Merge branch 'main' into Convert-Model-Endpoint

# Application-wide configuration service

This PR creates a new `InvokeAIAppConfig` object that reads
application-wide settings from an init file, the environment, and the
command line.

Arguments and fields are taken from the pydantic definition of the
model. Defaults can be set by creating a yaml configuration file that
has a top-level key of "InvokeAI" and subheadings for each of the
categories returned by `invokeai --help`.

The file looks like this:

[file: invokeai.yaml]
```
InvokeAI:
  Paths:
    root: /home/lstein/invokeai-main
    conf_path: configs/models.yaml
    legacy_conf_dir: configs/stable-diffusion
    outdir: outputs
    embedding_dir: embeddings
    lora_dir: loras
    autoconvert_dir: null
    gfpgan_model_dir: models/gfpgan/GFPGANv1.4.pth
  Models:
    model: stable-diffusion-1.5
    embeddings: true
  Memory/Performance:
    xformers_enabled: false
    sequential_guidance: false
    precision: float16
    max_loaded_models: 4
    always_use_cpu: false
    free_gpu_mem: false
  Features:
    nsfw_checker: true
    restore: true
    esrgan: true
    patchmatch: true
    internet_available: true
    log_tokenization: false
  Cross-Origin Resource Sharing:
    allow_origins: []
    allow_credentials: true
    allow_methods:
    - '*'
    allow_headers:
    - '*'
  Web Server:
    host: 127.0.0.1
    port: 8081

```

The default name of the configuration file is `invokeai.yaml`, located
in INVOKEAI_ROOT. You can use any OmegaConf dictionary by passing it to
the config object at initialization time:

```
 omegaconf = OmegaConf.load('/tmp/init.yaml')
 conf = InvokeAIAppConfig(conf=omegaconf)
```
The default name of the configuration file is `invokeai.yaml`, located
in INVOKEAI_ROOT. You can replace supersede this by providing
anyOmegaConf dictionary object initialization time:

```
omegaconf = OmegaConf.load('/tmp/init.yaml')
conf = InvokeAIAppConfig(conf=omegaconf)
```

By default, InvokeAIAppConfig will parse the contents of `sys.argv` at
initialization time. You may pass a list of strings in the optional
`argv` argument to use instead of the system argv:

```
conf = InvokeAIAppConfig(arg=['--xformers_enabled'])
```

It is also possible to set a value at initialization time. This value
has highest priority.
```
conf = InvokeAIAppConfig(xformers_enabled=True)
```
Any setting can be overwritten by setting an environment variable of
form: "INVOKEAI_<setting>", as in:

```
export INVOKEAI_port=8080
```

Order of precedence (from highest):
   1) initialization options
   2) command line options
   3) environment variable options
   4) config file options
   5) pydantic defaults

Typical usage:

```
from invokeai.app.services.config import InvokeAIAppConfig

# get global configuration and print its nsfw_checker value
conf = InvokeAIAppConfig()
print(conf.nsfw_checker)
```
Finally, the configuration object is able to recreate its (modified)
yaml file, by calling its `to_yaml()` method:

```
conf = InvokeAIAppConfig(outdir='/tmp', port=8080)
print(conf.to_yaml())
```

# Legacy code removal and porting

This PR replaces Globals with the InvokeAIAppConfig system throughout,
and therefore removes the `globals.py` and `args.py` modules. It also
removes `generate` and the legacy CLI. ***The old CLI and web servers
are now gone.***

I have ported the functionality of the configuration script, the model
installer, and the merge and textual inversion scripts. The `invokeai`
command will now launch `invokeai-node-cli`, and `invokeai-web` will
launch the web server.

I have changed the continuous invocation tests to accommodate the new
command syntax in `invokeai-node-cli`. As a convenience function, you
can also pass invocations to `invokeai-node-cli` (or its alias
`invokeai`) on the command line as as standard input:

```
invokeai-node-cli "t2i --positive_prompt 'banana sushi' --seed 42"
invokeai < invocation_commands.txt
```

.github/CODEOWNERS

@@ -1,16 +1,16 @@
 # continuous integration
-/.github/workflows/ @mauwii @lstein @blessedcoolant
+/.github/workflows/  @lstein @blessedcoolant
 
 # documentation
-/docs/ @lstein @mauwii @tildebyte @blessedcoolant
-/mkdocs.yml @lstein @mauwii @blessedcoolant
+/docs/ @lstein  @tildebyte @blessedcoolant
+/mkdocs.yml @lstein  @blessedcoolant
 
 # nodes
 /invokeai/app/ @Kyle0654 @blessedcoolant
 
 # installation and configuration
-/pyproject.toml @mauwii @lstein @blessedcoolant
-/docker/ @mauwii @lstein @blessedcoolant
+/pyproject.toml  @lstein @blessedcoolant
+/docker/  @lstein @blessedcoolant
 /scripts/ @ebr @lstein
 /installer/ @lstein @ebr
 /invokeai/assets @lstein @ebr
@@ -22,11 +22,11 @@
 /invokeai/backend @blessedcoolant @psychedelicious @lstein
 
 # generation, model management, postprocessing
-/invokeai/backend @keturn @damian0815 @lstein @blessedcoolant @jpphoto
+/invokeai/backend  @damian0815 @lstein @blessedcoolant @jpphoto @gregghelt2
 
 # front ends
 /invokeai/frontend/CLI @lstein
-/invokeai/frontend/install @lstein @ebr @mauwii 
+/invokeai/frontend/install @lstein @ebr  
 /invokeai/frontend/merge @lstein @blessedcoolant @hipsterusername
 /invokeai/frontend/training @lstein @blessedcoolant @hipsterusername
 /invokeai/frontend/web @psychedelicious @blessedcoolant

.github/workflows/mkdocs-material.yml

@@ -2,8 +2,7 @@ name: mkdocs-material
 on:
   push:
     branches:
-      - 'main'
-      - 'development'
+      - 'refs/heads/v2.3'
 
 permissions:
     contents: write
@@ -12,6 +11,10 @@ jobs:
   mkdocs-material:
     if: github.event.pull_request.draft == false
     runs-on: ubuntu-latest
+    env:
+      REPO_URL: '${{ github.server_url }}/${{ github.repository }}'
+      REPO_NAME: '${{ github.repository }}'
+      SITE_URL: 'https://${{ github.repository_owner }}.github.io/InvokeAI'
     steps:
       - name: checkout sources
         uses: actions/checkout@v3
@@ -22,11 +25,15 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
+          cache: pip
+          cache-dependency-path: pyproject.toml
 
       - name: install requirements
+        env:
+          PIP_USE_PEP517: 1
         run: |
           python -m \
-            pip install -r docs/requirements-mkdocs.txt
+            pip install ".[docs]"
 
       - name: confirm buildability
         run: |
@@ -36,7 +43,7 @@ jobs:
             --verbose
 
       - name: deploy to gh-pages
-        if: ${{ github.ref == 'refs/heads/main' }}
+        if: ${{ github.ref == 'refs/heads/v2.3' }}
         run: |
           python -m \
             mkdocs gh-deploy \

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

@@ -80,12 +80,7 @@ jobs:
         uses: actions/checkout@v3
 
       - name: set test prompt to main branch validation
-        if: ${{ github.ref == 'refs/heads/main' }}
-        run: echo "TEST_PROMPTS=tests/preflight_prompts.txt" >> ${{ matrix.github-env }}
-
-      - name: set test prompt to Pull Request validation
-        if: ${{ github.ref != 'refs/heads/main' }}
-        run: echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
+        run:echo "TEST_PROMPTS=tests/validate_pr_prompt.txt" >> ${{ matrix.github-env }}
 
       - name: setup python
         uses: actions/setup-python@v4
@@ -105,12 +100,6 @@ jobs:
         id: run-pytest
         run: pytest
 
-      - name: set INVOKEAI_OUTDIR
-        run: >
-          python -c
-          "import os;from invokeai.backend.globals import Globals;OUTDIR=os.path.join(Globals.root,str('outputs'));print(f'INVOKEAI_OUTDIR={OUTDIR}')"
-          >> ${{ matrix.github-env }}
-
       - name: run invokeai-configure
         id: run-preload-models
         env:
@@ -129,15 +118,20 @@ jobs:
           HF_HUB_OFFLINE: 1
           HF_DATASETS_OFFLINE: 1
           TRANSFORMERS_OFFLINE: 1
+          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
         run: >
           invokeai
           --no-patchmatch
           --no-nsfw_checker
-          --from_file ${{ env.TEST_PROMPTS }}
+          --precision=float32
+          --always_use_cpu
           --outdir ${{ env.INVOKEAI_OUTDIR }}/${{ matrix.python-version }}/${{ matrix.pytorch }}
+          --from_file ${{ env.TEST_PROMPTS }}
 
       - name: Archive results
         id: archive-results
+        env:
+          INVOKEAI_OUTDIR: ${{ github.workspace }}/results
         uses: actions/upload-artifact@v3
         with:
           name: results

.gitignore

@@ -9,6 +9,8 @@ models/ldm/stable-diffusion-v1/model.ckpt
 configs/models.user.yaml
 config/models.user.yml
 invokeai.init
+.version
+.last_model
 
 # ignore the Anaconda/Miniconda installer used while building Docker image
 anaconda.sh
@@ -199,6 +201,8 @@ checkpoints
 # If it's a Mac
 .DS_Store
 
+invokeai/frontend/web/dist/*
+
 # Let the frontend manage its own gitignore
 !invokeai/frontend/web/*
 

README.md

@@ -33,6 +33,8 @@
 
 </div>
 
+_**Note: The UI is not fully functional on `main`. If you need a stable UI based on `main`, use the `pre-nodes` tag while we [migrate to a new backend](https://github.com/invoke-ai/InvokeAI/discussions/3246).**_
+
 InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
 
 **Quick links**: [[How to Install](https://invoke-ai.github.io/InvokeAI/#installation)] [<a href="https://discord.gg/ZmtBAhwWhy">Discord Server</a>] [<a href="https://invoke-ai.github.io/InvokeAI/">Documentation and Tutorials</a>] [<a href="https://github.com/invoke-ai/InvokeAI/">Code and Downloads</a>] [<a href="https://github.com/invoke-ai/InvokeAI/issues">Bug Reports</a>] [<a href="https://github.com/invoke-ai/InvokeAI/discussions">Discussion, Ideas & Q&A</a>]
@@ -148,6 +150,11 @@ not supported.
     pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/rocm5.4.2
     ```
 
+    _For non-GPU systems:_
+    ```terminal
+    pip install InvokeAI --use-pep517 --extra-index-url https://download.pytorch.org/whl/cpu
+    ``` 
+
     _For Macintoshes, either Intel or M1/M2:_
 
     ```sh

docs/features/NSFW.md

@@ -32,7 +32,7 @@ turned on and off on the command line using `--nsfw_checker` and
 At installation time, InvokeAI will ask whether the checker should be
 activated by default (neither argument given on the command line). The
 response is stored in the InvokeAI initialization file (usually
-`.invokeai` in your home directory). You can change the default at any
+`invokeai.init` in your home directory). You can change the default at any
 time by opening this file in a text editor and commenting or
 uncommenting the line `--nsfw_checker`.
 

docs/installation/010_INSTALL_AUTOMATED.md

@@ -89,7 +89,7 @@ experimental versions later.
          sudo apt update
          sudo apt install -y software-properties-common
          sudo add-apt-repository -y ppa:deadsnakes/ppa
-         sudo apt install python3.10 python3-pip python3.10-venv
+         sudo apt install -y python3.10 python3-pip python3.10-venv
          sudo update-alternatives --install /usr/local/bin/python python /usr/bin/python3.10 3
          ```
 

installer/lib/installer.py

@@ -247,8 +247,8 @@ class InvokeAiInstance:
             pip[
                 "install",
                 "--require-virtualenv",
-                "torch",
-                "torchvision",
+                "torch~=2.0.0",
+                "torchvision>=0.14.1",
                 "--force-reinstall",
                 "--find-links" if find_links is not None else None,
                 find_links,

invokeai/app/api/dependencies.py

@@ -1,13 +1,12 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 import os
-from argparse import Namespace
+
+import invokeai.backend.util.logging as logger
+from typing import types
 
 from ..services.default_graphs import create_system_graphs
-
 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
 from ..services.graph import GraphExecutionState, LibraryGraph
@@ -17,6 +16,7 @@ from ..services.invocation_services import InvocationServices
 from ..services.invoker import Invoker
 from ..services.processor import DefaultInvocationProcessor
 from ..services.sqlite import SqliteItemStorage
+from ..services.metadata import PngMetadataService
 from .events import FastAPIEventService
 
 
@@ -41,16 +41,8 @@ class ApiDependencies:
 
     invoker: Invoker = None
 
-    @staticmethod
-    def initialize(config, event_handler_id: int):
-        Globals.try_patchmatch = config.patchmatch
-        Globals.always_use_cpu = config.always_use_cpu
-        Globals.internet_available = config.internet_available and check_internet()
-        Globals.disable_xformers = not config.xformers
-        Globals.ckpt_convert = config.ckpt_convert
-
-        # TODO: Use a logger
-        print(f">> Internet connectivity is {Globals.internet_available}")
+    def initialize(config, event_handler_id: int, logger: types.ModuleType=logger):
+        logger.info(f"Internet connectivity is {config.internet_available}")
 
         events = FastAPIEventService(event_handler_id)
 
@@ -60,16 +52,19 @@ class ApiDependencies:
 
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents'))
 
-        images = DiskImageStorage(f'{output_folder}/images')
+        metadata = PngMetadataService()
+
+        images = DiskImageStorage(f'{output_folder}/images', metadata_service=metadata)
 
         # TODO: build a file/path manager?
         db_location = os.path.join(output_folder, "invokeai.db")
 
         services = InvocationServices(
-            model_manager=get_model_manager(config),
+            model_manager=get_model_manager(config,logger),
             events=events,
             latents=latents,
             images=images,
+            metadata=metadata,
             queue=MemoryInvocationQueue(),
             graph_library=SqliteItemStorage[LibraryGraph](
                 filename=db_location, table_name="graphs"
@@ -78,7 +73,9 @@ class ApiDependencies:
                 filename=db_location, table_name="graph_executions"
             ),
             processor=DefaultInvocationProcessor(),
-            restoration=RestorationServices(config),
+            restoration=RestorationServices(config,logger),
+            configuration=config,
+            logger=logger,
         )
 
         create_system_graphs(services.graph_library)

invokeai/app/api/events.py

@@ -45,7 +45,7 @@ class FastAPIEventService(EventServiceBase):
                 )
 
             except Empty:
-                await asyncio.sleep(0.001)
+                await asyncio.sleep(0.1)
                 pass
 
             except asyncio.CancelledError as e:

invokeai/app/api/models/images.py

@@ -1,7 +1,19 @@
+from typing import Optional
 from pydantic import BaseModel, Field
 
 from invokeai.app.models.image import ImageType
-from invokeai.app.modules.metadata import ImageMetadata
+from invokeai.app.services.metadata import InvokeAIMetadata
+
+
+class ImageResponseMetadata(BaseModel):
+    """An image's metadata. Used only in HTTP responses."""
+
+    created: int = Field(description="The creation timestamp of the image")
+    width: int = Field(description="The width of the image in pixels")
+    height: int = Field(description="The height of the image in pixels")
+    invokeai: Optional[InvokeAIMetadata] = Field(
+        description="The image's InvokeAI-specific metadata"
+    )
 
 
 class ImageResponse(BaseModel):
@@ -11,11 +23,18 @@ class ImageResponse(BaseModel):
     image_name: str = Field(description="The name of the image")
     image_url: str = Field(description="The url of the image")
     thumbnail_url: str = Field(description="The url of the image's thumbnail")
-    metadata: ImageMetadata = Field(description="The image's metadata")
+    metadata: ImageResponseMetadata = Field(description="The image's metadata")
 
 
 class ProgressImage(BaseModel):
     """The progress image sent intermittently during processing"""
+
     width: int = Field(description="The effective width of the image in pixels")
     height: int = Field(description="The effective height of the image in pixels")
     dataURL: str = Field(description="The image data as a b64 data URL")
+
+
+class SavedImage(BaseModel):
+    image_name: str = Field(description="The name of the saved image")
+    thumbnail_name: str = Field(description="The name of the saved thumbnail")
+    created: int = Field(description="The created timestamp of the saved image")

invokeai/app/api/routers/images.py

@@ -3,16 +3,18 @@ import io
 from datetime import datetime, timezone
 import json
 import os
+from typing import Any
 import uuid
 
-from fastapi import HTTPException, Path, Query, Request, UploadFile
+from fastapi import Body, HTTPException, Path, Query, Request, UploadFile
 from fastapi.responses import FileResponse, Response
 from fastapi.routing import APIRouter
 from PIL import Image
-from invokeai.app.api.models.images import ImageResponse
-from invokeai.app.modules.metadata import ImageMetadata, InvokeAIMetadata
+from invokeai.app.api.models.images import (
+    ImageResponse,
+    ImageResponseMetadata,
+)
 from invokeai.app.services.item_storage import PaginatedResults
-from invokeai.app.util.image_paths import build_image_path
 
 from ...services.image_storage import ImageType
 from ..dependencies import ApiDependencies
@@ -24,8 +26,8 @@ images_router = APIRouter(prefix="/v1/images", tags=["images"])
 async def get_image(
     image_type: ImageType = Path(description="The type of image to get"),
     image_name: str = Path(description="The name of the image to get"),
-) -> FileResponse | Response:
-    """Gets a result"""
+) -> FileResponse:
+    """Gets an image"""
 
     path = ApiDependencies.invoker.services.images.get_path(
         image_type=image_type, image_name=image_name
@@ -35,31 +37,31 @@ async def get_image(
         return FileResponse(path)
     else:
         raise HTTPException(status_code=404)
-    
-@images_router.get("/path/{image_type}/{image_name}", operation_id="get_image_path")
-async def get_image_path(
-    image_type: ImageType = Path(description="The type of image to get"),
-    image_name: str = Path(description="The name of the image to get"),
-) -> str:
-    """Gets a result location"""
 
-    path = build_image_path(image_type=image_type, image_name=image_name)
 
-    return path
+@images_router.delete("/{image_type}/{image_name}", operation_id="delete_image")
+async def delete_image(
+    image_type: ImageType = Path(description="The type of image to delete"),
+    image_name: str = Path(description="The name of the image to delete"),
+) -> None:
+    """Deletes an image and its thumbnail"""
 
+    ApiDependencies.invoker.services.images.delete(
+        image_type=image_type, image_name=image_name
+    )
 
 
 @images_router.get(
-    "/{image_type}/thumbnails/{image_name}", operation_id="get_thumbnail"
+    "/{thumbnail_type}/thumbnails/{thumbnail_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"),
+    thumbnail_type: ImageType = Path(description="The type of thumbnail to get"),
+    thumbnail_name: str = Path(description="The name of the thumbnail to get"),
 ) -> FileResponse | Response:
     """Gets a thumbnail"""
 
     path = ApiDependencies.invoker.services.images.get_path(
-        image_type=image_type, image_name=image_name, is_thumbnail=True
+        image_type=thumbnail_type, image_name=thumbnail_name, is_thumbnail=True
     )
 
     if ApiDependencies.invoker.services.images.validate_path(path):
@@ -81,12 +83,13 @@ async def get_thumbnail(
     status_code=201,
 )
 async def upload_image(
-    file: UploadFile, request: Request, response: Response
+    file: UploadFile, image_type: ImageType, request: Request, response: Response
 ) -> ImageResponse:
     if not file.content_type.startswith("image"):
         raise HTTPException(status_code=415, detail="Not an image")
 
     contents = await file.read()
+
     try:
         img = Image.open(io.BytesIO(contents))
     except:
@@ -94,35 +97,36 @@ async def upload_image(
         raise HTTPException(status_code=415, detail="Failed to read image")
 
     filename = f"{uuid.uuid4()}_{str(int(datetime.now(timezone.utc).timestamp()))}.png"
-    (image_path, thumbnail_path, ctime) = ApiDependencies.invoker.services.images.save(
-        ImageType.UPLOAD, filename, img
+
+    saved_image = ApiDependencies.invoker.services.images.save(
+        image_type, filename, img
     )
 
-    # TODO: handle old `sd-metadata` style metadata
-    invokeai_metadata = img.info.get("invokeai", None)
+    invokeai_metadata = ApiDependencies.invoker.services.metadata.get_metadata(img)
 
-    if invokeai_metadata is not None:
-        invokeai_metadata = InvokeAIMetadata(**json.loads(invokeai_metadata))
+    image_url = ApiDependencies.invoker.services.images.get_uri(
+        image_type, saved_image.image_name
+    )
+
+    thumbnail_url = ApiDependencies.invoker.services.images.get_uri(
+        image_type, saved_image.image_name, True
+    )
 
-    # TODO: should creation of this object should happen elsewhere?
     res = ImageResponse(
-        image_type=ImageType.UPLOAD,
-        image_name=filename,
-        image_url=f"api/v1/images/{ImageType.UPLOAD.value}/{filename}",
-        thumbnail_url=f"api/v1/images/{ImageType.UPLOAD.value}/thumbnails/{os.path.splitext(filename)[0]}.webp",
-        metadata=ImageMetadata(
-            created=ctime,
+        image_type=image_type,
+        image_name=saved_image.image_name,
+        image_url=image_url,
+        thumbnail_url=thumbnail_url,
+        metadata=ImageResponseMetadata(
+            created=saved_image.created,
             width=img.width,
             height=img.height,
-            mode=img.mode,
             invokeai=invokeai_metadata,
         ),
     )
 
     response.status_code = 201
-    response.headers["Location"] = request.url_for(
-        "get_image", image_type=ImageType.UPLOAD.value, image_name=filename
-    )
+    response.headers["Location"] = image_url
 
     return res
 

invokeai/app/api/routers/models.py

@@ -1,17 +1,13 @@
-# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and 2023 Kent Keirsey (https://github.com/hipsterusername)
+# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) and Kent Keirsey (https://github.com/hipsterusername)
 
 import shutil
-import asyncio
+import os
 from typing import Annotated, Any, List, Literal, Optional, Union
 
 from fastapi.routing import APIRouter, HTTPException
 from pydantic import BaseModel, Field, parse_obj_as
 from pathlib import Path
 from ..dependencies import ApiDependencies
-from invokeai.backend.globals import Globals, global_converted_ckpts_dir
-from invokeai.backend.args import Args
-
-
 
 models_router = APIRouter(prefix="/v1/models", tags=["models"])
 
@@ -51,9 +47,7 @@ class CreateModelResponse(BaseModel):
 
 class ConversionRequest(BaseModel):
     name: str = Field(description="The name of the new model")
-    info: CkptModelInfo = Field(description="The converted model info")
     save_location: str = Field(description="The path to save the converted model weights")
-    
 
 class ConvertedModelResponse(BaseModel):
     name: str = Field(description="The name of the new model")
@@ -112,22 +106,112 @@ async def update_model(
 async def delete_model(model_name: str) -> None:
     """Delete Model"""
     model_names = ApiDependencies.invoker.services.model_manager.model_names()
+    logger = ApiDependencies.invoker.services.logger
     model_exists = model_name in model_names
 
     # check if model exists
-    print(f">> Checking for model {model_name}...")
+    logger.info(f"Checking for model {model_name}...")
            
     if model_exists:
-        print(f">> Deleting Model: {model_name}")
+        logger.info(f"Deleting Model: {model_name}")
         ApiDependencies.invoker.services.model_manager.del_model(model_name, delete_files=True)
-        print(f">> Model Deleted: {model_name}")
+        logger.info(f"Model Deleted: {model_name}")
         raise HTTPException(status_code=204, detail=f"Model '{model_name}' deleted successfully")
     
     else:
-        print(f">> Model not found")
+        logger.error(f"Model not found")
         raise HTTPException(status_code=404, detail=f"Model '{model_name}' not found")
+
+# TODO: Refactor these support functions below to live somewhere more appropriate
+
+def get_model_info(model_name: str):
+    model_info = ApiDependencies.invoker.services.model_manager.model_info(
+        model_name=model_name
+    )
+    if not model_info:
+        raise HTTPException(status_code=404, detail=f"Unable to retrieve model info for '{model_name}'")
+    return model_info
+
+
+def ckpt_validate(model_info: dict, model_name: str):
+    if "weights" not in model_info:
+        raise HTTPException(status_code=404, detail=f"Model '{model_name}' is not a valid checkpoint model")
     
 
+def get_paths(model: ConversionRequest, root: Path) -> tuple:
+    model_info = get_model_info(model.name)
+    ckpt_path = Path(model_info.weights)
+    config_path = Path(model_info.config)
+
+    if not ckpt_path.is_absolute():
+        ckpt_path = Path(root, ckpt_path)
+
+    if config_path and not config_path.is_absolute():
+        config_path = Path(root, config_path)
+
+    return ckpt_path, config_path
+
+
+def get_diffusers_path(convert_request: ConversionRequest, model_name: str) -> Path:
+    if convert_request.save_location == "root":
+        diffusers_path = Path(global_converted_ckpts_dir(), f"{model_name}_diffusers")
+    elif convert_request.save_location == "custom" and convert_request.save_location is not None:
+        diffusers_path = Path(convert_request.save_location, f"{model_name}_diffusers")
+    else:
+        raise ValueError("Invalid save_location value")
+
+    if diffusers_path.exists():
+        shutil.rmtree(diffusers_path)
+
+    return diffusers_path
+
+
+@models_router.post(
+    "/{model_to_convert}",
+    operation_id="convert_model",
+    responses={
+        200: {
+            "model_response": "Model converted successfully.",
+        }
+    },
+)
+async def convert_model(convert_request: ConversionRequest) -> ConvertedModelResponse:
+    """Convert Model"""
+
+    opt=Args()
+    args = opt.parse_args()
+
+    # Set the root directory for static files and relative paths
+    args.root_dir = os.path.expanduser(args.root_dir or "..")
+    if not os.path.isabs(args.outdir):
+        args.outdir = os.path.join(args.root_dir, args.outdir)
+
+    # normalize the config directory relative to root
+    if not os.path.isabs(opt.conf):
+        opt.conf = os.path.normpath(os.path.join(Globals.root, opt.conf))
+    model_info = get_model_info(convert_request.name)
+    ckpt_validate(model_info, convert_request.name)
+    ckpt_path, original_config_file = get_paths(convert_request, Globals.root)
+    diffusers_path = get_diffusers_path(convert_request, convert_request.name)
+
+    ApiDependencies.invoker.services.model_manager.convert_and_import(
+        ckpt_path,
+        diffusers_path,
+        model_name=convert_request.name,
+        model_description=model_info.description,
+        vae=None,
+        original_config_file=original_config_file,
+        commit_to_conf=opt.conf,
+    )
+
+    model_info = get_model_info(convert_request.name)
+    convert_response = ConvertedModelResponse(name=f"{convert_request.name}_diffusers", info=model_info)
+    
+    print(f">> Model Converted: {convert_request.name}")
+
+    return convert_response
+
+    
             # @socketio.on("convertToDiffusers")
         # def convert_to_diffusers(model_to_convert: dict):
         #     try:
@@ -248,4 +332,4 @@ async def delete_model(model_name: str) -> None:
         #         )
         #         print(f">> Models Merged: {models_to_merge}")
         #         print(f">> New Model Added: {model_merge_info['merged_model_name']}")
-        #     except Exception as e:
+        #     except Exception as e:

invokeai/app/api/routers/sessions.py

@@ -2,8 +2,7 @@
 
 from typing import Annotated, List, Optional, Union
 
-from fastapi import Body, Path, Query
-from fastapi.responses import Response
+from fastapi import Body, HTTPException, Path, Query, Response
 from fastapi.routing import APIRouter
 from pydantic.fields import Field
 
@@ -76,7 +75,7 @@ async def get_session(
     """Gets a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
     else:
         return session
 
@@ -99,7 +98,7 @@ async def add_node(
     """Adds a node to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.add_node(node)
@@ -108,9 +107,9 @@ async def add_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session.id
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.put(
@@ -132,7 +131,7 @@ async def update_node(
     """Updates a node in the graph and removes all linked edges"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.update_node(node_path, node)
@@ -141,9 +140,9 @@ async def update_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.delete(
@@ -162,7 +161,7 @@ async def delete_node(
     """Deletes a node in the graph and removes all linked edges"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.delete_node(node_path)
@@ -171,9 +170,9 @@ async def delete_node(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.post(
@@ -192,7 +191,7 @@ async def add_edge(
     """Adds an edge to the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         session.add_edge(edge)
@@ -201,9 +200,9 @@ async def add_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 # TODO: the edge being in the path here is really ugly, find a better solution
@@ -226,7 +225,7 @@ async def delete_edge(
     """Deletes an edge from the graph"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     try:
         edge = Edge(
@@ -239,9 +238,9 @@ async def delete_edge(
         )  # TODO: can this be done automatically, or add node through an API?
         return session
     except NodeAlreadyExecutedError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
     except IndexError:
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
 
 @session_router.put(
@@ -259,14 +258,14 @@ async def invoke_session(
     all: bool = Query(
         default=False, description="Whether or not to invoke all remaining invocations"
     ),
-) -> None:
+) -> Response:
     """Invokes a session"""
     session = ApiDependencies.invoker.services.graph_execution_manager.get(session_id)
     if session is None:
-        return Response(status_code=404)
+        raise HTTPException(status_code=404)
 
     if session.is_complete():
-        return Response(status_code=400)
+        raise HTTPException(status_code=400)
 
     ApiDependencies.invoker.invoke(session, invoke_all=all)
     return Response(status_code=202)
@@ -281,7 +280,7 @@ async def invoke_session(
 )
 async def cancel_session_invoke(
     session_id: str = Path(description="The id of the session to cancel"),
-) -> None:
+) -> Response:
     """Invokes a session"""
     ApiDependencies.invoker.cancel(session_id)
     return Response(status_code=202)

invokeai/app/api_app.py

@@ -3,6 +3,7 @@ import asyncio
 from inspect import signature
 
 import uvicorn
+import invokeai.backend.util.logging as logger
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
@@ -12,12 +13,11 @@ from fastapi_events.handlers.local import local_handler
 from fastapi_events.middleware import EventHandlerASGIMiddleware
 from pydantic.schema import schema
 
-from ..backend import Args
 from .api.dependencies import ApiDependencies
 from .api.routers import images, sessions, models
 from .api.sockets import SocketIO
-from .invocations import *
 from .invocations.baseinvocation import BaseInvocation
+from .services.config import InvokeAIAppConfig
 
 # Create the app
 # TODO: create this all in a method so configuration/etc. can be passed in?
@@ -33,30 +33,25 @@ app.add_middleware(
     middleware_id=event_handler_id,
 )
 
-# Add CORS
-# TODO: use configuration for this
-origins = []
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
 socket_io = SocketIO(app)
 
-config = {}
-
+# initialize config
+# this is a module global
+app_config = InvokeAIAppConfig()
 
 # Add startup event to load dependencies
 @app.on_event("startup")
 async def startup_event():
-    config = Args()
-    config.parse_args()
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=app_config.allow_origins,
+        allow_credentials=app_config.allow_credentials,
+        allow_methods=app_config.allow_methods,
+        allow_headers=app_config.allow_headers,
+    )
 
     ApiDependencies.initialize(
-        config=config, event_handler_id=event_handler_id
+        config=app_config, event_handler_id=event_handler_id, logger=logger
     )
 
 
@@ -126,7 +121,6 @@ app.openapi = custom_openapi
 # Override API doc favicons
 app.mount("/static", StaticFiles(directory="static/dream_web"), name="static")
 
-
 @app.get("/docs", include_in_schema=False)
 def overridden_swagger():
     return get_swagger_ui_html(
@@ -144,17 +138,16 @@ def overridden_redoc():
         redoc_favicon_url="/static/favicon.ico",
     )
 
+# Must mount *after* the other routes else it borks em
+app.mount("/", StaticFiles(directory="invokeai/frontend/web/dist", html=True), name="ui")
 
 def invoke_api():
     # Start our own event loop for eventing usage
-    # TODO: determine if there's a better way to do this
     loop = asyncio.new_event_loop()
-    config = uvicorn.Config(app=app, host="0.0.0.0", port=9090, loop=loop)
+    config = uvicorn.Config(app=app, host=app_config.host, port=app_config.port, loop=loop)
     # Use access_log to turn off logging
-
     server = uvicorn.Server(config)
     loop.run_until_complete(server.serve())
 
-
 if __name__ == "__main__":
     invoke_api()

invokeai/app/cli/commands.py

@@ -2,14 +2,15 @@
 
 from abc import ABC, abstractmethod
 import argparse
-from typing import Any, Callable, Iterable, Literal, get_args, get_origin, get_type_hints
+from typing import Any, Callable, Iterable, Literal, Union, get_args, get_origin, get_type_hints
 from pydantic import BaseModel, Field
 import networkx as nx
 import matplotlib.pyplot as plt
 
+import invokeai.backend.util.logging as logger
 from ..invocations.baseinvocation import BaseInvocation
 from ..invocations.image import ImageField
-from ..services.graph import GraphExecutionState, LibraryGraph, GraphInvocation, Edge
+from ..services.graph import GraphExecutionState, LibraryGraph, Edge
 from ..services.invoker import Invoker
 
 
@@ -229,7 +230,7 @@ class HistoryCommand(BaseCommand):
         for i in range(min(self.count, len(history))):
             entry_id = history[-1 - i]
             entry = context.get_session().graph.get_node(entry_id)
-            print(f"{entry_id}: {get_invocation_command(entry)}")
+            logger.info(f"{entry_id}: {get_invocation_command(entry)}")
 
 
 class SetDefaultCommand(BaseCommand):
@@ -284,3 +285,19 @@ class DrawExecutionGraphCommand(BaseCommand):
         nx.draw_networkx_labels(nxgraph, pos, font_size=20, font_family="sans-serif")
         plt.axis("off")
         plt.show()
+
+class SortedHelpFormatter(argparse.HelpFormatter):
+    def _iter_indented_subactions(self, action):
+        try:
+            get_subactions = action._get_subactions
+        except AttributeError:
+            pass
+        else:
+            self._indent()
+            if isinstance(action, argparse._SubParsersAction):
+                for subaction in sorted(get_subactions(), key=lambda x: x.dest):
+                    yield subaction
+            else:
+                for subaction in get_subactions():
+                    yield subaction
+                self._dedent()

invokeai/app/cli/completer.py

@@ -10,9 +10,11 @@ import shlex
 from pathlib import Path
 from typing import List, Dict, Literal, get_args, get_type_hints, get_origin
 
-from ...backend import ModelManager, Globals
+import invokeai.backend.util.logging as logger
+from ...backend import ModelManager
 from ..invocations.baseinvocation import BaseInvocation
 from .commands import BaseCommand
+from ..services.invocation_services import InvocationServices
 
 # singleton object, class variable
 completer = None
@@ -130,13 +132,13 @@ class Completer(object):
             readline.redisplay()
             self.linebuffer = None
     
-def set_autocompleter(model_manager: ModelManager) -> Completer:
+def set_autocompleter(services: InvocationServices) -> Completer:
     global completer
     
     if completer:
         return completer
     
-    completer = Completer(model_manager)
+    completer = Completer(services.model_manager)
 
     readline.set_completer(completer.complete)
     # pyreadline3 does not have a set_auto_history() method
@@ -152,7 +154,7 @@ def set_autocompleter(model_manager: ModelManager) -> Completer:
     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")
+    histfile = Path(services.configuration.root_dir / ".invoke_history")
     try:
         readline.read_history_file(histfile)
         readline.set_history_length(1000)
@@ -160,8 +162,8 @@ def set_autocompleter(model_manager: ModelManager) -> Completer:
         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}"
+        logger.error(
+            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

@@ -4,28 +4,29 @@ import argparse
 import os
 import re
 import shlex
+import sys
 import time
 from typing import (
     Union,
     get_type_hints,
 )
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ValidationError
 from pydantic.fields import Field
 
-from .services.default_graphs import create_system_graphs
 
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.metadata import PngMetadataService
+from .services.default_graphs import create_system_graphs
 from .services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
 
-from ..backend import Args
-from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, get_graph_execution_history
+from .cli.commands import BaseCommand, CliContext, ExitCli, add_graph_parsers, add_parsers, SortedHelpFormatter
 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, ExposedNodeInput, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
+from .services.graph import Edge, EdgeConnection, GraphExecutionState, GraphInvocation, LibraryGraph, are_connection_types_compatible
 from .services.default_graphs import default_text_to_image_graph_id
 from .services.image_storage import DiskImageStorage
 from .services.invocation_queue import MemoryInvocationQueue
@@ -33,7 +34,7 @@ from .services.invocation_services import InvocationServices
 from .services.invoker import Invoker
 from .services.processor import DefaultInvocationProcessor
 from .services.sqlite import SqliteItemStorage
-
+from .services.config import get_invokeai_config
 
 class CliCommand(BaseModel):
     command: Union[BaseCommand.get_commands() + BaseInvocation.get_invocations()] = Field(discriminator="type")  # type: ignore
@@ -63,7 +64,7 @@ def add_invocation_args(command_parser):
 
 def get_command_parser(services: InvocationServices) -> argparse.ArgumentParser:
     # Create invocation parser
-    parser = argparse.ArgumentParser()
+    parser = argparse.ArgumentParser(formatter_class=SortedHelpFormatter)
 
     def exit(*args, **kwargs):
         raise InvalidArgs
@@ -180,7 +181,7 @@ def invoke_all(context: CliContext):
     # Print any errors
     if context.session.has_error():
         for n in context.session.errors:
-            print(
+            context.invoker.services.logger.error(
                 f"Error in node {n} (source node {context.session.prepared_source_mapping[n]}): {context.session.errors[n]}"
             )
         
@@ -188,21 +189,24 @@ def invoke_all(context: CliContext):
 
 
 def invoke_cli():
-    config = Args()
-    config.parse_args()
-    model_manager = get_model_manager(config)
+    # this gets the basic configuration
+    config = get_invokeai_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)
+    # get the optional list of invocations to execute on the command line
+    parser = config.get_parser()
+    parser.add_argument('commands',nargs='*')
+    invocation_commands = parser.parse_args().commands
 
+    # get the optional file to read commands from.
+    # Simplest is to use it for STDIN
+    if infile := config.from_file:
+        sys.stdin = open(infile,"r")
+    
+    model_manager = get_model_manager(config,logger=logger)
+    
     events = EventServiceBase()
-
-    output_folder = os.path.abspath(
-        os.path.join(os.path.dirname(__file__), "../../../outputs")
-    )
+    output_folder = config.output_path
+    metadata = PngMetadataService()
 
     # TODO: build a file/path manager?
     db_location = os.path.join(output_folder, "invokeai.db")
@@ -211,7 +215,8 @@ def invoke_cli():
         model_manager=model_manager,
         events=events,
         latents = ForwardCacheLatentsStorage(DiskLatentsStorage(f'{output_folder}/latents')),
-        images=DiskImageStorage(f'{output_folder}/images'),
+        images=DiskImageStorage(f'{output_folder}/images', metadata_service=metadata),
+        metadata=metadata,
         queue=MemoryInvocationQueue(),
         graph_library=SqliteItemStorage[LibraryGraph](
             filename=db_location, table_name="graphs"
@@ -220,7 +225,9 @@ def invoke_cli():
             filename=db_location, table_name="graph_executions"
         ),
         processor=DefaultInvocationProcessor(),
-        restoration=RestorationServices(config),
+        restoration=RestorationServices(config,logger=logger),
+        logger=logger,
+        configuration=config,
     )
 
     system_graphs = create_system_graphs(services.graph_library)
@@ -236,10 +243,18 @@ def invoke_cli():
     # print(services.session_manager.list())
 
     context = CliContext(invoker, session, parser)
+    set_autocompleter(services)
 
-    while True:
+    command_line_args_exist = len(invocation_commands) > 0
+    done = False
+    
+    while not done:
         try:
-            cmd_input = input("invoke> ")
+            if command_line_args_exist:
+                cmd_input = invocation_commands.pop(0)
+                done = len(invocation_commands) == 0
+            else:
+                cmd_input = input("invoke> ")
         except (KeyboardInterrupt, EOFError):
             # Ctrl-c exits
             break
@@ -360,12 +375,15 @@ def invoke_cli():
             invoke_all(context)
 
         except InvalidArgs:
-            print('Invalid command, use "help" to list commands')
+            invoker.services.logger.warning('Invalid command, use "help" to list commands')
             continue
 
+        except ValidationError:
+            invoker.services.logger.warning('Invalid command arguments, run "<command> --help" for summary')
+
         except SessionError:
             # Start a new session
-            print("Session error: creating a new session")
+            invoker.services.logger.warning("Session error: creating a new session")
             context.reset()
 
         except ExitCli:

invokeai/app/invocations/collections.py

@@ -3,12 +3,12 @@
 from typing import Literal, Optional
 
 import numpy as np
-import numpy.random
 from pydantic import Field
 
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+
 from .baseinvocation import (
     BaseInvocation,
-    InvocationConfig,
     InvocationContext,
     BaseInvocationOutput,
 )
@@ -50,11 +50,11 @@ class RandomRangeInvocation(BaseInvocation):
         default=np.iinfo(np.int32).max, description="The exclusive high value"
     )
     size: int = Field(default=1, description="The number of values to generate")
-    seed: Optional[int] = Field(
+    seed: int = Field(
         ge=0,
-        le=np.iinfo(np.int32).max,
-        description="The seed for the RNG",
-        default_factory=lambda: numpy.random.randint(0, np.iinfo(np.int32).max),
+        le=SEED_MAX,
+        description="The seed for the RNG (omit for random)",
+        default_factory=get_random_seed,
     )
 
     def invoke(self, context: InvocationContext) -> IntCollectionOutput:

invokeai/app/invocations/compel.py

@@ -0,0 +1,244 @@
+from typing import Literal, Optional, Union
+from pydantic import BaseModel, Field
+
+from invokeai.app.invocations.util.choose_model import choose_model
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+
+from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
+from ...backend.stable_diffusion.textual_inversion_manager import TextualInversionManager
+
+from compel import Compel
+from compel.prompt_parser import (
+    Blend,
+    CrossAttentionControlSubstitute,
+    FlattenedPrompt,
+    Fragment,
+)
+
+
+class ConditioningField(BaseModel):
+    conditioning_name: Optional[str] = Field(default=None, description="The name of conditioning data")
+    class Config:
+        schema_extra = {"required": ["conditioning_name"]}
+
+
+class CompelOutput(BaseInvocationOutput):
+    """Compel parser output"""
+
+    #fmt: off
+    type: Literal["compel_output"] = "compel_output"
+
+    conditioning: ConditioningField = Field(default=None, description="Conditioning")
+    #fmt: on
+
+
+class CompelInvocation(BaseInvocation):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["compel"] = "compel"
+
+    prompt: str = Field(default="", description="Prompt")
+    model: str = Field(default="", description="Model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                  "model": "model"
+                }
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+
+        # TODO: load without model
+        model = choose_model(context.services.model_manager, self.model)
+        pipeline = model["model"]
+        tokenizer = pipeline.tokenizer
+        text_encoder = pipeline.text_encoder
+
+        # TODO: global? input?
+        #use_full_precision = precision == "float32" or precision == "autocast"
+        #use_full_precision = False
+
+        # TODO: redo TI when separate model loding implemented
+        #textual_inversion_manager = TextualInversionManager(
+        #    tokenizer=tokenizer,
+        #    text_encoder=text_encoder,
+        #    full_precision=use_full_precision,
+        #)
+
+        def load_huggingface_concepts(concepts: list[str]):
+            pipeline.textual_inversion_manager.load_huggingface_concepts(concepts)
+
+        # apply the concepts library to the prompt
+        prompt_str = pipeline.textual_inversion_manager.hf_concepts_library.replace_concepts_with_triggers(
+            self.prompt,
+            lambda concepts: load_huggingface_concepts(concepts),
+            pipeline.textual_inversion_manager.get_all_trigger_strings(),
+        )
+
+        # lazy-load any deferred textual inversions.
+        # this might take a couple of seconds the first time a textual inversion is used.
+        pipeline.textual_inversion_manager.create_deferred_token_ids_for_any_trigger_terms(
+            prompt_str
+        )
+
+        compel = Compel(
+            tokenizer=tokenizer,
+            text_encoder=text_encoder,
+            textual_inversion_manager=pipeline.textual_inversion_manager,
+            dtype_for_device_getter=torch_dtype,
+            truncate_long_prompts=True, # TODO:
+        )
+
+        # TODO: support legacy blend?
+
+        conjunction = Compel.parse_prompt_string(prompt_str)
+        prompt: Union[FlattenedPrompt, Blend] = conjunction.prompts[0]
+
+        if context.services.configuration.log_tokenization:
+            log_tokenization_for_prompt_object(prompt, tokenizer)
+
+        c, options = compel.build_conditioning_tensor_for_prompt_object(prompt)
+
+        # TODO: long prompt support
+        #if not self.truncate_long_prompts:
+        #    [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
+
+        ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+            tokens_count_including_eos_bos=get_max_token_count(tokenizer, prompt),
+            cross_attention_control_args=options.get("cross_attention_control", None),
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+
+        # TODO: hacky but works ;D maybe rename latents somehow?
+        context.services.latents.set(conditioning_name, (c, ec))
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
+def get_max_token_count(
+    tokenizer, prompt: Union[FlattenedPrompt, Blend], truncate_if_too_long=False
+) -> int:
+    if type(prompt) is Blend:
+        blend: Blend = prompt
+        return max(
+            [
+                get_max_token_count(tokenizer, c, truncate_if_too_long)
+                for c in blend.prompts
+            ]
+        )
+    else:
+        return len(
+            get_tokens_for_prompt_object(tokenizer, prompt, truncate_if_too_long)
+        )
+
+
+def get_tokens_for_prompt_object(
+    tokenizer, parsed_prompt: FlattenedPrompt, truncate_if_too_long=True
+) -> [str]:
+    if type(parsed_prompt) is Blend:
+        raise ValueError(
+            "Blend is not supported here - you need to get tokens for each of its .children"
+        )
+
+    text_fragments = [
+        x.text
+        if type(x) is Fragment
+        else (
+            " ".join([f.text for f in x.original])
+            if type(x) is CrossAttentionControlSubstitute
+            else str(x)
+        )
+        for x in parsed_prompt.children
+    ]
+    text = " ".join(text_fragments)
+    tokens = tokenizer.tokenize(text)
+    if truncate_if_too_long:
+        max_tokens_length = tokenizer.model_max_length - 2  # typically 75
+        tokens = tokens[0:max_tokens_length]
+    return tokens
+
+
+def log_tokenization_for_prompt_object(
+    p: Union[Blend, FlattenedPrompt], tokenizer, display_label_prefix=None
+):
+    display_label_prefix = display_label_prefix or ""
+    if type(p) is Blend:
+        blend: Blend = p
+        for i, c in enumerate(blend.prompts):
+            log_tokenization_for_prompt_object(
+                c,
+                tokenizer,
+                display_label_prefix=f"{display_label_prefix}(blend part {i + 1}, weight={blend.weights[i]})",
+            )
+    elif type(p) is FlattenedPrompt:
+        flattened_prompt: FlattenedPrompt = p
+        if flattened_prompt.wants_cross_attention_control:
+            original_fragments = []
+            edited_fragments = []
+            for f in flattened_prompt.children:
+                if type(f) is CrossAttentionControlSubstitute:
+                    original_fragments += f.original
+                    edited_fragments += f.edited
+                else:
+                    original_fragments.append(f)
+                    edited_fragments.append(f)
+
+            original_text = " ".join([x.text for x in original_fragments])
+            log_tokenization_for_text(
+                original_text,
+                tokenizer,
+                display_label=f"{display_label_prefix}(.swap originals)",
+            )
+            edited_text = " ".join([x.text for x in edited_fragments])
+            log_tokenization_for_text(
+                edited_text,
+                tokenizer,
+                display_label=f"{display_label_prefix}(.swap replacements)",
+            )
+        else:
+            text = " ".join([x.text for x in flattened_prompt.children])
+            log_tokenization_for_text(
+                text, tokenizer, display_label=display_label_prefix
+            )
+
+
+def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_too_long=False):
+    """shows how the prompt is tokenized
+    # usually tokens have '</w>' to indicate end-of-word,
+    # but for readability it has been replaced with ' '
+    """
+    tokens = tokenizer.tokenize(text)
+    tokenized = ""
+    discarded = ""
+    usedTokens = 0
+    totalTokens = len(tokens)
+
+    for i in range(0, totalTokens):
+        token = tokens[i].replace("</w>", " ")
+        # alternate color
+        s = (usedTokens % 6) + 1
+        if truncate_if_too_long and i >= tokenizer.model_max_length:
+            discarded = discarded + f"\x1b[0;3{s};40m{token}"
+        else:
+            tokenized = tokenized + f"\x1b[0;3{s};40m{token}"
+            usedTokens += 1
+
+    if usedTokens > 0:
+        print(f'\n>> [TOKENLOG] Tokens {display_label or ""} ({usedTokens}):')
+        print(f"{tokenized}\x1b[0m")
+
+    if discarded != "":
+        print(f"\n>> [TOKENLOG] Tokens Discarded ({totalTokens - usedTokens}):")
+        print(f"{discarded}\x1b[0m")

invokeai/app/invocations/cv.py

@@ -8,7 +8,6 @@ from PIL import Image, ImageOps
 from pydantic import BaseModel, Field
 
 from invokeai.app.models.image import ImageField, ImageType
-from invokeai.app.modules.metadata import MetadataModule
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
 from .image import ImageOutput, build_image_output
 
@@ -58,8 +57,8 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
         
         context.services.images.save(image_type, image_name, image_inpainted, metadata)

invokeai/app/invocations/generate.py

@@ -1,16 +1,17 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
 from functools import partial
-from typing import Literal, Optional, Union
+from typing import Literal, Optional, Union, get_args
 
 import numpy as np
 from torch import Tensor
 
 from pydantic import BaseModel, Field
 
-from invokeai.app.models.image import ImageField, ImageType
+from invokeai.app.models.image import ColorField, ImageField, ImageType
 from invokeai.app.invocations.util.choose_model import choose_model
-from invokeai.app.modules.metadata import MetadataModule
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.generator.inpaint import infill_methods
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
 from .image import ImageOutput, build_image_output
 from ...backend.generator import Txt2Img, Img2Img, Inpaint, InvokeAIGenerator
@@ -18,7 +19,8 @@ from ...backend.stable_diffusion import PipelineIntermediateState
 from ..util.step_callback import stable_diffusion_step_callback
 
 SAMPLER_NAME_VALUES = Literal[tuple(InvokeAIGenerator.schedulers())]
-
+INFILL_METHODS = Literal[tuple(infill_methods())]
+DEFAULT_INFILL_METHOD = 'patchmatch' if 'patchmatch' in get_args(INFILL_METHODS) else 'tile'
 
 class SDImageInvocation(BaseModel):
     """Helper class to provide all Stable Diffusion raster image invocations with additional config"""
@@ -45,15 +47,13 @@ class TextToImageInvocation(BaseInvocation, SDImageInvocation):
     # 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)", )
-    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", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
-    seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    seed:        int = Field(ge=0, le=SEED_MAX, description="The seed to use (omit for random)", default_factory=get_random_seed)
+    steps:       int = Field(default=30, gt=0, description="The number of steps to use to generate the image")
+    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting image", )
+    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting image", )
+    cfg_scale: float = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="lms", description="The scheduler to use" )
     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?
@@ -66,7 +66,7 @@ class TextToImageInvocation(BaseInvocation, SDImageInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            invocation_dict=self.dict(),
+            node=self.dict(),
             source_node_id=source_node_id,
         )
 
@@ -99,8 +99,8 @@ class TextToImageInvocation(BaseInvocation, SDImageInvocation):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(
@@ -137,7 +137,7 @@ class ImageToImageInvocation(TextToImageInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            invocation_dict=self.dict(),
+            node=self.dict(),
             source_node_id=source_node_id,
         )
 
@@ -149,7 +149,9 @@ class ImageToImageInvocation(TextToImageInvocation):
                 self.image.image_type, self.image.image_name
             )
         )
-        mask = None
+
+        if self.fit:
+            image = image.resize((self.width, self.height))
 
         # Handle invalid model parameter
         model = choose_model(context.services.model_manager, self.model)
@@ -163,7 +165,6 @@ class ImageToImageInvocation(TextToImageInvocation):
         outputs = Img2Img(model).generate(
             prompt=self.prompt,
             init_image=image,
-            init_mask=mask,
             step_callback=partial(self.dispatch_progress, context, source_node_id),
             **self.dict(
                 exclude={"prompt", "image", "mask"}
@@ -184,8 +185,8 @@ class ImageToImageInvocation(TextToImageInvocation):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, result_image, metadata)
@@ -195,7 +196,6 @@ class ImageToImageInvocation(TextToImageInvocation):
             image=result_image,
         )
 
-
 class InpaintInvocation(ImageToImageInvocation):
     """Generates an image using inpaint."""
 
@@ -203,6 +203,17 @@ class InpaintInvocation(ImageToImageInvocation):
 
     # Inputs
     mask: Union[ImageField, None] = Field(description="The mask")
+    seam_size: int = Field(default=96, ge=1, description="The seam inpaint size (px)")
+    seam_blur: int = Field(default=16, ge=0, description="The seam inpaint blur radius (px)")
+    seam_strength: float = Field(
+        default=0.75, gt=0, le=1, description="The seam inpaint strength"
+    )
+    seam_steps: int = Field(default=30, ge=1, description="The number of steps to use for seam inpaint")
+    tile_size: int = Field(default=32, ge=1, description="The tile infill method size (px)")
+    infill_method: INFILL_METHODS = Field(default=DEFAULT_INFILL_METHOD, description="The method used to infill empty regions (px)")
+    inpaint_width:       Optional[int] = Field(default=None, multiple_of=8, gt=0, description="The width of the inpaint region (px)")
+    inpaint_height:      Optional[int] = Field(default=None, multiple_of=8, gt=0, description="The height of the inpaint region (px)")
+    inpaint_fill: Optional[ColorField] = Field(default=ColorField(r=127, g=127, b=127, a=255), description="The solid infill method color")
     inpaint_replace: float = Field(
         default=0.0,
         ge=0.0,
@@ -219,7 +230,7 @@ class InpaintInvocation(ImageToImageInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            invocation_dict=self.dict(),
+            node=self.dict(),
             source_node_id=source_node_id,
         )
 
@@ -248,8 +259,8 @@ class InpaintInvocation(ImageToImageInvocation):
 
         outputs = Inpaint(model).generate(
             prompt=self.prompt,
-            init_img=image,
-            init_mask=mask,
+            init_image=image,
+            mask_image=mask,
             step_callback=partial(self.dispatch_progress, context, source_node_id),
             **self.dict(
                 exclude={"prompt", "image", "mask"}
@@ -270,8 +281,8 @@ class InpaintInvocation(ImageToImageInvocation):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, result_image, metadata)

invokeai/app/invocations/image.py

@@ -1,13 +1,12 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
+import io
 from typing import Literal, Optional
 
 import numpy
 from PIL import Image, ImageFilter, ImageOps
 from pydantic import BaseModel, Field
 
-from invokeai.app.modules.metadata import MetadataModule
-
 from ..models.image import ImageField, ImageType
 from .baseinvocation import (
     BaseInvocation,
@@ -34,15 +33,12 @@ class ImageOutput(BaseInvocationOutput):
     # fmt: off
     type: Literal["image"] = "image"
     image:      ImageField = Field(default=None, description="The output image")
-    width:   Optional[int] = Field(default=None, description="The width of the image in pixels")
-    height:  Optional[int] = Field(default=None, description="The height of the image in pixels")
-    mode:    Optional[str] = Field(default=None, description="The image mode (ie pixel format)")
+    width:             int = Field(description="The width of the image in pixels")
+    height:            int = Field(description="The height of the image in pixels")
     # fmt: on
 
     class Config:
-        schema_extra = {
-            "required": ["type", "image", "width", "height", "mode"]
-        }
+        schema_extra = {"required": ["type", "image", "width", "height"]}
 
 
 def build_image_output(
@@ -57,7 +53,6 @@ def build_image_output(
         image=image_field,
         width=image.width,
         height=image.height,
-        mode=image.mode,
     )
 
 
@@ -151,10 +146,10 @@ class CropImageInvocation(BaseInvocation, PILInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
-        
+
         context.services.images.save(image_type, image_name, image_crop, metadata)
         return build_image_output(
             image_type=image_type,
@@ -209,10 +204,10 @@ class PasteImageInvocation(BaseInvocation, PILInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
-        
+
         context.services.images.save(image_type, image_name, new_image, metadata)
         return build_image_output(
             image_type=image_type,
@@ -246,8 +241,8 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, image_mask, metadata)
@@ -283,8 +278,8 @@ class BlurInvocation(BaseInvocation, PILInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, blur_image, metadata)
@@ -320,8 +315,8 @@ class LerpInvocation(BaseInvocation, PILInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, lerp_image, metadata)
@@ -362,8 +357,8 @@ class InverseLerpInvocation(BaseInvocation, PILInvocationConfig):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, ilerp_image, metadata)

invokeai/app/invocations/infill.py

@@ -0,0 +1,233 @@
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+
+from typing import Literal, Optional, Union, get_args
+
+import numpy as np
+import math
+from PIL import Image, ImageOps
+from pydantic import Field
+
+from invokeai.app.invocations.image import ImageOutput, build_image_output
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
+from invokeai.backend.image_util.patchmatch import PatchMatch
+
+from ..models.image import ColorField, ImageField, ImageType
+from .baseinvocation import (
+    BaseInvocation,
+    InvocationContext,
+)
+
+
+def infill_methods() -> list[str]:
+    methods = [
+        "tile",
+        "solid",
+    ]
+    if PatchMatch.patchmatch_available():
+        methods.insert(0, "patchmatch")
+    return methods
+
+
+INFILL_METHODS = Literal[tuple(infill_methods())]
+DEFAULT_INFILL_METHOD = (
+    "patchmatch" if "patchmatch" in get_args(INFILL_METHODS) else "tile"
+)
+
+
+def infill_patchmatch(im: Image.Image) -> Image.Image:
+    if im.mode != "RGBA":
+        return im
+
+    # Skip patchmatch if patchmatch isn't available
+    if not PatchMatch.patchmatch_available():
+        return im
+
+    # Patchmatch (note, we may want to expose patch_size? Increasing it significantly impacts performance though)
+    im_patched_np = PatchMatch.inpaint(
+        im.convert("RGB"), ImageOps.invert(im.split()[-1]), patch_size=3
+    )
+    im_patched = Image.fromarray(im_patched_np, mode="RGB")
+    return im_patched
+
+
+def get_tile_images(image: np.ndarray, width=8, height=8):
+    _nrows, _ncols, depth = image.shape
+    _strides = image.strides
+
+    nrows, _m = divmod(_nrows, height)
+    ncols, _n = divmod(_ncols, width)
+    if _m != 0 or _n != 0:
+        return None
+
+    return np.lib.stride_tricks.as_strided(
+        np.ravel(image),
+        shape=(nrows, ncols, height, width, depth),
+        strides=(height * _strides[0], width * _strides[1], *_strides),
+        writeable=False,
+    )
+
+
+def tile_fill_missing(
+    im: Image.Image, tile_size: int = 16, seed: Union[int, None] = None
+) -> Image.Image:
+    # Only fill if there's an alpha layer
+    if im.mode != "RGBA":
+        return im
+
+    a = np.asarray(im, dtype=np.uint8)
+
+    tile_size_tuple = (tile_size, tile_size)
+
+    # Get the image as tiles of a specified size
+    tiles = get_tile_images(a, *tile_size_tuple).copy()
+
+    # Get the mask as tiles
+    tiles_mask = tiles[:, :, :, :, 3]
+
+    # Find any mask tiles with any fully transparent pixels (we will be replacing these later)
+    tmask_shape = tiles_mask.shape
+    tiles_mask = tiles_mask.reshape(math.prod(tiles_mask.shape))
+    n, ny = (math.prod(tmask_shape[0:2])), math.prod(tmask_shape[2:])
+    tiles_mask = tiles_mask > 0
+    tiles_mask = tiles_mask.reshape((n, ny)).all(axis=1)
+
+    # Get RGB tiles in single array and filter by the mask
+    tshape = tiles.shape
+    tiles_all = tiles.reshape((math.prod(tiles.shape[0:2]), *tiles.shape[2:]))
+    filtered_tiles = tiles_all[tiles_mask]
+
+    if len(filtered_tiles) == 0:
+        return im
+
+    # Find all invalid tiles and replace with a random valid tile
+    replace_count = (tiles_mask == False).sum()
+    rng = np.random.default_rng(seed=seed)
+    tiles_all[np.logical_not(tiles_mask)] = filtered_tiles[
+        rng.choice(filtered_tiles.shape[0], replace_count), :, :, :
+    ]
+
+    # Convert back to an image
+    tiles_all = tiles_all.reshape(tshape)
+    tiles_all = tiles_all.swapaxes(1, 2)
+    st = tiles_all.reshape(
+        (
+            math.prod(tiles_all.shape[0:2]),
+            math.prod(tiles_all.shape[2:4]),
+            tiles_all.shape[4],
+        )
+    )
+    si = Image.fromarray(st, mode="RGBA")
+
+    return si
+
+
+class InfillColorInvocation(BaseInvocation):
+    """Infills transparent areas of an image with a solid color"""
+
+    type: Literal["infill_rgba"] = "infill_rgba"
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
+    color: Optional[ColorField] = Field(
+        default=ColorField(r=127, g=127, b=127, a=255),
+        description="The color to use to infill",
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+
+        solid_bg = Image.new("RGBA", image.size, self.color.tuple())
+        infilled = Image.alpha_composite(solid_bg, image)
+
+        infilled.paste(image, (0, 0), image.split()[-1])
+
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, infilled, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image,
+        )
+
+
+class InfillTileInvocation(BaseInvocation):
+    """Infills transparent areas of an image with tiles of the image"""
+
+    type: Literal["infill_tile"] = "infill_tile"
+
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
+    tile_size: int = Field(default=32, ge=1, description="The tile size (px)")
+    seed: int = Field(
+        ge=0,
+        le=SEED_MAX,
+        description="The seed to use for tile generation (omit for random)",
+        default_factory=get_random_seed,
+    )
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+
+        infilled = tile_fill_missing(
+            image.copy(), seed=self.seed, tile_size=self.tile_size
+        )
+        infilled.paste(image, (0, 0), image.split()[-1])
+
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, infilled, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image,
+        )
+
+
+class InfillPatchMatchInvocation(BaseInvocation):
+    """Infills transparent areas of an image using the PatchMatch algorithm"""
+
+    type: Literal["infill_patchmatch"] = "infill_patchmatch"
+
+    image: Optional[ImageField] = Field(default=None, description="The image to infill")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+
+        if PatchMatch.patchmatch_available():
+            infilled = infill_patchmatch(image.copy())
+        else:
+            raise ValueError("PatchMatch is not available on this system")
+
+        image_type = ImageType.RESULT
+        image_name = context.services.images.create_name(
+            context.graph_execution_state_id, self.id
+        )
+
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
+        )
+
+        context.services.images.save(image_type, image_name, infilled, metadata)
+        return build_image_output(
+            image_type=image_type,
+            image_name=image_name,
+            image=image,
+        )

invokeai/app/invocations/latent.py

@@ -1,12 +1,13 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
 
 import random
-from typing import Literal, Optional
+from typing import Literal, Optional, Union
+import einops
 from pydantic import BaseModel, Field
 import torch
 
 from invokeai.app.invocations.util.choose_model import choose_model
-from invokeai.app.modules.metadata import MetadataModule
+from invokeai.app.util.misc import SEED_MAX, get_random_seed
 
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 
@@ -15,12 +16,14 @@ from ...backend.util.devices import choose_torch_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 ...backend.stable_diffusion.diffusers_pipeline import ConditioningData, StableDiffusionGeneratorPipeline, image_resized_to_grid_as_tensor
+from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
 import numpy as np
 from ..services.image_storage import ImageType
 from .baseinvocation import BaseInvocation, InvocationContext
 from .image import ImageField, ImageOutput, build_image_output
+from .compel import ConditioningField
 from ...backend.stable_diffusion import PipelineIntermediateState
 from diffusers.schedulers import SchedulerMixin as Scheduler
 import diffusers
@@ -32,45 +35,61 @@ class LatentsField(BaseModel):
 
     latents_name: Optional[str] = Field(default=None, description="The name of the latents")
 
+    class Config:
+        schema_extra = {"required": ["latents_name"]}
 
 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")
+    type: Literal["latents_output"] = "latents_output"
+
+    # Inputs
+    latents: LatentsField          = Field(default=None, description="The output latents")
+    width:                     int = Field(description="The width of the latents in pixels")
+    height:                    int = Field(description="The height of the latents in pixels")
     #fmt: on
 
+
+def build_latents_output(latents_name: str, latents: torch.Tensor):
+      return LatentsOutput(
+          latents=LatentsField(latents_name=latents_name),
+          width=latents.size()[3] * 8,
+          height=latents.size()[2] * 8,
+      )
+
 class NoiseOutput(BaseInvocationOutput):
     """Invocation noise output"""
     #fmt: off
-    type: Literal["noise_output"] = "noise_output"
+    type:  Literal["noise_output"] = "noise_output"
+
+    # Inputs
     noise: LatentsField            = Field(default=None, description="The output noise")
+    width:                     int = Field(description="The width of the noise in pixels")
+    height:                    int = Field(description="The height of the noise in pixels")
     #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,
-)
+def build_noise_output(latents_name: str, latents: torch.Tensor):
+      return NoiseOutput(
+          noise=LatentsField(latents_name=latents_name),
+          width=latents.size()[3] * 8,
+          height=latents.size()[2] * 8,
+      )
 
 
 SAMPLER_NAME_VALUES = Literal[
-    tuple(list(scheduler_map.keys()))
+    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)
+    scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
+    
+    scheduler_config = model.scheduler.config
+    if "_backup" in scheduler_config:
+        scheduler_config = scheduler_config["_backup"]
+    scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
+    scheduler = scheduler_class.from_config(scheduler_config)
+    
     # hack copied over from generate.py
     if not hasattr(scheduler, 'uses_inpainting_model'):
         scheduler.uses_inpainting_model = lambda: False
@@ -101,19 +120,15 @@ def get_noise(width:int, height:int, device:torch.device, seed:int = 0, latent_c
     return x
 
 
-def random_seed():
-    return random.randint(0, np.iinfo(np.uint32).max)
-
-
 class NoiseInvocation(BaseInvocation):
     """Generates latent noise."""
 
     type: Literal["noise"] = "noise"
 
     # Inputs
-    seed:        int = Field(ge=0, le=np.iinfo(np.uint32).max, description="The seed to use", default_factory=random_seed)
-    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", )
+    seed:       int = Field(ge=0, le=SEED_MAX, description="The seed to use", default_factory=get_random_seed)
+    width:       int = Field(default=512, multiple_of=8, gt=0, description="The width of the resulting noise", )
+    height:      int = Field(default=512, multiple_of=8, gt=0, description="The height of the resulting noise", )
 
 
     # Schema customisation
@@ -130,32 +145,26 @@ class NoiseInvocation(BaseInvocation):
 
         name = f'{context.graph_execution_state_id}__{self.id}'
         context.services.latents.set(name, noise)
-        return NoiseOutput(
-            noise=LatentsField(latents_name=name)
-        )
+        return build_noise_output(latents_name=name, latents=noise)
 
 
 # Text to image
 class TextToLatentsInvocation(BaseInvocation):
-    """Generates latents from a prompt."""
+    """Generates latents from conditionings."""
 
     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)", )
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
     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", )
-    scheduler: SAMPLER_NAME_VALUES = Field(default="k_lms", description="The scheduler to use" )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="lms", description="The scheduler to use" )
+    model:       str = Field(default="", description="The model to use (currently ignored)")
     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
 
     # Schema customisation
@@ -176,7 +185,7 @@ class TextToLatentsInvocation(BaseInvocation):
         stable_diffusion_step_callback(
             context=context,
             intermediate_state=intermediate_state,
-            invocation_dict=self.dict(),
+            node=self.dict(),
             source_node_id=source_node_id,
         )
 
@@ -205,8 +214,10 @@ class TextToLatentsInvocation(BaseInvocation):
         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)
+    def get_conditioning_data(self, context: InvocationContext, model: StableDiffusionGeneratorPipeline) -> ConditioningData:
+        c, extra_conditioning_info = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        uc, _ = context.services.latents.get(self.negative_conditioning.conditioning_name)
+
         conditioning_data = ConditioningData(
             uc,
             c,
@@ -218,7 +229,7 @@ class TextToLatentsInvocation(BaseInvocation):
                 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)
+        ).add_scheduler_args_if_applicable(model.scheduler, eta=0.0)#ddim_eta)
         return conditioning_data
 
 
@@ -233,7 +244,7 @@ class TextToLatentsInvocation(BaseInvocation):
             self.dispatch_progress(context, source_node_id, state)
 
         model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
+        conditioning_data = self.get_conditioning_data(context, model)
 
         # TODO: Verify the noise is the right size
 
@@ -250,9 +261,7 @@ class TextToLatentsInvocation(BaseInvocation):
 
         name = f'{context.graph_execution_state_id}__{self.id}'
         context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
+        return build_latents_output(latents_name=name, latents=result_latents)
 
 
 class LatentsToLatentsInvocation(TextToLatentsInvocation):
@@ -260,6 +269,10 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
 
     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")
+
     # Schema customisation
     class Config(InvocationConfig):
         schema_extra = {
@@ -271,10 +284,6 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             },
         }
 
-    # 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)
@@ -287,7 +296,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             self.dispatch_progress(context, source_node_id, state)
 
         model = self.get_model(context.services.model_manager)
-        conditioning_data = self.get_conditioning_data(model)
+        conditioning_data = self.get_conditioning_data(context, model)
 
         # TODO: Verify the noise is the right size
 
@@ -295,11 +304,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
             latent, device=model.device, dtype=latent.dtype
         )
 
-        timesteps, _ = model.get_img2img_timesteps(
-            self.steps,
-            self.strength,
-            device=model.device,
-        )
+        timesteps, _ = model.get_img2img_timesteps(self.steps, self.strength)
 
         result_latents, result_attention_map_saver = model.latents_from_embeddings(
             latents=initial_latents,
@@ -315,9 +320,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
 
         name = f'{context.graph_execution_state_id}__{self.id}'
         context.services.latents.set(name, result_latents)
-        return LatentsOutput(
-            latents=LatentsField(latents_name=name)
-        )
+        return build_latents_output(latents_name=name, latents=result_latents)
 
 
 # Latent to image
@@ -358,13 +361,122 @@ class LatentsToImageInvocation(BaseInvocation):
                 context.graph_execution_state_id, self.id
             )
 
-            metadata = MetadataModule.build_metadata(
-                session_id=context.graph_execution_state_id, invocation=self
+            metadata = context.services.metadata.build_metadata(
+                session_id=context.graph_execution_state_id, node=self
             )
 
+            torch.cuda.empty_cache()
+
             context.services.images.save(image_type, image_name, image, metadata)
             return build_image_output(
-                image_type=image_type,
-                image_name=image_name,
-                image=image
+                image_type=image_type, image_name=image_name, image=image
             )
+
+
+LATENTS_INTERPOLATION_MODE = Literal[
+    "nearest", "linear", "bilinear", "bicubic", "trilinear", "area", "nearest-exact"
+]
+
+
+class ResizeLatentsInvocation(BaseInvocation):
+    """Resizes latents to explicit width/height (in pixels). Provided dimensions are floor-divided by 8."""
+
+    type: Literal["lresize"] = "lresize"
+
+    # Inputs
+    latents:    Optional[LatentsField] = Field(description="The latents to resize")
+    width:                         int = Field(ge=64, multiple_of=8, description="The width to resize to (px)")
+    height:                        int = Field(ge=64, multiple_of=8, description="The height to resize to (px)")
+    mode:   LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
+    antialias:                    bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        resized_latents = torch.nn.functional.interpolate(
+            latents,
+            size=(self.height // 8, self.width // 8),
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
+        )
+
+        # 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, resized_latents)
+        return build_latents_output(latents_name=name, latents=resized_latents)
+
+
+class ScaleLatentsInvocation(BaseInvocation):
+    """Scales latents by a given factor."""
+
+    type: Literal["lscale"] = "lscale"
+
+    # Inputs
+    latents:   Optional[LatentsField] = Field(description="The latents to scale")
+    scale_factor:               float = Field(gt=0, description="The factor by which to scale the latents")
+    mode:  LATENTS_INTERPOLATION_MODE = Field(default="bilinear", description="The interpolation mode")
+    antialias:                   bool = Field(default=False, description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        # resizing
+        resized_latents = torch.nn.functional.interpolate(
+            latents,
+            scale_factor=self.scale_factor,
+            mode=self.mode,
+            antialias=self.antialias if self.mode in ["bilinear", "bicubic"] else False,
+        )
+
+        # 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, resized_latents)
+        return build_latents_output(latents_name=name, latents=resized_latents)
+
+
+class ImageToLatentsInvocation(BaseInvocation):
+    """Encodes an image into latents."""
+
+    type: Literal["i2l"] = "i2l"
+
+    # Inputs
+    image: Union[ImageField, None] = Field(description="The image to encode")
+    model: str = Field(default="", description="The model to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents", "image"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        image = context.services.images.get(
+            self.image.image_type, self.image.image_name
+        )
+
+        # TODO: this only really needs the vae
+        model_info = choose_model(context.services.model_manager, self.model)
+        model: StableDiffusionGeneratorPipeline = model_info["model"]
+
+        image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+
+        if image_tensor.dim() == 3:
+            image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
+
+        latents = model.non_noised_latents_from_image(
+            image_tensor,
+            device=model._model_group.device_for(model.unet),
+            dtype=model.unet.dtype,
+        )
+
+        name = f"{context.graph_execution_state_id}__{self.id}"
+        context.services.latents.set(name, latents)
+        return build_latents_output(latents_name=name, latents=latents)

invokeai/app/invocations/math.py

@@ -3,8 +3,14 @@
 from typing import Literal
 
 from pydantic import BaseModel, Field
+import numpy as np
 
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext, InvocationConfig
+from .baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    InvocationContext,
+    InvocationConfig,
+)
 
 
 class MathInvocationConfig(BaseModel):
@@ -21,19 +27,21 @@ class MathInvocationConfig(BaseModel):
 
 class IntOutput(BaseInvocationOutput):
     """An integer output"""
-    #fmt: off
+
+    # fmt: off
     type: Literal["int_output"] = "int_output"
     a: int = Field(default=None, description="The output integer")
-    #fmt: on
+    # fmt: on
 
 
 class AddInvocation(BaseInvocation, MathInvocationConfig):
     """Adds two numbers"""
-    #fmt: off
+
+    # 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
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a + self.b)
@@ -41,11 +49,12 @@ class AddInvocation(BaseInvocation, MathInvocationConfig):
 
 class SubtractInvocation(BaseInvocation, MathInvocationConfig):
     """Subtracts two numbers"""
-    #fmt: off
+
+    # 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
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a - self.b)
@@ -53,11 +62,12 @@ class SubtractInvocation(BaseInvocation, MathInvocationConfig):
 
 class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
     """Multiplies two numbers"""
-    #fmt: off
+
+    # 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
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=self.a * self.b)
@@ -65,11 +75,26 @@ class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
 
 class DivideInvocation(BaseInvocation, MathInvocationConfig):
     """Divides two numbers"""
-    #fmt: off
+
+    # 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
+    # fmt: on
 
     def invoke(self, context: InvocationContext) -> IntOutput:
         return IntOutput(a=int(self.a / self.b))
+
+
+class RandomIntInvocation(BaseInvocation):
+    """Outputs a single random integer."""
+
+    # fmt: off
+    type: Literal["rand_int"] = "rand_int"
+    low: int = Field(default=0, description="The inclusive low value")
+    high: int = Field(
+        default=np.iinfo(np.int32).max, description="The exclusive high value"
+    )
+    # fmt: on
+    def invoke(self, context: InvocationContext) -> IntOutput:
+        return IntOutput(a=np.random.randint(self.low, self.high))

invokeai/app/invocations/reconstruct.py

@@ -3,7 +3,6 @@ from typing import Literal, Union
 from pydantic import Field
 
 from invokeai.app.models.image import ImageField, ImageType
-from invokeai.app.modules.metadata import MetadataModule
 
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
 from .image import ImageOutput, build_image_output
@@ -45,8 +44,8 @@ class RestoreFaceInvocation(BaseInvocation):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, results[0][0], metadata)

invokeai/app/invocations/upscale.py

@@ -5,7 +5,6 @@ from typing import Literal, Union
 from pydantic import Field
 
 from invokeai.app.models.image import ImageField, ImageType
-from invokeai.app.modules.metadata import MetadataModule
 from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
 from .image import ImageOutput, build_image_output
 
@@ -49,8 +48,8 @@ class UpscaleInvocation(BaseInvocation):
             context.graph_execution_state_id, self.id
         )
 
-        metadata = MetadataModule.build_metadata(
-            session_id=context.graph_execution_state_id, invocation=self
+        metadata = context.services.metadata.build_metadata(
+            session_id=context.graph_execution_state_id, node=self
         )
 
         context.services.images.save(image_type, image_name, results[0][0], metadata)

invokeai/app/invocations/util/choose_model.py

@@ -3,12 +3,12 @@ from invokeai.backend.model_management.model_manager import ModelManager
 
 def choose_model(model_manager: ModelManager, model_name: str):
     """Returns the default model if the `model_name` not a valid model, else returns the selected model."""
-    if model_manager.valid_model(model_name):
-        model = model_manager.get_model(model_name)
-    else:
+    logger = model_manager.logger
+    if model_name and not model_manager.valid_model(model_name):
+        default_model_name = model_manager.default_model()
+        logger.warning(f"\'{model_name}\' is not a valid model name. Using default model \'{default_model_name}\' instead.")
         model = model_manager.get_model()
-        print(
-            f"* Warning: '{model_name}' is not a valid model name. Using default model \'{model['model_name']}\' instead."
-        )
+    else:
+        model = model_manager.get_model(model_name)
 
     return model

invokeai/app/models/image.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Optional
+from typing import Optional, Tuple
 from pydantic import BaseModel, Field
 
 
@@ -9,6 +9,14 @@ class ImageType(str, Enum):
     UPLOAD = "uploads"
 
 
+def is_image_type(obj):
+    try:
+        ImageType(obj)
+    except ValueError:
+        return False
+    return True
+
+
 class ImageField(BaseModel):
     """An image field used for passing image objects between invocations"""
 
@@ -18,6 +26,14 @@ class ImageField(BaseModel):
     image_name: Optional[str] = Field(default=None, description="The name of the image")
 
     class Config:
-        schema_extra = {
-            "required": ["image_type", "image_name"]
-        }
+        schema_extra = {"required": ["image_type", "image_name"]}
+
+
+class ColorField(BaseModel):
+    r: int = Field(ge=0, le=255, description="The red component")
+    g: int = Field(ge=0, le=255, description="The green component")
+    b: int = Field(ge=0, le=255, description="The blue component")
+    a: int = Field(ge=0, le=255, description="The alpha component")
+
+    def tuple(self) -> Tuple[int, int, int, int]:
+        return (self.r, self.g, self.b, self.a)

invokeai/app/modules/metadata.py

@@ -1,180 +0,0 @@
-import json
-from typing import Any, Dict, Literal, Optional
-from PIL import Image, PngImagePlugin
-from pydantic import (
-    BaseModel,
-    Extra,
-    Field,
-    StrictBool,
-    StrictInt,
-    StrictStr,
-    ValidationError,
-    root_validator,
-)
-
-from invokeai.app.models.image import ImageType
-
-
-class MetadataImageField(BaseModel):
-    """A non-nullable version of ImageField"""
-
-    image_type: Literal[tuple([t.value for t in ImageType])]  # type: ignore
-    image_name: StrictStr
-
-
-class MetadataLatentsField(BaseModel):
-    """A non-nullable version of LatentsField"""
-
-    latents_name: StrictStr
-
-
-# Union of all valid metadata field types - use mostly strict types
-NodeMetadataFieldTypes = (
-    StrictStr | StrictInt | float | StrictBool  # we want to cast ints to floats here
-)
-
-
-class NodeMetadataField(BaseModel):
-    """Helper class used as a hack for arbitrary metadata field keys."""
-
-    __root__: Dict[StrictStr, NodeMetadataFieldTypes]
-
-
-# `extra=Extra.allow` allows this to model any potential node with `id` and `type` fields
-class NodeMetadata(BaseModel, extra=Extra.allow):
-    """Node metadata model, used for validation of metadata."""
-
-    @root_validator
-    def validate_node_metadata(cls, values: dict[str, Any]) -> dict[str, Any]:
-        """Parses the node metadata, ignoring invalid values"""
-        parsed: dict[str, Any] = {}
-
-        # Conditionally build the parsed metadata, silently skipping invalid values
-        for name, value in values.items():
-            # explicitly parse `id` and `type` as strings
-            if name == "id":
-                if type(value) is not str:
-                    continue
-                parsed[name] = value
-            elif name == "type":
-                if type(value) is not str:
-                    continue
-                parsed[name] = value
-            else:
-                try:
-                    if type(value) is dict:
-                        # we only allow certain dicts, else just ignore the value entirely
-                        if "image_name" in value or "image_type" in value:
-                            # parse as an ImageField
-                            parsed[name] = MetadataImageField.parse_obj(value)
-                        elif "latents_name" in value:
-                            # this is a LatentsField
-                            parsed[name] = MetadataLatentsField.parse_obj(value)
-                    else:
-                        # hack to get parse and validate arbitrary keys
-                        NodeMetadataField.parse_obj({name: value})
-                        parsed[name] = value
-                except ValidationError:
-                    # TODO: do we want to somehow alert when metadata is not fully valid?
-                    continue
-        return parsed
-
-
-class InvokeAIMetadata(BaseModel):
-    session_id: Optional[StrictStr] = Field(
-        description="The session in which this image was created"
-    )
-    node: Optional[NodeMetadata] = Field(description="The node that created this image")
-
-    @root_validator(pre=True)
-    def validate_invokeai_metadata(cls, values: dict[str, Any]) -> dict[str, Any]:
-        parsed: dict[str, Any] = {}
-        # Conditionally build the parsed metadata, silently skipping invalid values
-        for name, value in values.items():
-            if name == "session_id":
-                if type(value) is not str:
-                    continue
-                parsed[name] = value
-            elif name == "node":
-                try:
-                    p = NodeMetadata.parse_obj(value)
-                    # check for empty NodeMetadata object
-                    if len(p.dict().items()) == 0:
-                        continue
-                except ValidationError:
-                    continue
-                parsed[name] = value
-
-        return parsed
-
-
-class ImageMetadata(BaseModel):
-    """An image's metadata. Used only in HTTP responses."""
-
-    created: int = Field(description="The creation timestamp of the image")
-    width: int = Field(description="The width of the image in pixels")
-    height: int = Field(description="The height of the image in pixels")
-    mode: str = Field(description="The color mode of the image")
-    invokeai: Optional[InvokeAIMetadata] = Field(
-        description="The image's InvokeAI-specific metadata"
-    )
-
-
-class MetadataModule:
-    """Handles loading metadata from images and parsing it."""
-
-    # TODO: Support parsing old format metadata **hurk**
-
-    @staticmethod
-    def _load_metadata(image: Image.Image, key="invokeai") -> Any:
-        """Loads a specific info entry from a PIL Image."""
-
-        raw_metadata = image.info.get(key)
-
-        # metadata should always be a dict
-        if type(raw_metadata) is not str:
-            return None
-
-        loaded_metadata = json.loads(raw_metadata)
-
-        return loaded_metadata
-
-    @staticmethod
-    def _parse_invokeai_metadata(
-        metadata: Any,
-    ) -> InvokeAIMetadata | None:
-        """Parses an object as InvokeAI metadata."""
-        if type(metadata) is not dict:
-            return None
-
-        parsed_metadata = InvokeAIMetadata.parse_obj(metadata)
-
-        return parsed_metadata
-
-    @staticmethod
-    def get_metadata(image: Image.Image) -> InvokeAIMetadata | None:
-        """Gets the InvokeAI metadata from a PIL Image, skipping invalid values"""
-        loaded_metadata = MetadataModule._load_metadata(image)
-        parsed_metadata = MetadataModule._parse_invokeai_metadata(loaded_metadata)
-
-        return parsed_metadata
-
-    @staticmethod
-    def build_metadata(
-        session_id: StrictStr, invocation: BaseModel
-    ) -> InvokeAIMetadata:
-        """Builds an InvokeAIMetadata object"""
-        metadata = InvokeAIMetadata(
-            session_id=session_id, node=NodeMetadata(**invocation.dict())
-        )
-
-        return metadata
-
-    @staticmethod
-    def build_png_info(metadata: InvokeAIMetadata | None):
-        png_info = PngImagePlugin.PngInfo()
-
-        if metadata is not None:
-            png_info.add_text("invokeai", metadata.json())
-
-        return png_info

invokeai/app/services/config.py

@@ -0,0 +1,521 @@
+# Copyright (c) 2023 Lincoln Stein (https://github.com/lstein) and the InvokeAI Development Team
+
+'''Invokeai configuration system.
+
+Arguments and fields are taken from the pydantic definition of the
+model.  Defaults can be set by creating a yaml configuration file that
+has a top-level key of "InvokeAI" and subheadings for each of the
+categories returned by `invokeai --help`. The file looks like this:
+
+[file: invokeai.yaml]
+
+InvokeAI:
+  Paths:
+    root: /home/lstein/invokeai-main
+    conf_path: configs/models.yaml
+    legacy_conf_dir: configs/stable-diffusion
+    outdir: outputs
+    embedding_dir: embeddings
+    lora_dir: loras
+    autoconvert_dir: null
+    gfpgan_model_dir: models/gfpgan/GFPGANv1.4.pth
+  Models:
+    model: stable-diffusion-1.5
+    embeddings: true
+  Memory/Performance:
+    xformers_enabled: false
+    sequential_guidance: false
+    precision: float16
+    max_loaded_models: 4
+    always_use_cpu: false
+    free_gpu_mem: false
+  Features:
+    nsfw_checker: true
+    restore: true
+    esrgan: true
+    patchmatch: true
+    internet_available: true
+    log_tokenization: false
+  Web Server:
+    host: 127.0.0.1
+    port: 8081
+    allow_origins: []
+    allow_credentials: true
+    allow_methods:
+    - '*'
+    allow_headers:
+    - '*'
+
+The default name of the configuration file is `invokeai.yaml`, located
+in INVOKEAI_ROOT. You can replace supersede this by providing any
+OmegaConf dictionary object initialization time:
+
+ omegaconf = OmegaConf.load('/tmp/init.yaml')
+ conf = InvokeAIAppConfig(conf=omegaconf)
+
+By default, InvokeAIAppConfig will parse the contents of `sys.argv` at
+initialization time. You may pass a list of strings in the optional
+`argv` argument to use instead of the system argv:
+
+ conf = InvokeAIAppConfig(arg=['--xformers_enabled'])
+
+It is also possible to set a value at initialization time. This value
+has highest priority.
+
+ conf = InvokeAIAppConfig(xformers_enabled=True)
+
+Any setting can be overwritten by setting an environment variable of
+form: "INVOKEAI_<setting>", as in:
+
+  export INVOKEAI_port=8080
+
+Order of precedence (from highest):
+   1) initialization options
+   2) command line options
+   3) environment variable options
+   4) config file options
+   5) pydantic defaults
+
+Typical usage:
+
+ from invokeai.app.services.config import InvokeAIAppConfig
+ from invokeai.invocations.generate import TextToImageInvocation
+
+ # get global configuration and print its nsfw_checker value
+ conf = InvokeAIAppConfig()
+ print(conf.nsfw_checker)
+
+ # get the text2image invocation and print its step value
+ text2image = TextToImageInvocation()
+ print(text2image.steps)
+
+Computed properties:
+
+The InvokeAIAppConfig object has a series of properties that
+resolve paths relative to the runtime root directory. They each return
+a Path object:
+
+ root_path          - path to InvokeAI root
+ output_path        - path to default outputs directory
+ model_conf_path    - path to models.yaml
+ conf               - alias for the above
+ embedding_path     - path to the embeddings directory
+ lora_path          - path to the LoRA directory
+
+In most cases, you will want to create a single InvokeAIAppConfig
+object for the entire application. The get_invokeai_config() function
+does this:
+
+  config = get_invokeai_config()
+  print(config.root)
+
+# Subclassing
+
+If you wish to create a similar class, please subclass the
+`InvokeAISettings` class and define a Literal field named "type",
+which is set to the desired top-level name.  For example, to create a
+"InvokeBatch" configuration, define like this:
+
+  class InvokeBatch(InvokeAISettings):
+     type: Literal["InvokeBatch"] = "InvokeBatch"
+     node_count : int = Field(default=1, description="Number of nodes to run on", category='Resources')
+     cpu_count  : int = Field(default=8, description="Number of GPUs to run on per node", category='Resources')
+
+This will now read and write from the "InvokeBatch" section of the
+config file, look for environment variables named INVOKEBATCH_*, and
+accept the command-line arguments `--node_count` and `--cpu_count`. The
+two configs are kept in separate sections of the config file:
+
+  # invokeai.yaml
+
+  InvokeBatch:
+     Resources:
+        node_count: 1
+        cpu_count: 8
+
+  InvokeAI:
+     Paths:
+        root: /home/lstein/invokeai-main
+        conf_path: configs/models.yaml
+        legacy_conf_dir: configs/stable-diffusion
+        outdir: outputs
+     ...
+'''
+import argparse
+import pydoc
+import typing
+import os
+import sys
+from argparse import ArgumentParser
+from omegaconf import OmegaConf, DictConfig
+from pathlib import Path
+from pydantic import BaseSettings, Field, parse_obj_as
+from typing import Any, ClassVar, Dict, List, Literal, Type, Union, get_origin, get_type_hints, get_args
+
+INIT_FILE = Path('invokeai.yaml')
+LEGACY_INIT_FILE = Path('invokeai.init')
+
+# This global stores a singleton InvokeAIAppConfig configuration object
+global_config = None
+
+class InvokeAISettings(BaseSettings):
+    '''
+    Runtime configuration settings in which default values are
+    read from an omegaconf .yaml file.
+    '''
+    initconf             : ClassVar[DictConfig] = None
+    argparse_groups      : ClassVar[Dict] = {}
+
+    def parse_args(self, argv: list=sys.argv[1:]):
+        parser = self.get_parser()
+        opt, _ = parser.parse_known_args(argv)
+        for name in self.__fields__:
+            if name not in self._excluded():
+                setattr(self, name, getattr(opt,name))
+
+    def to_yaml(self)->str:
+        """
+        Return a YAML string representing our settings. This can be used
+        as the contents of `invokeai.yaml` to restore settings later.
+        """
+        cls = self.__class__
+        type = get_args(get_type_hints(cls)['type'])[0]
+        field_dict = dict({type:dict()})
+        for name,field in self.__fields__.items():
+            if name in cls._excluded():
+                continue
+            category = field.field_info.extra.get("category") or "Uncategorized"
+            value = getattr(self,name)
+            if category not in field_dict[type]:
+                field_dict[type][category] = dict()
+            # keep paths as strings to make it easier to read
+            field_dict[type][category][name] = str(value) if isinstance(value,Path) else value
+        conf = OmegaConf.create(field_dict)
+        return OmegaConf.to_yaml(conf)
+
+    @classmethod
+    def add_parser_arguments(cls, parser):
+        if 'type' in get_type_hints(cls):
+            settings_stanza = get_args(get_type_hints(cls)['type'])[0]
+        else:
+            settings_stanza = "Uncategorized"
+
+        env_prefix = cls.Config.env_prefix if hasattr(cls.Config,'env_prefix') else settings_stanza.upper()
+
+        initconf = cls.initconf.get(settings_stanza) \
+            if cls.initconf and settings_stanza in cls.initconf \
+               else OmegaConf.create()
+
+        # create an upcase version of the environment in
+        # order to achieve case-insensitive environment
+        # variables (the way Windows does)
+        upcase_environ = dict()
+        for key,value in os.environ.items():
+            upcase_environ[key.upper()] = value
+        
+        fields = cls.__fields__
+        cls.argparse_groups = {}
+        
+        for name, field in fields.items():
+            if name not in cls._excluded():
+                current_default = field.default
+
+                category = field.field_info.extra.get("category","Uncategorized")
+                env_name = env_prefix + '_' + name
+                if category in initconf and name in initconf.get(category):
+                    field.default = initconf.get(category).get(name)
+                if env_name.upper() in upcase_environ:
+                    field.default = upcase_environ[env_name.upper()]
+                cls.add_field_argument(parser, name, field)
+
+                field.default = current_default
+
+    @classmethod
+    def cmd_name(self, command_field: str='type')->str:
+        hints = get_type_hints(self)
+        if command_field in hints:
+            return get_args(hints[command_field])[0]
+        else:
+            return 'Uncategorized'
+
+    @classmethod
+    def get_parser(cls)->ArgumentParser:
+        parser = PagingArgumentParser(
+            prog=cls.cmd_name(),
+            description=cls.__doc__,
+        )
+        cls.add_parser_arguments(parser)
+        return parser
+
+    @classmethod
+    def add_subparser(cls, parser: argparse.ArgumentParser):
+        parser.add_parser(cls.cmd_name(), help=cls.__doc__)
+
+    @classmethod
+    def _excluded(self)->List[str]:
+        return ['type','initconf']
+
+    class Config:
+        env_file_encoding = 'utf-8'
+        arbitrary_types_allowed = True
+        case_sensitive = True
+
+    @classmethod
+    def add_field_argument(cls, command_parser, name: str, field, default_override = None):
+        field_type = get_type_hints(cls).get(name)
+        default = default_override if default_override is not None else field.default if field.default_factory is None else field.default_factory()
+        if category := field.field_info.extra.get("category"):
+            if category not in cls.argparse_groups:
+                cls.argparse_groups[category] = command_parser.add_argument_group(category)
+            argparse_group = cls.argparse_groups[category]
+        else:
+            argparse_group = command_parser
+
+        if get_origin(field_type) == Literal:
+            allowed_values = get_args(field.type_)
+            allowed_types = set()
+            for val in allowed_values:
+                allowed_types.add(type(val))
+            allowed_types_list = list(allowed_types)
+            field_type = allowed_types_list[0] if len(allowed_types) == 1 else Union[allowed_types_list]  # type: ignore
+
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field_type,
+                default=default,
+                choices=allowed_values,
+                help=field.field_info.description,
+            )
+
+        elif get_origin(field_type) == list:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                nargs='*',
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+        else:
+            argparse_group.add_argument(
+                f"--{name}",
+                dest=name,
+                type=field.type_,
+                default=default,
+                action=argparse.BooleanOptionalAction if field.type_==bool else 'store',
+                help=field.field_info.description,
+            )
+def _find_root()->Path:
+    if os.environ.get("INVOKEAI_ROOT"):
+        root = Path(os.environ.get("INVOKEAI_ROOT")).resolve()
+    elif (
+            os.environ.get("VIRTUAL_ENV")
+            and (Path(os.environ.get("VIRTUAL_ENV"), "..", INIT_FILE).exists()
+                 or
+                 Path(os.environ.get("VIRTUAL_ENV"), "..", LEGACY_INIT_FILE).exists()
+                 )
+    ):
+        root = Path(os.environ.get("VIRTUAL_ENV"), "..").resolve()
+    else:
+        root = Path("~/invokeai").expanduser().resolve()
+    return root
+
+class InvokeAIAppConfig(InvokeAISettings):
+    '''
+Generate images using Stable Diffusion. Use "invokeai" to launch
+the command-line client (recommended for experts only), or
+"invokeai-web" to launch the web server. Global options
+can be changed by editing the file "INVOKEAI_ROOT/invokeai.yaml" or by
+setting environment variables INVOKEAI_<setting>.
+     '''
+    #fmt: off
+    type: Literal["InvokeAI"] = "InvokeAI"
+    host                : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
+    port                : int = Field(default=9090, description="Port to bind to", category='Web Server')
+    allow_origins       : List[str] = Field(default=[], description="Allowed CORS origins", category='Web Server')
+    allow_credentials   : bool = Field(default=True, description="Allow CORS credentials", category='Web Server')
+    allow_methods       : List[str] = Field(default=["*"], description="Methods allowed for CORS", category='Web Server')
+    allow_headers       : List[str] = Field(default=["*"], description="Headers allowed for CORS", category='Web Server')
+
+    esrgan              : bool = Field(default=True, description="Enable/disable upscaling code", category='Features')
+    internet_available  : bool = Field(default=True, description="If true, attempt to download models on the fly; otherwise only use local models", category='Features')
+    log_tokenization    : bool = Field(default=False, description="Enable logging of parsed prompt tokens.", category='Features')
+    nsfw_checker        : bool = Field(default=True, description="Enable/disable the NSFW checker", category='Features')
+    patchmatch          : bool = Field(default=True, description="Enable/disable patchmatch inpaint code", category='Features')
+    restore             : bool = Field(default=True, description="Enable/disable face restoration code", category='Features')
+
+    always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
+    free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
+    max_loaded_models   : int = Field(default=2, gt=0, description="Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
+    sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
+    xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
+
+    root                : Path = Field(default=_find_root(), description='InvokeAI runtime root directory', category='Paths')
+    autoconvert_dir     : Path = Field(default=None, description='Path to a directory of ckpt files to be converted into diffusers and imported on startup.', category='Paths')
+    conf_path           : Path = Field(default='configs/models.yaml', description='Path to models definition file', category='Paths')
+    embedding_dir       : Path = Field(default='embeddings', description='Path to InvokeAI textual inversion aembeddings directory', category='Paths')
+    gfpgan_model_dir    : Path = Field(default="./models/gfpgan/GFPGANv1.4.pth", description='Path to GFPGAN models directory.', category='Paths')
+    legacy_conf_dir     : Path = Field(default='configs/stable-diffusion', description='Path to directory of legacy checkpoint config files', category='Paths')
+    lora_dir            : Path = Field(default='loras', description='Path to InvokeAI LoRA model directory', category='Paths')
+    outdir              : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
+    from_file           : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
+
+    model               : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
+    embeddings          : bool = Field(default=True, description='Load contents of embeddings directory', category='Models')
+    #fmt: on
+
+    def __init__(self, conf: DictConfig = None, argv: List[str]=None, **kwargs):
+        '''
+        Initialize InvokeAIAppconfig.
+        :param conf: alternate Omegaconf dictionary object
+        :param argv: aternate sys.argv list
+        :param **kwargs: attributes to initialize with
+        '''
+        super().__init__(**kwargs)
+
+        # Set the runtime root directory. We parse command-line switches here
+        # in order to pick up the --root_dir option.
+        self.parse_args(argv)
+        if conf is None:
+            try:
+                conf = OmegaConf.load(self.root_dir / INIT_FILE)
+            except:
+                pass
+        InvokeAISettings.initconf = conf
+
+        # parse args again in order to pick up settings in configuration file
+        self.parse_args(argv)
+
+        # restore initialization values
+        hints = get_type_hints(self)
+        for k in kwargs:
+            setattr(self,k,parse_obj_as(hints[k],kwargs[k]))
+
+    @property
+    def root_path(self)->Path:
+        '''
+        Path to the runtime root directory
+        '''
+        if self.root:
+            return Path(self.root).expanduser()
+        else:
+            return self.find_root()
+
+    @property
+    def root_dir(self)->Path:
+        '''
+        Alias for above.
+        '''
+        return self.root_path
+
+    def _resolve(self,partial_path:Path)->Path:
+        return (self.root_path / partial_path).resolve()
+
+    @property
+    def output_path(self)->Path:
+        '''
+        Path to defaults outputs directory.
+        '''
+        return self._resolve(self.outdir)
+
+    @property
+    def model_conf_path(self)->Path:
+        '''
+        Path to models configuration file.
+        '''
+        return self._resolve(self.conf_path)
+
+    @property
+    def legacy_conf_path(self)->Path:
+        '''
+        Path to directory of legacy configuration files (e.g. v1-inference.yaml)
+        '''
+        return self._resolve(self.legacy_conf_dir)
+
+    @property
+    def cache_dir(self)->Path:
+        '''
+        Path to the global cache directory for HuggingFace hub-managed models
+        '''
+        return self.models_dir / "hub"
+
+    @property
+    def models_dir(self)->Path:
+        '''
+        Path to the models directory
+        '''
+        return self._resolve("models")
+
+    @property
+    def embedding_path(self)->Path:
+        '''
+        Path to the textual inversion embeddings directory.
+        '''
+        return self._resolve(self.embedding_dir) if self.embedding_dir else None
+
+    @property
+    def lora_path(self)->Path:
+        '''
+        Path to the LoRA models directory.
+        '''
+        return self._resolve(self.lora_dir) if self.lora_dir else None
+
+    @property
+    def autoconvert_path(self)->Path:
+        '''
+        Path to the directory containing models to be imported automatically at startup.
+        '''
+        return self._resolve(self.autoconvert_dir) if self.autoconvert_dir else None
+
+    @property
+    def gfpgan_model_path(self)->Path:
+        '''
+        Path to the GFPGAN model.
+        '''
+        return self._resolve(self.gfpgan_model_dir) if self.gfpgan_model_dir else None
+
+    # the following methods support legacy calls leftover from the Globals era
+    @property
+    def full_precision(self)->bool:
+        """Return true if precision set to float32"""
+        return self.precision=='float32'
+
+    @property
+    def disable_xformers(self)->bool:
+        """Return true if xformers_enabled is false"""
+        return not self.xformers_enabled
+
+    @property
+    def try_patchmatch(self)->bool:
+        """Return true if patchmatch true"""
+        return self.patchmatch
+
+    @staticmethod
+    def find_root()->Path:
+        '''
+        Choose the runtime root directory when not specified on command line or
+        init file.
+        '''
+        return _find_root()
+
+
+class PagingArgumentParser(argparse.ArgumentParser):
+    '''
+    A custom ArgumentParser that uses pydoc to page its output.
+    It also supports reading defaults from an init file.
+    '''
+    def print_help(self, file=None):
+        text = self.format_help()
+        pydoc.pager(text)
+
+def get_invokeai_config(cls:Type[InvokeAISettings]=InvokeAIAppConfig,**kwargs)->InvokeAISettings:
+    '''
+    This returns a singleton InvokeAIAppConfig configuration object.
+    '''
+    global global_config
+    if global_config is None or type(global_config)!=cls:
+        global_config = cls(**kwargs)
+    return global_config

invokeai/app/services/default_graphs.py

@@ -1,4 +1,5 @@
 from ..invocations.latent import LatentsToImageInvocation, NoiseInvocation, TextToLatentsInvocation
+from ..invocations.compel import CompelInvocation
 from ..invocations.params import ParamIntInvocation
 from .graph import Edge, EdgeConnection, ExposedNodeInput, ExposedNodeOutput, Graph, LibraryGraph
 from .item_storage import ItemStorageABC
@@ -16,38 +17,45 @@ def create_text_to_image() -> LibraryGraph:
             nodes={
                 'width': ParamIntInvocation(id='width', a=512),
                 'height': ParamIntInvocation(id='height', a=512),
+                'seed': ParamIntInvocation(id='seed', a=-1),
                 '3': NoiseInvocation(id='3'),
-                '4': TextToLatentsInvocation(id='4'),
-                '5': LatentsToImageInvocation(id='5')
+                '4': CompelInvocation(id='4'),
+                '5': CompelInvocation(id='5'),
+                '6': TextToLatentsInvocation(id='6'),
+                '7': LatentsToImageInvocation(id='7'),
             },
             edges=[
                 Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='3', field='width')),
                 Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='3', field='height')),
-                Edge(source=EdgeConnection(node_id='width', field='a'), destination=EdgeConnection(node_id='4', field='width')),
-                Edge(source=EdgeConnection(node_id='height', field='a'), destination=EdgeConnection(node_id='4', field='height')),
-                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='4', field='noise')),
-                Edge(source=EdgeConnection(node_id='4', field='latents'), destination=EdgeConnection(node_id='5', field='latents')),
+                Edge(source=EdgeConnection(node_id='seed', field='a'), destination=EdgeConnection(node_id='3', field='seed')),
+                Edge(source=EdgeConnection(node_id='3', field='noise'), destination=EdgeConnection(node_id='6', field='noise')),
+                Edge(source=EdgeConnection(node_id='6', field='latents'), destination=EdgeConnection(node_id='7', field='latents')),
+                Edge(source=EdgeConnection(node_id='4', field='conditioning'), destination=EdgeConnection(node_id='6', field='positive_conditioning')),
+                Edge(source=EdgeConnection(node_id='5', field='conditioning'), destination=EdgeConnection(node_id='6', field='negative_conditioning')),
             ]
         ),
         exposed_inputs=[
-            ExposedNodeInput(node_path='4', field='prompt', alias='prompt'),
+            ExposedNodeInput(node_path='4', field='prompt', alias='positive_prompt'),
+            ExposedNodeInput(node_path='5', field='prompt', alias='negative_prompt'),
             ExposedNodeInput(node_path='width', field='a', alias='width'),
-            ExposedNodeInput(node_path='height', field='a', alias='height')
+            ExposedNodeInput(node_path='height', field='a', alias='height'),
+            ExposedNodeInput(node_path='seed', field='a', alias='seed'),
         ],
         exposed_outputs=[
-            ExposedNodeOutput(node_path='5', field='image', alias='image')
+            ExposedNodeOutput(node_path='7', field='image', alias='image')
         ])
 
 
 def create_system_graphs(graph_library: ItemStorageABC[LibraryGraph]) -> list[LibraryGraph]:
     """Creates the default system graphs, or adds new versions if the old ones don't match"""
-
+    
+    # TODO: Uncomment this when we are ready to fix this up to prevent breaking changes
     graphs: list[LibraryGraph] = list()
 
-    text_to_image = graph_library.get(default_text_to_image_graph_id)
+    # text_to_image = graph_library.get(default_text_to_image_graph_id)
     
-    # TODO: Check if the graph is the same as the default one, and if not, update it
-    #if text_to_image is None:
+    # # TODO: Check if the graph is the same as the default one, and if not, update it
+    # #if text_to_image is None:
     text_to_image = create_text_to_image()
     graph_library.set(text_to_image)
 

invokeai/app/services/events.py

@@ -2,7 +2,7 @@
 
 from typing import Any
 from invokeai.app.api.models.images import ProgressImage
-from invokeai.app.util.get_timestamp import get_timestamp
+from invokeai.app.util.misc import get_timestamp
 
 
 class EventServiceBase:
@@ -14,6 +14,7 @@ class EventServiceBase:
         pass
 
     def __emit_session_event(self, event_name: str, payload: dict) -> None:
+        payload["timestamp"] = get_timestamp()
         self.dispatch(
             event_name=EventServiceBase.session_event,
             payload=dict(event=event_name, data=payload),
@@ -24,7 +25,7 @@ class EventServiceBase:
     def emit_generator_progress(
         self,
         graph_execution_state_id: str,
-        invocation_dict: dict,
+        node: dict,
         source_node_id: str,
         progress_image: ProgressImage | None,
         step: int,
@@ -35,12 +36,11 @@ class EventServiceBase:
             event_name="generator_progress",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
+                node=node,
                 source_node_id=source_node_id,
                 progress_image=progress_image.dict() if progress_image is not None else None,
                 step=step,
                 total_steps=total_steps,
-                timestamp=get_timestamp(),
             ),
         )
 
@@ -48,26 +48,24 @@ class EventServiceBase:
         self,
         graph_execution_state_id: str,
         result: dict,
-        invocation_dict: dict,
+        node: dict,
         source_node_id: str,
     ) -> None:
         """Emitted when an invocation has completed"""
-        print(result)
         self.__emit_session_event(
             event_name="invocation_complete",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
+                node=node,
                 source_node_id=source_node_id,
                 result=result,
-                timestamp=get_timestamp(),
             ),
         )
 
     def emit_invocation_error(
         self,
         graph_execution_state_id: str,
-        invocation_dict: dict,
+        node: dict,
         source_node_id: str,
         error: str,
     ) -> None:
@@ -76,24 +74,22 @@ class EventServiceBase:
             event_name="invocation_error",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
+                node=node,
                 source_node_id=source_node_id,
                 error=error,
-                timestamp=get_timestamp(),
             ),
         )
 
     def emit_invocation_started(
-        self, graph_execution_state_id: str, invocation_dict: dict, source_node_id: str
+        self, graph_execution_state_id: str, node: dict, source_node_id: str
     ) -> None:
         """Emitted when an invocation has started"""
         self.__emit_session_event(
             event_name="invocation_started",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                invocation=invocation_dict,
+                node=node,
                 source_node_id=source_node_id,
-                timestamp=get_timestamp(),
             ),
         )
 
@@ -103,6 +99,5 @@ class EventServiceBase:
             event_name="graph_execution_state_complete",
             payload=dict(
                 graph_execution_state_id=graph_execution_state_id,
-                timestamp=get_timestamp(),
             ),
         )

invokeai/app/services/graph.py

@@ -135,6 +135,7 @@ class GraphInvocationOutput(BaseInvocationOutput):
 
 # TODO: Fill this out and move to invocations
 class GraphInvocation(BaseInvocation):
+    """Execute a graph"""
     type: Literal["graph"] = "graph"
 
     # TODO: figure out how to create a default here
@@ -162,6 +163,7 @@ class IterateInvocationOutput(BaseInvocationOutput):
 
 # TODO: Fill this out and move to invocations
 class IterateInvocation(BaseInvocation):
+    """Iterates over a list of items"""
     type: Literal["iterate"] = "iterate"
 
     collection: list[Any] = Field(

invokeai/app/services/image_storage.py

@@ -1,27 +1,30 @@
 # Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
 
-import datetime
 import os
-import json
 from glob import glob
 from abc import ABC, abstractmethod
 from pathlib import Path
 from queue import Queue
-from typing import Any, Dict, List, Tuple
+from typing import Dict, List
 
 from PIL.Image import Image
 import PIL.Image as PILImage
-from PIL import PngImagePlugin
-from invokeai.app.api.models.images import ImageResponse
-from invokeai.app.models.image import  ImageType
-from invokeai.app.modules.metadata import ImageMetadata, InvokeAIMetadata, MetadataModule
+from send2trash import send2trash
+from invokeai.app.api.models.images import (
+    ImageResponse,
+    ImageResponseMetadata,
+    SavedImage,
+)
+from invokeai.app.models.image import ImageType
+from invokeai.app.services.metadata import (
+    InvokeAIMetadata,
+    MetadataServiceBase,
+    build_invokeai_metadata_pnginfo,
+)
 from invokeai.app.services.item_storage import PaginatedResults
-from invokeai.app.util.get_timestamp import get_timestamp
-from invokeai.app.util.image_paths import build_image_path
+from invokeai.app.util.misc import get_timestamp
 from invokeai.app.util.thumbnails import get_thumbnail_name, make_thumbnail
 
-from invokeai.backend.image_util import PngWriter
-
 
 class ImageStorageBase(ABC):
     """Responsible for storing and retrieving images."""
@@ -43,20 +46,32 @@ class ImageStorageBase(ABC):
     def get_path(
         self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
     ) -> str:
-        """Gets the path to an image or its thumbnail."""
+        """Gets the internal path to an image or its thumbnail."""
         pass
 
     # TODO: make this a bit more flexible for e.g. cloud storage
     @abstractmethod
-    def validate_path(
-        self, path: str
-    ) -> bool:
+    def get_uri(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        """Gets the external URI to an image or its thumbnail."""
+        pass
+
+    # TODO: make this a bit more flexible for e.g. cloud storage
+    @abstractmethod
+    def validate_path(self, path: str) -> bool:
         """Validates an image path."""
         pass
 
     @abstractmethod
-    def save(self, image_type: ImageType, image_name: str, image: Image, metadata: InvokeAIMetadata | None = None) -> Tuple[str, str, int]:
-        """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image path, thumbnail path, and created timestamp."""
+    def save(
+        self,
+        image_type: ImageType,
+        image_name: str,
+        image: Image,
+        metadata: InvokeAIMetadata | None = None,
+    ) -> SavedImage:
+        """Saves an image and a 256x256 WEBP thumbnail. Returns a tuple of the image name, thumbnail name, and created timestamp."""
         pass
 
     @abstractmethod
@@ -76,12 +91,14 @@ class DiskImageStorage(ImageStorageBase):
     __cache_ids: Queue  # TODO: this is an incredibly naive cache
     __cache: Dict[str, Image]
     __max_cache_size: int
+    __metadata_service: MetadataServiceBase
 
-    def __init__(self, output_folder: str):
+    def __init__(self, output_folder: str, metadata_service: MetadataServiceBase):
         self.__output_folder = output_folder
         self.__cache = dict()
         self.__cache_ids = Queue()
         self.__max_cache_size = 10  # TODO: get this from config
+        self.__metadata_service = metadata_service
 
         Path(output_folder).mkdir(parents=True, exist_ok=True)
 
@@ -114,22 +131,22 @@ class DiskImageStorage(ImageStorageBase):
         for path in page_of_image_paths:
             filename = os.path.basename(path)
             img = PILImage.open(path)
-            
-            invokeai_metadata = MetadataModule.get_metadata(img)
+
+            invokeai_metadata = self.__metadata_service.get_metadata(img)
 
             page_of_images.append(
                 ImageResponse(
                     image_type=image_type.value,
                     image_name=filename,
-                    image_url=build_image_path(image_type.value, filename),
-                    thumbnail_url = build_image_path(image_type.value, filename, True),
+                    # TODO: DiskImageStorage should not be building URLs...?
+                    image_url=self.get_uri(image_type, filename),
+                    thumbnail_url=self.get_uri(image_type, filename, True),
                     # TODO: Creation of this object should happen elsewhere (?), just making it fit here so it works
-                    metadata=ImageMetadata(
+                    metadata=ImageResponseMetadata(
                         created=int(os.path.getctime(path)),
                         width=img.width,
                         height=img.height,
-                        mode=img.mode,
-                        invokeai=invokeai_metadata
+                        invokeai=invokeai_metadata,
                     ),
                 )
             )
@@ -170,52 +187,79 @@ class DiskImageStorage(ImageStorageBase):
         else:
             path = os.path.join(self.__output_folder, image_type, basename)
 
-        return path
+        abspath = os.path.abspath(path)
 
-    def validate_path(
-        self, path: str
-    ) -> bool:
+        return abspath
+
+    def get_uri(
+        self, image_type: ImageType, image_name: str, is_thumbnail: bool = False
+    ) -> str:
+        # strip out any relative path shenanigans
+        basename = os.path.basename(image_name)
+
+        if is_thumbnail:
+            thumbnail_basename = get_thumbnail_name(basename)
+            uri = f"api/v1/images/{image_type.value}/thumbnails/{thumbnail_basename}"
+        else:
+            uri = f"api/v1/images/{image_type.value}/{basename}"
+
+        return uri
+
+    def validate_path(self, path: str) -> bool:
         try:
             os.stat(path)
             return True
         except Exception:
             return False
 
-
-    def save(self, image_type: ImageType, image_name: str, image: Image, metadata: InvokeAIMetadata | None = None) -> Tuple[str, str, int]:
+    def save(
+        self,
+        image_type: ImageType,
+        image_name: str,
+        image: Image,
+        metadata: InvokeAIMetadata | None = None,
+    ) -> SavedImage:
         image_path = self.get_path(image_type, image_name)
 
+        # TODO: Reading the image and then saving it strips the metadata...
+        if metadata:
+            pnginfo = build_invokeai_metadata_pnginfo(metadata=metadata)
+            image.save(image_path, "PNG", pnginfo=pnginfo)
+        else:
+            image.save(image_path)  # this saved image has an empty info
+
         thumbnail_name = get_thumbnail_name(image_name)
         thumbnail_path = self.get_path(image_type, thumbnail_name, is_thumbnail=True)
-
-        png_info = MetadataModule.build_png_info(metadata=metadata)
-
-        image.save(image_path, "PNG", pnginfo=png_info)
-
         thumbnail_image = make_thumbnail(image)
         thumbnail_image.save(thumbnail_path)
 
         self.__set_cache(image_path, image)
         self.__set_cache(thumbnail_path, thumbnail_image)
 
-        return (image_path, thumbnail_path, int(os.path.getctime(image_path)))
+        return SavedImage(
+            image_name=image_name,
+            thumbnail_name=thumbnail_name,
+            created=int(os.path.getctime(image_path)),
+        )
 
     def delete(self, image_type: ImageType, image_name: str) -> None:
-        image_path = self.get_path(image_type, image_name)
-        thumbnail_path = self.get_path(image_type, image_name, True)
-        if os.path.exists(image_path):
-            os.remove(image_path)
+        basename = os.path.basename(image_name)
+        image_path = self.get_path(image_type, basename)
 
+        if os.path.exists(image_path):
+            send2trash(image_path)
         if image_path in self.__cache:
             del self.__cache[image_path]
 
-        if os.path.exists(thumbnail_path):
-            os.remove(thumbnail_path)
+        thumbnail_name = get_thumbnail_name(image_name)
+        thumbnail_path = self.get_path(image_type, thumbnail_name, True)
 
+        if os.path.exists(thumbnail_path):
+            send2trash(thumbnail_path)
         if thumbnail_path in self.__cache:
             del self.__cache[thumbnail_path]
 
-    def __get_cache(self, image_name: str) -> Image:
+    def __get_cache(self, image_name: str) -> Image | None:
         return None if image_name not in self.__cache else self.__cache[image_name]
 
     def __set_cache(self, image_name: str, image: Image):
@@ -226,4 +270,5 @@ class DiskImageStorage(ImageStorageBase):
             )  # TODO: this should refresh position for LRU cache
             if len(self.__cache) > self.__max_cache_size:
                 cache_id = self.__cache_ids.get()
-                del self.__cache[cache_id]
+                if cache_id in self.__cache:
+                    del self.__cache[cache_id]

invokeai/app/services/invocation_services.py

@@ -1,4 +1,7 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
+
+from typing import types
+from invokeai.app.services.metadata import MetadataServiceBase
 from invokeai.backend import ModelManager
 
 from .events import EventServiceBase
@@ -7,6 +10,7 @@ from .image_storage import ImageStorageBase
 from .restoration_services import RestorationServices
 from .invocation_queue import InvocationQueueABC
 from .item_storage import ItemStorageABC
+from .config import InvokeAISettings
 
 class InvocationServices:
     """Services that can be used by invocations"""
@@ -14,10 +18,12 @@ class InvocationServices:
     events: EventServiceBase
     latents: LatentsStorageBase
     images: ImageStorageBase
+    metadata: MetadataServiceBase
     queue: InvocationQueueABC
     model_manager: ModelManager
     restoration: RestorationServices
-
+    configuration: InvokeAISettings
+    
     # NOTE: we must forward-declare any types that include invocations, since invocations can use services
     graph_library: ItemStorageABC["LibraryGraph"]
     graph_execution_manager: ItemStorageABC["GraphExecutionState"]
@@ -27,20 +33,26 @@ class InvocationServices:
             self,
             model_manager: ModelManager,
             events: EventServiceBase,
+            logger: types.ModuleType,
             latents: LatentsStorageBase,
             images: ImageStorageBase,
+            metadata: MetadataServiceBase,
             queue: InvocationQueueABC,
             graph_library: ItemStorageABC["LibraryGraph"],
             graph_execution_manager: ItemStorageABC["GraphExecutionState"],
             processor: "InvocationProcessorABC",
             restoration: RestorationServices,
+            configuration: InvokeAISettings=None,
     ):
         self.model_manager = model_manager
         self.events = events
+        self.logger = logger
         self.latents = latents
         self.images = images
+        self.metadata = metadata
         self.queue = queue
         self.graph_library = graph_library
         self.graph_execution_manager = graph_execution_manager
         self.processor = processor
         self.restoration = restoration
+        self.configuration = configuration

invokeai/app/services/invoker.py

@@ -49,7 +49,7 @@ class Invoker:
         new_state = GraphExecutionState(graph=Graph() if graph is None else graph)
         self.services.graph_execution_manager.set(new_state)
         return new_state
-    
+
     def cancel(self, graph_execution_state_id: str) -> None:
         """Cancels the given execution state"""
         self.services.queue.cancel(graph_execution_state_id)
@@ -71,18 +71,12 @@ class Invoker:
         for service in vars(self.services):
             self.__start_service(getattr(self.services, service))
 
-        for service in vars(self.services):
-            self.__start_service(getattr(self.services, service))
-
     def stop(self) -> None:
         """Stops the invoker. A new invoker will have to be created to execute further."""
         # First stop all services
         for service in vars(self.services):
             self.__stop_service(getattr(self.services, service))
 
-        for service in vars(self.services):
-            self.__stop_service(getattr(self.services, service))
-
         self.services.queue.put(None)
 
 

invokeai/app/services/metadata.py

@@ -0,0 +1,105 @@
+import json
+from abc import ABC, abstractmethod
+from typing import Any, Dict, Optional, TypedDict
+from PIL import Image, PngImagePlugin
+from pydantic import BaseModel
+
+from invokeai.app.models.image import ImageType, is_image_type
+
+
+class MetadataImageField(TypedDict):
+    """Pydantic-less ImageField, used for metadata parsing."""
+
+    image_type: ImageType
+    image_name: str
+
+
+class MetadataLatentsField(TypedDict):
+    """Pydantic-less LatentsField, used for metadata parsing."""
+
+    latents_name: str
+
+
+class MetadataColorField(TypedDict):
+    """Pydantic-less ColorField, used for metadata parsing"""
+    r: int
+    g: int
+    b: int
+    a: int
+
+
+
+# TODO: This is a placeholder for `InvocationsUnion` pending resolution of circular imports
+NodeMetadata = Dict[
+    str, None | str | int | float | bool | MetadataImageField | MetadataLatentsField | MetadataColorField
+]
+
+
+class InvokeAIMetadata(TypedDict, total=False):
+    """InvokeAI-specific metadata format."""
+
+    session_id: Optional[str]
+    node: Optional[NodeMetadata]
+
+
+def build_invokeai_metadata_pnginfo(
+    metadata: InvokeAIMetadata | None,
+) -> PngImagePlugin.PngInfo:
+    """Builds a PngInfo object with key `"invokeai"` and value `metadata`"""
+    pnginfo = PngImagePlugin.PngInfo()
+
+    if metadata is not None:
+        pnginfo.add_text("invokeai", json.dumps(metadata))
+
+    return pnginfo
+
+
+class MetadataServiceBase(ABC):
+    @abstractmethod
+    def get_metadata(self, image: Image.Image) -> InvokeAIMetadata | None:
+        """Gets the InvokeAI metadata from a PIL Image, skipping invalid values"""
+        pass
+
+    @abstractmethod
+    def build_metadata(
+        self, session_id: str, node: BaseModel
+    ) -> InvokeAIMetadata | None:
+        """Builds an InvokeAIMetadata object"""
+        pass
+
+
+class PngMetadataService(MetadataServiceBase):
+    """Handles loading and building metadata for images."""
+
+    # TODO: Use `InvocationsUnion` to **validate** metadata as representing a fully-functioning node
+    def _load_metadata(self, image: Image.Image) -> dict | None:
+        """Loads a specific info entry from a PIL Image."""
+
+        try:
+            info = image.info.get("invokeai")
+
+            if type(info) is not str:
+                return None
+
+            loaded_metadata = json.loads(info)
+
+            if type(loaded_metadata) is not dict:
+                return None
+
+            if len(loaded_metadata.items()) == 0:
+                return None
+
+            return loaded_metadata
+        except:
+            return None
+
+    def get_metadata(self, image: Image.Image) -> dict | None:
+        """Retrieves an image's metadata as a dict"""
+        loaded_metadata = self._load_metadata(image)
+
+        return loaded_metadata
+
+    def build_metadata(self, session_id: str, node: BaseModel) -> InvokeAIMetadata:
+        metadata = InvokeAIMetadata(session_id=session_id, node=node.dict())
+
+        return metadata

invokeai/app/services/model_manager_initializer.py

@@ -2,26 +2,25 @@ import os
 import sys
 import torch
 from argparse import Namespace
-from invokeai.backend import Args
 from omegaconf import OmegaConf
 from pathlib import Path
+from typing import types
 
 import invokeai.version
+from .config import InvokeAISettings
 from ...backend import ModelManager
 from ...backend.util import choose_precision, choose_torch_device
-from ...backend import Globals
 
 # TODO: Replace with an abstract class base ModelManagerBase
-def get_model_manager(config: Args) -> ModelManager:
-    if not config.conf:
-        config_file = os.path.join(Globals.root, "configs", "models.yaml")
-        if not os.path.exists(config_file):
-            report_model_error(
-                config, FileNotFoundError(f"The file {config_file} could not be found.")
-            )
+def get_model_manager(config: InvokeAISettings, logger: types.ModuleType) -> ModelManager:
+    model_config = config.model_conf_path
+    if not model_config.exists():
+        report_model_error(
+            config, FileNotFoundError(f"The file {model_config} could not be found."), logger
+        )
 
-    print(f">> {invokeai.version.__app_name__}, version {invokeai.version.__version__}")
-    print(f'>> InvokeAI runtime directory is "{Globals.root}"')
+    logger.info(f"{invokeai.version.__app_name__}, version {invokeai.version.__version__}")
+    logger.info(f'InvokeAI runtime directory is "{config.root}"')
 
     # these two lines prevent a horrible warning message from appearing
     # when the frozen CLIP tokenizer is imported
@@ -31,20 +30,7 @@ def get_model_manager(config: Args) -> ModelManager:
     import diffusers
 
     diffusers.logging.set_verbosity_error()
-
-    # normalize the config directory relative to root
-    if not os.path.isabs(config.conf):
-        config.conf = os.path.normpath(os.path.join(Globals.root, config.conf))
-
-    if config.embeddings:
-        if not os.path.isabs(config.embedding_path):
-            embedding_path = os.path.normpath(
-                os.path.join(Globals.root, config.embedding_path)
-            )
-        else:
-            embedding_path = config.embedding_path
-    else:
-        embedding_path = None
+    embedding_path = config.embedding_path
 
     # migrate legacy models
     ModelManager.migrate_models()
@@ -57,37 +43,36 @@ def get_model_manager(config: Args) -> ModelManager:
         else choose_precision(device)
         
         model_manager = ModelManager(
-            OmegaConf.load(config.conf),
+            OmegaConf.load(config.model_conf_path),
             precision=precision,
             device_type=device,
             max_loaded_models=config.max_loaded_models,
-            embedding_path = Path(embedding_path),
+            embedding_path = embedding_path,
+            logger = logger,
         )
     except (FileNotFoundError, TypeError, AssertionError) as e:
-        report_model_error(config, e)
+        report_model_error(config, e, logger)
     except (IOError, KeyError) as e:
-        print(f"{e}. Aborting.")
+        logger.error(f"{e}. Aborting.")
         sys.exit(-1)
 
     # try to autoconvert new models
     # autoimport new .ckpt files
-    if path := config.autoconvert:
-        model_manager.autoconvert_weights(
-            conf_path=config.conf,
-            weights_directory=path,
+    if config.autoconvert_path:
+        model_manager.heuristic_import(
+            config.autoconvert_path,
         )
-
     return model_manager
 
-def report_model_error(opt: Namespace, e: Exception):
-    print(f'** An error occurred while attempting to initialize the model: "{str(e)}"')
-    print(
-        "** This can be caused by a missing or corrupted models file, and can sometimes be fixed by (re)installing the models."
+def report_model_error(opt: Namespace, e: Exception, logger: types.ModuleType):
+    logger.error(f'An error occurred while attempting to initialize the model: "{str(e)}"')
+    logger.error(
+        "This can be caused by a missing or corrupted models file, and can sometimes be fixed by (re)installing the models."
     )
     yes_to_all = os.environ.get("INVOKE_MODEL_RECONFIGURE")
     if yes_to_all:
-        print(
-            "** Reconfiguration is being forced by environment variable INVOKE_MODEL_RECONFIGURE"
+        logger.warning(
+            "Reconfiguration is being forced by environment variable INVOKE_MODEL_RECONFIGURE"
         )
     else:
         response = input(
@@ -96,13 +81,12 @@ def report_model_error(opt: Namespace, e: Exception):
         if response.startswith(("n", "N")):
             return
 
-    print("invokeai-configure is launching....\n")
+    logger.info("invokeai-configure is launching....\n")
 
     # Match arguments that were set on the CLI
     # only the arguments accepted by the configuration script are parsed
     root_dir = ["--root", opt.root_dir] if opt.root_dir is not None else []
     config = ["--config", opt.conf] if opt.conf is not None else []
-    previous_config = sys.argv
     sys.argv = ["invokeai-configure"]
     sys.argv.extend(root_dir)
     sys.argv.extend(config.to_dict())

invokeai/app/services/processor.py

@@ -1,17 +1,22 @@
+import time
 import traceback
-from threading import Event, Thread
+from threading import Event, Thread, BoundedSemaphore
 
 from ..invocations.baseinvocation import InvocationContext
 from .invocation_queue import InvocationQueueItem
 from .invoker import InvocationProcessorABC, Invoker
 from ..models.exceptions import CanceledException
 
+import invokeai.backend.util.logging as logger
 class DefaultInvocationProcessor(InvocationProcessorABC):
     __invoker_thread: Thread
     __stop_event: Event
     __invoker: Invoker
+    __threadLimit: BoundedSemaphore
 
     def start(self, invoker) -> None:
+        # if we do want multithreading at some point, we could make this configurable
+        self.__threadLimit = BoundedSemaphore(1)
         self.__invoker = invoker
         self.__stop_event = Event()
         self.__invoker_thread = Thread(
@@ -20,7 +25,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
             kwargs=dict(stop_event=self.__stop_event),
         )
         self.__invoker_thread.daemon = (
-            True  # TODO: probably better to just not use threads?
+            True  # TODO: make async and do not use threads
         )
         self.__invoker_thread.start()
 
@@ -29,9 +34,16 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
 
     def __process(self, stop_event: Event):
         try:
+            self.__threadLimit.acquire()
             while not stop_event.is_set():
-                queue_item: InvocationQueueItem = self.__invoker.services.queue.get()
+                try:
+                    queue_item: InvocationQueueItem = self.__invoker.services.queue.get()
+                except Exception as e:
+                    logger.debug("Exception while getting from queue: %s" % e)
+
                 if not queue_item:  # Probably stopping
+                    # do not hammer the queue
+                    time.sleep(0.5)
                     continue
 
                 graph_execution_state = (
@@ -49,7 +61,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 # Send starting event
                 self.__invoker.services.events.emit_invocation_started(
                     graph_execution_state_id=graph_execution_state.id,
-                    invocation_dict=invocation.dict(),
+                    node=invocation.dict(),
                     source_node_id=source_node_id
                 )
 
@@ -79,7 +91,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # Send complete event
                     self.__invoker.services.events.emit_invocation_complete(
                         graph_execution_state_id=graph_execution_state.id,
-                        invocation_dict=invocation.dict(),
+                        node=invocation.dict(),
                         source_node_id=source_node_id,
                         result=outputs.dict(),
                     )
@@ -104,13 +116,13 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                     # Send error event
                     self.__invoker.services.events.emit_invocation_error(
                         graph_execution_state_id=graph_execution_state.id,
-                        invocation_dict=invocation.dict(),
+                        node=invocation.dict(),
                         source_node_id=source_node_id,
                         error=error,
                     )
 
                     pass
-                
+
                 # Check queue to see if this is canceled, and skip if so
                 if self.__invoker.services.queue.is_canceled(
                     graph_execution_state.id
@@ -120,11 +132,22 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
                 # Queue any further commands if invoking all
                 is_complete = graph_execution_state.is_complete()
                 if queue_item.invoke_all and not is_complete:
-                    self.__invoker.invoke(graph_execution_state, invoke_all=True)
+                    try:
+                        self.__invoker.invoke(graph_execution_state, invoke_all=True)
+                    except Exception as e:
+                        logger.error("Error while invoking: %s" % e)
+                        self.__invoker.services.events.emit_invocation_error(
+                            graph_execution_state_id=graph_execution_state.id,
+                            node=invocation.dict(),
+                            source_node_id=source_node_id,
+                            error=traceback.format_exc()
+                        )
                 elif is_complete:
                     self.__invoker.services.events.emit_graph_execution_complete(
                         graph_execution_state.id
                     )
 
         except KeyboardInterrupt:
-            ...  # Log something?
+            pass  # Log something? KeyboardInterrupt is probably not going to be seen by the processor
+        finally:
+            self.__threadLimit.release()

invokeai/app/services/restoration_services.py

@@ -1,6 +1,7 @@
 import sys
 import traceback
 import torch
+from typing import types
 from ...backend.restoration import Restoration
 from ...backend.util import choose_torch_device, CPU_DEVICE, MPS_DEVICE
 
@@ -10,7 +11,7 @@ from ...backend.util import choose_torch_device, CPU_DEVICE, MPS_DEVICE
 class RestorationServices:
     '''Face restoration and upscaling'''
     
-    def __init__(self,args):
+    def __init__(self,args,logger:types.ModuleType):
         try:
             gfpgan, codeformer, esrgan = None, None, None
             if args.restore or args.esrgan:
@@ -20,20 +21,22 @@ class RestorationServices:
                         args.gfpgan_model_path
                     )
                 else:
-                    print(">> Face restoration disabled")
+                    logger.info("Face restoration disabled")
                     if args.esrgan:
                         esrgan = restoration.load_esrgan(args.esrgan_bg_tile)
                     else:
-                        print(">> Upscaling disabled")
+                        logger.info("Upscaling disabled")
             else:
-                print(">> Face restoration and upscaling disabled")
+                logger.info("Face restoration and upscaling disabled")
         except (ModuleNotFoundError, ImportError):
             print(traceback.format_exc(), file=sys.stderr)
-            print(">> You may need to install the ESRGAN and/or GFPGAN modules")
+            logger.info("You may need to install the ESRGAN and/or GFPGAN modules")
         self.device = torch.device(choose_torch_device())
         self.gfpgan = gfpgan
         self.codeformer = codeformer
         self.esrgan = esrgan
+        self.logger = logger
+        self.logger.info('Face restoration initialized')
 
     # note that this one method does gfpgan and codepath reconstruction, as well as
     # esrgan upscaling
@@ -58,15 +61,15 @@ class RestorationServices:
                     if self.gfpgan is not None or self.codeformer is not None:
                         if facetool == "gfpgan":
                             if self.gfpgan is None:
-                                print(
-                                    ">> GFPGAN not found. Face restoration is disabled."
+                                self.logger.info(
+                                    "GFPGAN not found. Face restoration is disabled."
                                 )
                             else:
                                 image = self.gfpgan.process(image, strength, seed)
                         if facetool == "codeformer":
                             if self.codeformer is None:
-                                print(
-                                    ">> CodeFormer not found. Face restoration is disabled."
+                                self.logger.info(
+                                    "CodeFormer not found. Face restoration is disabled."
                                 )
                             else:
                                 cf_device = (
@@ -80,7 +83,7 @@ class RestorationServices:
                                     fidelity=codeformer_fidelity,
                                 )
                     else:
-                        print(">> Face Restoration is disabled.")
+                        self.logger.info("Face Restoration is disabled.")
                 if upscale is not None:
                     if self.esrgan is not None:
                         if len(upscale) < 2:
@@ -93,10 +96,10 @@ class RestorationServices:
                             denoise_str=upscale_denoise_str,
                         )
                     else:
-                        print(">> ESRGAN is disabled. Image not upscaled.")
+                        self.logger.info("ESRGAN is disabled. Image not upscaled.")
             except Exception as e:
-                print(
-                    f">> Error running RealESRGAN or GFPGAN. Your image was not upscaled.\n{e}"
+                self.logger.info(
+                    f"Error running RealESRGAN or GFPGAN. Your image was not upscaled.\n{e}"
                 )
 
             if image_callback is not None:

invokeai/app/util/get_timestamp.py

@@ -1,5 +0,0 @@
-import datetime
-
-
-def get_timestamp():
-    return int(datetime.datetime.now(datetime.timezone.utc).timestamp())

invokeai/app/util/image_paths.py

@@ -1,12 +0,0 @@
-from typing import Optional
-from invokeai.app.models.image import ImageType
-from invokeai.app.util.thumbnails import get_thumbnail_name
-
-
-def build_image_path(image_type: ImageType, image_name: str, is_thumbnail: Optional[bool] = False) -> str:
-    """Gets path to access an image"""
-    if is_thumbnail is None:
-        return f"api/v1/images/{image_type}/{image_name}"
-    else:
-        thumbnail_name = get_thumbnail_name(image_name)
-        return f"api/v1/images/{image_type}/thumbnails/{thumbnail_name}"

invokeai/app/util/misc.py

@@ -0,0 +1,13 @@
+import datetime
+import numpy as np
+
+
+def get_timestamp():
+    return int(datetime.datetime.now(datetime.timezone.utc).timestamp())
+
+
+SEED_MAX = np.iinfo(np.int32).max
+
+
+def get_random_seed():
+    return np.random.randint(0, SEED_MAX)

invokeai/app/util/step_callback.py

@@ -9,7 +9,7 @@ from ...backend.stable_diffusion import PipelineIntermediateState
 def stable_diffusion_step_callback(
     context: InvocationContext,
     intermediate_state: PipelineIntermediateState,
-    invocation_dict: dict,
+    node: dict,
     source_node_id: str,
 ):
     if context.services.queue.is_canceled(context.graph_execution_state_id):
@@ -47,9 +47,9 @@ def stable_diffusion_step_callback(
 
     context.services.events.emit_generator_progress(
         graph_execution_state_id=context.graph_execution_state_id,
-        invocation_dict=invocation_dict,
+        node=node,
         source_node_id=source_node_id,
         progress_image=ProgressImage(width=width, height=height, dataURL=dataURL),
         step=intermediate_state.step,
-        total_steps=invocation_dict["steps"],
+        total_steps=node["steps"],
     )

invokeai/backend/__init__.py

@@ -1,7 +1,6 @@
 """
 Initialization file for invokeai.backend
 """
-from .generate import Generate
 from .generator import (
     InvokeAIGeneratorBasicParams,
     InvokeAIGenerator,
@@ -10,7 +9,5 @@ from .generator import (
     Img2Img,
     Inpaint
 )
-from .model_management import ModelManager
+from .model_management import ModelManager, SDModelComponent
 from .safety_checker import SafetyChecker
-from .args import Args
-from .globals import Globals

invokeai/backend/config/invokeai_configure.py

@@ -19,10 +19,10 @@ import warnings
 from argparse import Namespace
 from pathlib import Path
 from shutil import get_terminal_size
+from typing import get_type_hints
 from urllib import request
 
 import npyscreen
-import torch
 import transformers
 from diffusers import AutoencoderKL
 from huggingface_hub import HfFolder
@@ -38,34 +38,40 @@ from transformers import (
 
 import invokeai.configs as configs
 
-from ...frontend.install.model_install import addModelsForm, process_and_execute
-from ...frontend.install.widgets import (
+from invokeai.frontend.install.model_install import addModelsForm, process_and_execute
+from invokeai.frontend.install.widgets import (
     CenteredButtonPress,
     IntTitleSlider,
     set_min_terminal_size,
 )
-from ..args import PRECISION_CHOICES, Args
-from ..globals import Globals, global_cache_dir, global_config_dir, global_config_file
-from .model_install_backend import (
+from invokeai.backend.config.legacy_arg_parsing import legacy_parser
+from invokeai.backend.config.model_install_backend import (
     default_dataset,
     download_from_hf,
     hf_download_with_resume,
     recommended_datasets,
 )
+from invokeai.app.services.config import (
+    get_invokeai_config,
+    InvokeAIAppConfig,
+)
 
 warnings.filterwarnings("ignore")
 
 transformers.logging.set_verbosity_error()
 
+
 # --------------------------globals-----------------------
+config = get_invokeai_config()
+
 Model_dir = "models"
 Weights_dir = "ldm/stable-diffusion-v1/"
 
 # the initial "configs" dir is now bundled in the `invokeai.configs` package
 Dataset_path = Path(configs.__path__[0]) / "INITIAL_MODELS.yaml"
 
-Default_config_file = Path(global_config_dir()) / "models.yaml"
-SD_Configs = Path(global_config_dir()) / "stable-diffusion"
+Default_config_file = config.model_conf_path
+SD_Configs = config.legacy_conf_path
 
 Datasets = OmegaConf.load(Dataset_path)
 
@@ -73,17 +79,12 @@ Datasets = OmegaConf.load(Dataset_path)
 MIN_COLS = 135
 MIN_LINES = 45
 
+PRECISION_CHOICES = ['auto','float16','float32','autocast']
+
 INIT_FILE_PREAMBLE = """# InvokeAI initialization file
 # This is the InvokeAI initialization file, which contains command-line default values.
 # Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
 # or renaming it and then running invokeai-configure again.
-# Place  frequently-used startup commands here, one or more per line.
-# Examples:
-# --outdir=D:\data\images
-# --no-nsfw_checker
-# --web --host=0.0.0.0
-# --steps=20
-# -Ak_euler_a -C10.0
 """
 
 
@@ -96,14 +97,13 @@ If you installed manually from source or with 'pip install': activate the virtua
 then run one of the following commands to start InvokeAI.
 
 Web UI:
-   invokeai --web # (connect to http://localhost:9090)
-   invokeai --web --host 0.0.0.0 # (connect to http://your-lan-ip:9090 from another computer on the local network)
+   invokeai-web
 
-Command-line interface:
+Command-line client:
    invokeai
 
 If you installed using an installation script, run:
-  {Globals.root}/invoke.{"bat" if sys.platform == "win32" else "sh"}
+  {config.root}/invoke.{"bat" if sys.platform == "win32" else "sh"}
 
 Add the '--help' argument to see all of the command-line switches available for use.
 """
@@ -216,11 +216,11 @@ def download_realesrgan():
     wdn_model_url = "https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth"
 
     model_dest = os.path.join(
-        Globals.root, "models/realesrgan/realesr-general-x4v3.pth"
+        config.root, "models/realesrgan/realesr-general-x4v3.pth"
     )
 
     wdn_model_dest = os.path.join(
-        Globals.root, "models/realesrgan/realesr-general-wdn-x4v3.pth"
+        config.root, "models/realesrgan/realesr-general-wdn-x4v3.pth"
     )
 
     download_with_progress_bar(model_url, model_dest, "RealESRGAN")
@@ -243,7 +243,7 @@ def download_gfpgan():
             "./models/gfpgan/weights/parsing_parsenet.pth",
         ],
     ):
-        model_url, model_dest = model[0], os.path.join(Globals.root, model[1])
+        model_url, model_dest = model[0], os.path.join(config.root, model[1])
         download_with_progress_bar(model_url, model_dest, "GFPGAN weights")
 
 
@@ -253,7 +253,7 @@ def download_codeformer():
     model_url = (
         "https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth"
     )
-    model_dest = os.path.join(Globals.root, "models/codeformer/codeformer.pth")
+    model_dest = os.path.join(config.root, "models/codeformer/codeformer.pth")
     download_with_progress_bar(model_url, model_dest, "CodeFormer")
 
 
@@ -295,7 +295,7 @@ def download_vaes():
         # first the diffusers version
         repo_id = "stabilityai/sd-vae-ft-mse"
         args = dict(
-            cache_dir=global_cache_dir("hub"),
+            cache_dir=config.cache_dir,
         )
         if not AutoencoderKL.from_pretrained(repo_id, **args):
             raise Exception(f"download of {repo_id} failed")
@@ -306,7 +306,7 @@ def download_vaes():
         if not hf_download_with_resume(
             repo_id=repo_id,
             model_name=model_name,
-            model_dir=str(Globals.root / Model_dir / Weights_dir),
+            model_dir=str(config.root / Model_dir / Weights_dir),
         ):
             raise Exception(f"download of {model_name} failed")
     except Exception as e:
@@ -321,8 +321,7 @@ def get_root(root: str = None) -> str:
     elif os.environ.get("INVOKEAI_ROOT"):
         return os.environ.get("INVOKEAI_ROOT")
     else:
-        return Globals.root
-
+        return config.root
 
 # -------------------------------------
 class editOptsForm(npyscreen.FormMultiPage):
@@ -332,7 +331,7 @@ class editOptsForm(npyscreen.FormMultiPage):
     def create(self):
         program_opts = self.parentApp.program_opts
         old_opts = self.parentApp.invokeai_opts
-        first_time = not (Globals.root / Globals.initfile).exists()
+        first_time = not (config.root / 'invokeai.yaml').exists()
         access_token = HfFolder.get_token()
         window_width, window_height = get_terminal_size()
         for i in [
@@ -366,7 +365,7 @@ class editOptsForm(npyscreen.FormMultiPage):
         self.outdir = self.add_widget_intelligent(
             npyscreen.TitleFilename,
             name="(<tab> autocompletes, ctrl-N advances):",
-            value=old_opts.outdir or str(default_output_dir()),
+            value=str(old_opts.outdir) or str(default_output_dir()),
             select_dir=True,
             must_exist=False,
             use_two_lines=False,
@@ -381,17 +380,17 @@ class editOptsForm(npyscreen.FormMultiPage):
             editable=False,
             color="CONTROL",
         )
-        self.safety_checker = self.add_widget_intelligent(
+        self.nsfw_checker = self.add_widget_intelligent(
             npyscreen.Checkbox,
             name="NSFW checker",
-            value=old_opts.safety_checker,
+            value=old_opts.nsfw_checker,
             relx=5,
             scroll_exit=True,
         )
         self.nextrely += 1
         for i in [
-            "If you have an account at HuggingFace you may paste your access token here",
-            'to allow InvokeAI to download styles & subjects from the "Concept Library".',
+            "If you have an account at HuggingFace you may optionally paste your access token here",
+            'to allow InvokeAI to download restricted styles & subjects from the "Concept Library".',
             "See https://huggingface.co/settings/tokens",
         ]:
             self.add_widget_intelligent(
@@ -435,17 +434,10 @@ class editOptsForm(npyscreen.FormMultiPage):
             relx=5,
             scroll_exit=True,
         )
-        self.xformers = self.add_widget_intelligent(
+        self.xformers_enabled = self.add_widget_intelligent(
             npyscreen.Checkbox,
             name="Enable xformers support if available",
-            value=old_opts.xformers,
-            relx=5,
-            scroll_exit=True,
-        )
-        self.ckpt_convert = self.add_widget_intelligent(
-            npyscreen.Checkbox,
-            name="Load legacy checkpoint models into memory as diffusers models",
-            value=old_opts.ckpt_convert,
+            value=old_opts.xformers_enabled,
             relx=5,
             scroll_exit=True,
         )
@@ -480,19 +472,30 @@ class editOptsForm(npyscreen.FormMultiPage):
         self.nextrely += 1
         self.add_widget_intelligent(
             npyscreen.FixedText,
-            value="Directory containing embedding/textual inversion files:",
+            value="Directories containing textual inversion and LoRA models (<tab> autocompletes, ctrl-N advances):",
             editable=False,
             color="CONTROL",
         )
-        self.embedding_path = self.add_widget_intelligent(
+        self.embedding_dir = self.add_widget_intelligent(
             npyscreen.TitleFilename,
-            name="(<tab> autocompletes, ctrl-N advances):",
+            name=" Textual Inversion Embeddings:",
             value=str(default_embedding_dir()),
             select_dir=True,
             must_exist=False,
             use_two_lines=False,
             labelColor="GOOD",
-            begin_entry_at=40,
+            begin_entry_at=32,
+            scroll_exit=True,
+        )
+        self.lora_dir = self.add_widget_intelligent(
+            npyscreen.TitleFilename,
+            name="             LoRA and LyCORIS:",
+            value=str(default_lora_dir()),
+            select_dir=True,
+            must_exist=False,
+            use_two_lines=False,
+            labelColor="GOOD",
+            begin_entry_at=32,
             scroll_exit=True,
         )
         self.nextrely += 1
@@ -559,9 +562,9 @@ class editOptsForm(npyscreen.FormMultiPage):
             bad_fields.append(
                 f"The output directory does not seem to be valid. Please check that {str(Path(opt.outdir).parent)} is an existing directory."
             )
-        if not Path(opt.embedding_path).parent.exists():
+        if not Path(opt.embedding_dir).parent.exists():
             bad_fields.append(
-                f"The embedding directory does not seem to be valid. Please check that {str(Path(opt.embedding_path).parent)} is an existing directory."
+                f"The embedding directory does not seem to be valid. Please check that {str(Path(opt.embedding_dir).parent)} is an existing directory."
             )
         if len(bad_fields) > 0:
             message = "The following problems were detected and must be corrected:\n"
@@ -576,20 +579,23 @@ class editOptsForm(npyscreen.FormMultiPage):
         new_opts = Namespace()
 
         for attr in [
-            "outdir",
-            "safety_checker",
-            "free_gpu_mem",
-            "max_loaded_models",
-            "xformers",
-            "always_use_cpu",
-            "embedding_path",
-            "ckpt_convert",
+                "outdir",
+                "nsfw_checker",
+                "free_gpu_mem",
+                "max_loaded_models",
+                "xformers_enabled",
+                "always_use_cpu",
+                "embedding_dir",
+                "lora_dir",
         ]:
             setattr(new_opts, attr, getattr(self, attr).value)
 
         new_opts.hf_token = self.hf_token.value
         new_opts.license_acceptance = self.license_acceptance.value
         new_opts.precision = PRECISION_CHOICES[self.precision.value[0]]
+        
+        # widget library workaround to make max_loaded_models an int rather than a float
+        new_opts.max_loaded_models = int(new_opts.max_loaded_models)
 
         return new_opts
 
@@ -628,15 +634,14 @@ def edit_opts(program_opts: Namespace, invokeai_opts: Namespace) -> argparse.Nam
 
 
 def default_startup_options(init_file: Path) -> Namespace:
-    opts = Args().parse_args([])
+    opts = InvokeAIAppConfig(argv=[])
     outdir = Path(opts.outdir)
     if not outdir.is_absolute():
-        opts.outdir = str(Globals.root / opts.outdir)
+        opts.outdir = str(config.root / opts.outdir)
     if not init_file.exists():
-        opts.safety_checker = True
+        opts.nsfw_checker = True
     return opts
 
-
 def default_user_selections(program_opts: Namespace) -> Namespace:
     return Namespace(
         starter_models=default_dataset()
@@ -690,70 +695,61 @@ def run_console_ui(
 # -------------------------------------
 def write_opts(opts: Namespace, init_file: Path):
     """
-    Update the invokeai.init file with values from opts Namespace
+    Update the invokeai.yaml file with values from current settings.
     """
-    # touch file if it doesn't exist
-    if not init_file.exists():
-        with open(init_file, "w") as f:
-            f.write(INIT_FILE_PREAMBLE)
 
-    # We want to write in the changed arguments without clobbering
-    # any other initialization values the user has entered. There is
-    # no good way to do this because of the one-way nature of
-    # argparse: i.e. --outdir could be --outdir, --out, or -o
-    # initfile needs to be replaced with a fully structured format
-    # such as yaml; this is a hack that will work much of the time
-    args_to_skip = re.compile(
-        "^--?(o|out|no-xformer|xformer|no-ckpt|ckpt|free|no-nsfw|nsfw|prec|max_load|embed|always|ckpt|free_gpu)"
-    )
-    # fix windows paths
-    opts.outdir = opts.outdir.replace("\\", "/")
-    opts.embedding_path = opts.embedding_path.replace("\\", "/")
-    new_file = f"{init_file}.new"
-    try:
-        lines = [x.strip() for x in open(init_file, "r").readlines()]
-        with open(new_file, "w") as out_file:
-            for line in lines:
-                if len(line) > 0 and not args_to_skip.match(line):
-                    out_file.write(line + "\n")
-            out_file.write(
-                f"""
---outdir={opts.outdir}
---embedding_path={opts.embedding_path}
---precision={opts.precision}
---max_loaded_models={int(opts.max_loaded_models)}
---{'no-' if not opts.safety_checker else ''}nsfw_checker
---{'no-' if not opts.xformers else ''}xformers
---{'no-' if not opts.ckpt_convert else ''}ckpt_convert
-{'--free_gpu_mem' if opts.free_gpu_mem else ''}
-{'--always_use_cpu' if opts.always_use_cpu else ''}
-"""
-            )
-    except OSError as e:
-        print(f"** An error occurred while writing the init file: {str(e)}")
-
-    os.replace(new_file, init_file)
-
-    if opts.hf_token:
-        HfLogin(opts.hf_token)
+    # this will load current settings
+    config = InvokeAIAppConfig()
+    for key,value in opts.__dict__.items():
+        if hasattr(config,key):
+            setattr(config,key,value)
 
+    with open(init_file,'w', encoding='utf-8') as file:
+        file.write(config.to_yaml())
 
 # -------------------------------------
 def default_output_dir() -> Path:
-    return Globals.root / "outputs"
-
+    return config.root / "outputs"
 
 # -------------------------------------
 def default_embedding_dir() -> Path:
-    return Globals.root / "embeddings"
+    return config.root / "embeddings"
 
+# -------------------------------------
+def default_lora_dir() -> Path:
+    return config.root / "loras"
 
 # -------------------------------------
 def write_default_options(program_opts: Namespace, initfile: Path):
     opt = default_startup_options(initfile)
-    opt.hf_token = HfFolder.get_token()
     write_opts(opt, initfile)
 
+# -------------------------------------
+# Here we bring in
+# the legacy Args object in order to parse
+# the old init file and write out the new
+# yaml format.
+def migrate_init_file(legacy_format:Path):
+    old = legacy_parser.parse_args([f'@{str(legacy_format)}'])
+    new = InvokeAIAppConfig(conf={})
+
+    fields = list(get_type_hints(InvokeAIAppConfig).keys())
+    for attr in fields:
+        if hasattr(old,attr):
+            setattr(new,attr,getattr(old,attr))
+
+    # a few places where the field names have changed and we have to
+    # manually add in the new names/values
+    new.nsfw_checker = old.safety_checker
+    new.xformers_enabled = old.xformers
+    new.conf_path = old.conf
+    new.embedding_dir = old.embedding_path
+
+    invokeai_yaml = legacy_format.parent / 'invokeai.yaml'
+    with open(invokeai_yaml,"w", encoding="utf-8") as outfile:
+        outfile.write(new.to_yaml())
+
+    legacy_format.replace(legacy_format.parent / 'invokeai.init.old')
 
 # -------------------------------------
 def main():
@@ -810,7 +806,8 @@ def main():
     opt = parser.parse_args()
 
     # setting a global here
-    Globals.root = Path(os.path.expanduser(get_root(opt.root) or ""))
+    global config
+    config.root = Path(os.path.expanduser(get_root(opt.root) or ""))
 
     errors = set()
 
@@ -818,19 +815,26 @@ def main():
         models_to_download = default_user_selections(opt)
 
         # We check for to see if the runtime directory is correctly initialized.
-        init_file = Path(Globals.root, Globals.initfile)
-        if not init_file.exists() or not global_config_file().exists():
-            initialize_rootdir(Globals.root, opt.yes_to_all)
+        old_init_file = Path(config.root, 'invokeai.init')
+        new_init_file = Path(config.root, 'invokeai.yaml')
+        if old_init_file.exists() and not new_init_file.exists():
+            print('** Migrating invokeai.init to invokeai.yaml')
+            migrate_init_file(old_init_file)
+            config = get_invokeai_config()  # reread defaults
+
+
+        if not config.model_conf_path.exists():
+            initialize_rootdir(config.root, opt.yes_to_all)
 
         if opt.yes_to_all:
-            write_default_options(opt, init_file)
+            write_default_options(opt, new_init_file)
             init_options = Namespace(
                 precision="float32" if opt.full_precision else "float16"
             )
         else:
-            init_options, models_to_download = run_console_ui(opt, init_file)
+            init_options, models_to_download = run_console_ui(opt, new_init_file)
             if init_options:
-                write_opts(init_options, init_file)
+                write_opts(init_options, new_init_file)
             else:
                 print(
                     '\n** CANCELLED AT USER\'S REQUEST. USE THE "invoke.sh" LAUNCHER TO RUN LATER **\n'

invokeai/backend/config/legacy_arg_parsing.py

@@ -0,0 +1,390 @@
+# Copyright 2023 Lincoln D. Stein and the InvokeAI Team
+
+import argparse
+import shlex
+from argparse import ArgumentParser
+
+SAMPLER_CHOICES = [
+    "ddim",
+    "ddpm",
+    "deis",
+    "lms",
+    "pndm",
+    "heun",
+    "heun_k",
+    "euler",
+    "euler_k",
+    "euler_a",
+    "kdpm_2",
+    "kdpm_2_a",
+    "dpmpp_2s",
+    "dpmpp_2m",
+    "dpmpp_2m_k",
+    "unipc",
+]
+
+PRECISION_CHOICES = [
+    "auto",
+    "float32",
+    "autocast",
+    "float16",
+]
+
+class FileArgumentParser(ArgumentParser):
+    """
+    Supports reading defaults from an init file.
+    """
+    def convert_arg_line_to_args(self, arg_line):
+        return shlex.split(arg_line, comments=True)
+
+
+legacy_parser = FileArgumentParser(
+    description=
+    """
+Generate images using Stable Diffusion.
+    Use --web to launch the web interface.
+    Use --from_file to load prompts from a file path or standard input ("-").
+    Otherwise you will be dropped into an interactive command prompt (type -h for help.)
+    Other command-line arguments are defaults that can usually be overridden
+    prompt the command prompt.
+    """,
+    fromfile_prefix_chars='@',
+)
+general_group    = legacy_parser.add_argument_group('General')
+model_group      = legacy_parser.add_argument_group('Model selection')
+file_group       = legacy_parser.add_argument_group('Input/output')
+web_server_group = legacy_parser.add_argument_group('Web server')
+render_group     = legacy_parser.add_argument_group('Rendering')
+postprocessing_group     = legacy_parser.add_argument_group('Postprocessing')
+deprecated_group = legacy_parser.add_argument_group('Deprecated options')
+
+deprecated_group.add_argument('--laion400m')
+deprecated_group.add_argument('--weights') # deprecated
+general_group.add_argument(
+    '--version','-V',
+    action='store_true',
+    help='Print InvokeAI version number'
+)
+model_group.add_argument(
+    '--root_dir',
+    default=None,
+    help='Path to directory containing "models", "outputs" and "configs". If not present will read from environment variable INVOKEAI_ROOT. Defaults to ~/invokeai.',
+)
+model_group.add_argument(
+    '--config',
+    '-c',
+    '-config',
+    dest='conf',
+    default='./configs/models.yaml',
+    help='Path to configuration file for alternate models.',
+)
+model_group.add_argument(
+    '--model',
+    help='Indicates which diffusion model to load (defaults to "default" stanza in configs/models.yaml)',
+)
+model_group.add_argument(
+    '--weight_dirs',
+    nargs='+',
+    type=str,
+    help='List of one or more directories that will be auto-scanned for new model weights to import',
+)
+model_group.add_argument(
+    '--png_compression','-z',
+    type=int,
+    default=6,
+    choices=range(0,9),
+    dest='png_compression',
+    help='level of PNG compression, from 0 (none) to 9 (maximum). Default is 6.'
+)
+model_group.add_argument(
+    '-F',
+    '--full_precision',
+    dest='full_precision',
+    action='store_true',
+    help='Deprecated way to set --precision=float32',
+)
+model_group.add_argument(
+    '--max_loaded_models',
+    dest='max_loaded_models',
+    type=int,
+    default=2,
+    help='Maximum number of models to keep in memory for fast switching, including the one in GPU',
+)
+model_group.add_argument(
+    '--free_gpu_mem',
+    dest='free_gpu_mem',
+    action='store_true',
+    help='Force free gpu memory before final decoding',
+)
+model_group.add_argument(
+    '--sequential_guidance',
+    dest='sequential_guidance',
+    action='store_true',
+    help="Calculate guidance in serial instead of in parallel, lowering memory requirement "
+         "at the expense of speed",
+)
+model_group.add_argument(
+    '--xformers',
+    action=argparse.BooleanOptionalAction,
+    default=True,
+    help='Enable/disable xformers support (default enabled if installed)',
+)
+model_group.add_argument(
+    "--always_use_cpu",
+    dest="always_use_cpu",
+    action="store_true",
+    help="Force use of CPU even if GPU is available"
+)
+model_group.add_argument(
+    '--precision',
+    dest='precision',
+    type=str,
+    choices=PRECISION_CHOICES,
+    metavar='PRECISION',
+    help=f'Set model precision. Defaults to auto selected based on device. Options: {", ".join(PRECISION_CHOICES)}',
+    default='auto',
+)
+model_group.add_argument(
+    '--ckpt_convert',
+    action=argparse.BooleanOptionalAction,
+    dest='ckpt_convert',
+    default=True,
+    help='Deprecated option. Legacy ckpt files are now always converted to diffusers when loaded.'
+)
+model_group.add_argument(
+    '--internet',
+    action=argparse.BooleanOptionalAction,
+    dest='internet_available',
+    default=True,
+    help='Indicate whether internet is available for just-in-time model downloading (default: probe automatically).',
+)
+model_group.add_argument(
+    '--nsfw_checker',
+    '--safety_checker',
+    action=argparse.BooleanOptionalAction,
+    dest='safety_checker',
+    default=False,
+    help='Check for and blur potentially NSFW images. Use --no-nsfw_checker to disable.',
+)
+model_group.add_argument(
+    '--autoimport',
+    default=None,
+    type=str,
+    help='Check the indicated directory for .ckpt/.safetensors weights files at startup and import directly',
+)
+model_group.add_argument(
+    '--autoconvert',
+    default=None,
+    type=str,
+    help='Check the indicated directory for .ckpt/.safetensors weights files at startup and import as optimized diffuser models',
+)
+model_group.add_argument(
+    '--patchmatch',
+    action=argparse.BooleanOptionalAction,
+    default=True,
+    help='Load the patchmatch extension for outpainting. Use --no-patchmatch to disable.',
+)
+file_group.add_argument(
+    '--from_file',
+    dest='infile',
+    type=str,
+    help='If specified, load prompts from this file',
+)
+file_group.add_argument(
+    '--outdir',
+    '-o',
+    type=str,
+    help='Directory to save generated images and a log of prompts and seeds. Default: ROOTDIR/outputs',
+    default='outputs',
+)
+file_group.add_argument(
+    '--prompt_as_dir',
+    '-p',
+    action='store_true',
+    help='Place images in subdirectories named after the prompt.',
+)
+render_group.add_argument(
+    '--fnformat',
+    default='{prefix}.{seed}.png',
+    type=str,
+    help='Overwrite the filename format. You can use any argument as wildcard enclosed in curly braces. Default is {prefix}.{seed}.png',
+)
+render_group.add_argument(
+    '-s',
+    '--steps',
+    type=int,
+    default=50,
+    help='Number of steps'
+)
+render_group.add_argument(
+    '-W',
+    '--width',
+    type=int,
+    help='Image width, multiple of 64',
+)
+render_group.add_argument(
+    '-H',
+    '--height',
+    type=int,
+    help='Image height, multiple of 64',
+)
+render_group.add_argument(
+    '-C',
+    '--cfg_scale',
+    default=7.5,
+    type=float,
+    help='Classifier free guidance (CFG) scale - higher numbers cause generator to "try" harder.',
+)
+render_group.add_argument(
+    '--sampler',
+    '-A',
+    '-m',
+    dest='sampler_name',
+    type=str,
+    choices=SAMPLER_CHOICES,
+    metavar='SAMPLER_NAME',
+    help=f'Set the default sampler. Supported samplers: {", ".join(SAMPLER_CHOICES)}',
+    default='k_lms',
+)
+render_group.add_argument(
+    '--log_tokenization',
+    '-t',
+    action='store_true',
+    help='shows how the prompt is split into tokens'
+)
+render_group.add_argument(
+    '-f',
+    '--strength',
+    type=float,
+    help='img2img strength for noising/unnoising. 0.0 preserves image exactly, 1.0 replaces it completely',
+)
+render_group.add_argument(
+    '-T',
+    '-fit',
+    '--fit',
+    action=argparse.BooleanOptionalAction,
+    help='If specified, will resize the input image to fit within the dimensions of width x height (512x512 default)',
+)
+
+render_group.add_argument(
+    '--grid',
+    '-g',
+    action=argparse.BooleanOptionalAction,
+    help='generate a grid'
+)
+render_group.add_argument(
+    '--embedding_directory',
+    '--embedding_path',
+    dest='embedding_path',
+    default='embeddings',
+    type=str,
+    help='Path to a directory containing .bin and/or .pt files, or a single .bin/.pt file. You may use subdirectories. (default is ROOTDIR/embeddings)'
+)
+render_group.add_argument(
+    '--lora_directory',
+    dest='lora_path',
+    default='loras',
+    type=str,
+    help='Path to a directory containing LoRA files; subdirectories are not supported. (default is ROOTDIR/loras)'
+)
+render_group.add_argument(
+    '--embeddings',
+    action=argparse.BooleanOptionalAction,
+    default=True,
+    help='Enable embedding directory (default). Use --no-embeddings to disable.',
+)
+render_group.add_argument(
+    '--enable_image_debugging',
+    action='store_true',
+    help='Generates debugging image to display'
+)
+render_group.add_argument(
+    '--karras_max',
+    type=int,
+    default=None,
+    help="control the point at which the K* samplers will shift from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts). Set to 0 to use LatentDiffusion for all step values, and to a high value (e.g. 1000) to use Karras for all step values. [29]."
+)
+# Restoration related args
+postprocessing_group.add_argument(
+    '--no_restore',
+    dest='restore',
+    action='store_false',
+    help='Disable face restoration with GFPGAN or codeformer',
+)
+postprocessing_group.add_argument(
+    '--no_upscale',
+    dest='esrgan',
+    action='store_false',
+    help='Disable upscaling with ESRGAN',
+)
+postprocessing_group.add_argument(
+    '--esrgan_bg_tile',
+    type=int,
+    default=400,
+    help='Tile size for background sampler, 0 for no tile during testing. Default: 400.',
+)
+postprocessing_group.add_argument(
+    '--esrgan_denoise_str',
+    type=float,
+    default=0.75,
+    help='esrgan denoise str. 0 is no denoise, 1 is max denoise.  Default: 0.75',
+)
+postprocessing_group.add_argument(
+    '--gfpgan_model_path',
+    type=str,
+    default='./models/gfpgan/GFPGANv1.4.pth',
+    help='Indicates the path to the GFPGAN model',
+)
+web_server_group.add_argument(
+    '--web',
+    dest='web',
+    action='store_true',
+    help='Start in web server mode.',
+)
+web_server_group.add_argument(
+    '--web_develop',
+    dest='web_develop',
+    action='store_true',
+    help='Start in web server development mode.',
+)
+web_server_group.add_argument(
+    "--web_verbose",
+    action="store_true",
+    help="Enables verbose logging",
+)
+web_server_group.add_argument(
+    "--cors",
+    nargs="*",
+    type=str,
+    help="Additional allowed origins, comma-separated",
+)
+web_server_group.add_argument(
+    '--host',
+    type=str,
+    default='127.0.0.1',
+    help='Web server: Host or IP to listen on. Set to 0.0.0.0 to accept traffic from other devices on your network.'
+)
+web_server_group.add_argument(
+    '--port',
+    type=int,
+    default='9090',
+    help='Web server: Port to listen on'
+)
+web_server_group.add_argument(
+    '--certfile',
+    type=str,
+    default=None,
+    help='Web server: Path to certificate file to use for SSL. Use together with --keyfile'
+)
+web_server_group.add_argument(
+    '--keyfile',
+    type=str,
+    default=None,
+    help='Web server: Path to private key file to use for SSL. Use together with --certfile'
+)
+web_server_group.add_argument(
+    '--gui',
+    dest='gui',
+    action='store_true',
+    help='Start InvokeAI GUI',
+)

invokeai/backend/config/model_install_backend.py

@@ -19,13 +19,15 @@ from tqdm import tqdm
 
 import invokeai.configs as configs
 
-from ..globals import Globals, global_cache_dir, global_config_dir
+from invokeai.app.services.config import get_invokeai_config
 from ..model_management import ModelManager
 from ..stable_diffusion import StableDiffusionGeneratorPipeline
 
+
 warnings.filterwarnings("ignore")
 
 # --------------------------globals-----------------------
+config = get_invokeai_config()
 Model_dir = "models"
 Weights_dir = "ldm/stable-diffusion-v1/"
 
@@ -47,12 +49,11 @@ Config_preamble = """
 
 
 def default_config_file():
-    return Path(global_config_dir()) / "models.yaml"
+    return config.model_conf_path
 
 
 def sd_configs():
-    return Path(global_config_dir()) / "stable-diffusion"
-
+    return config.legacy_conf_path
 
 def initial_models():
     global Datasets
@@ -121,8 +122,9 @@ def install_requested_models(
 
     if scan_at_startup and scan_directory.is_dir():
         argument = "--autoconvert"
-        initfile = Path(Globals.root, Globals.initfile)
-        replacement = Path(Globals.root, f"{Globals.initfile}.new")
+        print('** The global initfile is no longer supported; rewrite to support new yaml format **')
+        initfile = Path(config.root, 'invokeai.init')
+        replacement = Path(config.root, f"invokeai.init.new")
         directory = str(scan_directory).replace("\\", "/")
         with open(initfile, "r") as input:
             with open(replacement, "w") as output:
@@ -150,7 +152,7 @@ def get_root(root: str = None) -> str:
     elif os.environ.get("INVOKEAI_ROOT"):
         return os.environ.get("INVOKEAI_ROOT")
     else:
-        return Globals.root
+        return config.root
 
 
 # ---------------------------------------------
@@ -183,7 +185,7 @@ def all_datasets() -> dict:
 # look for legacy model.ckpt in models directory and offer to
 # normalize its name
 def migrate_models_ckpt():
-    model_path = os.path.join(Globals.root, Model_dir, Weights_dir)
+    model_path = os.path.join(config.root, Model_dir, Weights_dir)
     if not os.path.exists(os.path.join(model_path, "model.ckpt")):
         return
     new_name = initial_models()["stable-diffusion-1.4"]["file"]
@@ -228,7 +230,7 @@ def _download_repo_or_file(
 def _download_ckpt_weights(mconfig: DictConfig, access_token: str) -> Path:
     repo_id = mconfig["repo_id"]
     filename = mconfig["file"]
-    cache_dir = os.path.join(Globals.root, Model_dir, Weights_dir)
+    cache_dir = os.path.join(config.root, Model_dir, Weights_dir)
     return hf_download_with_resume(
         repo_id=repo_id,
         model_dir=cache_dir,
@@ -239,9 +241,9 @@ def _download_ckpt_weights(mconfig: DictConfig, access_token: str) -> Path:
 
 # ---------------------------------------------
 def download_from_hf(
-    model_class: object, model_name: str, cache_subdir: Path = Path("hub"), **kwargs
+    model_class: object, model_name: str, **kwargs
 ):
-    path = global_cache_dir(cache_subdir)
+    path = config.cache_dir
     model = model_class.from_pretrained(
         model_name,
         cache_dir=path,
@@ -417,7 +419,7 @@ def new_config_file_contents(
             stanza["height"] = mod["height"]
         if "file" in mod:
             stanza["weights"] = os.path.relpath(
-                successfully_downloaded[model], start=Globals.root
+                successfully_downloaded[model], start=config.root
             )
             stanza["config"] = os.path.normpath(
                 os.path.join(sd_configs(), mod["config"])
@@ -456,7 +458,7 @@ def delete_weights(model_name: str, conf_stanza: dict):
 
     weights = Path(weights)
     if not weights.is_absolute():
-        weights = Path(Globals.root) / weights
+        weights = Path(config.root) / weights
         try:
             weights.unlink()
         except OSError as e:

invokeai/backend/generator/base.py

@@ -25,11 +25,13 @@ from typing import Callable, List, Iterator, Optional, Type
 from dataclasses import dataclass, field
 from diffusers.schedulers import SchedulerMixin as Scheduler
 
+import invokeai.backend.util.logging as logger
 from ..image_util import configure_model_padding
 from ..util.util import rand_perlin_2d
 from ..safety_checker import SafetyChecker
 from ..prompting.conditioning import get_uc_and_c_and_ec
 from ..stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
+from ..stable_diffusion.schedulers import SCHEDULER_MAP
 
 downsampling = 8
 
@@ -70,19 +72,6 @@ class InvokeAIGeneratorOutput:
 # we are interposing a wrapper around the original Generator classes so that
 # old code that calls Generate will continue to work.
 class InvokeAIGenerator(metaclass=ABCMeta):
-    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,
-    )
-
     def __init__(self,
                  model_info: dict,
                  params: InvokeAIGeneratorBasicParams=InvokeAIGeneratorBasicParams(),
@@ -174,14 +163,20 @@ class InvokeAIGenerator(metaclass=ABCMeta):
         '''
         Return list of all the schedulers that we currently handle.
         '''
-        return list(self.scheduler_map.keys())
+        return list(SCHEDULER_MAP.keys())
 
     def load_generator(self, model: StableDiffusionGeneratorPipeline, generator_class: Type[Generator]):
         return generator_class(model, self.params.precision)
 
     def get_scheduler(self, scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
-        scheduler_class = self.scheduler_map.get(scheduler_name,'ddim')
-        scheduler = scheduler_class.from_config(model.scheduler.config)
+        scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
+        
+        scheduler_config = model.scheduler.config
+        if "_backup" in scheduler_config:
+            scheduler_config = scheduler_config["_backup"]
+        scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
+        scheduler = scheduler_class.from_config(scheduler_config)
+        
         # hack copied over from generate.py
         if not hasattr(scheduler, 'uses_inpainting_model'):
             scheduler.uses_inpainting_model = lambda: False
@@ -225,10 +220,10 @@ class Inpaint(Img2Img):
     def generate(self,
                  mask_image: Image.Image | torch.FloatTensor,
                  # Seam settings - when 0, doesn't fill seam
-                 seam_size: int = 0,
-                 seam_blur: int = 0,
+                 seam_size: int = 96,
+                 seam_blur: int = 16,
                  seam_strength: float = 0.7,
-                 seam_steps: int = 10,
+                 seam_steps: int = 30,
                  tile_size: int = 32,
                  inpaint_replace=False,
                  infill_method=None,
@@ -372,7 +367,7 @@ class Generator:
                     try:
                         x_T = self.get_noise(width, height)
                     except:
-                        print("** An error occurred while getting initial noise **")
+                        logger.error("An error occurred while getting initial noise")
                         print(traceback.format_exc())
 
                 # Pass on the seed in case a layer beneath us needs to generate noise on its own.
@@ -607,7 +602,7 @@ class Generator:
         image = self.sample_to_image(sample)
         dirname = os.path.dirname(filepath) or "."
         if not os.path.exists(dirname):
-            print(f"** creating directory {dirname}")
+            logger.info(f"creating directory {dirname}")
             os.makedirs(dirname, exist_ok=True)
         image.save(filepath, "PNG")
 

invokeai/backend/generator/embiggen.py

@@ -8,10 +8,11 @@ import torch
 from PIL import Image
 from tqdm import trange
 
+import invokeai.backend.util.logging as logger
+
 from .base import Generator
 from .img2img import Img2Img
 
-
 class Embiggen(Generator):
     def __init__(self, model, precision):
         super().__init__(model, precision)
@@ -72,22 +73,22 @@ class Embiggen(Generator):
             embiggen = [1.0]  # If not specified, assume no scaling
         elif embiggen[0] < 0:
             embiggen[0] = 1.0
-            print(
-                ">> Embiggen scaling factor cannot be negative, fell back to the default of 1.0 !"
+            logger.warning(
+                "Embiggen scaling factor cannot be negative, fell back to the default of 1.0 !"
             )
         if len(embiggen) < 2:
             embiggen.append(0.75)
         elif embiggen[1] > 1.0 or embiggen[1] < 0:
             embiggen[1] = 0.75
-            print(
-                ">> Embiggen upscaling strength for ESRGAN must be between 0 and 1, fell back to the default of 0.75 !"
+            logger.warning(
+                "Embiggen upscaling strength for ESRGAN must be between 0 and 1, fell back to the default of 0.75 !"
             )
         if len(embiggen) < 3:
             embiggen.append(0.25)
         elif embiggen[2] < 0:
             embiggen[2] = 0.25
-            print(
-                ">> Overlap size for Embiggen must be a positive ratio between 0 and 1 OR a number of pixels, fell back to the default of 0.25 !"
+            logger.warning(
+                "Overlap size for Embiggen must be a positive ratio between 0 and 1 OR a number of pixels, fell back to the default of 0.25 !"
             )
 
         # Convert tiles from their user-freindly count-from-one to count-from-zero, because we need to do modulo math
@@ -97,8 +98,8 @@ class Embiggen(Generator):
             embiggen_tiles.sort()
 
         if strength >= 0.5:
-            print(
-                f"* WARNING: Embiggen may produce mirror motifs if the strength (-f) is too high (currently {strength}). Try values between 0.35-0.45."
+            logger.warning(
+                f"Embiggen may produce mirror motifs if the strength (-f) is too high (currently {strength}). Try values between 0.35-0.45."
             )
 
         # Prep img2img generator, since we wrap over it
@@ -121,8 +122,8 @@ class Embiggen(Generator):
                 from ..restoration.realesrgan import ESRGAN
 
                 esrgan = ESRGAN()
-                print(
-                    f">> ESRGAN upscaling init image prior to cutting with Embiggen with strength {embiggen[1]}"
+                logger.info(
+                    f"ESRGAN upscaling init image prior to cutting with Embiggen with strength {embiggen[1]}"
                 )
                 if embiggen[0] > 2:
                     initsuperimage = esrgan.process(
@@ -312,10 +313,10 @@ class Embiggen(Generator):
         def make_image():
             # Make main tiles -------------------------------------------------
             if embiggen_tiles:
-                print(f">> Making {len(embiggen_tiles)} Embiggen tiles...")
+                logger.info(f"Making {len(embiggen_tiles)} Embiggen tiles...")
             else:
-                print(
-                    f">> Making {(emb_tiles_x * emb_tiles_y)} Embiggen tiles ({emb_tiles_x}x{emb_tiles_y})..."
+                logger.info(
+                    f"Making {(emb_tiles_x * emb_tiles_y)} Embiggen tiles ({emb_tiles_x}x{emb_tiles_y})..."
                 )
 
             emb_tile_store = []
@@ -361,11 +362,11 @@ class Embiggen(Generator):
                 # newinitimage.save(newinitimagepath)
 
                 if embiggen_tiles:
-                    print(
+                    logger.debug(
                         f"Making tile #{tile + 1} ({embiggen_tiles.index(tile) + 1} of {len(embiggen_tiles)} requested)"
                     )
                 else:
-                    print(f"Starting {tile + 1} of {(emb_tiles_x * emb_tiles_y)} tiles")
+                    logger.debug(f"Starting {tile + 1} of {(emb_tiles_x * emb_tiles_y)} tiles")
 
                 # create a torch tensor from an Image
                 newinitimage = np.array(newinitimage).astype(np.float32) / 255.0
@@ -547,8 +548,8 @@ class Embiggen(Generator):
                     # Layer tile onto final image
                     outputsuperimage.alpha_composite(intileimage, (left, top))
             else:
-                print(
-                    "Error: could not find all Embiggen output tiles in memory? Something must have gone wrong with img2img generation."
+                logger.error(
+                    "Could not find all Embiggen output tiles in memory? Something must have gone wrong with img2img generation."
                 )
 
             # after internal loops and patching up return Embiggen image

invokeai/backend/generator/inpaint.py

@@ -4,6 +4,7 @@ invokeai.backend.generator.inpaint descends from .generator
 from __future__ import annotations
 
 import math
+from typing import Tuple, Union
 
 import cv2
 import numpy as np
@@ -59,7 +60,7 @@ class Inpaint(Img2Img):
             writeable=False,
         )
 
-    def infill_patchmatch(self, im: Image.Image) -> Image:
+    def infill_patchmatch(self, im: Image.Image) -> Image.Image:
         if im.mode != "RGBA":
             return im
 
@@ -75,18 +76,18 @@ class Inpaint(Img2Img):
         return im_patched
 
     def tile_fill_missing(
-        self, im: Image.Image, tile_size: int = 16, seed: int = None
-    ) -> Image:
+        self, im: Image.Image, tile_size: int = 16, seed: Union[int, None] = None
+    ) -> Image.Image:
         # Only fill if there's an alpha layer
         if im.mode != "RGBA":
             return im
 
         a = np.asarray(im, dtype=np.uint8)
 
-        tile_size = (tile_size, tile_size)
+        tile_size_tuple = (tile_size, tile_size)
 
         # Get the image as tiles of a specified size
-        tiles = self.get_tile_images(a, *tile_size).copy()
+        tiles = self.get_tile_images(a, *tile_size_tuple).copy()
 
         # Get the mask as tiles
         tiles_mask = tiles[:, :, :, :, 3]
@@ -127,7 +128,9 @@ class Inpaint(Img2Img):
 
         return si
 
-    def mask_edge(self, mask: Image, edge_size: int, edge_blur: int) -> Image:
+    def mask_edge(
+        self, mask: Image.Image, edge_size: int, edge_blur: int
+    ) -> Image.Image:
         npimg = np.asarray(mask, dtype=np.uint8)
 
         # Detect any partially transparent regions
@@ -206,15 +209,15 @@ class Inpaint(Img2Img):
         cfg_scale,
         ddim_eta,
         conditioning,
-        init_image: PIL.Image.Image | torch.FloatTensor,
-        mask_image: PIL.Image.Image | torch.FloatTensor,
+        init_image: Image.Image | torch.FloatTensor,
+        mask_image: Image.Image | torch.FloatTensor,
         strength: float,
         mask_blur_radius: int = 8,
         # Seam settings - when 0, doesn't fill seam
-        seam_size: int = 0,
-        seam_blur: int = 0,
+        seam_size: int = 96,
+        seam_blur: int = 16,
         seam_strength: float = 0.7,
-        seam_steps: int = 10,
+        seam_steps: int = 30,
         tile_size: int = 32,
         step_callback=None,
         inpaint_replace=False,
@@ -222,7 +225,7 @@ class Inpaint(Img2Img):
         infill_method=None,
         inpaint_width=None,
         inpaint_height=None,
-        inpaint_fill: tuple(int) = (0x7F, 0x7F, 0x7F, 0xFF),
+        inpaint_fill: Tuple[int, int, int, int] = (0x7F, 0x7F, 0x7F, 0xFF),
         attention_maps_callback=None,
         **kwargs,
     ):
@@ -239,7 +242,7 @@ class Inpaint(Img2Img):
         self.inpaint_width = inpaint_width
         self.inpaint_height = inpaint_height
 
-        if isinstance(init_image, PIL.Image.Image):
+        if isinstance(init_image, Image.Image):
             self.pil_image = init_image.copy()
 
             # Do infill
@@ -250,8 +253,8 @@ class Inpaint(Img2Img):
                     self.pil_image.copy(), seed=self.seed, tile_size=tile_size
                 )
             elif infill_method == "solid":
-                solid_bg = PIL.Image.new("RGBA", init_image.size, inpaint_fill)
-                init_filled = PIL.Image.alpha_composite(solid_bg, init_image)
+                solid_bg = Image.new("RGBA", init_image.size, inpaint_fill)
+                init_filled = Image.alpha_composite(solid_bg, init_image)
             else:
                 raise ValueError(
                     f"Non-supported infill type {infill_method}", infill_method
@@ -269,7 +272,7 @@ class Inpaint(Img2Img):
             # Create init tensor
             init_image = image_resized_to_grid_as_tensor(init_filled.convert("RGB"))
 
-        if isinstance(mask_image, PIL.Image.Image):
+        if isinstance(mask_image, Image.Image):
             self.pil_mask = mask_image.copy()
             debug_image(
                 mask_image,

invokeai/backend/generator/txt2img2img.py

@@ -14,6 +14,8 @@ from ..stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeli
 from ..stable_diffusion.diffusers_pipeline import ConditioningData
 from ..stable_diffusion.diffusers_pipeline import trim_to_multiple_of
 
+import invokeai.backend.util.logging as logger
+
 class Txt2Img2Img(Generator):
     def __init__(self, model, precision):
         super().__init__(model, precision)
@@ -77,8 +79,8 @@ class Txt2Img2Img(Generator):
             # the message below is accurate.
             init_width = first_pass_latent_output.size()[3] * self.downsampling_factor
             init_height = first_pass_latent_output.size()[2] * self.downsampling_factor
-            print(
-                f"\n>> Interpolating from {init_width}x{init_height} to {width}x{height} using DDIM sampling"
+            logger.info(
+                f"Interpolating from {init_width}x{init_height} to {width}x{height} using DDIM sampling"
             )
 
             # resizing

invokeai/backend/globals.py

@@ -1,122 +0,0 @@
-"""
-invokeai.backend.globals defines a small number of global variables that would
-otherwise have to be passed through long and complex call chains.
-
-It defines a Namespace object named "Globals" that contains
-the attributes:
-
-  - root           - the root directory under which "models" and "outputs" can be found
-  - initfile       - path to the initialization file
-  - try_patchmatch - option to globally disable loading of 'patchmatch' module
-  - always_use_cpu - force use of CPU even if GPU is available
-"""
-
-import os
-import os.path as osp
-from argparse import Namespace
-from pathlib import Path
-from typing import Union
-
-Globals = Namespace()
-
-# Where to look for the initialization file and other key components
-Globals.initfile = "invokeai.init"
-Globals.models_file = "models.yaml"
-Globals.models_dir = "models"
-Globals.config_dir = "configs"
-Globals.autoscan_dir = "weights"
-Globals.converted_ckpts_dir = "converted_ckpts"
-
-# Set the default root directory. This can be overwritten by explicitly
-# passing the `--root <directory>` argument on the command line.
-# logic is:
-# 1) use INVOKEAI_ROOT environment variable (no check for this being a valid directory)
-# 2) use VIRTUAL_ENV environment variable, with a check for initfile being there
-# 3) use ~/invokeai
-
-if os.environ.get("INVOKEAI_ROOT"):
-    Globals.root = osp.abspath(os.environ.get("INVOKEAI_ROOT"))
-elif (
-    os.environ.get("VIRTUAL_ENV")
-    and Path(os.environ.get("VIRTUAL_ENV"), "..", Globals.initfile).exists()
-):
-    Globals.root = osp.abspath(osp.join(os.environ.get("VIRTUAL_ENV"), ".."))
-else:
-    Globals.root = osp.abspath(osp.expanduser("~/invokeai"))
-
-# Try loading patchmatch
-Globals.try_patchmatch = True
-
-# Use CPU even if GPU is available (main use case is for debugging MPS issues)
-Globals.always_use_cpu = False
-
-# Whether the internet is reachable for dynamic downloads
-# The CLI will test connectivity at startup time.
-Globals.internet_available = True
-
-# Whether to disable xformers
-Globals.disable_xformers = False
-
-# Low-memory tradeoff for guidance calculations.
-Globals.sequential_guidance = False
-
-# whether we are forcing full precision
-Globals.full_precision = False
-
-# whether we should convert ckpt files into diffusers models on the fly
-Globals.ckpt_convert = True
-
-# logging tokenization everywhere
-Globals.log_tokenization = False
-
-
-def global_config_file() -> Path:
-    return Path(Globals.root, Globals.config_dir, Globals.models_file)
-
-
-def global_config_dir() -> Path:
-    return Path(Globals.root, Globals.config_dir)
-
-
-def global_models_dir() -> Path:
-    return Path(Globals.root, Globals.models_dir)
-
-
-def global_autoscan_dir() -> Path:
-    return Path(Globals.root, Globals.autoscan_dir)
-
-
-def global_converted_ckpts_dir() -> Path:
-    return Path(global_models_dir(), Globals.converted_ckpts_dir)
-
-
-def global_set_root(root_dir: Union[str, Path]):
-    Globals.root = root_dir
-
-
-def global_cache_dir(subdir: Union[str, Path] = "") -> Path:
-    """
-    Returns Path to the model cache directory. If a subdirectory
-    is provided, it will be appended to the end of the path, allowing
-    for Hugging Face-style conventions. Currently, Hugging Face has
-    moved all models into the "hub" subfolder, so for any pretrained
-    HF model, use:
-         global_cache_dir('hub')
-
-    The legacy location for transformers used to be global_cache_dir('transformers')
-    and global_cache_dir('diffusers') for diffusers.
-    """
-    home: str = os.getenv("HF_HOME")
-
-    if home is None:
-        home = os.getenv("XDG_CACHE_HOME")
-
-        if home is not None:
-            # Set `home` to $XDG_CACHE_HOME/huggingface, which is the default location mentioned in Hugging Face Hub Client Library.
-            # See: https://huggingface.co/docs/huggingface_hub/main/en/package_reference/environment_variables#xdgcachehome
-            home += os.sep + "huggingface"
-
-    if home is not None:
-        return Path(home, subdir)
-    else:
-        return Path(Globals.root, "models", subdir)

invokeai/backend/image_util/patchmatch.py

@@ -5,9 +5,8 @@ wraps the actual patchmatch object. It respects the global
 be suppressed or deferred
 """
 import numpy as np
-
-from invokeai.backend.globals import Globals
-
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 class PatchMatch:
     """
@@ -22,18 +21,19 @@ class PatchMatch:
 
     @classmethod
     def _load_patch_match(self):
+        config = get_invokeai_config()
         if self.tried_load:
             return
-        if Globals.try_patchmatch:
+        if config.try_patchmatch:
             from patchmatch import patch_match as pm
 
             if pm.patchmatch_available:
-                print(">> Patchmatch initialized")
+                logger.info("Patchmatch initialized")
             else:
-                print(">> Patchmatch not loaded (nonfatal)")
+                logger.info("Patchmatch not loaded (nonfatal)")
             self.patch_match = pm
         else:
-            print(">> Patchmatch loading disabled")
+            logger.info("Patchmatch loading disabled")
         self.tried_load = True
 
     @classmethod

invokeai/backend/image_util/txt2mask.py

@@ -30,15 +30,14 @@ work fine.
 import numpy as np
 import torch
 from PIL import Image, ImageOps
-from torchvision import transforms
 from transformers import AutoProcessor, CLIPSegForImageSegmentation
 
-from invokeai.backend.globals import global_cache_dir
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 CLIPSEG_MODEL = "CIDAS/clipseg-rd64-refined"
 CLIPSEG_SIZE = 352
 
-
 class SegmentedGrayscale(object):
     def __init__(self, image: Image, heatmap: torch.Tensor):
         self.heatmap = heatmap
@@ -83,15 +82,16 @@ class Txt2Mask(object):
     """
 
     def __init__(self, device="cpu", refined=False):
-        print(">> Initializing clipseg model for text to mask inference")
+        logger.info("Initializing clipseg model for text to mask inference")
+        config = get_invokeai_config()
 
         # BUG: we are not doing anything with the device option at this time
         self.device = device
         self.processor = AutoProcessor.from_pretrained(
-            CLIPSEG_MODEL, cache_dir=global_cache_dir("hub")
+            CLIPSEG_MODEL, cache_dir=config.cache_dir
         )
         self.model = CLIPSegForImageSegmentation.from_pretrained(
-            CLIPSEG_MODEL, cache_dir=global_cache_dir("hub")
+            CLIPSEG_MODEL, cache_dir=config.cache_dir
         )
 
     @torch.no_grad()
@@ -101,18 +101,6 @@ class Txt2Mask(object):
         provided image and returns a SegmentedGrayscale object in which the brighter
         pixels indicate where the object is inferred to be.
         """
-        transform = transforms.Compose(
-            [
-                transforms.ToTensor(),
-                transforms.Normalize(
-                    mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
-                ),
-                transforms.Resize(
-                    (CLIPSEG_SIZE, CLIPSEG_SIZE)
-                ),  # must be multiple of 64...
-            ]
-        )
-
         if type(image) is str:
             image = Image.open(image).convert("RGB")
 

invokeai/backend/model_management/__init__.py

@@ -5,6 +5,7 @@ from .convert_ckpt_to_diffusers import (
     convert_ckpt_to_diffusers,
     load_pipeline_from_original_stable_diffusion_ckpt,
 )
-from .model_manager import ModelManager
+from .model_manager import ModelManager,SDModelComponent
+
 
 

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -25,7 +25,8 @@ from typing import Union
 import torch
 from safetensors.torch import load_file
 
-from invokeai.backend.globals import global_cache_dir, global_config_dir
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 from .model_manager import ModelManager, SDLegacyType
 
@@ -46,6 +47,7 @@ from diffusers import (
     LDMTextToImagePipeline,
     LMSDiscreteScheduler,
     PNDMScheduler,
+    UniPCMultistepScheduler,
     StableDiffusionPipeline,
     UNet2DConditionModel,
 )
@@ -72,7 +74,6 @@ from transformers import (
 
 from ..stable_diffusion import StableDiffusionGeneratorPipeline
 
-
 def shave_segments(path, n_shave_prefix_segments=1):
     """
     Removes segments. Positive values shave the first segments, negative shave the last segments.
@@ -372,9 +373,9 @@ 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.")
+        logger.debug(f"Checkpoint {path} has both EMA and non-EMA weights.")
         if extract_ema:
-            print("   | Extracting EMA weights (usually better for inference)")
+            logger.debug("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:])
@@ -392,8 +393,8 @@ def convert_ldm_unet_checkpoint(checkpoint, config, path=None, extract_ema=False
                             key
                         )
         else:
-            print(
-                "   | Extracting only the non-EMA weights (usually better for fine-tuning)"
+            logger.debug(
+                "Extracting only the non-EMA weights (usually better for fine-tuning)"
             )
 
     for key in keys:
@@ -841,7 +842,7 @@ def convert_ldm_bert_checkpoint(checkpoint, config):
 
 def convert_ldm_clip_checkpoint(checkpoint):
     text_model = CLIPTextModel.from_pretrained(
-        "openai/clip-vit-large-patch14", cache_dir=global_cache_dir("hub")
+        "openai/clip-vit-large-patch14", cache_dir=get_invokeai_config().cache_dir
     )
 
     keys = list(checkpoint.keys())
@@ -896,7 +897,7 @@ textenc_pattern = re.compile("|".join(protected.keys()))
 
 
 def convert_paint_by_example_checkpoint(checkpoint):
-    cache_dir = global_cache_dir("hub")
+    cache_dir = get_invokeai_config().cache_dir
     config = CLIPVisionConfig.from_pretrained(
         "openai/clip-vit-large-patch14", cache_dir=cache_dir
     )
@@ -968,7 +969,7 @@ def convert_paint_by_example_checkpoint(checkpoint):
 
 
 def convert_open_clip_checkpoint(checkpoint):
-    cache_dir = global_cache_dir("hub")
+    cache_dir = get_invokeai_config().cache_dir
     text_model = CLIPTextModel.from_pretrained(
         "stabilityai/stable-diffusion-2", subfolder="text_encoder", cache_dir=cache_dir
     )
@@ -1091,7 +1092,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
     :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.
     """
-
+    config = get_invokeai_config()
     with warnings.catch_warnings():
         warnings.simplefilter("ignore")
         verbosity = dlogging.get_verbosity()
@@ -1104,7 +1105,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         else:
             checkpoint = load_file(checkpoint_path)
 
-        cache_dir = global_cache_dir("hub")
+        cache_dir = config.cache_dir
         pipeline_class = (
             StableDiffusionGeneratorPipeline
             if return_generator_pipeline
@@ -1115,7 +1116,7 @@ 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")
+            logger.debug("global_step key not found in model")
             global_step = None
 
         # sometimes there is a state_dict key and sometimes not
@@ -1128,25 +1129,23 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
 
             if model_type == SDLegacyType.V2_v:
                 original_config_file = (
-                    global_config_dir() / "stable-diffusion" / "v2-inference-v.yaml"
+                    config.legacy_conf_path / "v2-inference-v.yaml"
                 )
                 if global_step == 110000:
                     # v2.1 needs to upcast attention
                     upcast_attention = True
             elif model_type == SDLegacyType.V2_e:
                 original_config_file = (
-                    global_config_dir() / "stable-diffusion" / "v2-inference.yaml"
+                    config.legacy_conf_path / "v2-inference.yaml"
                 )
             elif model_type == SDLegacyType.V1_INPAINT:
                 original_config_file = (
-                    global_config_dir()
-                    / "stable-diffusion"
-                    / "v1-inpainting-inference.yaml"
+                    config.legacy_conf_path / "v1-inpainting-inference.yaml"
                 )
 
             elif model_type == SDLegacyType.V1:
                 original_config_file = (
-                    global_config_dir() / "stable-diffusion" / "v1-inference.yaml"
+                    config.legacy_conf_path / "v1-inference.yaml"
                 )
 
             else:
@@ -1208,6 +1207,8 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
             scheduler = EulerAncestralDiscreteScheduler.from_config(scheduler.config)
         elif scheduler_type == "dpm":
             scheduler = DPMSolverMultistepScheduler.from_config(scheduler.config)
+        elif scheduler_type == 'unipc':
+            scheduler = UniPCMultistepScheduler.from_config(scheduler.config)
         elif scheduler_type == "ddim":
             scheduler = scheduler
         else:
@@ -1229,15 +1230,15 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
         # 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}")
+            logger.debug(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")
+            logger.debug("Using checkpoint model's original VAE")
 
         if vae:
-            print("   | Using replacement diffusers VAE")
+            logger.debug("Using replacement diffusers VAE")
         else:  # convert the original or replacement VAE
             vae_config = create_vae_diffusers_config(
                 original_config, image_size=image_size
@@ -1296,7 +1297,7 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
             )
             safety_checker = StableDiffusionSafetyChecker.from_pretrained(
                 "CompVis/stable-diffusion-safety-checker",
-                cache_dir=global_cache_dir("hub"),
+                cache_dir=config.cache_dir,
             )
             feature_extractor = AutoFeatureExtractor.from_pretrained(
                 "CompVis/stable-diffusion-safety-checker", cache_dir=cache_dir

invokeai/backend/model_management/model_manager.py

@@ -18,25 +18,24 @@ import warnings
 from enum import Enum, auto
 from pathlib import Path
 from shutil import move, rmtree
-from typing import Any, Optional, Union, Callable
+from typing import Any, Optional, Union, Callable, types
 
 import safetensors
 import safetensors.torch
 import torch
 import transformers
+import invokeai.backend.util.logging as logger
 from diffusers import (
     AutoencoderKL,
     UNet2DConditionModel,
     SchedulerMixin,
     logging as dlogging,
-)    
+)
 from huggingface_hub import scan_cache_dir
 from omegaconf import OmegaConf
 from omegaconf.dictconfig import DictConfig
 from picklescan.scanner import scan_file_path
 
-from invokeai.backend.globals import Globals, global_cache_dir
-
 from transformers import (
     CLIPTextModel,
     CLIPTokenizer,
@@ -48,9 +47,9 @@ from diffusers.pipelines.stable_diffusion.safety_checker import (
 from ..stable_diffusion import (
     StableDiffusionGeneratorPipeline,
 )
+from invokeai.app.services.config import get_invokeai_config
 from ..util import CUDA_DEVICE, ask_user, download_with_resume
 
-
 class SDLegacyType(Enum):
     V1 = auto()
     V1_INPAINT = auto()
@@ -67,7 +66,7 @@ class SDModelComponent(Enum):
     scheduler="scheduler"
     safety_checker="safety_checker"
     feature_extractor="feature_extractor"
-    
+
 DEFAULT_MAX_MODELS = 2
 
 class ModelManager(object):
@@ -75,6 +74,8 @@ class ModelManager(object):
     Model manager handles loading, caching, importing, deleting, converting, and editing models.
     """
 
+    logger: types.ModuleType = logger
+
     def __init__(
         self,
         config: OmegaConf | Path,
@@ -83,6 +84,7 @@ class ModelManager(object):
         max_loaded_models=DEFAULT_MAX_MODELS,
         sequential_offload=False,
         embedding_path: Path = None,
+        logger: types.ModuleType = logger,
     ):
         """
         Initialize with the path to the models.yaml config file or
@@ -96,6 +98,7 @@ class ModelManager(object):
         if not isinstance(config, DictConfig):
             config = OmegaConf.load(config)
         self.config = config
+        self.globals = get_invokeai_config()
         self.precision = precision
         self.device = torch.device(device_type)
         self.max_loaded_models = max_loaded_models
@@ -104,6 +107,7 @@ class ModelManager(object):
         self.current_model = None
         self.sequential_offload = sequential_offload
         self.embedding_path = embedding_path
+        self.logger = logger
 
     def valid_model(self, model_name: str) -> bool:
         """
@@ -132,8 +136,8 @@ class ModelManager(object):
             )
 
         if not self.valid_model(model_name):
-            print(
-                f'** "{model_name}" is not a known model name. Please check your models.yaml file'
+            self.logger.error(
+                f'"{model_name}" is not a known model name. Please check your models.yaml file'
             )
             return self.current_model
 
@@ -144,7 +148,7 @@ class ModelManager(object):
 
         if model_name in self.models:
             requested_model = self.models[model_name]["model"]
-            print(f">> Retrieving model {model_name} from system RAM cache")
+            self.logger.info(f"Retrieving model {model_name} from system RAM cache")
             requested_model.ready()
             width = self.models[model_name]["width"]
             height = self.models[model_name]["height"]
@@ -177,7 +181,7 @@ class ModelManager(object):
         vae from the model currently in the GPU.
         """
         return self._get_sub_model(model_name, SDModelComponent.vae)
-                                   
+
     def get_model_tokenizer(self, model_name: str=None)->CLIPTokenizer:
         """Given a model name identified in models.yaml, load the model into
         GPU if necessary and return its assigned CLIPTokenizer. If no
@@ -185,12 +189,12 @@ class ModelManager(object):
         currently in the GPU.
         """
         return self._get_sub_model(model_name, SDModelComponent.tokenizer)
-                                   
+
     def get_model_unet(self, model_name: str=None)->UNet2DConditionModel:
         """Given a model name identified in models.yaml, load the model into
         GPU if necessary and return its assigned UNet2DConditionModel. If no model
         name is provided, return the UNet from the model
-        currently in the GPU.  
+        currently in the GPU.
         """
         return self._get_sub_model(model_name, SDModelComponent.unet)
 
@@ -217,7 +221,7 @@ class ModelManager(object):
         currently in the GPU.
         """
         return self._get_sub_model(model_name, SDModelComponent.scheduler)
-    
+
     def _get_sub_model(
             self,
             model_name: str=None,
@@ -287,7 +291,7 @@ class ModelManager(object):
         """
         # if we are converting legacy files automatically, then
         # there are no legacy ckpts!
-        if Globals.ckpt_convert:
+        if self.globals.ckpt_convert:
             return False
         info = self.model_info(model_name)
         if "weights" in info and info["weights"].endswith((".ckpt", ".safetensors")):
@@ -379,7 +383,7 @@ class ModelManager(object):
         """
         omega = self.config
         if model_name not in omega:
-            print(f"** Unknown model {model_name}")
+            self.logger.error(f"Unknown model {model_name}")
             return
         # save these for use in deletion later
         conf = omega[model_name]
@@ -392,13 +396,13 @@ class ModelManager(object):
             self.stack.remove(model_name)
         if delete_files:
             if weights:
-                print(f"** Deleting file {weights}")
+                self.logger.info(f"Deleting file {weights}")
                 Path(weights).unlink(missing_ok=True)
             elif path:
-                print(f"** Deleting directory {path}")
+                self.logger.info(f"Deleting directory {path}")
                 rmtree(path, ignore_errors=True)
             elif repo_id:
-                print(f"** Deleting the cached model directory for {repo_id}")
+                self.logger.info(f"Deleting the cached model directory for {repo_id}")
                 self._delete_model_from_cache(repo_id)
 
     def add_model(
@@ -439,7 +443,7 @@ class ModelManager(object):
     def _load_model(self, model_name: str):
         """Load and initialize the model from configuration variables passed at object creation time"""
         if model_name not in self.config:
-            print(
+            self.logger.error(
                 f'"{model_name}" is not a known model name. Please check your models.yaml file'
             )
             return
@@ -457,7 +461,7 @@ class ModelManager(object):
         model_format = mconfig.get("format", "ckpt")
         if model_format == "ckpt":
             weights = mconfig.weights
-            print(f">> Loading {model_name} from {weights}")
+            self.logger.info(f"Loading {model_name} from {weights}")
             model, width, height, model_hash = self._load_ckpt_model(
                 model_name, mconfig
             )
@@ -473,13 +477,15 @@ class ModelManager(object):
 
         # usage statistics
         toc = time.time()
-        print(">> Model loaded in", "%4.2fs" % (toc - tic))
+        self.logger.info("Model loaded in " + "%4.2fs" % (toc - tic))
         if self._has_cuda():
-            print(
-                ">> Max VRAM used to load the model:",
-                "%4.2fG" % (torch.cuda.max_memory_allocated() / 1e9),
-                "\n>> Current VRAM usage:"
-                "%4.2fG" % (torch.cuda.memory_allocated() / 1e9),
+            self.logger.info(
+                "Max VRAM used to load the model: "+
+                "%4.2fG" % (torch.cuda.max_memory_allocated() / 1e9)
+            )
+            self.logger.info(
+                "Current VRAM usage: "+
+                "%4.2fG" % (torch.cuda.memory_allocated() / 1e9)
             )
         return model, width, height, model_hash
 
@@ -487,21 +493,21 @@ class ModelManager(object):
         name_or_path = self.model_name_or_path(mconfig)
         using_fp16 = self.precision == "float16"
 
-        print(f">> Loading diffusers model from {name_or_path}")
+        self.logger.info(f"Loading diffusers model from {name_or_path}")
         if using_fp16:
-            print("   | Using faster float16 precision")
+            self.logger.debug("Using faster float16 precision")
         else:
-            print("   | Using more accurate float32 precision")
+            self.logger.debug("Using more accurate float32 precision")
 
         # TODO: scan weights maybe?
         pipeline_args: dict[str, Any] = dict(
-            safety_checker=None, local_files_only=not Globals.internet_available
+            safety_checker=None, local_files_only=not self.globals.internet_available
         )
         if "vae" in mconfig and mconfig["vae"] is not None:
             if vae := self._load_vae(mconfig["vae"]):
                 pipeline_args.update(vae=vae)
         if not isinstance(name_or_path, Path):
-            pipeline_args.update(cache_dir=global_cache_dir("hub"))
+            pipeline_args.update(cache_dir=self.globals.cache_dir)
         if using_fp16:
             pipeline_args.update(torch_dtype=torch.float16)
             fp_args_list = [{"revision": "fp16"}, {}]
@@ -523,8 +529,8 @@ class ModelManager(object):
                 if str(e).startswith("fp16 is not a valid"):
                     pass
                 else:
-                    print(
-                        f"** An unexpected error occurred while downloading the model: {e})"
+                    self.logger.error(
+                        f"An unexpected error occurred while downloading the model: {e})"
                     )
             if pipeline:
                 break
@@ -542,7 +548,7 @@ 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}")
+        self.logger.debug(f"Default image dimensions = {width} x {height}")
 
         return pipeline, width, height, model_hash
 
@@ -553,29 +559,24 @@ class ModelManager(object):
         width = mconfig.width
         height = mconfig.height
 
-        if not os.path.isabs(config):
-            config = os.path.join(Globals.root, config)
-        if not os.path.isabs(weights):
-            weights = os.path.normpath(os.path.join(Globals.root, weights))
+        root_dir = self.globals.root_dir
+        config = str(root_dir / config)
+        weights = str(root_dir / weights)
 
         # Convert to diffusers and return a diffusers pipeline
-        print(f">> Converting legacy checkpoint {model_name} into a diffusers model...")
+        self.logger.info(f"Converting legacy checkpoint {model_name} into a diffusers model...")
 
         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:
+        except Exception:
             pass
 
         vae_path = None
         if vae:
-            vae_path = (
-                vae
-                if os.path.isabs(vae)
-                else os.path.normpath(os.path.join(Globals.root, vae))
-            )
+            vae_path = str(root_dir / vae)
         if self._has_cuda():
             torch.cuda.empty_cache()
         pipeline = load_pipeline_from_original_stable_diffusion_ckpt(
@@ -607,9 +608,7 @@ class ModelManager(object):
             )
 
         if "path" in mconfig and mconfig["path"] is not None:
-            path = Path(mconfig["path"])
-            if not path.is_absolute():
-                path = Path(Globals.root, path).resolve()
+            path = self.globals.root_dir / Path(mconfig["path"])
             return path
         elif "repo_id" in mconfig:
             return mconfig["repo_id"]
@@ -624,7 +623,7 @@ class ModelManager(object):
         if model_name not in self.models:
             return
 
-        print(f">> Offloading {model_name} to CPU")
+        self.logger.info(f"Offloading {model_name} to CPU")
         model = self.models[model_name]["model"]
         model.offload_all()
         self.current_model = None
@@ -640,30 +639,26 @@ class ModelManager(object):
         and option to exit if an infected file is identified.
         """
         # scan model
-        print(f"   | Scanning Model: {model_name}")
+        self.logger.debug(f"Scanning Model: {model_name}")
         scan_result = scan_file_path(checkpoint)
         if scan_result.infected_files != 0:
             if scan_result.infected_files == 1:
-                print(f"\n### Issues Found In Model: {scan_result.issues_count}")
-                print(
-                    "### WARNING: The model you are trying to load seems to be infected."
-                )
-                print("### For your safety, InvokeAI will not load this model.")
-                print("### Please use checkpoints from trusted sources.")
-                print("### Exiting InvokeAI")
+                self.logger.critical(f"Issues Found In Model: {scan_result.issues_count}")
+                self.logger.critical("The model you are trying to load seems to be infected.")
+                self.logger.critical("For your safety, InvokeAI will not load this model.")
+                self.logger.critical("Please use checkpoints from trusted sources.")
+                self.logger.critical("Exiting InvokeAI")
                 sys.exit()
             else:
-                print(
-                    "\n### WARNING: InvokeAI was unable to scan the model you are using."
-                )
+                self.logger.warning("InvokeAI was unable to scan the model you are using.")
                 model_safe_check_fail = ask_user(
                     "Do you want to to continue loading the model?", ["y", "n"]
                 )
                 if model_safe_check_fail.lower() != "y":
-                    print("### Exiting InvokeAI")
+                    self.logger.critical("Exiting InvokeAI")
                     sys.exit()
         else:
-            print("   | Model scanned ok")
+            self.logger.debug("Model scanned ok")
 
     def import_diffuser_model(
         self,
@@ -780,26 +775,24 @@ class ModelManager(object):
         model_path: Path = None
         thing = path_url_or_repo  # to save typing
 
-        print(f">> Probing {thing} for import")
+        self.logger.info(f"Probing {thing} for import")
 
         if thing.startswith(("http:", "https:", "ftp:")):
-            print(f"   | {thing} appears to be a URL")
+            self.logger.info(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
 
         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"
-                )
+                self.logger.debug(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")
+                self.logger.debug(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")
+            self.logger.debug(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"),
@@ -810,34 +803,30 @@ class ModelManager(object):
 
         elif Path(thing).is_dir():
             if (Path(thing) / "model_index.json").exists():
-                print(f"   | {thing} appears to be a diffusers model.")
+                self.logger.debug(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"
-                )
+                self.logger.debug(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
                     ):
-                        print(f" >> {model_name} successfully imported")
+                        self.logger.info(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")
+            self.logger.debug(f"{thing} appears to be a HuggingFace diffusers repo_id")
             model_name = self.import_diffuser_model(
                 thing, commit_to_conf=commit_to_conf
             )
             pipeline, _, _, _ = self._load_diffusers_model(self.config[model_name])
             return model_name
         else:
-            print(
-                f"** {thing}: Unknown thing. Please provide a URL, file path, directory or HuggingFace repo_id"
-            )
+            self.logger.warning(f"{thing}: Unknown thing. Please provide a URL, file path, directory or HuggingFace repo_id")
 
         # Model_path is set in the event of a legacy checkpoint file.
         # If not set, we're all done
@@ -845,7 +834,7 @@ class ModelManager(object):
             return
 
         if model_path.stem in self.config:  # already imported
-            print("   | Already imported. Skipping")
+            self.logger.debug("Already imported. Skipping")
             return model_path.stem
 
         # another round of heuristics to guess the correct config file.
@@ -861,39 +850,30 @@ class ModelManager(object):
             # 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}")
+                self.logger.debug(f"Using config file {model_config_file.name}")
 
             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"
-                    )
+                    self.logger.debug("SD-v1 model detected")
+                    model_config_file = self.globals.legacy_conf_path / "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",
-                    )
+                    self.logger.debug("SD-v1 inpainting model detected")
+                    model_config_file = self.globals.legacy_conf_path / "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"
-                    )
+                    self.logger.debug("SD-v2-v model detected")
+                    model_config_file = self.globals.legacy_conf_path / "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"
-                    )
+                    self.logger.debug("SD-v2-e model detected")
+                    model_config_file = self.globals.legacy_conf_path / "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."
+                    self.logger.warning(
+                        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."
+                    self.logger.warning(
+                        f"{thing} is a legacy checkpoint file but not a known Stable Diffusion model. Please provide configuration file path."
                     )
                     return
 
@@ -909,12 +889,10 @@ class ModelManager(object):
         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}")
+                self.logger.debug(f"Using VAE file {vae_path.name}")
         vae = None if vae_path else dict(repo_id="stabilityai/sd-vae-ft-mse")
 
-        diffuser_path = Path(
-            Globals.root, "models", Globals.converted_ckpts_dir, model_path.stem
-        )
+        diffuser_path = self.globals.root_dir / "models/converted_ckpts" / model_path.stem
         model_name = self.convert_and_import(
             model_path,
             diffusers_path=diffuser_path,
@@ -955,14 +933,14 @@ class ModelManager(object):
         from . import convert_ckpt_to_diffusers
 
         if diffusers_path.exists():
-            print(
-                f"ERROR: The path {str(diffusers_path)} already exists. Please move or remove it and try again."
+            self.logger.error(
+                f"The path {str(diffusers_path)} already exists. Please move or remove it and try again."
             )
             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)")
+        self.logger.debug(f"Converting {model_name} to diffusers (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
@@ -979,10 +957,10 @@ class ModelManager(object):
                 vae_path=vae_path,
                 scan_needed=scan_needed,
             )
-            print(
-                f"   | Success. Converted model is now located at {str(diffusers_path)}"
+            self.logger.debug(
+                f"Success. Converted model is now located at {str(diffusers_path)}"
             )
-            print(f"   | Writing new config file entry for {model_name}")
+            self.logger.debug(f"Writing new config file entry for {model_name}")
             new_config = dict(
                 path=str(diffusers_path),
                 description=model_description,
@@ -993,17 +971,17 @@ class ModelManager(object):
             self.add_model(model_name, new_config, True)
             if commit_to_conf:
                 self.commit(commit_to_conf)
-            print("   | Conversion succeeded")
+            self.logger.debug("Conversion succeeded")
         except Exception as e:
-            print(f"** Conversion failed: {str(e)}")
-            print(
-                "** If you are trying to convert an inpainting or 2.X model, please indicate the correct config file (e.g. v1-inpainting-inference.yaml)"
+            self.logger.warning(f"Conversion failed: {str(e)}")
+            self.logger.warning(
+                "If you are trying to convert an inpainting or 2.X model, please indicate the correct config file (e.g. v1-inpainting-inference.yaml)"
             )
 
         return model_name
 
     def search_models(self, search_folder):
-        print(f">> Finding Models In: {search_folder}")
+        self.logger.info(f"Finding Models In: {search_folder}")
         models_folder_ckpt = Path(search_folder).glob("**/*.ckpt")
         models_folder_safetensors = Path(search_folder).glob("**/*.safetensors")
 
@@ -1027,8 +1005,8 @@ class ModelManager(object):
         num_loaded_models = len(self.models)
         if num_loaded_models >= self.max_loaded_models:
             least_recent_model = self._pop_oldest_model()
-            print(
-                f">> Cache limit (max={self.max_loaded_models}) reached. Purging {least_recent_model}"
+            self.logger.info(
+                f"Cache limit (max={self.max_loaded_models}) reached. Purging {least_recent_model}"
             )
             if least_recent_model is not None:
                 del self.models[least_recent_model]
@@ -1036,8 +1014,8 @@ class ModelManager(object):
 
     def print_vram_usage(self) -> None:
         if self._has_cuda:
-            print(
-                ">> Current VRAM usage: ",
+            self.logger.info(
+                "Current VRAM usage:"+
                 "%4.2fG" % (torch.cuda.memory_allocated() / 1e9),
             )
 
@@ -1047,9 +1025,7 @@ class ModelManager(object):
         """
         yaml_str = OmegaConf.to_yaml(self.config)
         if not os.path.isabs(config_file_path):
-            config_file_path = os.path.normpath(
-                os.path.join(Globals.root, config_file_path)
-            )
+            config_file_path = self.globals.model_conf_path
         tmpfile = os.path.join(os.path.dirname(config_file_path), "new_config.tmp")
         with open(tmpfile, "w", encoding="utf-8") as outfile:
             outfile.write(self.preamble())
@@ -1081,7 +1057,8 @@ class ModelManager(object):
         """
         # Three transformer models to check: bert, clip and safety checker, and
         # the diffusers as well
-        models_dir = Path(Globals.root, "models")
+        config = get_invokeai_config()
+        models_dir = config.root_dir / "models"
         legacy_locations = [
             Path(
                 models_dir,
@@ -1093,8 +1070,8 @@ class ModelManager(object):
                 "openai/clip-vit-large-patch14/models--openai--clip-vit-large-patch14",
             ),
         ]
-        legacy_locations.extend(list(global_cache_dir("diffusers").glob("*")))
-
+        legacy_cache_dir = config.cache_dir / "../diffusers"
+        legacy_locations.extend(list(legacy_cache_dir.glob("*")))
         legacy_layout = False
         for model in legacy_locations:
             legacy_layout = legacy_layout or model.exists()
@@ -1116,7 +1093,7 @@ class ModelManager(object):
 
         # transformer files get moved into the hub directory
         if cls._is_huggingface_hub_directory_present():
-            hub = global_cache_dir("hub")
+            hub = config.cache_dir
         else:
             hub = models_dir / "hub"
 
@@ -1126,10 +1103,10 @@ class ModelManager(object):
             dest = hub / model.stem
             if dest.exists() and not source.exists():
                 continue
-            print(f"** {source} => {dest}")
+            cls.logger.info(f"{source} => {dest}")
             if source.exists():
                 if dest.is_symlink():
-                    print(f"** Found symlink at {dest.name}. Not migrating.")
+                    logger.warning(f"Found symlink at {dest.name}. Not migrating.")
                 elif dest.exists():
                     if source.is_dir():
                         rmtree(source)
@@ -1146,7 +1123,7 @@ class ModelManager(object):
         ]
         for d in empty:
             os.rmdir(d)
-        print("** Migration is done. Continuing...")
+        cls.logger.info("Migration is done. Continuing...")
 
     def _resolve_path(
         self, source: Union[str, Path], dest_directory: str
@@ -1155,13 +1132,12 @@ class ModelManager(object):
         if str(source).startswith(("http:", "https:", "ftp:")):
             dest_directory = Path(dest_directory)
             if not dest_directory.is_absolute():
-                dest_directory = Globals.root / dest_directory
+                dest_directory = self.globals.root_dir / dest_directory
             dest_directory.mkdir(parents=True, exist_ok=True)
             resolved_path = download_with_resume(str(source), dest_directory)
         else:
-            if not os.path.isabs(source):
-                source = os.path.join(Globals.root, source)
-            resolved_path = Path(source)
+            source = self.globals.root_dir / source
+            resolved_path = source
         return resolved_path
 
     def _invalidate_cached_model(self, model_name: str) -> None:
@@ -1189,15 +1165,15 @@ class ModelManager(object):
 
     def _add_embeddings_to_model(self, model: StableDiffusionGeneratorPipeline):
         if self.embedding_path is not None:
-            print(f">> Loading embeddings from {self.embedding_path}")
+            self.logger.info(f"Loading embeddings from {self.embedding_path}")
             for root, _, files in os.walk(self.embedding_path):
                 for name in files:
                     ti_path = os.path.join(root, name)
                     model.textual_inversion_manager.load_textual_inversion(
                         ti_path, defer_injecting_tokens=True
                     )
-            print(
-                f'>> Textual inversion triggers: {", ".join(sorted(model.textual_inversion_manager.get_all_trigger_strings()))}'
+            self.logger.info(
+                f'Textual inversion triggers: {", ".join(sorted(model.textual_inversion_manager.get_all_trigger_strings()))}'
             )
 
     def _has_cuda(self) -> bool:
@@ -1211,7 +1187,7 @@ class ModelManager(object):
             path = name_or_path
         else:
             owner, repo = name_or_path.split("/")
-            path = Path(global_cache_dir("hub") / f"models--{owner}--{repo}")
+            path = self.globals.cache_dir / f"models--{owner}--{repo}"
         if not path.exists():
             return None
         hashpath = path / "checksum.sha256"
@@ -1219,7 +1195,7 @@ class ModelManager(object):
             with open(hashpath) as f:
                 hash = f.read()
             return hash
-        print("   | Calculating sha256 hash of model files")
+        self.logger.debug("Calculating sha256 hash of model files")
         tic = time.time()
         sha = hashlib.sha256()
         count = 0
@@ -1231,7 +1207,7 @@ class ModelManager(object):
                         sha.update(chunk)
         hash = sha.hexdigest()
         toc = time.time()
-        print(f"   | sha256 = {hash} ({count} files hashed in", "%4.2fs)" % (toc - tic))
+        self.logger.debug(f"sha256 = {hash} ({count} files hashed in {toc - tic:4.2f}s)")
         with open(hashpath, "w") as f:
             f.write(hash)
         return hash
@@ -1249,13 +1225,13 @@ class ModelManager(object):
                 hash = f.read()
             return hash
 
-        print("   | Calculating sha256 hash of weights file")
+        self.logger.debug("Calculating sha256 hash of weights file")
         tic = time.time()
         sha = hashlib.sha256()
         sha.update(data)
         hash = sha.hexdigest()
         toc = time.time()
-        print(f">> sha256 = {hash}", "(%4.2fs)" % (toc - tic))
+        self.logger.debug(f"sha256 = {hash} "+"(%4.2fs)" % (toc - tic))
 
         with open(hashpath, "w") as f:
             f.write(hash)
@@ -1272,16 +1248,16 @@ class ModelManager(object):
         using_fp16 = self.precision == "float16"
 
         vae_args.update(
-            cache_dir=global_cache_dir("hub"),
-            local_files_only=not Globals.internet_available,
+            cache_dir=self.globals.cache_dir,
+            local_files_only=not self.globals.internet_available,
         )
 
-        print(f"   | Loading diffusers VAE from {name_or_path}")
+        self.logger.debug(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")
+            self.logger.debug("Using more accurate float32 precision")
             fp_args_list = [{}]
 
         vae = None
@@ -1305,13 +1281,13 @@ class ModelManager(object):
                 break
 
         if not vae and deferred_error:
-            print(f"** Could not load VAE {name_or_path}: {str(deferred_error)}")
+            self.logger.warning(f"Could not load VAE {name_or_path}: {str(deferred_error)}")
 
         return vae
 
-    @staticmethod
-    def _delete_model_from_cache(repo_id):
-        cache_info = scan_cache_dir(global_cache_dir("hub"))
+    @classmethod
+    def _delete_model_from_cache(cls,repo_id):
+        cache_info = scan_cache_dir(get_invokeai_config().cache_dir)
 
         # I'm sure there is a way to do this with comprehensions
         # but the code quickly became incomprehensible!
@@ -1321,16 +1297,17 @@ class ModelManager(object):
                 for revision in repo.revisions:
                     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}"
+        cls.logger.warning(
+            f"Deletion of this model is expected to free {strategy.expected_freed_size_str}"
         )
         strategy.execute()
 
     @staticmethod
     def _abs_path(path: str | Path) -> Path:
+        globals = get_invokeai_config()
         if path is None or Path(path).is_absolute():
             return path
-        return Path(Globals.root, path).resolve()
+        return Path(globals.root_dir, path).resolve()
 
     @staticmethod
     def _is_huggingface_hub_directory_present() -> bool:

invokeai/backend/prompting/conditioning.py

@@ -16,66 +16,59 @@ from compel.prompt_parser import (
     FlattenedPrompt,
     Fragment,
     PromptParser,
+    Conjunction,
 )
 
-from invokeai.backend.globals import Globals
+import invokeai.backend.util.logging as logger
 
+from invokeai.app.services.config import get_invokeai_config
 from ..stable_diffusion import InvokeAIDiffuserComponent
 from ..util import torch_dtype
 
-
-def get_uc_and_c_and_ec(
-    prompt_string, model, log_tokens=False, skip_normalize_legacy_blend=False
-):
+def get_uc_and_c_and_ec(prompt_string,
+                        model: InvokeAIDiffuserComponent,
+                        log_tokens=False, skip_normalize_legacy_blend=False):
     # lazy-load any deferred textual inversions.
     # this might take a couple of seconds the first time a textual inversion is used.
-    model.textual_inversion_manager.create_deferred_token_ids_for_any_trigger_terms(
-        prompt_string
-    )
+    model.textual_inversion_manager.create_deferred_token_ids_for_any_trigger_terms(prompt_string)
 
-    tokenizer = model.tokenizer
-    compel = Compel(
-        tokenizer=tokenizer,
-        text_encoder=model.text_encoder,
-        textual_inversion_manager=model.textual_inversion_manager,
-        dtype_for_device_getter=torch_dtype,
-        truncate_long_prompts=False
-    )
+    compel = Compel(tokenizer=model.tokenizer,
+                    text_encoder=model.text_encoder,
+                    textual_inversion_manager=model.textual_inversion_manager,
+                    dtype_for_device_getter=torch_dtype,
+                    truncate_long_prompts=False,
+                    )
+    
+    config = get_invokeai_config()
 
     # get rid of any newline characters
     prompt_string = prompt_string.replace("\n", " ")
-    (
-        positive_prompt_string,
-        negative_prompt_string,
-    ) = split_prompt_to_positive_and_negative(prompt_string)
-    legacy_blend = try_parse_legacy_blend(
-        positive_prompt_string, skip_normalize_legacy_blend
-    )
-    positive_prompt: Union[FlattenedPrompt, Blend]
-    if legacy_blend is not None:
-        positive_prompt = legacy_blend
-    else:
-        positive_prompt = Compel.parse_prompt_string(positive_prompt_string)
-    negative_prompt: Union[FlattenedPrompt, Blend] = Compel.parse_prompt_string(
-        negative_prompt_string
-    )
+    positive_prompt_string, negative_prompt_string = split_prompt_to_positive_and_negative(prompt_string)
 
-    if log_tokens or getattr(Globals, "log_tokenization", False):
-        log_tokenization(positive_prompt, negative_prompt, tokenizer=tokenizer)
+    legacy_blend = try_parse_legacy_blend(positive_prompt_string, skip_normalize_legacy_blend)
+    positive_conjunction: Conjunction
+    if legacy_blend is not None:
+        positive_conjunction = legacy_blend
+    else:
+        positive_conjunction = Compel.parse_prompt_string(positive_prompt_string)
+    positive_prompt = positive_conjunction.prompts[0]
+
+    negative_conjunction = Compel.parse_prompt_string(negative_prompt_string)
+    negative_prompt: FlattenedPrompt | Blend = negative_conjunction.prompts[0]
+
+    tokens_count = get_max_token_count(model.tokenizer, positive_prompt)
+    if log_tokens or config.log_tokenization:
+        log_tokenization(positive_prompt, negative_prompt, tokenizer=model.tokenizer)
 
     c, options = compel.build_conditioning_tensor_for_prompt_object(positive_prompt)
     uc, _ = compel.build_conditioning_tensor_for_prompt_object(negative_prompt)
     [c, uc] = compel.pad_conditioning_tensors_to_same_length([c, uc])
 
-    tokens_count = get_max_token_count(tokenizer, positive_prompt)
-
-    ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
-        tokens_count_including_eos_bos=tokens_count,
-        cross_attention_control_args=options.get("cross_attention_control", None),
-    )
+    ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(tokens_count_including_eos_bos=tokens_count,
+                                                         cross_attention_control_args=options.get(
+                                                             'cross_attention_control', None))
     return uc, c, ec
 
-
 def get_prompt_structure(
     prompt_string, skip_normalize_legacy_blend: bool = False
 ) -> (Union[FlattenedPrompt, Blend], FlattenedPrompt):
@@ -86,18 +79,17 @@ def get_prompt_structure(
     legacy_blend = try_parse_legacy_blend(
         positive_prompt_string, skip_normalize_legacy_blend
     )
-    positive_prompt: Union[FlattenedPrompt, Blend]
+    positive_prompt: Conjunction
     if legacy_blend is not None:
-        positive_prompt = legacy_blend
+        positive_conjunction = legacy_blend
     else:
-        positive_prompt = Compel.parse_prompt_string(positive_prompt_string)
-    negative_prompt: Union[FlattenedPrompt, Blend] = Compel.parse_prompt_string(
-        negative_prompt_string
-    )
+        positive_conjunction = Compel.parse_prompt_string(positive_prompt_string)
+    positive_prompt = positive_conjunction.prompts[0]
+    negative_conjunction = Compel.parse_prompt_string(negative_prompt_string)
+    negative_prompt: FlattenedPrompt|Blend = negative_conjunction.prompts[0]
 
     return positive_prompt, negative_prompt
 
-
 def get_max_token_count(
     tokenizer, prompt: Union[FlattenedPrompt, Blend], truncate_if_too_long=False
 ) -> int:
@@ -162,8 +154,8 @@ def log_tokenization(
     negative_prompt: Union[Blend, FlattenedPrompt],
     tokenizer,
 ):
-    print(f"\n>> [TOKENLOG] Parsed Prompt: {positive_prompt}")
-    print(f"\n>> [TOKENLOG] Parsed Negative Prompt: {negative_prompt}")
+    logger.info(f"[TOKENLOG] Parsed Prompt: {positive_prompt}")
+    logger.info(f"[TOKENLOG] Parsed Negative Prompt: {negative_prompt}")
 
     log_tokenization_for_prompt_object(positive_prompt, tokenizer)
     log_tokenization_for_prompt_object(
@@ -237,29 +229,28 @@ def log_tokenization_for_text(text, tokenizer, display_label=None, truncate_if_t
             usedTokens += 1
 
     if usedTokens > 0:
-        print(f'\n>> [TOKENLOG] Tokens {display_label or ""} ({usedTokens}):')
-        print(f"{tokenized}\x1b[0m")
+        logger.info(f'[TOKENLOG] Tokens {display_label or ""} ({usedTokens}):')
+        logger.debug(f"{tokenized}\x1b[0m")
 
     if discarded != "":
-        print(f"\n>> [TOKENLOG] Tokens Discarded ({totalTokens - usedTokens}):")
-        print(f"{discarded}\x1b[0m")
+        logger.info(f"[TOKENLOG] Tokens Discarded ({totalTokens - usedTokens}):")
+        logger.debug(f"{discarded}\x1b[0m")
 
-
-def try_parse_legacy_blend(text: str, skip_normalize: bool = False) -> Optional[Blend]:
+def try_parse_legacy_blend(text: str, skip_normalize: bool = False) -> Optional[Conjunction]:
     weighted_subprompts = split_weighted_subprompts(text, skip_normalize=skip_normalize)
     if len(weighted_subprompts) <= 1:
         return None
     strings = [x[0] for x in weighted_subprompts]
-    weights = [x[1] for x in weighted_subprompts]
 
     pp = PromptParser()
     parsed_conjunctions = [pp.parse_conjunction(x) for x in strings]
-    flattened_prompts = [x.prompts[0] for x in parsed_conjunctions]
-
-    return Blend(
-        prompts=flattened_prompts, weights=weights, normalize_weights=not skip_normalize
-    )
-
+    flattened_prompts = []
+    weights = []
+    for i, x in enumerate(parsed_conjunctions):
+        if len(x.prompts)>0:
+            flattened_prompts.append(x.prompts[0])
+            weights.append(weighted_subprompts[i][1])
+    return Conjunction([Blend(prompts=flattened_prompts, weights=weights, normalize_weights=not skip_normalize)])
 
 def split_weighted_subprompts(text, skip_normalize=False) -> list:
     """
@@ -295,8 +286,8 @@ def split_weighted_subprompts(text, skip_normalize=False) -> list:
         return parsed_prompts
     weight_sum = sum(map(lambda x: x[1], parsed_prompts))
     if weight_sum == 0:
-        print(
-            "* Warning: Subprompt weights add up to zero. Discarding and using even weights instead."
+        logger.warning(
+            "Subprompt weights add up to zero. Discarding and using even weights instead."
         )
         equal_weight = 1 / max(len(parsed_prompts), 1)
         return [(x[0], equal_weight) for x in parsed_prompts]

invokeai/backend/restoration/base.py

@@ -1,3 +1,5 @@
+import invokeai.backend.util.logging as logger
+
 class Restoration:
     def __init__(self) -> None:
         pass
@@ -8,17 +10,17 @@ class Restoration:
         # Load GFPGAN
         gfpgan = self.load_gfpgan(gfpgan_model_path)
         if gfpgan.gfpgan_model_exists:
-            print(">> GFPGAN Initialized")
+            logger.info("GFPGAN Initialized")
         else:
-            print(">> GFPGAN Disabled")
+            logger.info("GFPGAN Disabled")
             gfpgan = None
 
         # Load CodeFormer
         codeformer = self.load_codeformer()
         if codeformer.codeformer_model_exists:
-            print(">> CodeFormer Initialized")
+            logger.info("CodeFormer Initialized")
         else:
-            print(">> CodeFormer Disabled")
+            logger.info("CodeFormer Disabled")
             codeformer = None
 
         return gfpgan, codeformer
@@ -39,5 +41,5 @@ class Restoration:
         from .realesrgan import ESRGAN
 
         esrgan = ESRGAN(esrgan_bg_tile)
-        print(">> ESRGAN Initialized")
+        logger.info("ESRGAN Initialized")
         return esrgan

invokeai/backend/restoration/codeformer.py

@@ -5,7 +5,8 @@ import warnings
 import numpy as np
 import torch
 
-from ..globals import Globals
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 pretrained_model_url = (
     "https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth"
@@ -16,19 +17,19 @@ class CodeFormerRestoration:
     def __init__(
         self, codeformer_dir="models/codeformer", codeformer_model_path="codeformer.pth"
     ) -> None:
-        if not os.path.isabs(codeformer_dir):
-            codeformer_dir = os.path.join(Globals.root, codeformer_dir)
 
-        self.model_path = os.path.join(codeformer_dir, codeformer_model_path)
-        self.codeformer_model_exists = os.path.isfile(self.model_path)
+        self.globals = get_invokeai_config()
+        codeformer_dir = self.globals.root_dir / codeformer_dir
+        self.model_path = codeformer_dir / codeformer_model_path
+        self.codeformer_model_exists = self.model_path.exists()
 
         if not self.codeformer_model_exists:
-            print("## NOT FOUND: CodeFormer model not found at " + self.model_path)
+            logger.error("NOT FOUND: CodeFormer model not found at " + self.model_path)
         sys.path.append(os.path.abspath(codeformer_dir))
 
     def process(self, image, strength, device, seed=None, fidelity=0.75):
         if seed is not None:
-            print(f">> CodeFormer - Restoring Faces for image seed:{seed}")
+            logger.info(f"CodeFormer - Restoring Faces for image seed:{seed}")
         with warnings.catch_warnings():
             warnings.filterwarnings("ignore", category=DeprecationWarning)
             warnings.filterwarnings("ignore", category=UserWarning)
@@ -70,9 +71,7 @@ class CodeFormerRestoration:
                 upscale_factor=1,
                 use_parse=True,
                 device=device,
-                model_rootpath=os.path.join(
-                    Globals.root, "models", "gfpgan", "weights"
-                ),
+                model_rootpath = self.globals.root_dir / "gfpgan" / "weights"
             )
             face_helper.clean_all()
             face_helper.read_image(bgr_image_array)
@@ -97,7 +96,7 @@ class CodeFormerRestoration:
                     del output
                     torch.cuda.empty_cache()
                 except RuntimeError as error:
-                    print(f"\tFailed inference for CodeFormer: {error}.")
+                    logger.error(f"Failed inference for CodeFormer: {error}.")
                     restored_face = cropped_face
 
                 restored_face = restored_face.astype("uint8")

invokeai/backend/restoration/gfpgan.py

@@ -6,20 +6,19 @@ import numpy as np
 import torch
 from PIL import Image
 
-from invokeai.backend.globals import Globals
-
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 class GFPGAN:
     def __init__(self, gfpgan_model_path="models/gfpgan/GFPGANv1.4.pth") -> None:
+        self.globals = get_invokeai_config()
         if not os.path.isabs(gfpgan_model_path):
-            gfpgan_model_path = os.path.abspath(
-                os.path.join(Globals.root, gfpgan_model_path)
-            )
+            gfpgan_model_path = self.globals.root_dir / gfpgan_model_path
         self.model_path = gfpgan_model_path
         self.gfpgan_model_exists = os.path.isfile(self.model_path)
 
         if not self.gfpgan_model_exists:
-            print("## NOT FOUND: GFPGAN model not found at " + self.model_path)
+            logger.error("NOT FOUND: GFPGAN model not found at " + self.model_path)
             return None
 
     def model_exists(self):
@@ -27,13 +26,13 @@ class GFPGAN:
 
     def process(self, image, strength: float, seed: str = None):
         if seed is not None:
-            print(f">> GFPGAN - Restoring Faces for image seed:{seed}")
+            logger.info(f"GFPGAN - Restoring Faces for image seed:{seed}")
 
         with warnings.catch_warnings():
             warnings.filterwarnings("ignore", category=DeprecationWarning)
             warnings.filterwarnings("ignore", category=UserWarning)
             cwd = os.getcwd()
-            os.chdir(os.path.join(Globals.root, "models"))
+            os.chdir(self.globals.root_dir / 'models')
             try:
                 from gfpgan import GFPGANer
 
@@ -47,14 +46,14 @@ class GFPGAN:
             except Exception:
                 import traceback
 
-                print(">> Error loading GFPGAN:", file=sys.stderr)
+                logger.error("Error loading GFPGAN:", file=sys.stderr)
                 print(traceback.format_exc(), file=sys.stderr)
             os.chdir(cwd)
 
         if self.gfpgan is None:
-            print(f">> WARNING: GFPGAN not initialized.")
-            print(
-                f">> Download https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth to {self.model_path}"
+            logger.warning("WARNING: GFPGAN not initialized.")
+            logger.warning(
+                f"Download https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth to {self.model_path}"
             )
 
         image = image.convert("RGB")

invokeai/backend/restoration/outcrop.py

@@ -1,7 +1,7 @@
 import math
 
 from PIL import Image
-
+import invokeai.backend.util.logging as logger
 
 class Outcrop(object):
     def __init__(
@@ -82,7 +82,7 @@ class Outcrop(object):
             pixels = extents[direction]
             # round pixels up to the nearest 64
             pixels = math.ceil(pixels / 64) * 64
-            print(f">> extending image {direction}ward by {pixels} pixels")
+            logger.info(f"extending image {direction}ward by {pixels} pixels")
             image = self._rotate(image, direction)
             image = self._extend(image, pixels)
             image = self._rotate(image, direction, reverse=True)

invokeai/backend/restoration/realesrgan.py

@@ -1,4 +1,3 @@
-import os
 import warnings
 
 import numpy as np
@@ -6,18 +5,14 @@ import torch
 from PIL import Image
 from PIL.Image import Image as ImageType
 
-from invokeai.backend.globals import Globals
-
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
+config = get_invokeai_config()
 
 class ESRGAN:
     def __init__(self, bg_tile_size=400) -> None:
         self.bg_tile_size = bg_tile_size
 
-        if not torch.cuda.is_available():  # CPU or MPS on M1
-            use_half_precision = False
-        else:
-            use_half_precision = True
-
     def load_esrgan_bg_upsampler(self, denoise_str):
         if not torch.cuda.is_available():  # CPU or MPS on M1
             use_half_precision = False
@@ -35,12 +30,8 @@ class ESRGAN:
             upscale=4,
             act_type="prelu",
         )
-        model_path = os.path.join(
-            Globals.root, "models/realesrgan/realesr-general-x4v3.pth"
-        )
-        wdn_model_path = os.path.join(
-            Globals.root, "models/realesrgan/realesr-general-wdn-x4v3.pth"
-        )
+        model_path = config.root_dir / "models/realesrgan/realesr-general-x4v3.pth"
+        wdn_model_path = config.root_dir / "models/realesrgan/realesr-general-wdn-x4v3.pth"
         scale = 4
 
         bg_upsampler = RealESRGANer(
@@ -74,16 +65,16 @@ class ESRGAN:
                 import sys
                 import traceback
 
-                print(">> Error loading Real-ESRGAN:", file=sys.stderr)
+                logger.error("Error loading Real-ESRGAN:")
                 print(traceback.format_exc(), file=sys.stderr)
 
         if upsampler_scale == 0:
-            print(">> Real-ESRGAN: Invalid scaling option. Image not upscaled.")
+            logger.warning("Real-ESRGAN: Invalid scaling option. Image not upscaled.")
             return image
 
         if seed is not None:
-            print(
-                f">> Real-ESRGAN Upscaling seed:{seed}, scale:{upsampler_scale}x, tile:{self.bg_tile_size}, denoise:{denoise_str}"
+            logger.info(
+                f"Real-ESRGAN Upscaling seed:{seed}, scale:{upsampler_scale}x, tile:{self.bg_tile_size}, denoise:{denoise_str}"
             )
         # ESRGAN outputs images with partial transparency if given RGBA images; convert to RGB
         image = image.convert("RGB")

invokeai/backend/safety_checker.py

@@ -14,7 +14,8 @@ from PIL import Image, ImageFilter
 from transformers import AutoFeatureExtractor
 
 import invokeai.assets.web as web_assets
-from .globals import global_cache_dir
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 from .util import CPU_DEVICE
 
 class SafetyChecker(object):
@@ -25,10 +26,11 @@ class SafetyChecker(object):
         caution = Image.open(path)
         self.caution_img = caution.resize((caution.width // 2, caution.height // 2))
         self.device = device
-        
+        config = get_invokeai_config()
+
         try:
             safety_model_id = "CompVis/stable-diffusion-safety-checker"
-            safety_model_path = global_cache_dir("hub")
+            safety_model_path = config.cache_dir
             self.safety_checker = StableDiffusionSafetyChecker.from_pretrained(
                 safety_model_id,
                 local_files_only=True,
@@ -40,8 +42,8 @@ class SafetyChecker(object):
                 cache_dir=safety_model_path,
             )
         except Exception:
-            print(
-                "** An error was encountered while installing the safety checker:"
+            logger.error(
+                "An error was encountered while installing the safety checker:"
             )
             print(traceback.format_exc())
 
@@ -65,8 +67,8 @@ class SafetyChecker(object):
         )
         self.safety_checker.to(CPU_DEVICE) # offload
         if has_nsfw_concept[0]:
-            print(
-                "** An image with potential non-safe content has been detected. A blurred image will be returned. **"
+            logger.warning(
+                "An image with potential non-safe content has been detected. A blurred image will be returned."
             )
             return self.blur(image)
         else:

invokeai/backend/stable_diffusion/concepts_lib.py

@@ -17,15 +17,16 @@ from huggingface_hub import (
     hf_hub_url,
 )
 
-from invokeai.backend.globals import Globals
-
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 class HuggingFaceConceptsLibrary(object):
     def __init__(self, root=None):
         """
         Initialize the Concepts object. May optionally pass a root directory.
         """
-        self.root = root or Globals.root
+        self.config = get_invokeai_config()
+        self.root = root or self.config.root
         self.hf_api = HfApi()
         self.local_concepts = dict()
         self.concept_list = None
@@ -57,7 +58,7 @@ class HuggingFaceConceptsLibrary(object):
                 self.concept_list.extend(list(local_concepts_to_add))
                 return self.concept_list
             return self.concept_list
-        elif Globals.internet_available is True:
+        elif self.config.internet_available is True:
             try:
                 models = self.hf_api.list_models(
                     filter=ModelFilter(model_name="sd-concepts-library/")
@@ -66,11 +67,11 @@ class HuggingFaceConceptsLibrary(object):
                 # when init, add all in dir. when not init, add only concepts added between init and now
                 self.concept_list.extend(list(local_concepts_to_add))
             except Exception as e:
-                print(
-                    f" ** WARNING: Hugging Face textual inversion concepts libraries could not be loaded. The error was {str(e)}."
+                logger.warning(
+                    f"Hugging Face textual inversion concepts libraries could not be loaded. The error was {str(e)}."
                 )
-                print(
-                    " ** You may load .bin and .pt file(s) manually using the --embedding_directory argument."
+                logger.warning(
+                    "You may load .bin and .pt file(s) manually using the --embedding_directory argument."
                 )
             return self.concept_list
         else: 
@@ -83,7 +84,7 @@ class HuggingFaceConceptsLibrary(object):
         be downloaded.
         """
         if not concept_name in self.list_concepts():
-            print(
+            logger.warning(
                 f"{concept_name} is not a local embedding trigger, nor is it a HuggingFace concept. Generation will continue without the concept."
             )
             return None
@@ -221,7 +222,7 @@ class HuggingFaceConceptsLibrary(object):
             if chunk == 0:
                 bytes += total
 
-        print(f">> Downloading {repo_id}...", end="")
+        logger.info(f"Downloading {repo_id}...", end="")
         try:
             for file in (
                 "README.md",
@@ -235,22 +236,22 @@ class HuggingFaceConceptsLibrary(object):
                 )
         except ul_error.HTTPError as e:
             if e.code == 404:
-                print(
+                logger.warning(
                     f"Concept {concept_name} is not known to the Hugging Face library. Generation will continue without the concept."
                 )
             else:
-                print(
+                logger.warning(
                     f"Failed to download {concept_name}/{file} ({str(e)}. Generation will continue without the concept.)"
                 )
             os.rmdir(dest)
             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."
+            logger.error(
+                f"an error occurred while downloading {concept_name}: {str(e)}. This may reflect a network issue. Generation will continue without the concept."
             )
             os.rmdir(dest)
             return False
-        print("...{:.2f}Kb".format(bytes / 1024))
+        logger.info("...{:.2f}Kb".format(bytes / 1024))
         return succeeded
 
     def _concept_id(self, concept_name: str) -> str:

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -33,8 +33,7 @@ from torchvision.transforms.functional import resize as tv_resize
 from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
 from typing_extensions import ParamSpec
 
-from invokeai.backend.globals import Globals
-
+from invokeai.app.services.config import get_invokeai_config
 from ..util import CPU_DEVICE, normalize_device
 from .diffusion import (
     AttentionMapSaver,
@@ -44,7 +43,6 @@ from .diffusion import (
 from .offloading import FullyLoadedModelGroup, LazilyLoadedModelGroup, ModelGroup
 from .textual_inversion_manager import TextualInversionManager
 
-
 @dataclass
 class PipelineIntermediateState:
     run_id: str
@@ -348,10 +346,11 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         """
         if xformers is available, use it, otherwise use sliced attention.
         """
+        config = get_invokeai_config()
         if (
             torch.cuda.is_available()
             and is_xformers_available()
-            and not Globals.disable_xformers
+            and not config.disable_xformers
         ):
             self.enable_xformers_memory_efficient_attention()
         else:
@@ -445,8 +444,15 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
     @property
     def _submodels(self) -> Sequence[torch.nn.Module]:
         module_names, _, _ = self.extract_init_dict(dict(self.config))
-        values = [getattr(self, name) for name in module_names.keys()]
-        return [m for m in values if isinstance(m, torch.nn.Module)]
+        submodels = []
+        for name in module_names.keys():
+            if hasattr(self, name):
+                value = getattr(self, name)
+            else:
+                value = getattr(self.config, name)
+            if isinstance(value, torch.nn.Module):
+                submodels.append(value)
+        return submodels
 
     def image_from_embeddings(
         self,
@@ -502,10 +508,13 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         run_id=None,
         callback: Callable[[PipelineIntermediateState], None] = None,
     ) -> tuple[torch.Tensor, Optional[AttentionMapSaver]]:
+        if self.scheduler.config.get("cpu_only", False):
+            scheduler_device = torch.device('cpu')
+        else:
+            scheduler_device = self._model_group.device_for(self.unet)
+
         if timesteps is None:
-            self.scheduler.set_timesteps(
-                num_inference_steps, device=self._model_group.device_for(self.unet)
-            )
+            self.scheduler.set_timesteps(num_inference_steps, device=scheduler_device)
             timesteps = self.scheduler.timesteps
         infer_latents_from_embeddings = GeneratorToCallbackinator(
             self.generate_latents_from_embeddings, PipelineIntermediateState
@@ -538,13 +547,14 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             additional_guidance = []
         extra_conditioning_info = conditioning_data.extra
         with self.invokeai_diffuser.custom_attention_context(
-            extra_conditioning_info=extra_conditioning_info,
-            step_count=len(self.scheduler.timesteps),
+                self.invokeai_diffuser.model,
+                extra_conditioning_info=extra_conditioning_info,
+                step_count=len(self.scheduler.timesteps),
         ):
             yield PipelineIntermediateState(
                 run_id=run_id,
                 step=-1,
-                timestep=self.scheduler.num_train_timesteps,
+                timestep=self.scheduler.config.num_train_timesteps,
                 latents=latents,
             )
 
@@ -718,12 +728,8 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         noise: torch.Tensor,
         run_id=None,
         callback=None,
-    ) -> InvokeAIStableDiffusionPipelineOutput:
-        timesteps, _ = self.get_img2img_timesteps(
-            num_inference_steps,
-            strength,
-            device=self._model_group.device_for(self.unet),
-        )
+    ) -> InvokeAIStableDiffusionPipelineOutput:        
+        timesteps, _ = self.get_img2img_timesteps(num_inference_steps, strength)
         result_latents, result_attention_maps = self.latents_from_embeddings(
             latents=initial_latents if strength < 1.0 else torch.zeros_like(
                 initial_latents, device=initial_latents.device, dtype=initial_latents.dtype
@@ -749,13 +755,19 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             return self.check_for_safety(output, dtype=conditioning_data.dtype)
 
     def get_img2img_timesteps(
-        self, num_inference_steps: int, strength: float, device
+        self, num_inference_steps: int, strength: float, device=None
     ) -> (torch.Tensor, int):
         img2img_pipeline = StableDiffusionImg2ImgPipeline(**self.components)
         assert img2img_pipeline.scheduler is self.scheduler
-        img2img_pipeline.scheduler.set_timesteps(num_inference_steps, device=device)
+
+        if self.scheduler.config.get("cpu_only", False):
+            scheduler_device = torch.device('cpu')
+        else:
+            scheduler_device = self._model_group.device_for(self.unet)
+
+        img2img_pipeline.scheduler.set_timesteps(num_inference_steps, device=scheduler_device)
         timesteps, adjusted_steps = img2img_pipeline.get_timesteps(
-            num_inference_steps, strength, device=device
+            num_inference_steps, strength, device=scheduler_device
         )
         # Workaround for low strength resulting in zero timesteps.
         # TODO: submit upstream fix for zero-step img2img
@@ -789,9 +801,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         if init_image.dim() == 3:
             init_image = init_image.unsqueeze(0)
 
-        timesteps, _ = self.get_img2img_timesteps(
-            num_inference_steps, strength, device=device
-        )
+        timesteps, _ = self.get_img2img_timesteps(num_inference_steps, strength)
 
         # 6. Prepare latent variables
         # can't quite use upstream StableDiffusionImg2ImgPipeline.prepare_latents
@@ -915,7 +925,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
     @property
     def channels(self) -> int:
         """Compatible with DiffusionWrapper"""
-        return self.unet.in_channels
+        return self.unet.config.in_channels
 
     def decode_latents(self, latents):
         # Explicit call to get the vae loaded, since `decode` isn't the forward method.

invokeai/backend/stable_diffusion/diffusion/cross_attention_control.py

@@ -10,13 +10,13 @@ import diffusers
 import psutil
 import torch
 from compel.cross_attention_control import Arguments
-from diffusers.models.cross_attention import AttnProcessor
 from diffusers.models.unet_2d_condition import UNet2DConditionModel
+from diffusers.models.attention_processor import AttentionProcessor
 from torch import nn
 
+import invokeai.backend.util.logging as logger
 from ...util import torch_dtype
 
-
 class CrossAttentionType(enum.Enum):
     SELF = 1
     TOKENS = 2
@@ -188,7 +188,7 @@ class Context:
 
 class InvokeAICrossAttentionMixin:
     """
-    Enable InvokeAI-flavoured CrossAttention calculation, which does aggressive low-memory slicing and calls
+    Enable InvokeAI-flavoured Attention calculation, which does aggressive low-memory slicing and calls
     through both to an attention_slice_wrangler and a slicing_strategy_getter for custom attention map wrangling
     and dymamic slicing strategy selection.
     """
@@ -209,7 +209,7 @@ class InvokeAICrossAttentionMixin:
         Set custom attention calculator to be called when attention is calculated
         :param wrangler: Callback, with args (module, suggested_attention_slice, dim, offset, slice_size),
         which returns either the suggested_attention_slice or an adjusted equivalent.
-            `module` is the current CrossAttention module for which the callback is being invoked.
+            `module` is the current Attention module for which the callback is being invoked.
             `suggested_attention_slice` is the default-calculated attention slice
             `dim` is -1 if the attenion map has not been sliced, or 0 or 1 for dimension-0 or dimension-1 slicing.
                 If `dim` is >= 0, `offset` and `slice_size` specify the slice start and length.
@@ -345,16 +345,15 @@ class InvokeAICrossAttentionMixin:
 def restore_default_cross_attention(
     model,
     is_running_diffusers: bool,
-    restore_attention_processor: Optional[AttnProcessor] = None,
+    restore_attention_processor: Optional[AttentionProcessor] = None,
 ):
     if is_running_diffusers:
         unet = model
-        unet.set_attn_processor(restore_attention_processor or CrossAttnProcessor())
+        unet.set_attn_processor(restore_attention_processor or AttnProcessor())
     else:
         remove_attention_function(model)
 
-
-def override_cross_attention(model, context: Context, is_running_diffusers=False):
+def setup_cross_attention_control_attention_processors(unet: UNet2DConditionModel, context: Context):
     """
     Inject attention parameters and functions into the passed in model to enable cross attention editing.
 
@@ -373,47 +372,29 @@ def override_cross_attention(model, context: Context, is_running_diffusers=False
     indices = torch.arange(max_length, dtype=torch.long)
     for name, a0, a1, b0, b1 in context.arguments.edit_opcodes:
         if b0 < max_length:
-            if name == "equal":  # or (name == "replace" and a1 - a0 == b1 - b0):
+            if name == "equal":# or (name == "replace" and a1 - a0 == b1 - b0):
                 # these tokens have not been edited
                 indices[b0:b1] = indices_target[a0:a1]
                 mask[b0:b1] = 1
 
     context.cross_attention_mask = mask.to(device)
     context.cross_attention_index_map = indices.to(device)
-    if is_running_diffusers:
-        unet = model
-        old_attn_processors = unet.attn_processors
-        if torch.backends.mps.is_available():
-            # see note in StableDiffusionGeneratorPipeline.__init__ about borked slicing on MPS
-            unet.set_attn_processor(SwapCrossAttnProcessor())
-        else:
-            # try to re-use an existing slice size
-            default_slice_size = 4
-            slice_size = next(
-                (
-                    p.slice_size
-                    for p in old_attn_processors.values()
-                    if type(p) is SlicedAttnProcessor
-                ),
-                default_slice_size,
-            )
-            unet.set_attn_processor(SlicedSwapCrossAttnProcesser(slice_size=slice_size))
-        return old_attn_processors
+    old_attn_processors = unet.attn_processors
+    if torch.backends.mps.is_available():
+        # see note in StableDiffusionGeneratorPipeline.__init__ about borked slicing on MPS
+        unet.set_attn_processor(SwapCrossAttnProcessor())
     else:
-        context.register_cross_attention_modules(model)
-        inject_attention_function(model, context)
-        return None
-
+        # try to re-use an existing slice size
+        default_slice_size = 4
+        slice_size = next((p.slice_size for p in old_attn_processors.values() if type(p) is SlicedAttnProcessor), default_slice_size)
+        unet.set_attn_processor(SlicedSwapCrossAttnProcesser(slice_size=slice_size))
 
 def get_cross_attention_modules(
     model, which: CrossAttentionType
 ) -> list[tuple[str, InvokeAICrossAttentionMixin]]:
-    from ldm.modules.attention import CrossAttention  # avoid circular import
 
     cross_attention_class: type = (
         InvokeAIDiffusersCrossAttention
-        if isinstance(model, UNet2DConditionModel)
-        else CrossAttention
     )
     which_attn = "attn1" if which is CrossAttentionType.SELF else "attn2"
     attention_module_tuples = [
@@ -425,13 +406,13 @@ def get_cross_attention_modules(
     expected_count = 16
     if cross_attention_modules_in_model_count != expected_count:
         # non-fatal error but .swap() won't work.
-        print(
+        logger.error(
             f"Error! CrossAttentionControl found an unexpected number of {cross_attention_class} modules in the model "
             + f"(expected {expected_count}, found {cross_attention_modules_in_model_count}). Either monkey-patching failed "
-            + f"or some assumption has changed about the structure of the model itself. Please fix the monkey-patching, "
+            + "or some assumption has changed about the structure of the model itself. Please fix the monkey-patching, "
             + f"and/or update the {expected_count} above to an appropriate number, and/or find and inform someone who knows "
-            + f"what it means. This error is non-fatal, but it is likely that .swap() and attention map display will not "
-            + f"work properly until it is fixed."
+            + "what it means. This error is non-fatal, but it is likely that .swap() and attention map display will not "
+            + "work properly until it is fixed."
         )
     return attention_module_tuples
 
@@ -550,7 +531,7 @@ def get_mem_free_total(device):
 
 
 class InvokeAIDiffusersCrossAttention(
-    diffusers.models.attention.CrossAttention, InvokeAICrossAttentionMixin
+    diffusers.models.attention.Attention, InvokeAICrossAttentionMixin
 ):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -572,8 +553,8 @@ class InvokeAIDiffusersCrossAttention(
 """
 # base implementation
 
-class CrossAttnProcessor:
-    def __call__(self, attn: CrossAttention, hidden_states, encoder_hidden_states=None, attention_mask=None):
+class AttnProcessor:
+    def __call__(self, attn: Attention, hidden_states, encoder_hidden_states=None, attention_mask=None):
         batch_size, sequence_length, _ = hidden_states.shape
         attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length)
 
@@ -601,9 +582,9 @@ class CrossAttnProcessor:
 from dataclasses import dataclass, field
 
 import torch
-from diffusers.models.cross_attention import (
-    CrossAttention,
-    CrossAttnProcessor,
+from diffusers.models.attention_processor import (
+    Attention,
+    AttnProcessor,
     SlicedAttnProcessor,
 )
 
@@ -653,7 +634,7 @@ class SlicedSwapCrossAttnProcesser(SlicedAttnProcessor):
 
     def __call__(
         self,
-        attn: CrossAttention,
+        attn: Attention,
         hidden_states,
         encoder_hidden_states=None,
         attention_mask=None,

invokeai/backend/stable_diffusion/diffusion/shared_invokeai_diffusion.py

@@ -5,10 +5,12 @@ from typing import Any, Callable, Dict, Optional, Union
 
 import numpy as np
 import torch
-from diffusers.models.cross_attention import AttnProcessor
+from diffusers import UNet2DConditionModel
+from diffusers.models.attention_processor import AttentionProcessor
 from typing_extensions import TypeAlias
 
-from invokeai.backend.globals import Globals
+import invokeai.backend.util.logging as logger
+from invokeai.app.services.config import get_invokeai_config
 
 from .cross_attention_control import (
     Arguments,
@@ -16,8 +18,8 @@ from .cross_attention_control import (
     CrossAttentionType,
     SwapCrossAttnContext,
     get_cross_attention_modules,
-    override_cross_attention,
     restore_default_cross_attention,
+    setup_cross_attention_control_attention_processors,
 )
 from .cross_attention_map_saving import AttentionMapSaver
 
@@ -30,7 +32,6 @@ ModelForwardCallback: TypeAlias = Union[
     Callable[[torch.Tensor, torch.Tensor, torch.Tensor], torch.Tensor],
 ]
 
-
 @dataclass(frozen=True)
 class PostprocessingSettings:
     threshold: float
@@ -71,37 +72,49 @@ class InvokeAIDiffuserComponent:
         :param model: the unet model to pass through to cross attention control
         :param model_forward_callback: a lambda with arguments (x, sigma, conditioning_to_apply). will be called repeatedly. most likely, this should simply call model.forward(x, sigma, conditioning)
         """
+        config = get_invokeai_config()
         self.conditioning = None
         self.model = model
         self.is_running_diffusers = is_running_diffusers
         self.model_forward_callback = model_forward_callback
         self.cross_attention_control_context = None
-        self.sequential_guidance = Globals.sequential_guidance
+        self.sequential_guidance = config.sequential_guidance
 
+    @classmethod
     @contextmanager
     def custom_attention_context(
-        self, extra_conditioning_info: Optional[ExtraConditioningInfo], step_count: int
+        cls,
+        unet: UNet2DConditionModel, # note: also may futz with the text encoder depending on requested LoRAs
+        extra_conditioning_info: Optional[ExtraConditioningInfo],
+        step_count: int
     ):
-        do_swap = (
-            extra_conditioning_info is not None
-            and extra_conditioning_info.wants_cross_attention_control
-        )
-        old_attn_processor = None
-        if do_swap:
-            old_attn_processor = self.override_cross_attention(
-                extra_conditioning_info, step_count=step_count
-            )
+        old_attn_processors = None
+        if extra_conditioning_info and (
+            extra_conditioning_info.wants_cross_attention_control
+        ):
+            old_attn_processors = unet.attn_processors
+            # Load lora conditions into the model
+            if extra_conditioning_info.wants_cross_attention_control:
+                cross_attention_control_context = Context(
+                    arguments=extra_conditioning_info.cross_attention_control_args,
+                    step_count=step_count,
+                )
+                setup_cross_attention_control_attention_processors(
+                    unet,
+                    cross_attention_control_context,
+                )
+
         try:
             yield None
         finally:
-            if old_attn_processor is not None:
-                self.restore_default_cross_attention(old_attn_processor)
+            if old_attn_processors is not None:
+                unet.set_attn_processor(old_attn_processors)
             # TODO resuscitate attention map saving
             # self.remove_attention_map_saving()
 
     def override_cross_attention(
         self, conditioning: ExtraConditioningInfo, step_count: int
-    ) -> Dict[str, AttnProcessor]:
+    ) -> Dict[str, AttentionProcessor]:
         """
         setup cross attention .swap control. for diffusers this replaces the attention processor, so
         the previous attention processor is returned so that the caller can restore it later.
@@ -118,7 +131,7 @@ class InvokeAIDiffuserComponent:
         )
 
     def restore_default_cross_attention(
-        self, restore_attention_processor: Optional["AttnProcessor"] = None
+        self, restore_attention_processor: Optional["AttentionProcessor"] = None
     ):
         self.conditioning = None
         self.cross_attention_control_context = None
@@ -262,7 +275,7 @@ class InvokeAIDiffuserComponent:
             # TODO remove when compvis codepath support is dropped
             if step_index is None and sigma is None:
                 raise ValueError(
-                    f"Either step_index or sigma is required when doing cross attention control, but both are None."
+                    "Either step_index or sigma is required when doing cross attention control, but both are None."
                 )
             percent_through = self.estimate_percent_through(step_index, sigma)
         return percent_through
@@ -466,10 +479,14 @@ class InvokeAIDiffuserComponent:
             outside = torch.count_nonzero(
                 (latents < -current_threshold) | (latents > current_threshold)
             )
-            print(
-                f"\nThreshold: %={percent_through} threshold={current_threshold:.3f} (of {threshold:.3f})\n"
-                f"  | min, mean, max = {minval:.3f}, {mean:.3f}, {maxval:.3f}\tstd={std}\n"
-                f"  | {outside / latents.numel() * 100:.2f}% values outside threshold"
+            logger.info(
+                f"Threshold: %={percent_through} threshold={current_threshold:.3f} (of {threshold:.3f})"
+                )
+            logger.debug(
+                f"min, mean, max = {minval:.3f}, {mean:.3f}, {maxval:.3f}\tstd={std}"
+            )
+            logger.debug(   
+                f"{outside / latents.numel() * 100:.2f}% values outside threshold"
             )
 
         if maxval < current_threshold and minval > -current_threshold:
@@ -496,9 +513,11 @@ class InvokeAIDiffuserComponent:
             )
 
         if self.debug_thresholding:
-            print(
-                f"  | min,     , max = {minval:.3f},        , {maxval:.3f}\t(scaled by {scale})\n"
-                f"  | {num_altered / latents.numel() * 100:.2f}% values altered"
+            logger.debug(
+                f"min,     , max = {minval:.3f},        , {maxval:.3f}\t(scaled by {scale})"
+            )
+            logger.debug(
+                f"{num_altered / latents.numel() * 100:.2f}% values altered"
             )
 
         return latents
@@ -599,7 +618,6 @@ class InvokeAIDiffuserComponent:
         )
 
         # below is fugly omg
-        num_actual_conditionings = len(c_or_weighted_c_list)
         conditionings = [uc] + [c for c, weight in weighted_cond_list]
         weights = [1] + [weight for c, weight in weighted_cond_list]
         chunk_count = ceil(len(conditionings) / 2)

invokeai/backend/stable_diffusion/image_degradation/utils_image.py

@@ -10,7 +10,7 @@ from torchvision.utils import make_grid
 
 # import matplotlib.pyplot as plt   # TODO: check with Dominik, also bsrgan.py vs bsrgan_light.py
 
-
+import invokeai.backend.util.logging as logger
 os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
 
 
@@ -191,7 +191,7 @@ def mkdirs(paths):
 def mkdir_and_rename(path):
     if os.path.exists(path):
         new_name = path + "_archived_" + get_timestamp()
-        print("Path already exists. Rename it to [{:s}]".format(new_name))
+        logger.error("Path already exists. Rename it to [{:s}]".format(new_name))
         os.replace(path, new_name)
     os.makedirs(path)
 

invokeai/backend/stable_diffusion/schedulers/__init__.py

@@ -0,0 +1 @@
+from .schedulers import SCHEDULER_MAP

invokeai/backend/stable_diffusion/schedulers/schedulers.py

@@ -0,0 +1,23 @@
+from diffusers import DDIMScheduler, DPMSolverMultistepScheduler, KDPM2DiscreteScheduler, \
+    KDPM2AncestralDiscreteScheduler, EulerDiscreteScheduler, EulerAncestralDiscreteScheduler, \
+    HeunDiscreteScheduler, LMSDiscreteScheduler, PNDMScheduler, UniPCMultistepScheduler, \
+    DPMSolverSinglestepScheduler, DEISMultistepScheduler, DDPMScheduler
+
+SCHEDULER_MAP = dict(
+    ddim=(DDIMScheduler, dict()),
+    ddpm=(DDPMScheduler, dict()),
+    deis=(DEISMultistepScheduler, dict()),
+    lms=(LMSDiscreteScheduler, dict()),
+    pndm=(PNDMScheduler, dict()),
+    heun=(HeunDiscreteScheduler, dict(use_karras_sigmas=False)),
+    heun_k=(HeunDiscreteScheduler, dict(use_karras_sigmas=True)),
+    euler=(EulerDiscreteScheduler, dict(use_karras_sigmas=False)),
+    euler_k=(EulerDiscreteScheduler, dict(use_karras_sigmas=True)),
+    euler_a=(EulerAncestralDiscreteScheduler, dict()),
+    kdpm_2=(KDPM2DiscreteScheduler, dict()),
+    kdpm_2_a=(KDPM2AncestralDiscreteScheduler, dict()),
+    dpmpp_2s=(DPMSolverSinglestepScheduler, dict()),
+    dpmpp_2m=(DPMSolverMultistepScheduler, dict(use_karras_sigmas=False)),
+    dpmpp_2m_k=(DPMSolverMultistepScheduler, dict(use_karras_sigmas=True)),
+    unipc=(UniPCMultistepScheduler, dict(cpu_only=True))
+)

invokeai/backend/stable_diffusion/textual_inversion_manager.py

@@ -10,6 +10,7 @@ from compel.embeddings_provider import BaseTextualInversionManager
 from picklescan.scanner import scan_file_path
 from transformers import CLIPTextModel, CLIPTokenizer
 
+import invokeai.backend.util.logging as logger
 from .concepts_lib import HuggingFaceConceptsLibrary
 
 @dataclass
@@ -59,12 +60,12 @@ class TextualInversionManager(BaseTextualInversionManager):
                 or self.has_textual_inversion_for_trigger_string(concept_name)
                 or self.has_textual_inversion_for_trigger_string(f"<{concept_name}>")
             ):  # in case a token with literal angle brackets encountered
-                print(f">> Loaded local embedding for trigger {concept_name}")
+                logger.info(f"Loaded local embedding for trigger {concept_name}")
                 continue
             bin_file = self.hf_concepts_library.get_concept_model_path(concept_name)
             if not bin_file:
                 continue
-            print(f">> Loaded remote embedding for trigger {concept_name}")
+            logger.info(f"Loaded remote embedding for trigger {concept_name}")
             self.load_textual_inversion(bin_file)
             self.hf_concepts_library.concepts_loaded[concept_name] = True
 
@@ -85,8 +86,8 @@ class TextualInversionManager(BaseTextualInversionManager):
         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):
-                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}."
+                logger.warning(
+                    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}."
                 )
                 continue
 
@@ -105,8 +106,8 @@ class TextualInversionManager(BaseTextualInversionManager):
                     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}"
+                logger.info(
+                    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
 
@@ -120,8 +121,8 @@ class TextualInversionManager(BaseTextualInversionManager):
                 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)}")
+                logger.debug(f'Ignoring incompatible embedding {embedding_info["name"]}')
+                logger.debug(f"The error was {str(e)}")
 
     def _add_textual_inversion(
         self, trigger_str, embedding, defer_injecting_tokens=False
@@ -133,8 +134,8 @@ class TextualInversionManager(BaseTextualInversionManager):
         :return: The token id for the added embedding, either existing or newly-added.
         """
         if trigger_str in [ti.trigger_string for ti in self.textual_inversions]:
-            print(
-                f"** TextualInversionManager refusing to overwrite already-loaded token '{trigger_str}'"
+            logger.warning(
+                f"TextualInversionManager refusing to overwrite already-loaded token '{trigger_str}'"
             )
             return
         if not self.full_precision:
@@ -155,11 +156,11 @@ class TextualInversionManager(BaseTextualInversionManager):
 
         except ValueError as e:
             if str(e).startswith("Warning"):
-                print(f">> {str(e)}")
+                logger.warning(f"{str(e)}")
             else:
                 traceback.print_exc()
-                print(
-                    f"** TextualInversionManager was unable to add a textual inversion with trigger string {trigger_str}."
+                logger.error(
+                    f"TextualInversionManager was unable to add a textual inversion with trigger string {trigger_str}."
                 )
                 raise
 
@@ -219,16 +220,16 @@ class TextualInversionManager(BaseTextualInversionManager):
         for ti in self.textual_inversions:
             if ti.trigger_token_id is None and ti.trigger_string in prompt_string:
                 if ti.embedding_vector_length > 1:
-                    print(
-                        f">> Preparing tokens for textual inversion {ti.trigger_string}..."
+                    logger.info(
+                        f"Preparing tokens for textual inversion {ti.trigger_string}..."
                     )
                 try:
                     self._inject_tokens_and_assign_embeddings(ti)
                 except ValueError as e:
-                    print(
-                        f"   | Ignoring incompatible embedding trigger {ti.trigger_string}"
+                    logger.debug(
+                        f"Ignoring incompatible embedding trigger {ti.trigger_string}"
                     )
-                    print(f"   | The error was {str(e)}")
+                    logger.debug(f"The error was {str(e)}")
                     continue
                 injected_token_ids.append(ti.trigger_token_id)
                 injected_token_ids.extend(ti.pad_token_ids)
@@ -306,16 +307,16 @@ class TextualInversionManager(BaseTextualInversionManager):
             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}"
+                    logger.critical(
+                        f"Security Issues Found in Model: {scan_result.issues_count}"
                     )
-                    print("   ** For your safety, InvokeAI will not load this embed.")
+                    logger.critical("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}")
+            logger.warning(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
@@ -334,7 +335,7 @@ class TextualInversionManager(BaseTextualInversionManager):
 
     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}')
+        logger.debug(f'Loading v1 embedding file: {basename}')
 
         embeddings = list()
         token_counter = -1
@@ -342,7 +343,7 @@ class TextualInversionManager(BaseTextualInversionManager):
             if token_counter < 0:
                 trigger = embedding_ckpt["name"]
             elif token_counter == 0:
-                trigger = f'<basename>'
+                trigger = '<basename>'
             else:
                 trigger = f'<{basename}-{int(token_counter:=token_counter)}>'
             token_counter += 1
@@ -365,7 +366,7 @@ class TextualInversionManager(BaseTextualInversionManager):
         This handles embedding .pt file variant #2.
         """
         basename = Path(file_path).stem
-        print(f'   | Loading v2 embedding file: {basename}')
+        logger.debug(f'Loading v2 embedding file: {basename}')
         embeddings = list()
         
         if isinstance(
@@ -384,7 +385,7 @@ class TextualInversionManager(BaseTextualInversionManager):
                 )
                 embeddings.append(embedding_info)
         else:
-            print(f"   ** {basename}: Unrecognized embedding format")
+            logger.warning(f"{basename}: Unrecognized embedding format")
 
         return embeddings
 
@@ -393,7 +394,7 @@ class TextualInversionManager(BaseTextualInversionManager):
         Parse 'version 3' of the .pt textual inversion embedding files.
         """
         basename = Path(file_path).stem
-        print(f'   | Loading v3 embedding file: {basename}')
+        logger.debug(f'Loading v3 embedding file: {basename}')
         embedding = embedding_ckpt['emb_params']
         embedding_info = EmbeddingInfo(
             name = f'<{basename}>',
@@ -411,11 +412,11 @@ class TextualInversionManager(BaseTextualInversionManager):
         basename = Path(filepath).stem
         short_path = Path(filepath).parents[0].name+'/'+Path(filepath).name
         
-        print(f'   | Loading v4 embedding file: {short_path}')
+        logger.debug(f'Loading v4 embedding file: {short_path}')
         
         embeddings = list()
         if list(embedding_ckpt.keys()) == 0:
-            print(f"   ** Invalid embeddings file: {short_path}")
+            logger.warning(f"Invalid embeddings file: {short_path}")
         else:
             for token,embedding in embedding_ckpt.items():
                 embedding_info = EmbeddingInfo(

invokeai/backend/training/textual_inversion_training.py

@@ -7,7 +7,6 @@
 This is the backend to "textual_inversion.py"
 """
 
-import argparse
 import logging
 import math
 import os
@@ -47,8 +46,7 @@ from tqdm.auto import tqdm
 from transformers import CLIPTextModel, CLIPTokenizer
 
 # invokeai stuff
-from ..args import ArgFormatter, PagingArgumentParser
-from ..globals import Globals, global_cache_dir
+from invokeai.app.services.config import InvokeAIAppConfig,PagingArgumentParser
 
 if version.parse(version.parse(PIL.__version__).base_version) >= version.parse("9.1.0"):
     PIL_INTERPOLATION = {
@@ -90,8 +88,9 @@ def save_progress(
 
 
 def parse_args():
+    config = InvokeAIAppConfig(argv=[])
     parser = PagingArgumentParser(
-        description="Textual inversion training", formatter_class=ArgFormatter
+        description="Textual inversion training"
     )
     general_group = parser.add_argument_group("General")
     model_group = parser.add_argument_group("Models and Paths")
@@ -112,7 +111,7 @@ def parse_args():
         "--root_dir",
         "--root",
         type=Path,
-        default=Globals.root,
+        default=config.root,
         help="Path to the invokeai runtime directory",
     )
     general_group.add_argument(
@@ -127,7 +126,7 @@ def parse_args():
     general_group.add_argument(
         "--output_dir",
         type=Path,
-        default=f"{Globals.root}/text-inversion-model",
+        default=f"{config.root}/text-inversion-model",
         help="The output directory where the model predictions and checkpoints will be written.",
     )
     model_group.add_argument(
@@ -528,6 +527,7 @@ def get_full_repo_name(
 
 
 def do_textual_inversion_training(
+    config: InvokeAIAppConfig,
     model: str,
     train_data_dir: Path,
     output_dir: Path,
@@ -580,7 +580,7 @@ def do_textual_inversion_training(
 
     # setting up things the way invokeai expects them
     if not os.path.isabs(output_dir):
-        output_dir = os.path.join(Globals.root, output_dir)
+        output_dir = os.path.join(config.root, output_dir)
 
     logging_dir = output_dir / logging_dir
 
@@ -628,7 +628,7 @@ def do_textual_inversion_training(
         elif output_dir is not None:
             os.makedirs(output_dir, exist_ok=True)
 
-    models_conf = OmegaConf.load(os.path.join(Globals.root, "configs/models.yaml"))
+    models_conf = OmegaConf.load(config.model_conf_path)
     model_conf = models_conf.get(model, None)
     assert model_conf is not None, f"Unknown model: {model}"
     assert (
@@ -640,7 +640,7 @@ def do_textual_inversion_training(
     assert (
         pretrained_model_name_or_path
     ), f"models.yaml error: neither 'repo_id' nor 'path' is defined for {model}"
-    pipeline_args = dict(cache_dir=global_cache_dir("hub"))
+    pipeline_args = dict(cache_dir=config.cache_dir)
 
     # Load tokenizer
     if tokenizer_name:

invokeai/backend/util/devices.py

@@ -4,17 +4,16 @@ from contextlib import nullcontext
 
 import torch
 from torch import autocast
-
-from invokeai.backend.globals import Globals
+from invokeai.app.services.config import get_invokeai_config
 
 CPU_DEVICE = torch.device("cpu")
 CUDA_DEVICE = torch.device("cuda")
 MPS_DEVICE = torch.device("mps")
 
-
 def choose_torch_device() -> torch.device:
     """Convenience routine for guessing which GPU device to run model on"""
-    if Globals.always_use_cpu:
+    config = get_invokeai_config()    
+    if config.always_use_cpu:
         return CPU_DEVICE
     if torch.cuda.is_available():
         return torch.device("cuda")
@@ -33,7 +32,8 @@ def choose_precision(device: torch.device) -> str:
 
 
 def torch_dtype(device: torch.device) -> torch.dtype:
-    if Globals.full_precision:
+    config = get_invokeai_config()
+    if config.full_precision:
         return torch.float32
     if choose_precision(device) == "float16":
         return torch.float16

invokeai/backend/util/logging.py

@@ -0,0 +1,110 @@
+# Copyright (c) 2023 Lincoln D. Stein and The InvokeAI Development Team
+
+"""invokeai.util.logging
+
+Logging class for InvokeAI that produces console messages
+
+Usage:
+
+from invokeai.backend.util.logging import InvokeAILogger
+
+logger = InvokeAILogger.getLogger(name='InvokeAI') // Initialization
+(or)
+logger = InvokeAILogger.getLogger(__name__) // To use the filename
+
+logger.critical('this is critical') // Critical Message
+logger.error('this is an error') // Error Message
+logger.warning('this is a warning') // Warning Message
+logger.info('this is info') // Info Message
+logger.debug('this is debugging') // Debug Message
+
+Console messages:
+    [12-05-2023 20]::[InvokeAI]::CRITICAL --> This is an info message [In Bold Red]
+    [12-05-2023 20]::[InvokeAI]::ERROR --> This is an info message [In Red]
+    [12-05-2023 20]::[InvokeAI]::WARNING --> This is an info message [In Yellow]
+    [12-05-2023 20]::[InvokeAI]::INFO --> This is an info message [In Grey]
+    [12-05-2023 20]::[InvokeAI]::DEBUG --> This is an info message [In Grey]
+
+Alternate Method (in this case the logger name will be set to InvokeAI):
+import invokeai.backend.util.logging as IAILogger
+IAILogger.debug('this is a debugging message')
+"""
+
+import logging
+
+
+# module level functions
+def debug(msg, *args, **kwargs):
+    InvokeAILogger.getLogger().debug(msg, *args, **kwargs)
+
+def info(msg, *args, **kwargs):
+    InvokeAILogger.getLogger().info(msg, *args, **kwargs)
+
+def warning(msg, *args, **kwargs):
+    InvokeAILogger.getLogger().warning(msg, *args, **kwargs)
+
+def error(msg, *args, **kwargs):
+    InvokeAILogger.getLogger().error(msg, *args, **kwargs)
+
+def critical(msg, *args, **kwargs):
+    InvokeAILogger.getLogger().critical(msg, *args, **kwargs)
+
+def log(level, msg, *args, **kwargs):
+    InvokeAILogger.getLogger().log(level, msg, *args, **kwargs)
+
+def disable(level=logging.CRITICAL):
+    InvokeAILogger.getLogger().disable(level)
+
+def basicConfig(**kwargs):
+    InvokeAILogger.getLogger().basicConfig(**kwargs)
+
+def getLogger(name: str = None) -> logging.Logger:
+    return InvokeAILogger.getLogger(name)
+
+
+class InvokeAILogFormatter(logging.Formatter):
+    '''
+    Custom Formatting for the InvokeAI Logger
+    '''
+
+    # Color Codes
+    grey = "\x1b[38;20m"
+    yellow = "\x1b[33;20m"
+    red = "\x1b[31;20m"
+    cyan = "\x1b[36;20m"
+    bold_red = "\x1b[31;1m"
+    reset = "\x1b[0m"
+
+    # Log Format
+    format = "[%(asctime)s]::[%(name)s]::%(levelname)s --> %(message)s"
+    ## More Formatting Options: %(pathname)s, %(filename)s, %(module)s, %(lineno)d
+
+    # Format Map
+    FORMATS = {
+        logging.DEBUG: cyan + format + reset,
+        logging.INFO: grey + format + reset,
+        logging.WARNING: yellow + format + reset,
+        logging.ERROR: red + format + reset,
+        logging.CRITICAL: bold_red + format + reset
+    }
+
+    def format(self, record):
+        log_fmt = self.FORMATS.get(record.levelno)
+        formatter = logging.Formatter(log_fmt, datefmt="%d-%m-%Y %H:%M:%S")
+        return formatter.format(record)
+
+
+class InvokeAILogger(object):
+    loggers = dict()
+
+    @classmethod
+    def getLogger(self, name: str = 'InvokeAI') -> logging.Logger:
+        if name not in self.loggers:
+            logger = logging.getLogger(name)
+            logger.setLevel(logging.DEBUG)
+            ch = logging.StreamHandler()
+            fmt = InvokeAILogFormatter()
+            ch.setFormatter(fmt)
+            logger.addHandler(ch)
+            self.loggers[name] = logger
+        return self.loggers[name]

invokeai/backend/util/util.py

@@ -18,6 +18,7 @@ import torch
 from PIL import Image, ImageDraw, ImageFont
 from tqdm import tqdm
 
+import invokeai.backend.util.logging as logger
 from .devices import torch_dtype
 
 
@@ -38,7 +39,7 @@ def log_txt_as_img(wh, xc, size=10):
         try:
             draw.text((0, 0), lines, fill="black", font=font)
         except UnicodeEncodeError:
-            print("Cant encode string for logging. Skipping.")
+            logger.warning("Cant encode string for logging. Skipping.")
 
         txt = np.array(txt).transpose(2, 0, 1) / 127.5 - 1.0
         txts.append(txt)
@@ -80,8 +81,8 @@ def mean_flat(tensor):
 def count_params(model, verbose=False):
     total_params = sum(p.numel() for p in model.parameters())
     if verbose:
-        print(
-            f"   | {model.__class__.__name__} has {total_params * 1.e-6:.2f} M params."
+        logger.debug(
+            f"{model.__class__.__name__} has {total_params * 1.e-6:.2f} M params."
         )
     return total_params
 
@@ -132,8 +133,8 @@ def parallel_data_prefetch(
         raise ValueError("list expected but function got ndarray.")
     elif isinstance(data, abc.Iterable):
         if isinstance(data, dict):
-            print(
-                'WARNING:"data" argument passed to parallel_data_prefetch is a dict: Using only its values and disregarding keys.'
+            logger.warning(
+                '"data" argument passed to parallel_data_prefetch is a dict: Using only its values and disregarding keys.'
             )
             data = list(data.values())
         if target_data_type == "ndarray":
@@ -175,7 +176,7 @@ def parallel_data_prefetch(
         processes += [p]
 
     # start processes
-    print("Start prefetching...")
+    logger.info("Start prefetching...")
     import time
 
     start = time.time()
@@ -194,7 +195,7 @@ def parallel_data_prefetch(
                 gather_res[res[0]] = res[1]
 
     except Exception as e:
-        print("Exception: ", e)
+        logger.error("Exception: ", e)
         for p in processes:
             p.terminate()
 
@@ -202,7 +203,7 @@ def parallel_data_prefetch(
     finally:
         for p in processes:
             p.join()
-        print(f"Prefetching complete. [{time.time() - start} sec.]")
+        logger.info(f"Prefetching complete. [{time.time() - start} sec.]")
 
     if target_data_type == "ndarray":
         if not isinstance(gather_res[0], np.ndarray):
@@ -318,23 +319,23 @@ def download_with_resume(url: str, dest: Path, access_token: str = None) -> Path
         resp = requests.get(url, headers=header, stream=True)  # new request with range
 
     if exist_size > content_length:
-        print("* corrupt existing file found. re-downloading")
+        logger.warning("corrupt existing file found. re-downloading")
         os.remove(dest)
         exist_size = 0
 
     if resp.status_code == 416 or exist_size == content_length:
-        print(f"* {dest}: complete file found. Skipping.")
+        logger.warning(f"{dest}: complete file found. Skipping.")
         return dest
     elif resp.status_code == 206 or exist_size > 0:
-        print(f"* {dest}: partial file found. Resuming...")
+        logger.warning(f"{dest}: partial file found. Resuming...")
     elif resp.status_code != 200:
-        print(f"** An error occurred during downloading {dest}: {resp.reason}")
+        logger.error(f"An error occurred during downloading {dest}: {resp.reason}")
     else:
-        print(f"* {dest}: Downloading...")
+        logger.error(f"{dest}: Downloading...")
 
     try:
         if content_length < 2000:
-            print(f"*** ERROR DOWNLOADING {url}: {resp.text}")
+            logger.error(f"ERROR DOWNLOADING {url}: {resp.text}")
             return None
 
         with open(dest, open_mode) as file, tqdm(
@@ -349,7 +350,7 @@ def download_with_resume(url: str, dest: Path, access_token: str = None) -> Path
                 size = file.write(data)
                 bar.update(size)
     except Exception as e:
-        print(f"An error occurred while downloading {dest}: {str(e)}")
+        logger.error(f"An error occurred while downloading {dest}: {str(e)}")
         return None
 
     return dest

invokeai/backend/web/invoke_ai_web_server.py

@@ -19,6 +19,7 @@ from PIL import Image
 from PIL.Image import Image as ImageType
 from werkzeug.utils import secure_filename
 
+import invokeai.backend.util.logging as logger
 import invokeai.frontend.web.dist as frontend
 
 from .. import Generate
@@ -77,7 +78,6 @@ class InvokeAIWebServer:
         mimetypes.add_type("application/javascript", ".js")
         mimetypes.add_type("text/css", ".css")
         # Socket IO
-        logger = True if args.web_verbose else False
         engineio_logger = True if args.web_verbose else False
         max_http_buffer_size = 10000000
 
@@ -213,7 +213,7 @@ class InvokeAIWebServer:
         self.load_socketio_listeners(self.socketio)
 
         if args.gui:
-            print(">> Launching Invoke AI GUI")
+            logger.info("Launching Invoke AI GUI")
             try:
                 from flaskwebgui import FlaskUI
 
@@ -231,17 +231,17 @@ class InvokeAIWebServer:
                 sys.exit(0)
         else:
             useSSL = args.certfile or args.keyfile
-            print(">> Started Invoke AI Web Server")
+            logger.info("Started Invoke AI Web Server")
             if self.host == "0.0.0.0":
-                print(
+                logger.info(
                     f"Point your browser at http{'s' if useSSL else ''}://localhost:{self.port} or use the host's DNS name or IP address."
                 )
             else:
-                print(
-                    ">> Default host address now 127.0.0.1 (localhost). Use --host 0.0.0.0 to bind any address."
+                logger.info(
+                    "Default host address now 127.0.0.1 (localhost). Use --host 0.0.0.0 to bind any address."
                 )
-                print(
-                    f">> Point your browser at http{'s' if useSSL else ''}://{self.host}:{self.port}"
+                logger.info(
+                    f"Point your browser at http{'s' if useSSL else ''}://{self.host}:{self.port}"
                 )
             if not useSSL:
                 self.socketio.run(app=self.app, host=self.host, port=self.port)
@@ -273,7 +273,7 @@ class InvokeAIWebServer:
         # path for thumbnail images
         self.thumbnail_image_path = os.path.join(self.result_path, "thumbnails/")
         # txt log
-        self.log_path = os.path.join(self.result_path, "invoke_log.txt")
+        self.log_path = os.path.join(self.result_path, "invoke_logger.txt")
         # make all output paths
         [
             os.makedirs(path, exist_ok=True)
@@ -290,7 +290,7 @@ class InvokeAIWebServer:
     def load_socketio_listeners(self, socketio):
         @socketio.on("requestSystemConfig")
         def handle_request_capabilities():
-            print(">> System config requested")
+            logger.info("System config requested")
             config = self.get_system_config()
             config["model_list"] = self.generate.model_manager.list_models()
             config["infill_methods"] = infill_methods()
@@ -330,7 +330,7 @@ class InvokeAIWebServer:
                 if model_name in current_model_list:
                     update = True
 
-                print(f">> Adding New Model: {model_name}")
+                logger.info(f"Adding New Model: {model_name}")
 
                 self.generate.model_manager.add_model(
                     model_name=model_name,
@@ -348,14 +348,14 @@ class InvokeAIWebServer:
                         "update": update,
                     },
                 )
-                print(f">> New Model Added: {model_name}")
+                logger.info(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}")
+                logger.info(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()
@@ -366,14 +366,14 @@ class InvokeAIWebServer:
                         "model_list": updated_model_list,
                     },
                 )
-                print(f">> Model Deleted: {model_name}")
+                logger.info(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}")
+                logger.info(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:
@@ -454,7 +454,7 @@ class InvokeAIWebServer:
                         "update": True,
                     },
                 )
-                print(f">> Model Converted: {model_name}")
+                logger.info(f"Model Converted: {model_name}")
             except Exception as e:
                 self.handle_exceptions(e)
 
@@ -490,7 +490,7 @@ class InvokeAIWebServer:
                 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]}")
+                    logger.info(f"Using configured VAE assigned to {models_to_merge[0]}")
                     merged_model_config.update(vae=vae)
 
                 self.generate.model_manager.import_diffuser_model(
@@ -507,8 +507,8 @@ class InvokeAIWebServer:
                         "update": True,
                     },
                 )
-                print(f">> Models Merged: {models_to_merge}")
-                print(f">> New Model Added: {model_merge_info['merged_model_name']}")
+                logger.info(f"Models Merged: {models_to_merge}")
+                logger.info(f"New Model Added: {model_merge_info['merged_model_name']}")
             except Exception as e:
                 self.handle_exceptions(e)
 
@@ -698,7 +698,7 @@ class InvokeAIWebServer:
                             }
                         )
                     except Exception as e:
-                        print(f">> Unable to load {path}")
+                        logger.info(f"Unable to load {path}")
                         socketio.emit(
                             "error", {"message": f"Unable to load {path}: {str(e)}"}
                         )
@@ -735,9 +735,9 @@ class InvokeAIWebServer:
                         printable_parameters["init_mask"][:64] + "..."
                     )
 
-                print(f"\n>> Image Generation Parameters:\n\n{printable_parameters}\n")
-                print(f">> ESRGAN Parameters: {esrgan_parameters}")
-                print(f">> Facetool Parameters: {facetool_parameters}")
+                logger.info(f"Image Generation Parameters:\n\n{printable_parameters}\n")
+                logger.info(f"ESRGAN Parameters: {esrgan_parameters}")
+                logger.info(f"Facetool Parameters: {facetool_parameters}")
 
                 self.generate_images(
                     generation_parameters,
@@ -750,8 +750,8 @@ class InvokeAIWebServer:
         @socketio.on("runPostprocessing")
         def handle_run_postprocessing(original_image, postprocessing_parameters):
             try:
-                print(
-                    f'>> Postprocessing requested for "{original_image["url"]}": {postprocessing_parameters}'
+                logger.info(
+                    f'Postprocessing requested for "{original_image["url"]}": {postprocessing_parameters}'
                 )
 
                 progress = Progress()
@@ -861,14 +861,14 @@ class InvokeAIWebServer:
 
         @socketio.on("cancel")
         def handle_cancel():
-            print(">> Cancel processing requested")
+            logger.info("Cancel processing requested")
             self.canceled.set()
 
         # TODO: I think this needs a safety mechanism.
         @socketio.on("deleteImage")
         def handle_delete_image(url, thumbnail, uuid, category):
             try:
-                print(f'>> Delete requested "{url}"')
+                logger.info(f'Delete requested "{url}"')
                 from send2trash import send2trash
 
                 path = self.get_image_path_from_url(url)
@@ -1263,7 +1263,7 @@ class InvokeAIWebServer:
                     image, os.path.basename(path), self.thumbnail_image_path
                 )
 
-                print(f'\n\n>> Image generated: "{path}"\n')
+                logger.info(f'Image generated: "{path}"\n')
                 self.write_log_message(f'[Generated] "{path}": {command}')
 
                 if progress.total_iterations > progress.current_iteration:
@@ -1329,7 +1329,7 @@ class InvokeAIWebServer:
         except Exception as e:
             # Clear the CUDA cache on an exception
             self.empty_cuda_cache()
-            print(e)
+            logger.error(e)
             self.handle_exceptions(e)
 
     def empty_cuda_cache(self):

invokeai/backend/web/modules/parameters.py

@@ -4,17 +4,21 @@ from .parse_seed_weights import parse_seed_weights
 
 SAMPLER_CHOICES = [
     "ddim",
-    "k_dpm_2_a",
-    "k_dpm_2",
-    "k_dpmpp_2_a",
-    "k_dpmpp_2",
-    "k_euler_a",
-    "k_euler",
-    "k_heun",
-    "k_lms",
-    "plms",
-    # diffusers:
+    "ddpm",
+    "deis",
+    "lms",
     "pndm",
+    "heun",
+    'heun_k',
+    "euler",
+    "euler_k",
+    "euler_a",
+    "kdpm_2",
+    "kdpm_2_a",
+    "dpmpp_2s",
+    "dpmpp_2m",
+    "dpmpp_2m_k",
+    "unipc",
 ]
 
 

invokeai/frontend/CLI/readline.py

@@ -1,497 +0,0 @@
-"""
-Readline helper functions for invoke.py.
-You may import the global singleton `completer` to get access to the
-completer object itself. This is useful when you want to autocomplete
-seeds:
-
- from invokeai.frontend.CLI.readline import completer
- completer.add_seed(18247566)
- completer.add_seed(9281839)
-"""
-import atexit
-import os
-import re
-
-from ...backend.args import Args
-from ...backend.globals import Globals
-from ...backend.stable_diffusion import HuggingFaceConceptsLibrary
-
-# ---------------readline utilities---------------------
-try:
-    import readline
-
-    readline_available = True
-except (ImportError, ModuleNotFoundError) as e:
-    print(f"** An error occurred when loading the readline module: {str(e)}")
-    readline_available = False
-
-IMG_EXTENSIONS = (".png", ".jpg", ".jpeg", ".PNG", ".JPG", ".JPEG", ".gif", ".GIF")
-WEIGHT_EXTENSIONS = (".ckpt", ".vae", ".safetensors")
-TEXT_EXTENSIONS = (".txt", ".TXT")
-CONFIG_EXTENSIONS = (".yaml", ".yml")
-COMMANDS = (
-    "--steps",
-    "-s",
-    "--seed",
-    "-S",
-    "--iterations",
-    "-n",
-    "--width",
-    "-W",
-    "--height",
-    "-H",
-    "--cfg_scale",
-    "-C",
-    "--threshold",
-    "--perlin",
-    "--grid",
-    "-g",
-    "--individual",
-    "-i",
-    "--save_intermediates",
-    "--init_img",
-    "-I",
-    "--init_mask",
-    "-M",
-    "--init_color",
-    "--strength",
-    "-f",
-    "--variants",
-    "-v",
-    "--outdir",
-    "-o",
-    "--sampler",
-    "-A",
-    "-m",
-    "--embedding_path",
-    "--device",
-    "--grid",
-    "-g",
-    "--facetool",
-    "-ft",
-    "--facetool_strength",
-    "-G",
-    "--codeformer_fidelity",
-    "-cf",
-    "--upscale",
-    "-U",
-    "-save_orig",
-    "--save_original",
-    "--log_tokenization",
-    "-t",
-    "--hires_fix",
-    "--inpaint_replace",
-    "-r",
-    "--png_compression",
-    "-z",
-    "--text_mask",
-    "-tm",
-    "--h_symmetry_time_pct",
-    "--v_symmetry_time_pct",
-    "!fix",
-    "!fetch",
-    "!replay",
-    "!history",
-    "!search",
-    "!clear",
-    "!models",
-    "!switch",
-    "!import_model",
-    "!optimize_model",
-    "!convert_model",
-    "!edit_model",
-    "!del_model",
-    "!mask",
-    "!triggers",
-)
-MODEL_COMMANDS = (
-    "!switch",
-    "!edit_model",
-    "!del_model",
-)
-CKPT_MODEL_COMMANDS = ("!optimize_model",)
-WEIGHT_COMMANDS = (
-    "!import_model",
-    "!convert_model",
-)
-IMG_PATH_COMMANDS = ("--outdir[=\s]",)
-TEXT_PATH_COMMANDS = ("!replay",)
-IMG_FILE_COMMANDS = (
-    "!fix",
-    "!fetch",
-    "!mask",
-    "--init_img[=\s]",
-    "-I",
-    "--init_mask[=\s]",
-    "-M",
-    "--init_color[=\s]",
-    "--embedding_path[=\s]",
-)
-
-path_regexp = "(" + "|".join(IMG_PATH_COMMANDS + IMG_FILE_COMMANDS) + ")\s*\S*$"
-weight_regexp = "(" + "|".join(WEIGHT_COMMANDS) + ")\s*\S*$"
-text_regexp = "(" + "|".join(TEXT_PATH_COMMANDS) + ")\s*\S*$"
-
-
-class Completer(object):
-    def __init__(self, options, models={}):
-        self.options = sorted(options)
-        self.models = models
-        self.seeds = set()
-        self.matches = list()
-        self.default_dir = None
-        self.linebuffer = None
-        self.auto_history_active = True
-        self.extensions = None
-        self.concepts = None
-        self.embedding_terms = set()
-        return
-
-    def complete(self, text, state):
-        """
-        Completes invoke command line.
-        BUG: it doesn't correctly complete files that have spaces in the name.
-        """
-        buffer = readline.get_line_buffer()
-
-        if state == 0:
-            # extensions defined, so go directly into path completion mode
-            if self.extensions is not None:
-                self.matches = self._path_completions(text, state, self.extensions)
-
-            # looking for an image file
-            elif re.search(path_regexp, buffer):
-                do_shortcut = re.search("^" + "|".join(IMG_FILE_COMMANDS), buffer)
-                self.matches = self._path_completions(
-                    text, state, IMG_EXTENSIONS, shortcut_ok=do_shortcut
-                )
-
-            # looking for a seed
-            elif re.search("(-S\s*|--seed[=\s])\d*$", buffer):
-                self.matches = self._seed_completions(text, state)
-
-            # looking for an embedding concept
-            elif re.search("<[\w-]*$", buffer):
-                self.matches = self._concept_completions(text, state)
-
-            # looking for a model
-            elif re.match("^" + "|".join(MODEL_COMMANDS), buffer):
-                self.matches = self._model_completions(text, state)
-
-            # looking for a ckpt model
-            elif re.match("^" + "|".join(CKPT_MODEL_COMMANDS), buffer):
-                self.matches = self._model_completions(text, state, ckpt_only=True)
-
-            elif re.search(weight_regexp, buffer):
-                self.matches = self._path_completions(
-                    text,
-                    state,
-                    WEIGHT_EXTENSIONS,
-                    default_dir=Globals.root,
-                )
-
-            elif re.search(text_regexp, buffer):
-                self.matches = self._path_completions(text, state, TEXT_EXTENSIONS)
-
-            # This is the first time for this text, so build a match list.
-            elif text:
-                self.matches = [s for s in self.options if s and s.startswith(text)]
-            else:
-                self.matches = self.options[:]
-
-        # Return the state'th item from the match list,
-        # if we have that many.
-        try:
-            response = self.matches[state]
-        except IndexError:
-            response = None
-        return response
-
-    def complete_extensions(self, extensions: list):
-        """
-        If called with a list of extensions, will force completer
-        to do file path completions.
-        """
-        self.extensions = extensions
-
-    def add_history(self, line):
-        """
-        Pass thru to readline
-        """
-        if not self.auto_history_active:
-            readline.add_history(line)
-
-    def clear_history(self):
-        """
-        Pass clear_history() thru to readline
-        """
-        readline.clear_history()
-
-    def search_history(self, match: str):
-        """
-        Like show_history() but only shows items that
-        contain the match string.
-        """
-        self.show_history(match)
-
-    def remove_history_item(self, pos):
-        readline.remove_history_item(pos)
-
-    def add_seed(self, seed):
-        """
-        Add a seed to the autocomplete list for display when -S is autocompleted.
-        """
-        if seed is not None:
-            self.seeds.add(str(seed))
-
-    def set_default_dir(self, path):
-        self.default_dir = path
-
-    def set_options(self, options):
-        self.options = options
-
-    def get_line(self, index):
-        try:
-            line = self.get_history_item(index)
-        except IndexError:
-            return None
-        return line
-
-    def get_current_history_length(self):
-        return readline.get_current_history_length()
-
-    def get_history_item(self, index):
-        return readline.get_history_item(index)
-
-    def show_history(self, match=None):
-        """
-        Print the session history using the pydoc pager
-        """
-        import pydoc
-
-        lines = list()
-        h_len = self.get_current_history_length()
-        if h_len < 1:
-            print("<empty history>")
-            return
-
-        for i in range(0, h_len):
-            line = self.get_history_item(i + 1)
-            if match and match not in line:
-                continue
-            lines.append(f"[{i+1}] {line}")
-        pydoc.pager("\n".join(lines))
-
-    def set_line(self, line) -> None:
-        """
-        Set the default string displayed in the next line of input.
-        """
-        self.linebuffer = line
-        readline.redisplay()
-
-    def update_models(self, models: dict) -> None:
-        """
-        update our list of models
-        """
-        self.models = models
-
-    def _seed_completions(self, text, state):
-        m = re.search("(-S\s?|--seed[=\s]?)(\d*)", text)
-        if m:
-            switch = m.groups()[0]
-            partial = m.groups()[1]
-        else:
-            switch = ""
-            partial = text
-
-        matches = list()
-        for s in self.seeds:
-            if s.startswith(partial):
-                matches.append(switch + s)
-        matches.sort()
-        return matches
-
-    def add_embedding_terms(self, terms: list[str]):
-        self.embedding_terms = set(terms)
-        if self.concepts:
-            self.embedding_terms.update(set(self.concepts.list_concepts()))
-
-    def _concept_completions(self, text, state):
-        if self.concepts is None:
-            # cache Concepts() instance so we can check for updates in concepts_list during runtime.
-            self.concepts = HuggingFaceConceptsLibrary()
-            self.embedding_terms.update(set(self.concepts.list_concepts()))
-        else:
-            self.embedding_terms.update(set(self.concepts.list_concepts()))
-
-        partial = text[1:]  # this removes the leading '<'
-        if len(partial) == 0:
-            return list(self.embedding_terms)  # whole dump - think if user wants this!
-
-        matches = list()
-        for concept in self.embedding_terms:
-            if concept.startswith(partial):
-                matches.append(f"<{concept}>")
-        matches.sort()
-        return matches
-
-    def _model_completions(self, text, state, ckpt_only=False):
-        m = re.search("(!switch\s+)(\w*)", text)
-        if m:
-            switch = m.groups()[0]
-            partial = m.groups()[1]
-        else:
-            switch = ""
-            partial = text
-        matches = list()
-        for s in self.models:
-            format = self.models[s]["format"]
-            if format == "vae":
-                continue
-            if ckpt_only and format != "ckpt":
-                continue
-            if s.startswith(partial):
-                matches.append(switch + s)
-        matches.sort()
-        return matches
-
-    def _pre_input_hook(self):
-        if self.linebuffer:
-            readline.insert_text(self.linebuffer)
-            readline.redisplay()
-            self.linebuffer = None
-
-    def _path_completions(
-        self, text, state, extensions, shortcut_ok=True, default_dir: str = ""
-    ):
-        # separate the switch from the partial path
-        match = re.search("^(-\w|--\w+=?)(.*)", text)
-        if match is None:
-            switch = None
-            partial_path = text
-        else:
-            switch, partial_path = match.groups()
-
-        partial_path = partial_path.lstrip()
-
-        matches = list()
-        path = os.path.expanduser(partial_path)
-
-        if os.path.isdir(path):
-            dir = path
-        elif os.path.dirname(path) != "":
-            dir = os.path.dirname(path)
-        else:
-            dir = default_dir if os.path.exists(default_dir) else ""
-            path = os.path.join(dir, path)
-
-        dir_list = os.listdir(dir or ".")
-        if shortcut_ok and os.path.exists(self.default_dir) and dir == "":
-            dir_list += os.listdir(self.default_dir)
-
-        for node in dir_list:
-            if node.startswith(".") and len(node) > 1:
-                continue
-            full_path = os.path.join(dir, node)
-
-            if not (node.endswith(extensions) or os.path.isdir(full_path)):
-                continue
-
-            if path and not full_path.startswith(path):
-                continue
-
-            if switch is None:
-                match_path = os.path.join(dir, node)
-                matches.append(
-                    match_path + "/" if os.path.isdir(full_path) else match_path
-                )
-            elif os.path.isdir(full_path):
-                matches.append(
-                    switch + os.path.join(os.path.dirname(full_path), node) + "/"
-                )
-            elif node.endswith(extensions):
-                matches.append(switch + os.path.join(os.path.dirname(full_path), node))
-
-        return matches
-
-
-class DummyCompleter(Completer):
-    def __init__(self, options):
-        super().__init__(options)
-        self.history = list()
-
-    def add_history(self, line):
-        self.history.append(line)
-
-    def clear_history(self):
-        self.history = list()
-
-    def get_current_history_length(self):
-        return len(self.history)
-
-    def get_history_item(self, index):
-        return self.history[index - 1]
-
-    def remove_history_item(self, index):
-        return self.history.pop(index - 1)
-
-    def set_line(self, line):
-        print(f"# {line}")
-
-
-def generic_completer(commands: list) -> Completer:
-    if readline_available:
-        completer = Completer(commands, [])
-        readline.set_completer(completer.complete)
-        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")
-    else:
-        completer = DummyCompleter(commands)
-    return completer
-
-
-def get_completer(opt: Args, models=[]) -> Completer:
-    if readline_available:
-        completer = Completer(COMMANDS, models)
-
-        readline.set_completer(completer.complete)
-        # pyreadline3 does not have a set_auto_history() method
-        try:
-            readline.set_auto_history(False)
-            completer.auto_history_active = False
-        except:
-            completer.auto_history_active = True
-        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")
-
-        outdir = os.path.expanduser(opt.outdir)
-        if os.path.isabs(outdir):
-            histfile = os.path.join(outdir, ".invoke_history")
-        else:
-            histfile = os.path.join(Globals.root, outdir, ".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}"
-            )
-            os.replace(histfile, newname)
-        atexit.register(readline.write_history_file, histfile)
-
-    else:
-        completer = DummyCompleter(COMMANDS)
-    return completer

invokeai/frontend/CLI/sd_metadata.py

@@ -1,30 +0,0 @@
-'''
-This is a modularized version of the sd-metadata.py script,
-which retrieves and prints the metadata from a series of generated png files.
-'''
-import sys
-import json
-from invokeai.backend.image_util import retrieve_metadata
-
-
-def print_metadata():
-    if len(sys.argv) < 2:
-        print("Usage: file2prompt.py <file1.png> <file2.png> <file3.png>...")
-        print("This script opens up the indicated invoke.py-generated PNG file(s) and prints out their metadata.")
-        exit(-1)
-
-    filenames = sys.argv[1:]
-    for f in filenames:
-        try:
-            metadata = retrieve_metadata(f)
-            print(f'{f}:\n',json.dumps(metadata['sd-metadata'], indent=4))
-        except FileNotFoundError:
-            sys.stderr.write(f'{f} not found\n')
-            continue
-        except PermissionError:
-            sys.stderr.write(f'{f} could not be opened due to inadequate permissions\n')
-            continue
-
-if __name__== '__main__':
-    print_metadata()
-

invokeai/frontend/install/invokeai_update.py

@@ -1,10 +1,9 @@
-"""
+'''
 Minimalist updater script. Prompts user for the tag or branch to update to and runs
 pip install <path_to_git_source>.
-"""
+'''
 import os
 import platform
-
 import requests
 from rich import box, print
 from rich.console import Console, Group, group
@@ -16,8 +15,10 @@ from rich.text import Text
 
 from invokeai.version import __version__
 
-INVOKE_AI_SRC = "https://github.com/invoke-ai/InvokeAI/archive"
-INVOKE_AI_REL = "https://api.github.com/repos/invoke-ai/InvokeAI/releases"
+INVOKE_AI_SRC="https://github.com/invoke-ai/InvokeAI/archive"
+INVOKE_AI_TAG="https://github.com/invoke-ai/InvokeAI/archive/refs/tags"
+INVOKE_AI_BRANCH="https://github.com/invoke-ai/InvokeAI/archive/refs/heads"
+INVOKE_AI_REL="https://api.github.com/repos/invoke-ai/InvokeAI/releases"
 
 OS = platform.uname().system
 ARCH = platform.uname().machine
@@ -28,22 +29,22 @@ if OS == "Windows":
 else:
     console = Console(style=Style(color="grey74", bgcolor="grey19"))
 
-
-def get_versions() -> dict:
+def get_versions()->dict:
     return requests.get(url=INVOKE_AI_REL).json()
 
-
 def welcome(versions: dict):
+    
     @group()
     def text():
-        yield f"InvokeAI Version: [bold yellow]{__version__}"
-        yield ""
-        yield "This script will update InvokeAI to the latest release, or to a development version of your choice."
-        yield ""
-        yield "[bold yellow]Options:"
-        yield f"""[1] Update to the latest official release ([italic]{versions[0]['tag_name']}[/italic])
+        yield f'InvokeAI Version: [bold yellow]{__version__}'
+        yield ''
+        yield 'This script will update InvokeAI to the latest release, or to a development version of your choice.'
+        yield ''
+        yield '[bold yellow]Options:'
+        yield f'''[1] Update to the latest official release ([italic]{versions[0]['tag_name']}[/italic])
 [2] Update to the bleeding-edge development version ([italic]main[/italic])
-[3] Manually enter the tag or branch name you wish to update"""
+[3] Manually enter the [bold]tag name[/bold] for the version you wish to update to
+[4] Manually enter the [bold]branch name[/bold] for the version you wish to update to'''        
 
     console.rule()
     print(
@@ -59,33 +60,41 @@ def welcome(versions: dict):
     )
     console.line()
 
-
 def main():
     versions = get_versions()
     welcome(versions)
 
     tag = None
-    choice = Prompt.ask("Choice:", choices=["1", "2", "3"], default="1")
+    branch = None
+    release = None
+    choice = Prompt.ask('Choice:',choices=['1','2','3','4'],default='1')
+    
+    if choice=='1':
+        release = versions[0]['tag_name']
+    elif choice=='2':
+        release = 'main'
+    elif choice=='3':
+        tag = Prompt.ask('Enter an InvokeAI tag name')
+    elif choice=='4':
+        branch = Prompt.ask('Enter an InvokeAI branch name')
 
-    if choice == "1":
-        tag = versions[0]["tag_name"]
-    elif choice == "2":
-        tag = "main"
-    elif choice == "3":
-        tag = Prompt.ask("Enter an InvokeAI tag or branch name")
-
-    print(f":crossed_fingers: Upgrading to [yellow]{tag}[/yellow]")
-    cmd = f"pip install {INVOKE_AI_SRC}/{tag}.zip --use-pep517"
-    print("")
-    print("")
-    if os.system(cmd) == 0:
-        print(f":heavy_check_mark: Upgrade successful")
+    print(f':crossed_fingers: Upgrading to [yellow]{tag if tag else release}[/yellow]')
+    if release:
+        cmd = f'pip install {INVOKE_AI_SRC}/{release}.zip --use-pep517 --upgrade'
+    elif tag:
+        cmd = f'pip install {INVOKE_AI_TAG}/{tag}.zip --use-pep517 --upgrade'
     else:
-        print(f":exclamation: [bold red]Upgrade failed[/red bold]")
-
-
+        cmd = f'pip install {INVOKE_AI_BRANCH}/{branch}.zip --use-pep517 --upgrade'
+    print('')
+    print('')
+    if os.system(cmd)==0:
+        print(f':heavy_check_mark: Upgrade successful')
+    else:
+        print(f':exclamation: [bold red]Upgrade failed[/red bold]')
+    
 if __name__ == "__main__":
     try:
         main()
     except KeyboardInterrupt:
         pass
+

invokeai/frontend/install/model_install.py

@@ -22,7 +22,7 @@ import torch
 from npyscreen import widget
 from omegaconf import OmegaConf
 
-from invokeai.backend.globals import Globals, global_config_dir
+import invokeai.backend.util.logging as logger
 
 from ...backend.config.model_install_backend import (
     Dataset_path,
@@ -40,11 +40,13 @@ from .widgets import (
     TextBox,
     set_min_terminal_size,
 )
+from invokeai.app.services.config import get_invokeai_config
 
 # minimum size for the UI
 MIN_COLS = 120
 MIN_LINES = 45
 
+config = get_invokeai_config()
 
 class addModelsForm(npyscreen.FormMultiPage):
     # for responsive resizing - disabled
@@ -452,11 +454,11 @@ def main():
     opt = parser.parse_args()
 
     # setting a global here
-    Globals.root = os.path.expanduser(get_root(opt.root) or "")
+    config.root = os.path.expanduser(get_root(opt.root) or "")
 
-    if not global_config_dir().exists():
-        print(
-            ">> Your InvokeAI root directory is not set up. Calling invokeai-configure."
+    if not (config.conf_path / '..' ).exists():
+        logger.info(
+            "Your InvokeAI root directory is not set up. Calling invokeai-configure."
         )
         from invokeai.frontend.install import invokeai_configure
 
@@ -466,18 +468,18 @@ def main():
     try:
         select_and_download_models(opt)
     except AssertionError as e:
-        print(str(e))
+        logger.error(e)
         sys.exit(-1)
     except KeyboardInterrupt:
-        print("\nGoodbye! Come back soon.")
+        logger.info("Goodbye! Come back soon.")
     except widget.NotEnoughSpaceForWidget as e:
         if str(e).startswith("Height of 1 allocated"):
-            print(
-                "** Insufficient vertical space for the interface. Please make your window taller and try again"
+            logger.error(
+                "Insufficient vertical space for the interface. Please make your window taller and try again"
             )
         elif str(e).startswith("addwstr"):
-            print(
-                "** Insufficient horizontal space for the interface. Please make your window wider and try again."
+            logger.error(
+                "Insufficient horizontal space for the interface. Please make your window wider and try again."
             )
 
 

invokeai/frontend/merge/merge_diffusers.py

@@ -8,7 +8,6 @@ import argparse
 import curses
 import os
 import sys
-import traceback
 import warnings
 from argparse import Namespace
 from pathlib import Path
@@ -20,18 +19,13 @@ from diffusers import logging as dlogging
 from npyscreen import widget
 from omegaconf import OmegaConf
 
-from ...backend.globals import (
-    Globals,
-    global_cache_dir,
-    global_config_file,
-    global_models_dir,
-    global_set_root,
-)
+import invokeai.backend.util.logging as logger
+from invokeai.services.config import get_invokeai_config
 from ...backend.model_management import ModelManager
 from ...frontend.install.widgets import FloatTitleSlider
 
 DEST_MERGED_MODEL_DIR = "merged_models"
-
+config = get_invokeai_config()
 
 def merge_diffusion_models(
     model_ids_or_paths: List[Union[str, Path]],
@@ -58,7 +52,7 @@ def merge_diffusion_models(
 
         pipe = DiffusionPipeline.from_pretrained(
             model_ids_or_paths[0],
-            cache_dir=kwargs.get("cache_dir", global_cache_dir()),
+            cache_dir=kwargs.get("cache_dir", config.cache_dir),
             custom_pipeline="checkpoint_merger",
         )
         merged_pipe = pipe.merge(
@@ -92,7 +86,7 @@ def merge_diffusion_models_and_commit(
     **kwargs - the default DiffusionPipeline.get_config_dict kwargs:
          cache_dir, resume_download, force_download, proxies, local_files_only, use_auth_token, revision, torch_dtype, device_map
     """
-    config_file = global_config_file()
+    config_file = config.model_conf_path
     model_manager = ModelManager(OmegaConf.load(config_file))
     for mod in models:
         assert mod in model_manager.model_names(), f'** Unknown model "{mod}"'
@@ -104,7 +98,7 @@ def merge_diffusion_models_and_commit(
     merged_pipe = merge_diffusion_models(
         model_ids_or_paths, alpha, interp, force, **kwargs
     )
-    dump_path = global_models_dir() / DEST_MERGED_MODEL_DIR
+    dump_path = config.models_dir / DEST_MERGED_MODEL_DIR
 
     os.makedirs(dump_path, exist_ok=True)
     dump_path = dump_path / merged_model_name
@@ -113,7 +107,7 @@ def merge_diffusion_models_and_commit(
         model_name=merged_model_name, description=f'Merge of models {", ".join(models)}'
     )
     if vae := model_manager.config[models[0]].get("vae", None):
-        print(f">> Using configured VAE assigned to {models[0]}")
+        logger.info(f"Using configured VAE assigned to {models[0]}")
         import_args.update(vae=vae)
     model_manager.import_diffuser_model(dump_path, **import_args)
     model_manager.commit(config_file)
@@ -124,7 +118,7 @@ def _parse_args() -> Namespace:
     parser.add_argument(
         "--root_dir",
         type=Path,
-        default=Globals.root,
+        default=config.root,
         help="Path to the invokeai runtime directory",
     )
     parser.add_argument(
@@ -391,14 +385,12 @@ class mergeModelsForm(npyscreen.FormMultiPageAction):
             for name in self.model_manager.model_names()
             if self.model_manager.model_info(name).get("format") == "diffusers"
         ]
-        print(model_names)
         return sorted(model_names)
 
-
 class Mergeapp(npyscreen.NPSAppManaged):
     def __init__(self):
         super().__init__()
-        conf = OmegaConf.load(global_config_file())
+        conf = OmegaConf.load(config.model_conf_path)
         self.model_manager = ModelManager(
             conf, "cpu", "float16"
         )  # precision doesn't really matter here
@@ -414,7 +406,7 @@ def run_gui(args: Namespace):
 
     args = mergeapp.merge_arguments
     merge_diffusion_models_and_commit(**args)
-    print(f'>> Models merged into new model: "{args["merged_model_name"]}".')
+    logger.info(f'Models merged into new model: "{args["merged_model_name"]}".')
 
 
 def run_cli(args: Namespace):
@@ -425,24 +417,24 @@ def run_cli(args: Namespace):
 
     if not args.merged_model_name:
         args.merged_model_name = "+".join(args.models)
-        print(
-            f'>> No --merged_model_name provided. Defaulting to "{args.merged_model_name}"'
+        logger.info(
+            f'No --merged_model_name provided. Defaulting to "{args.merged_model_name}"'
         )
 
-        model_manager = ModelManager(OmegaConf.load(global_config_file()))
+        model_manager = ModelManager(OmegaConf.load(config.model_conf_path))
         assert (
             args.clobber or args.merged_model_name not in model_manager.model_names()
         ), f'A model named "{args.merged_model_name}" already exists. Use --clobber to overwrite.'
 
         merge_diffusion_models_and_commit(**vars(args))
-        print(f'>> Models merged into new model: "{args.merged_model_name}".')
+        logger.info(f'Models merged into new model: "{args.merged_model_name}".')
 
 
 def main():
     args = _parse_args()
-    global_set_root(args.root_dir)
+    config.root = args.root_dir
 
-    cache_dir = str(global_cache_dir("hub"))
+    cache_dir = config.cache_dir
     os.environ[
         "HF_HOME"
     ] = cache_dir  # because not clear the merge pipeline is honoring cache_dir
@@ -455,17 +447,16 @@ def main():
             run_cli(args)
     except widget.NotEnoughSpaceForWidget as e:
         if str(e).startswith("Height of 1 allocated"):
-            print(
-                "** You need to have at least two diffusers models defined in models.yaml in order to merge"
+            logger.error(
+                "You need to have at least two diffusers models defined in models.yaml in order to merge"
             )
         else:
-            print(
-                "** Not enough room for the user interface. Try making this window larger."
+            logger.error(
+                "Not enough room for the user interface. Try making this window larger."
             )
         sys.exit(-1)
-    except Exception:
-        print(">> An error occurred:")
-        traceback.print_exc()
+    except Exception as e:
+        logger.error(e)
         sys.exit(-1)
     except KeyboardInterrupt:
         sys.exit(-1)

invokeai/frontend/training/textual_inversion.py

@@ -20,14 +20,18 @@ import npyscreen
 from npyscreen import widget
 from omegaconf import OmegaConf
 
-from invokeai.backend.globals import Globals, global_set_root
+import invokeai.backend.util.logging as logger
 
-from ...backend.training import do_textual_inversion_training, parse_args
+from invokeai.app.services.config import get_invokeai_config
+from ...backend.training import (
+    do_textual_inversion_training,
+    parse_args
+)
 
 TRAINING_DATA = "text-inversion-training-data"
 TRAINING_DIR = "text-inversion-output"
 CONF_FILE = "preferences.conf"
-
+config = None
 
 class textualInversionForm(npyscreen.FormMultiPageAction):
     resolutions = [512, 768, 1024]
@@ -121,7 +125,7 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
             value=str(
                 saved_args.get(
                     "train_data_dir",
-                    Path(Globals.root) / TRAINING_DATA / default_placeholder_token,
+                    config.root_dir / TRAINING_DATA / default_placeholder_token,
                 )
             ),
             scroll_exit=True,
@@ -134,7 +138,7 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
             value=str(
                 saved_args.get(
                     "output_dir",
-                    Path(Globals.root) / TRAINING_DIR / default_placeholder_token,
+                    config.root_dir / TRAINING_DIR / default_placeholder_token,
                 )
             ),
             scroll_exit=True,
@@ -240,9 +244,9 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
         placeholder = self.placeholder_token.value
         self.prompt_token.value = f"(Trigger by using <{placeholder}> in your prompts)"
         self.train_data_dir.value = str(
-            Path(Globals.root) / TRAINING_DATA / placeholder
+            config.root_dir / TRAINING_DATA / placeholder
         )
-        self.output_dir.value = str(Path(Globals.root) / TRAINING_DIR / placeholder)
+        self.output_dir.value = str(config.root_dir / TRAINING_DIR / placeholder)
         self.resume_from_checkpoint.value = Path(self.output_dir.value).exists()
 
     def on_ok(self):
@@ -283,7 +287,7 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
             return True
 
     def get_model_names(self) -> Tuple[List[str], int]:
-        conf = OmegaConf.load(os.path.join(Globals.root, "configs/models.yaml"))
+        conf = OmegaConf.load(config.root_dir / "configs/models.yaml")
         model_names = [
             idx
             for idx in sorted(list(conf.keys()))
@@ -366,23 +370,23 @@ def copy_to_embeddings_folder(args: dict):
     """
     source = Path(args["output_dir"], "learned_embeds.bin")
     dest_dir_name = args["placeholder_token"].strip("<>")
-    destination = Path(Globals.root, "embeddings", dest_dir_name)
+    destination = config.root_dir / "embeddings" / dest_dir_name
     os.makedirs(destination, exist_ok=True)
-    print(f">> Training completed. Copying learned_embeds.bin into {str(destination)}")
+    logger.info(f"Training completed. Copying learned_embeds.bin into {str(destination)}")
     shutil.copy(source, destination)
     if (
         input("Delete training logs and intermediate checkpoints? [y] ") or "y"
     ).startswith(("y", "Y")):
         shutil.rmtree(Path(args["output_dir"]))
     else:
-        print(f'>> Keeping {args["output_dir"]}')
+        logger.info(f'Keeping {args["output_dir"]}')
 
 
 def save_args(args: dict):
     """
     Save the current argument values to an omegaconf file
     """
-    dest_dir = Path(Globals.root) / TRAINING_DIR
+    dest_dir = config.root_dir / TRAINING_DIR
     os.makedirs(dest_dir, exist_ok=True)
     conf_file = dest_dir / CONF_FILE
     conf = OmegaConf.create(args)
@@ -393,7 +397,7 @@ def previous_args() -> dict:
     """
     Get the previous arguments used.
     """
-    conf_file = Path(Globals.root) / TRAINING_DIR / CONF_FILE
+    conf_file = config.root_dir / TRAINING_DIR / CONF_FILE
     try:
         conf = OmegaConf.load(conf_file)
         conf["placeholder_token"] = conf["placeholder_token"].strip("<>")
@@ -419,39 +423,46 @@ def do_front_end(args: Namespace):
         save_args(args)
 
         try:
-            do_textual_inversion_training(**args)
+            do_textual_inversion_training(get_invokeai_config(),**args)
             copy_to_embeddings_folder(args)
         except Exception as e:
-            print("** An exception occurred during training. The exception was:")
-            print(str(e))
-            print("** DETAILS:")
-            print(traceback.format_exc())
+            logger.error("An exception occurred during training. The exception was:")
+            logger.error(str(e))
+            logger.error("DETAILS:")
+            logger.error(traceback.format_exc())
 
 
 def main():
+    global config
+    
     args = parse_args()
-    global_set_root(args.root_dir or Globals.root)
+    config = get_invokeai_config(argv=[])
+
+    # change root if needed
+    if args.root_dir:
+        config.root = args.root_dir
+    
     try:
         if args.front_end:
             do_front_end(args)
         else:
-            do_textual_inversion_training(**vars(args))
+            do_textual_inversion_training(config,**vars(args))
     except AssertionError as e:
-        print(str(e))
+        logger.error(e)
         sys.exit(-1)
     except KeyboardInterrupt:
         pass
     except (widget.NotEnoughSpaceForWidget, Exception) as e:
         if str(e).startswith("Height of 1 allocated"):
-            print(
-                "** You need to have at least one diffusers models defined in models.yaml in order to train"
+            logger.error(
+                "You need to have at least one diffusers models defined in models.yaml in order to train"
             )
         elif str(e).startswith("addwstr"):
-            print(
-                "** Not enough window space for the interface. Please make your window larger and try again."
+            logger.error(
+                "Not enough window space for the interface. Please make your window larger and try again."
             )
         else:
-            print(f"** An error has occurred: {str(e)}")
+            logger.error(e)
         sys.exit(-1)
 
 

invokeai/frontend/web/.babelrc

@@ -1,13 +0,0 @@
-{
-  "plugins": [
-    [
-      "transform-imports",
-      {
-        "lodash": {
-          "transform": "lodash/${member}",
-          "preventFullImport": true
-        }
-      }
-    ]
-  ]
-}

invokeai/frontend/web/.gitignore

@@ -34,4 +34,8 @@ stats.html
 !.yarn/plugins
 !.yarn/releases
 !.yarn/sdks
-!.yarn/versions
+!.yarn/versions
+
+# Yalc
+.yalc
+yalc.lock

invokeai/frontend/web/config/vite.app.config.ts

@@ -0,0 +1,40 @@
+import react from '@vitejs/plugin-react-swc';
+import { visualizer } from 'rollup-plugin-visualizer';
+import { PluginOption, UserConfig } from 'vite';
+import eslint from 'vite-plugin-eslint';
+import tsconfigPaths from 'vite-tsconfig-paths';
+
+export const appConfig: UserConfig = {
+  base: './',
+  plugins: [
+    react(),
+    eslint(),
+    tsconfigPaths(),
+    visualizer() as unknown as PluginOption,
+  ],
+  build: {
+    chunkSizeWarningLimit: 1500,
+  },
+  server: {
+    // Proxy HTTP requests to the flask server
+    proxy: {
+      // Proxy socket.io to the nodes socketio server
+      '/ws/socket.io': {
+        target: 'ws://127.0.0.1:9090',
+        ws: true,
+      },
+      // Proxy openapi schema definiton
+      '/openapi.json': {
+        target: 'http://127.0.0.1:9090/openapi.json',
+        rewrite: (path) => path.replace(/^\/openapi.json/, ''),
+        changeOrigin: true,
+      },
+      // proxy nodes api
+      '/api/v1': {
+        target: 'http://127.0.0.1:9090/api/v1',
+        rewrite: (path) => path.replace(/^\/api\/v1/, ''),
+        changeOrigin: true,
+      },
+    },
+  },
+};

invokeai/frontend/web/config/vite.package.config.ts

@@ -0,0 +1,50 @@
+import react from '@vitejs/plugin-react-swc';
+import path from 'path';
+import { visualizer } from 'rollup-plugin-visualizer';
+import { PluginOption, UserConfig } from 'vite';
+import dts from 'vite-plugin-dts';
+import eslint from 'vite-plugin-eslint';
+import tsconfigPaths from 'vite-tsconfig-paths';
+import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js';
+
+export const packageConfig: UserConfig = {
+  base: './',
+  plugins: [
+    react(),
+    eslint(),
+    tsconfigPaths(),
+    visualizer() as unknown as PluginOption,
+    dts({
+      insertTypesEntry: true,
+    }),
+    cssInjectedByJsPlugin(),
+  ],
+  build: {
+    cssCodeSplit: true,
+    lib: {
+      entry: path.resolve(__dirname, '../src/index.ts'),
+      name: 'InvokeAIUI',
+      fileName: (format) => `invoke-ai-ui.${format}.js`,
+    },
+    rollupOptions: {
+      external: ['react', 'react-dom', '@emotion/react'],
+      output: {
+        globals: {
+          react: 'React',
+          'react-dom': 'ReactDOM',
+          '@emotion/react': 'EmotionReact',
+        },
+      },
+    },
+  },
+  resolve: {
+    alias: {
+      app: path.resolve(__dirname, '../src/app'),
+      assets: path.resolve(__dirname, '../src/assets'),
+      common: path.resolve(__dirname, '../src/common'),
+      features: path.resolve(__dirname, '../src/features'),
+      services: path.resolve(__dirname, '../src/services'),
+      theme: path.resolve(__dirname, '../src/theme'),
+    },
+  },
+};

invokeai/frontend/web/docs/PACKAGE_SCRIPTS.md

@@ -15,15 +15,3 @@ The `postinstall` script patches a few packages and runs the Chakra CLI to gener
 ### Patch `@chakra-ui/cli`
 
 See: <https://github.com/chakra-ui/chakra-ui/issues/7394>
-
-### Patch `redux-persist`
-
-We want to persist the canvas state to `localStorage` but many canvas operations change data very quickly, so we need to debounce the writes to `localStorage`.
-
-`redux-persist` is unfortunately unmaintained. The repo's current code is nonfunctional, but the last release's code depends on a package that was removed from `npm` for being malware, so we cannot just fork it.
-
-So, we have to patch it directly. Perhaps a better way would be to write a debounced storage adapter, but I couldn't figure out how to do that.
-
-### Patch `redux-deep-persist`
-
-This package makes blacklisting and whitelisting persist configs very simple, but we have to patch it to match `redux-persist` for the types to work.

invokeai/frontend/web/docs/README.md

@@ -37,7 +37,7 @@ From `invokeai/frontend/web/` run `yarn install` to get everything set up.
 Start everything in dev mode:
 
 1. Start the dev server: `yarn dev`
-2. Start the InvokeAI UI per usual: `invokeai --web`
+2. Start the InvokeAI Nodes backend: `python scripts/invokeai-new.py --web # run from the repo root`
 3. Point your browser to the dev server address e.g. <http://localhost:5173/>
 
 ### Production builds

invokeai/frontend/web/index.d.ts

@@ -1,97 +0,0 @@
-import React, { PropsWithChildren } from 'react';
-import { IAIPopoverProps } from '../web/src/common/components/IAIPopover';
-import { IAIIconButtonProps } from '../web/src/common/components/IAIIconButton';
-import { InvokeTabName } from 'features/ui/store/tabMap';
-
-export {};
-
-declare module 'redux-socket.io-middleware';
-
-declare global {
-  /* eslint-disable @typescript-eslint/no-explicit-any */
-  interface Array<T> {
-    /**
-     * Returns the value of the last element in the array where predicate is true, and undefined
-     * otherwise.
-     * @param predicate findLast calls predicate once for each element of the array, in descending
-     * order, until it finds one where predicate returns true. If such an element is found, findLast
-     * immediately returns that element value. Otherwise, findLast returns undefined.
-     * @param thisArg If provided, it will be used as the this value for each invocation of
-     * predicate. If it is not provided, undefined is used instead.
-     */
-    findLast<S extends T>(
-      predicate: (value: T, index: number, array: T[]) => value is S,
-      thisArg?: any
-    ): S | undefined;
-    findLast(
-      predicate: (value: T, index: number, array: T[]) => unknown,
-      thisArg?: any
-    ): T | undefined;
-
-    /**
-     * Returns the index of the last element in the array where predicate is true, and -1
-     * otherwise.
-     * @param predicate findLastIndex calls predicate once for each element of the array, in descending
-     * order, until it finds one where predicate returns true. If such an element is found,
-     * findLastIndex immediately returns that element index. Otherwise, findLastIndex returns -1.
-     * @param thisArg If provided, it will be used as the this value for each invocation of
-     * predicate. If it is not provided, undefined is used instead.
-     */
-    findLastIndex(
-      predicate: (value: T, index: number, array: T[]) => unknown,
-      thisArg?: any
-    ): number;
-  }
-  /* eslint-enable @typescript-eslint/no-explicit-any */
-}
-
-declare module '@invoke-ai/invoke-ai-ui' {
-  declare class ThemeChanger extends React.Component<ThemeChangerProps> {
-    public constructor(props: ThemeChangerProps);
-  }
-
-  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 class StatusIndicator extends React.Component<StatusIndicatorProps> {
-    public constructor(props: StatusIndicatorProps);
-  }
-
-  declare class ModelSelect extends React.Component<ModelSelectProps> {
-    public constructor(props: ModelSelectProps);
-  }
-}
-
-interface InvokeProps extends PropsWithChildren {
-  apiUrl?: string;
-  disabledPanels?: string[];
-  disabledTabs?: InvokeTabName[];
-  token?: string;
-  shouldTransformUrls?: boolean;
-}
-
-declare function Invoke(props: InvokeProps): JSX.Element;
-
-export {
-  ThemeChanger,
-  InvokeAiLogoComponent,
-  IAIPopover,
-  IAIIconButton,
-  SettingsModal,
-  StatusIndicator,
-  ModelSelect,
-};
-export = Invoke;

invokeai/frontend/web/package.json

@@ -1,11 +1,27 @@
 {
-  "name": "invoke-ai-ui",
+  "name": "@invoke-ai/invoke-ai-ui",
   "private": true,
   "version": "0.0.1",
+  "publishConfig": {
+    "access": "restricted",
+    "registry": "https://npm.pkg.github.com"
+  },
+  "main": "./dist/invoke-ai-ui.umd.js",
+  "module": "./dist/invoke-ai-ui.es.js",
+  "exports": {
+    ".": {
+      "import": "./dist/invoke-ai-ui.es.js",
+      "require": "./dist/invoke-ai-ui.umd.js"
+    }
+  },
+  "types": "./dist/index.d.ts",
+  "files": [
+    "dist"
+  ],
   "scripts": {
     "prepare": "cd ../../../ && husky install invokeai/frontend/web/.husky",
     "dev": "concurrently \"vite dev\" \"yarn run theme:watch\"",
-    "dev:nodes": "concurrently \"vite dev --mode nodes\" \"yarn run theme:watch\"",
+    "dev:host": "concurrently \"vite dev --host\" \"yarn run theme:watch\"",
     "build": "yarn run lint && vite build",
     "api:web": "openapi -i http://localhost:9090/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --exportSchemas true --indent 2 --request src/services/fixtures/request.ts",
     "api:file": "openapi -i src/services/fixtures/openapi.json -o src/services/api --client axios --useOptions --useUnionTypes --exportSchemas true --indent 2 --request src/services/fixtures/request.ts",
@@ -39,79 +55,97 @@
   },
   "dependencies": {
     "@chakra-ui/anatomy": "^2.1.1",
-    "@chakra-ui/cli": "^2.3.0",
-    "@chakra-ui/icons": "^2.0.17",
-    "@chakra-ui/react": "^2.5.1",
-    "@chakra-ui/styled-system": "^2.6.1",
+    "@chakra-ui/icons": "^2.0.19",
+    "@chakra-ui/react": "^2.6.0",
+    "@chakra-ui/styled-system": "^2.9.0",
     "@chakra-ui/theme-tools": "^2.0.16",
     "@dagrejs/graphlib": "^2.1.12",
     "@emotion/react": "^11.10.6",
     "@emotion/styled": "^11.10.6",
+    "@floating-ui/react-dom": "^2.0.0",
     "@fontsource/inter": "^4.5.15",
-    "@reduxjs/toolkit": "^1.9.3",
+    "@reduxjs/toolkit": "^1.9.5",
+    "@roarr/browser-log-writer": "^1.1.5",
     "chakra-ui-contextmenu": "^1.0.5",
     "dateformat": "^5.0.3",
+    "downshift": "^7.6.0",
     "formik": "^2.2.9",
-    "framer-motion": "^9.0.4",
-    "i18next": "^22.4.10",
+    "framer-motion": "^10.12.4",
+    "fuse.js": "^6.6.2",
+    "i18next": "^22.4.15",
     "i18next-browser-languagedetector": "^7.0.1",
-    "i18next-http-backend": "^2.1.1",
-    "konva": "^8.4.2",
-    "lodash": "^4.17.21",
-    "patch-package": "^6.5.1",
+    "i18next-http-backend": "^2.2.0",
+    "konva": "^9.0.1",
+    "lodash-es": "^4.17.21",
+    "overlayscrollbars": "^2.1.1",
+    "overlayscrollbars-react": "^0.5.0",
+    "patch-package": "^7.0.0",
     "re-resizable": "^6.9.9",
     "react": "^18.2.0",
     "react-colorful": "^5.6.1",
     "react-dom": "^18.2.0",
     "react-dropzone": "^14.2.3",
-    "react-hotkeys-hook": "4.3.5",
-    "react-i18next": "^12.1.5",
+    "react-hotkeys-hook": "4.4.0",
+    "react-i18next": "^12.2.2",
     "react-icons": "^4.7.1",
-    "react-konva": "^18.2.4",
-    "react-konva-utils": "^0.3.2",
+    "react-konva": "^18.2.7",
     "react-redux": "^8.0.5",
-    "react-transition-group": "^4.4.5",
-    "react-zoom-pan-pinch": "^2.6.1",
+    "react-resizable-panels": "^0.0.42",
+    "react-use": "^17.4.0",
+    "react-virtuoso": "^4.3.5",
+    "react-zoom-pan-pinch": "^3.0.7",
     "reactflow": "^11.7.0",
-    "redux-deep-persist": "^1.0.7",
     "redux-dynamic-middlewares": "^2.2.0",
-    "redux-persist": "^6.0.0",
+    "redux-remember": "^3.3.1",
+    "roarr": "^7.15.0",
+    "serialize-error": "^11.0.0",
     "socket.io-client": "^4.6.0",
     "use-image": "^1.1.0",
     "uuid": "^9.0.0"
   },
+  "peerDependencies": {
+    "@chakra-ui/cli": "^2.4.0",
+    "react": "^18.2.0",
+    "react-dom": "^18.2.0",
+    "ts-toolbelt": "^9.6.0"
+  },
   "devDependencies": {
+    "@chakra-ui/cli": "^2.4.0",
     "@types/dateformat": "^5.0.0",
-    "@types/lodash": "^4.14.194",
-    "@types/react": "^18.0.28",
-    "@types/react-dom": "^18.0.11",
+    "@types/lodash-es": "^4.14.194",
+    "@types/node": "^18.16.2",
+    "@types/react": "^18.2.0",
+    "@types/react-dom": "^18.2.1",
+    "@types/react-redux": "^7.1.25",
     "@types/react-transition-group": "^4.4.5",
     "@types/uuid": "^9.0.0",
-    "@typescript-eslint/eslint-plugin": "^5.52.0",
-    "@typescript-eslint/parser": "^5.52.0",
-    "@vitejs/plugin-react-swc": "^3.2.0",
-    "axios": "^1.3.4",
+    "@typescript-eslint/eslint-plugin": "^5.59.1",
+    "@typescript-eslint/parser": "^5.59.1",
+    "@vitejs/plugin-react-swc": "^3.3.0",
+    "axios": "^1.4.0",
     "babel-plugin-transform-imports": "^2.0.0",
-    "concurrently": "^7.6.0",
-    "eslint": "^8.34.0",
-    "eslint-config-prettier": "^8.6.0",
+    "concurrently": "^8.0.1",
+    "eslint": "^8.39.0",
+    "eslint-config-prettier": "^8.8.0",
     "eslint-plugin-prettier": "^4.2.1",
     "eslint-plugin-react": "^7.32.2",
     "eslint-plugin-react-hooks": "^4.6.0",
     "form-data": "^4.0.0",
     "husky": "^8.0.3",
-    "lint-staged": "^13.1.2",
+    "lint-staged": "^13.2.2",
     "madge": "^6.0.0",
     "openapi-types": "^12.1.0",
-    "openapi-typescript-codegen": "^0.23.0",
+    "openapi-typescript-codegen": "^0.24.0",
     "postinstall-postinstall": "^2.1.0",
-    "prettier": "^2.8.4",
+    "prettier": "^2.8.8",
     "rollup-plugin-visualizer": "^5.9.0",
-    "terser": "^5.16.4",
-    "typescript": "4.9.5",
-    "vite": "^4.1.2",
+    "terser": "^5.17.1",
+    "ts-toolbelt": "^9.6.0",
+    "vite": "^4.3.3",
+    "vite-plugin-css-injected-by-js": "^3.1.1",
+    "vite-plugin-dts": "^2.3.0",
     "vite-plugin-eslint": "^1.8.1",
-    "vite-tsconfig-paths": "^4.0.5",
+    "vite-tsconfig-paths": "^4.2.0",
     "yarn": "^1.22.19"
   }
 }

invokeai/frontend/web/patches/redux-deep-persist+1.0.7.patch

@@ -1,24 +0,0 @@
-diff --git a/node_modules/redux-deep-persist/lib/types.d.ts b/node_modules/redux-deep-persist/lib/types.d.ts
-index b67b8c2..7fc0fa1 100644
---- a/node_modules/redux-deep-persist/lib/types.d.ts
-+++ b/node_modules/redux-deep-persist/lib/types.d.ts
-@@ -35,6 +35,7 @@ export interface PersistConfig<S, RS = any, HSS = any, ESS = any> {
-     whitelist?: Array<string>;
-     transforms?: Array<Transform<HSS, ESS, S, RS>>;
-     throttle?: number;
-+    debounce?: number;
-     migrate?: PersistMigrate;
-     stateReconciler?: false | StateReconciler<S>;
-     getStoredState?: (config: PersistConfig<S, RS, HSS, ESS>) => Promise<PersistedState>;
-diff --git a/node_modules/redux-deep-persist/src/types.ts b/node_modules/redux-deep-persist/src/types.ts
-index 398ac19..cbc5663 100644
---- a/node_modules/redux-deep-persist/src/types.ts
-+++ b/node_modules/redux-deep-persist/src/types.ts
-@@ -91,6 +91,7 @@ export interface PersistConfig<S, RS = any, HSS = any, ESS = any> {
-     whitelist?: Array<string>;
-     transforms?: Array<Transform<HSS, ESS, S, RS>>;
-     throttle?: number;
-+    debounce?: number;
-     migrate?: PersistMigrate;
-     stateReconciler?: false | StateReconciler<S>;
-     /**