for the hidden drawers, closing the open drawer.
+   *
+   * TODO: Add logic to the `useOutsideClick` in ResizableDrawer to enable it only for the active
+   * tab's drawer.
+   */
   return (
     <Tabs
+      isLazy
       defaultIndex={activeTab}
       index={activeTab}
       onChange={(index: number) => {