InvokeAI/invokeai/app/invocations/cv.py
psychedelicious a1773197e9 feat(nodes): remove image_origin from most places
- remove `image_origin` from most places where we interact with images
- consolidate image file storage into a single `images/` dir

Images have an `image_origin` attribute but it is not actually used when retrieving images, nor will it ever be. It is still used when creating images and helps to differentiate between internally generated images and uploads.

It was included in eg API routes and image service methods as a holdover from the previous app implementation where images were not managed in a database. Now that we have images in a db, we can do away with this and simplify basically everything that touches images.

The one potentially controversial change is to no longer separate internal and external images on disk. If we retain this separation, we have to keep `image_origin` around in a number of spots and it getting image paths on disk painful.

So, I am have gotten rid of this organisation. Images are now all stored in `images`, regardless of their origin. As we improve the image management features, this change will hopefully become transparent.
2023-06-14 23:08:27 +10:00

68 lines
2.2 KiB
Python

# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
from typing import Literal
import cv2 as cv
import numpy
from PIL import Image, ImageOps
from pydantic import BaseModel, Field
from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
from .baseinvocation import BaseInvocation, InvocationContext, InvocationConfig
from .image import ImageOutput
class CvInvocationConfig(BaseModel):
"""Helper class to provide all OpenCV invocations with additional config"""
# Schema customisation
class Config(InvocationConfig):
schema_extra = {
"ui": {
"tags": ["cv", "image"],
},
}
class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
"""Simple inpaint using opencv."""
# fmt: off
type: Literal["cv_inpaint"] = "cv_inpaint"
# Inputs
image: ImageField = Field(default=None, description="The image to inpaint")
mask: ImageField = Field(default=None, description="The mask to use when inpainting")
# fmt: on
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
mask = context.services.images.get_pil_image(self.mask.image_name)
# Convert to cv image/mask
# TODO: consider making these utility functions
cv_image = cv.cvtColor(numpy.array(image.convert("RGB")), cv.COLOR_RGB2BGR)
cv_mask = numpy.array(ImageOps.invert(mask.convert("L")))
# Inpaint
cv_inpainted = cv.inpaint(cv_image, cv_mask, 3, cv.INPAINT_TELEA)
# Convert back to Pillow
# TODO: consider making a utility function
image_inpainted = Image.fromarray(cv.cvtColor(cv_inpainted, cv.COLOR_BGR2RGB))
image_dto = context.services.images.create(
image=image_inpainted,
image_origin=ResourceOrigin.INTERNAL,
image_category=ImageCategory.GENERAL,
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
)
return ImageOutput(
image=ImageField(image_name=image_dto.image_name),
width=image_dto.width,
height=image_dto.height,
)