Merge branch 'main' into lstein/feat/multi-gpu

Author: lstein

README.md

@@ -51,13 +51,11 @@ The settings in this file will override the defaults. You only need
 to change this file if the default for a particular setting doesn't
 work for you.
 
+You'll find an example file next to `invokeai.yaml` that shows the default values.
+
 Some settings, like [Model Marketplace API Keys], require the YAML
 to be formatted correctly. Here is a [basic guide to YAML files].
 
-You can fix a broken `invokeai.yaml` by deleting it and running the
-configuration script again -- option [6] in the launcher, "Re-run the
-configure script".
-
 #### Custom Config File Location
 
 You can use any config file with the `--config` CLI arg. Pass in the path to the `invokeai.yaml` file you want to use.

docs/features/CONFIGURATION.md

@@ -35,22 +35,16 @@
 from invokeai.app.invocations.primitives import ImageOutput
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES, heuristic_resize
 from invokeai.backend.image_util.canny import get_canny_edges
 from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
 from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
 from invokeai.backend.image_util.hed import HEDProcessor
 from invokeai.backend.image_util.lineart import LineartProcessor
 from invokeai.backend.image_util.lineart_anime import LineartAnimeProcessor
+from invokeai.backend.image_util.util import np_to_pil, pil_to_np
 
-from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
-
-CONTROLNET_MODE_VALUES = Literal["balanced", "more_prompt", "more_control", "unbalanced"]
-CONTROLNET_RESIZE_VALUES = Literal[
-    "just_resize",
-    "crop_resize",
-    "fill_resize",
-    "just_resize_simple",
-]
+from .baseinvocation import BaseInvocation, BaseInvocationOutput, Classification, invocation, invocation_output
 
 
 class ControlField(BaseModel):
@@ -641,3 +635,27 @@ def run_processor(self, image: Image.Image):
             resolution=self.image_resolution,
         )
         return processed_image
+
+
+@invocation(
+    "heuristic_resize",
+    title="Heuristic Resize",
+    tags=["image, controlnet"],
+    category="image",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class HeuristicResizeInvocation(BaseInvocation):
+    """Resize an image using a heuristic method. Preserves edge maps."""
+
+    image: ImageField = InputField(description="The image to resize")
+    width: int = InputField(default=512, gt=0, description="The width to resize to (px)")
+    height: int = InputField(default=512, gt=0, description="The height to resize to (px)")
+
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        image = context.images.get_pil(self.image.image_name, "RGB")
+        np_img = pil_to_np(image)
+        np_resized = heuristic_resize(np_img, (self.width, self.height))
+        resized = np_to_pil(np_resized)
+        image_dto = context.images.save(image=resized)
+        return ImageOutput.build(image_dto)

invokeai/app/invocations/controlnet_image_processors.py

@@ -51,6 +51,7 @@
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
 from invokeai.backend.lora import LoRAModelRaw
 from invokeai.backend.model_manager import BaseModelType, LoadedModel
+from invokeai.backend.model_manager.config import MainConfigBase, ModelVariantType
 from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
@@ -185,7 +186,7 @@ class GradientMaskOutput(BaseInvocationOutput):
     title="Create Gradient Mask",
     tags=["mask", "denoise"],
     category="latents",
-    version="1.0.0",
+    version="1.1.0",
 )
 class CreateGradientMaskInvocation(BaseInvocation):
     """Creates mask for denoising model run."""
@@ -198,6 +199,32 @@ class CreateGradientMaskInvocation(BaseInvocation):
     minimum_denoise: float = InputField(
         default=0.0, ge=0, le=1, description="Minimum denoise level for the coherence region", ui_order=4
     )
+    image: Optional[ImageField] = InputField(
+        default=None,
+        description="OPTIONAL: Only connect for specialized Inpainting models, masked_latents will be generated from the image with the VAE",
+        title="[OPTIONAL] Image",
+        ui_order=6,
+    )
+    unet: Optional[UNetField] = InputField(
+        description="OPTIONAL: If the Unet is a specialized Inpainting model, masked_latents will be generated from the image with the VAE",
+        default=None,
+        input=Input.Connection,
+        title="[OPTIONAL] UNet",
+        ui_order=5,
+    )
+    vae: Optional[VAEField] = InputField(
+        default=None,
+        description="OPTIONAL: Only connect for specialized Inpainting models, masked_latents will be generated from the image with the VAE",
+        title="[OPTIONAL] VAE",
+        input=Input.Connection,
+        ui_order=7,
+    )
+    tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=8)
+    fp32: bool = InputField(
+        default=DEFAULT_PRECISION == "float32",
+        description=FieldDescriptions.fp32,
+        ui_order=9,
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> GradientMaskOutput:
@@ -233,8 +260,27 @@ def invoke(self, context: InvocationContext) -> GradientMaskOutput:
         expanded_mask_image = Image.fromarray((expanded_mask.squeeze(0).numpy() * 255).astype(np.uint8), mode="L")
         expanded_image_dto = context.images.save(expanded_mask_image)
 
+        masked_latents_name = None
+        if self.unet is not None and self.vae is not None and self.image is not None:
+            # all three fields must be present at the same time
+            main_model_config = context.models.get_config(self.unet.unet.key)
+            assert isinstance(main_model_config, MainConfigBase)
+            if main_model_config.variant is ModelVariantType.Inpaint:
+                mask = blur_tensor
+                vae_info: LoadedModel = context.models.load(self.vae.vae)
+                image = context.images.get_pil(self.image.image_name)
+                image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+                if image_tensor.dim() == 3:
+                    image_tensor = image_tensor.unsqueeze(0)
+                img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+                masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
+                masked_latents = ImageToLatentsInvocation.vae_encode(
+                    vae_info, self.fp32, self.tiled, masked_image.clone()
+                )
+                masked_latents_name = context.tensors.save(tensor=masked_latents)
+
         return GradientMaskOutput(
-            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=None, gradient=True),
+            denoise_mask=DenoiseMaskField(mask_name=mask_name, masked_latents_name=masked_latents_name, gradient=True),
             expanded_mask_area=ImageField(image_name=expanded_image_dto.image_name),
         )
 
@@ -295,7 +341,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
     )
     steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
     cfg_scale: Union[float, List[float]] = InputField(
-        default=7.5, ge=1, description=FieldDescriptions.cfg_scale, title="CFG Scale"
+        default=7.5, description=FieldDescriptions.cfg_scale, title="CFG Scale"
     )
     denoising_start: float = InputField(
         default=0.0,
@@ -517,6 +563,11 @@ def get_conditioning_data(
             dtype=unet.dtype,
         )
 
+        if isinstance(self.cfg_scale, list):
+            assert (
+                len(self.cfg_scale) == self.steps
+            ), "cfg_scale (list) must have the same length as the number of steps"
+
         conditioning_data = TextConditioningData(
             uncond_text=uncond_text_embedding,
             cond_text=cond_text_embedding,

invokeai/app/invocations/latent.py

@@ -1,7 +1,8 @@
+import numpy as np
 import torch
 
-from invokeai.app.invocations.baseinvocation import BaseInvocation, InvocationContext, invocation
-from invokeai.app.invocations.fields import InputField, TensorField, WithMetadata
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, InvocationContext, invocation
+from invokeai.app.invocations.fields import ImageField, InputField, TensorField, WithMetadata
 from invokeai.app.invocations.primitives import MaskOutput
 
 
@@ -34,3 +35,86 @@ def invoke(self, context: InvocationContext) -> MaskOutput:
             width=self.width,
             height=self.height,
         )
+
+
+@invocation(
+    "alpha_mask_to_tensor",
+    title="Alpha Mask to Tensor",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.0",
+    classification=Classification.Beta,
+)
+class AlphaMaskToTensorInvocation(BaseInvocation):
+    """Convert a mask image to a tensor. Opaque regions are 1 and transparent regions are 0."""
+
+    image: ImageField = InputField(description="The mask image to convert.")
+    invert: bool = InputField(default=False, description="Whether to invert the mask.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        image = context.images.get_pil(self.image.image_name)
+        mask = torch.zeros((1, image.height, image.width), dtype=torch.bool)
+        if self.invert:
+            mask[0] = torch.tensor(np.array(image)[:, :, 3] == 0, dtype=torch.bool)
+        else:
+            mask[0] = torch.tensor(np.array(image)[:, :, 3] > 0, dtype=torch.bool)
+
+        return MaskOutput(
+            mask=TensorField(tensor_name=context.tensors.save(mask)),
+            height=mask.shape[1],
+            width=mask.shape[2],
+        )
+
+
+@invocation(
+    "invert_tensor_mask",
+    title="Invert Tensor Mask",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.0",
+    classification=Classification.Beta,
+)
+class InvertTensorMaskInvocation(BaseInvocation):
+    """Inverts a tensor mask."""
+
+    mask: TensorField = InputField(description="The tensor mask to convert.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        mask = context.tensors.load(self.mask.tensor_name)
+        inverted = ~mask
+
+        return MaskOutput(
+            mask=TensorField(tensor_name=context.tensors.save(inverted)),
+            height=inverted.shape[1],
+            width=inverted.shape[2],
+        )
+
+
+@invocation(
+    "image_mask_to_tensor",
+    title="Image Mask to Tensor",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.0",
+)
+class ImageMaskToTensorInvocation(BaseInvocation, WithMetadata):
+    """Convert a mask image to a tensor. Converts the image to grayscale and uses thresholding at the specified value."""
+
+    image: ImageField = InputField(description="The mask image to convert.")
+    cutoff: int = InputField(ge=0, le=255, description="Cutoff (<)", default=128)
+    invert: bool = InputField(default=False, description="Whether to invert the mask.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        image = context.images.get_pil(self.image.image_name, mode="L")
+
+        mask = torch.zeros((1, image.height, image.width), dtype=torch.bool)
+        if self.invert:
+            mask[0] = torch.tensor(np.array(image)[:, :] >= self.cutoff, dtype=torch.bool)
+        else:
+            mask[0] = torch.tensor(np.array(image)[:, :] < self.cutoff, dtype=torch.bool)
+
+        return MaskOutput(
+            mask=TensorField(tensor_name=context.tensors.save(mask)),
+            height=mask.shape[1],
+            width=mask.shape[2],
+        )

invokeai/app/invocations/mask.py

@@ -3,7 +3,6 @@
 from pydantic import BaseModel, ConfigDict, Field
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
-from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES
 from invokeai.app.invocations.fields import (
     FieldDescriptions,
     ImageField,
@@ -14,6 +13,7 @@
 )
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES
 
 from ...version import __version__
 

invokeai/app/invocations/metadata.py

@@ -8,11 +8,11 @@
     invocation,
     invocation_output,
 )
-from invokeai.app.invocations.controlnet_image_processors import CONTROLNET_RESIZE_VALUES
 from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, OutputField, UIType
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
 from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.app.util.controlnet_utils import CONTROLNET_RESIZE_VALUES
 
 
 class T2IAdapterField(BaseModel):

invokeai/app/invocations/t2i_adapter.py

@@ -318,10 +318,8 @@ def _do_download(self, job: DownloadJob) -> None:
         in_progress_path.rename(job.download_path)
 
     def _validate_filename(self, directory: str, filename: str) -> bool:
-        pc_name_max = os.pathconf(directory, "PC_NAME_MAX") if hasattr(os, "pathconf") else 260  # hardcoded for windows
-        pc_path_max = (
-            os.pathconf(directory, "PC_PATH_MAX") if hasattr(os, "pathconf") else 32767
-        )  # hardcoded for windows with long names enabled
+        pc_name_max = get_pc_name_max(directory)
+        pc_path_max = get_pc_path_max(directory)
         if "/" in filename:
             return False
         if filename.startswith(".."):
@@ -419,6 +417,26 @@ def _cleanup_cancelled_job(self, job: DownloadJob) -> None:
             self._logger.warning(excp)
 
 
+def get_pc_name_max(directory: str) -> int:
+    if hasattr(os, "pathconf"):
+        try:
+            return os.pathconf(directory, "PC_NAME_MAX")
+        except OSError:
+            # macOS w/ external drives raise OSError
+            pass
+    return 260  # hardcoded for windows
+
+
+def get_pc_path_max(directory: str) -> int:
+    if hasattr(os, "pathconf"):
+        try:
+            return os.pathconf(directory, "PC_PATH_MAX")
+        except OSError:
+            # some platforms may not have this value
+            pass
+    return 32767  # hardcoded for windows with long names enabled
+
+
 # Example on_progress event handler to display a TQDM status bar
 # Activate with:
 #   download_service.download(DownloadJob('http://foo.bar/baz', '/tmp', on_progress=TqdmProgress().update))

invokeai/app/services/download/download_default.py

@@ -3,7 +3,6 @@
 import locale
 import os
 import re
-import signal
 import threading
 import time
 from hashlib import sha256
@@ -43,6 +42,7 @@
 from invokeai.backend.model_manager.probe import ModelProbe
 from invokeai.backend.model_manager.search import ModelSearch
 from invokeai.backend.util import InvokeAILogger
+from invokeai.backend.util.catch_sigint import catch_sigint
 from invokeai.backend.util.devices import TorchDevice
 
 from .model_install_base import (
@@ -112,17 +112,6 @@ def event_bus(self) -> Optional[EventServiceBase]:  # noqa D102
     def start(self, invoker: Optional[Invoker] = None) -> None:
         """Start the installer thread."""
 
-        # Yes, this is weird. When the installer thread is running, the
-        # thread masks the ^C signal. When we receive a
-        # sigINT, we stop the thread, reset sigINT, and send a new
-        # sigINT to the parent process.
-        def sigint_handler(signum, frame):
-            self.stop()
-            signal.signal(signal.SIGINT, signal.SIG_DFL)
-            signal.raise_signal(signal.SIGINT)
-
-        signal.signal(signal.SIGINT, sigint_handler)
-
         with self._lock:
             if self._running:
                 raise Exception("Attempt to start the installer service twice")
@@ -132,7 +121,8 @@ def sigint_handler(signum, frame):
             # In normal use, we do not want to scan the models directory - it should never have orphaned models.
             # We should only do the scan when the flag is set (which should only be set when testing).
             if self.app_config.scan_models_on_startup:
-                self._register_orphaned_models()
+                with catch_sigint():
+                    self._register_orphaned_models()
 
             # Check all models' paths and confirm they exist. A model could be missing if it was installed on a volume
             # that isn't currently mounted. In this case, we don't want to delete the model from the database, but we do