mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
545d8968fd
build(ui): fix husky path build(ui): fix hmr issue, remove emotion cache build(ui): clean up package.json build(ui): update gh action and npm scripts feat(ui): wip port lightbox to chakra theme feat(ui): wip use chakra theme tokens feat(ui): Add status text to main loading spinner feat(ui): wip chakra theme tweaking feat(ui): simply iaisimplemenu button feat(ui): wip chakra theming feat(ui): Theme Management feat(ui): Add Ocean Blue Theme feat(ui): wip lightbox fix(ui): fix lightbox mouse feat(ui): set default theme variants feat(ui): model manager chakra theme chore(ui): lint feat(ui): remove last scss feat(ui): fix switch theme feat(ui): Theme Cleanup feat(ui): Stylize Search Models Found List feat(ui): hide scrollbars feat(ui): fix floating button position feat(ui): Scrollbar Styling fix broken scripts This PR fixes the following scripts: 1) Scripts that can be executed within the repo's scripts directory. Note that these are for development testing and are not intended to be exposed to the user. configure_invokeai.py - configuration dream.py - the legacy CLI images2prompt.py - legacy "dream prompt" retriever invoke-new.py - new nodes-based CLI invoke.py - the legacy CLI under another name make_models_markdown_table.py - a utility used during the release/doc process pypi_helper.py - another utility used during the release process sd-metadata.py - retrieve JSON-formatted metadata from a PNG file 2) Scripts that are installed by pip install. They get placed into the venv's PATH and are intended to be the official entry points: invokeai-node-cli - new nodes-based CLI invokeai-node-web - new nodes-based web server invokeai - legacy CLI invokeai-configure - install time configuration script invokeai-merge - model merging script invokeai-ti - textual inversion script invokeai-model-install - model installer invokeai-update - update script invokeai-metadata" - retrieve JSON-formatted metadata from PNG files protect invocations against black autoformatting deps: upgrade to diffusers 0.14, safetensors 0.3, transformers 4.26, accelerate 0.16
288 lines
10 KiB
Python
288 lines
10 KiB
Python
# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
|
|
|
|
from datetime import datetime, timezone
|
|
from typing import Literal, Optional
|
|
|
|
import numpy
|
|
from PIL import Image, ImageFilter, ImageOps
|
|
from pydantic import BaseModel, Field
|
|
|
|
from ..services.image_storage import ImageType
|
|
from ..services.invocation_services import InvocationServices
|
|
from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
|
|
|
|
|
|
class ImageField(BaseModel):
|
|
"""An image field used for passing image objects between invocations"""
|
|
|
|
image_type: str = Field(
|
|
default=ImageType.RESULT, description="The type of the image"
|
|
)
|
|
image_name: Optional[str] = Field(default=None, description="The name of the image")
|
|
|
|
|
|
class ImageOutput(BaseInvocationOutput):
|
|
"""Base class for invocations that output an image"""
|
|
#fmt: off
|
|
type: Literal["image"] = "image"
|
|
image: ImageField = Field(default=None, description="The output image")
|
|
#fmt: on
|
|
|
|
class MaskOutput(BaseInvocationOutput):
|
|
"""Base class for invocations that output a mask"""
|
|
#fmt: off
|
|
type: Literal["mask"] = "mask"
|
|
mask: ImageField = Field(default=None, description="The output mask")
|
|
#fomt: on
|
|
|
|
# TODO: this isn't really necessary anymore
|
|
class LoadImageInvocation(BaseInvocation):
|
|
"""Load an image from a filename and provide it as output."""
|
|
#fmt: off
|
|
type: Literal["load_image"] = "load_image"
|
|
|
|
# Inputs
|
|
image_type: ImageType = Field(description="The type of the image")
|
|
image_name: str = Field(description="The name of the image")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
return ImageOutput(
|
|
image=ImageField(image_type=self.image_type, image_name=self.image_name)
|
|
)
|
|
|
|
|
|
class ShowImageInvocation(BaseInvocation):
|
|
"""Displays a provided image, and passes it forward in the pipeline."""
|
|
|
|
type: Literal["show_image"] = "show_image"
|
|
|
|
# Inputs
|
|
image: ImageField = Field(default=None, description="The image to show")
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
if image:
|
|
image.show()
|
|
|
|
# TODO: how to handle failure?
|
|
|
|
return ImageOutput(
|
|
image=ImageField(
|
|
image_type=self.image.image_type, image_name=self.image.image_name
|
|
)
|
|
)
|
|
|
|
|
|
class CropImageInvocation(BaseInvocation):
|
|
"""Crops an image to a specified box. The box can be outside of the image."""
|
|
#fmt: off
|
|
type: Literal["crop"] = "crop"
|
|
|
|
# Inputs
|
|
image: ImageField = Field(default=None, description="The image to crop")
|
|
x: int = Field(default=0, description="The left x coordinate of the crop rectangle")
|
|
y: int = Field(default=0, description="The top y coordinate of the crop rectangle")
|
|
width: int = Field(default=512, gt=0, description="The width of the crop rectangle")
|
|
height: int = Field(default=512, gt=0, description="The height of the crop rectangle")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
|
|
image_crop = Image.new(
|
|
mode="RGBA", size=(self.width, self.height), color=(0, 0, 0, 0)
|
|
)
|
|
image_crop.paste(image, (-self.x, -self.y))
|
|
|
|
image_type = ImageType.INTERMEDIATE
|
|
image_name = context.services.images.create_name(
|
|
context.graph_execution_state_id, self.id
|
|
)
|
|
context.services.images.save(image_type, image_name, image_crop)
|
|
return ImageOutput(
|
|
image=ImageField(image_type=image_type, image_name=image_name)
|
|
)
|
|
|
|
|
|
class PasteImageInvocation(BaseInvocation):
|
|
"""Pastes an image into another image."""
|
|
#fmt: off
|
|
type: Literal["paste"] = "paste"
|
|
|
|
# Inputs
|
|
base_image: ImageField = Field(default=None, description="The base image")
|
|
image: ImageField = Field(default=None, description="The image to paste")
|
|
mask: Optional[ImageField] = Field(default=None, description="The mask to use when pasting")
|
|
x: int = Field(default=0, description="The left x coordinate at which to paste the image")
|
|
y: int = Field(default=0, description="The top y coordinate at which to paste the image")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
base_image = context.services.images.get(
|
|
self.base_image.image_type, self.base_image.image_name
|
|
)
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
mask = (
|
|
None
|
|
if self.mask is None
|
|
else ImageOps.invert(
|
|
services.images.get(self.mask.image_type, self.mask.image_name)
|
|
)
|
|
)
|
|
# TODO: probably shouldn't invert mask here... should user be required to do it?
|
|
|
|
min_x = min(0, self.x)
|
|
min_y = min(0, self.y)
|
|
max_x = max(base_image.width, image.width + self.x)
|
|
max_y = max(base_image.height, image.height + self.y)
|
|
|
|
new_image = Image.new(
|
|
mode="RGBA", size=(max_x - min_x, max_y - min_y), color=(0, 0, 0, 0)
|
|
)
|
|
new_image.paste(base_image, (abs(min_x), abs(min_y)))
|
|
new_image.paste(image, (max(0, self.x), max(0, self.y)), mask=mask)
|
|
|
|
image_type = ImageType.RESULT
|
|
image_name = context.services.images.create_name(
|
|
context.graph_execution_state_id, self.id
|
|
)
|
|
context.services.images.save(image_type, image_name, new_image)
|
|
return ImageOutput(
|
|
image=ImageField(image_type=image_type, image_name=image_name)
|
|
)
|
|
|
|
|
|
class MaskFromAlphaInvocation(BaseInvocation):
|
|
"""Extracts the alpha channel of an image as a mask."""
|
|
#fmt: off
|
|
type: Literal["tomask"] = "tomask"
|
|
|
|
# Inputs
|
|
image: ImageField = Field(default=None, description="The image to create the mask from")
|
|
invert: bool = Field(default=False, description="Whether or not to invert the mask")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> MaskOutput:
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
|
|
image_mask = image.split()[-1]
|
|
if self.invert:
|
|
image_mask = ImageOps.invert(image_mask)
|
|
|
|
image_type = ImageType.INTERMEDIATE
|
|
image_name = context.services.images.create_name(
|
|
context.graph_execution_state_id, self.id
|
|
)
|
|
context.services.images.save(image_type, image_name, image_mask)
|
|
return MaskOutput(mask=ImageField(image_type=image_type, image_name=image_name))
|
|
|
|
|
|
class BlurInvocation(BaseInvocation):
|
|
"""Blurs an image"""
|
|
|
|
#fmt: off
|
|
type: Literal["blur"] = "blur"
|
|
|
|
# Inputs
|
|
image: ImageField = Field(default=None, description="The image to blur")
|
|
radius: float = Field(default=8.0, ge=0, description="The blur radius")
|
|
blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
|
|
blur = (
|
|
ImageFilter.GaussianBlur(self.radius)
|
|
if self.blur_type == "gaussian"
|
|
else ImageFilter.BoxBlur(self.radius)
|
|
)
|
|
blur_image = image.filter(blur)
|
|
|
|
image_type = ImageType.INTERMEDIATE
|
|
image_name = context.services.images.create_name(
|
|
context.graph_execution_state_id, self.id
|
|
)
|
|
context.services.images.save(image_type, image_name, blur_image)
|
|
return ImageOutput(
|
|
image=ImageField(image_type=image_type, image_name=image_name)
|
|
)
|
|
|
|
|
|
class LerpInvocation(BaseInvocation):
|
|
"""Linear interpolation of all pixels of an image"""
|
|
#fmt: off
|
|
type: Literal["lerp"] = "lerp"
|
|
|
|
# Inputs
|
|
image: ImageField = Field(default=None, description="The image to lerp")
|
|
min: int = Field(default=0, ge=0, le=255, description="The minimum output value")
|
|
max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
|
|
image_arr = numpy.asarray(image, dtype=numpy.float32) / 255
|
|
image_arr = image_arr * (self.max - self.min) + self.max
|
|
|
|
lerp_image = Image.fromarray(numpy.uint8(image_arr))
|
|
|
|
image_type = ImageType.INTERMEDIATE
|
|
image_name = context.services.images.create_name(
|
|
context.graph_execution_state_id, self.id
|
|
)
|
|
context.services.images.save(image_type, image_name, lerp_image)
|
|
return ImageOutput(
|
|
image=ImageField(image_type=image_type, image_name=image_name)
|
|
)
|
|
|
|
|
|
class InverseLerpInvocation(BaseInvocation):
|
|
"""Inverse linear interpolation of all pixels of an image"""
|
|
#fmt: off
|
|
type: Literal["ilerp"] = "ilerp"
|
|
|
|
# Inputs
|
|
image: ImageField = Field(default=None, description="The image to lerp")
|
|
min: int = Field(default=0, ge=0, le=255, description="The minimum input value")
|
|
max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
|
|
#fmt: on
|
|
|
|
def invoke(self, context: InvocationContext) -> ImageOutput:
|
|
image = context.services.images.get(
|
|
self.image.image_type, self.image.image_name
|
|
)
|
|
|
|
image_arr = numpy.asarray(image, dtype=numpy.float32)
|
|
image_arr = (
|
|
numpy.minimum(
|
|
numpy.maximum(image_arr - self.min, 0) / float(self.max - self.min), 1
|
|
)
|
|
* 255
|
|
)
|
|
|
|
ilerp_image = Image.fromarray(numpy.uint8(image_arr))
|
|
|
|
image_type = ImageType.INTERMEDIATE
|
|
image_name = context.services.images.create_name(
|
|
context.graph_execution_state_id, self.id
|
|
)
|
|
context.services.images.save(image_type, image_name, ilerp_image)
|
|
return ImageOutput(
|
|
image=ImageField(image_type=image_type, image_name=image_name)
|
|
)
|