Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: String Param Node + titles and tags for all Nodes (#3819)

Browse Source 
## What type of PR is this? (check all applicable)

- [x] Feature
- [x] Optimization


## Have you discussed this change with the InvokeAI team?
- [ ] Yes
- [ ] No, because:

      
## Description


## Related Tickets & Documents

<!--
For pull requests that relate or close an issue, please include them
below. 

For example having the text: "closes #1234" would connect the current
pull
request to issue 1234.  And when we merge the pull request, Github will
automatically close the issue.
-->

- Related Issue #
- Closes #

## QA Instructions, Screenshots, Recordings

<!-- 
Please provide steps on how to test changes, any hardware or 
software specifications as well as any other pertinent information. 
-->

## Added/updated tests?

- [ ] Yes
- [ ] No : _please replace this line with details on why tests
      have not been included_

## [optional] Are there any post deployment tasks we need to perform?
This commit is contained in:
blessedcoolant 2023-07-19 03:55:34 +12:00 committed by GitHub
commit 3d4cef0099
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
16 changed files with 611 additions and 146 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
invokeai/app/invocations/collections.py
View File

@ -4,17 +4,12 @@ from typing import Literal
import numpy as np import numpy as np
from pydantic import Field, validator from pydantic import Field, validator
from invokeai.app.models.image import ImageField
from invokeai.app.models.image import ImageField
from invokeai.app.util.misc import SEED_MAX, get_random_seed from invokeai.app.util.misc import SEED_MAX, get_random_seed
from .baseinvocation import ( from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
BaseInvocation, InvocationConfig, InvocationContext, UIConfig)
InvocationConfig,
InvocationContext,
BaseInvocationOutput,
UIConfig,
)
class IntCollectionOutput(BaseInvocationOutput): class IntCollectionOutput(BaseInvocationOutput):
@ -32,7 +27,8 @@ class FloatCollectionOutput(BaseInvocationOutput):
type: Literal["float_collection"] = "float_collection" type: Literal["float_collection"] = "float_collection"
# Outputs # Outputs
collection: list[float] = Field(default=[], description="The float collection") collection: list[float] = Field(
default=[], description="The float collection")
class ImageCollectionOutput(BaseInvocationOutput): class ImageCollectionOutput(BaseInvocationOutput):
@ -41,7 +37,8 @@ class ImageCollectionOutput(BaseInvocationOutput):
type: Literal["image_collection"] = "image_collection" type: Literal["image_collection"] = "image_collection"
# Outputs # Outputs
collection: list[ImageField] = Field(default=[], description="The output images") collection: list[ImageField] = Field(
default=[], description="The output images")
class Config: class Config:
schema_extra = {"required": ["type", "collection"]} schema_extra = {"required": ["type", "collection"]}
@ -57,6 +54,14 @@ class RangeInvocation(BaseInvocation):
stop: int = Field(default=10, description="The stop of the range") stop: int = Field(default=10, description="The stop of the range")
step: int = Field(default=1, description="The step of the range") step: int = Field(default=1, description="The step of the range")
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Range",
"tags": ["range", "integer", "collection"]
},
}
@validator("stop") @validator("stop")
def stop_gt_start(cls, v, values): def stop_gt_start(cls, v, values):
if "start" in values and v <= values["start"]: if "start" in values and v <= values["start"]:
@ -79,10 +84,20 @@ class RangeOfSizeInvocation(BaseInvocation):
size: int = Field(default=1, description="The number of values") size: int = Field(default=1, description="The number of values")
step: int = Field(default=1, description="The step of the range") step: int = Field(default=1, description="The step of the range")
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Sized Range",
"tags": ["range", "integer", "size", "collection"]
},
}
def invoke(self, context: InvocationContext) -> IntCollectionOutput: def invoke(self, context: InvocationContext) -> IntCollectionOutput:
return IntCollectionOutput( return IntCollectionOutput(
collection=list(range(self.start, self.start + self.size, self.step)) collection=list(
) range(
self.start, self.start + self.size,
self.step)))
class RandomRangeInvocation(BaseInvocation): class RandomRangeInvocation(BaseInvocation):
@ -103,11 +118,21 @@ class RandomRangeInvocation(BaseInvocation):
default_factory=get_random_seed, default_factory=get_random_seed,
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Random Range",
"tags": ["range", "integer", "random", "collection"]
},
}
def invoke(self, context: InvocationContext) -> IntCollectionOutput: def invoke(self, context: InvocationContext) -> IntCollectionOutput:
rng = np.random.default_rng(self.seed) rng = np.random.default_rng(self.seed)
return IntCollectionOutput( return IntCollectionOutput(
collection=list(rng.integers(low=self.low, high=self.high, size=self.size)) collection=list(
) rng.integers(
low=self.low, high=self.high,
size=self.size)))
class ImageCollectionInvocation(BaseInvocation): class ImageCollectionInvocation(BaseInvocation):
@ -121,6 +146,7 @@ class ImageCollectionInvocation(BaseInvocation):
default=[], description="The image collection to load" default=[], description="The image collection to load"
) )
# fmt: on # fmt: on
def invoke(self, context: InvocationContext) -> ImageCollectionOutput: def invoke(self, context: InvocationContext) -> ImageCollectionOutput:
return ImageCollectionOutput(collection=self.images) return ImageCollectionOutput(collection=self.images)
@ -128,6 +154,7 @@ class ImageCollectionInvocation(BaseInvocation):
schema_extra = { schema_extra = {
"ui": { "ui": {
"type_hints": { "type_hints": {
"title": "Image Collection",
"images": "image_collection", "images": "image_collection",
} }
}, },

8
invokeai/app/invocations/compel.py
View File

@ -571,6 +571,14 @@ class ClipSkipInvocation(BaseInvocation):
clip: ClipField = Field(None, description="Clip to use") clip: ClipField = Field(None, description="Clip to use")
skipped_layers: int = Field(0, description="Number of layers to skip in text_encoder") skipped_layers: int = Field(0, description="Number of layers to skip in text_encoder")
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "CLIP Skip",
"tags": ["clip", "skip"]
},
}
def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput: def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
self.clip.skipped_layers += self.skipped_layers self.clip.skipped_layers += self.skipped_layers
return ClipSkipInvocationOutput( return ClipSkipInvocationOutput(

389
invokeai/app/invocations/controlnet_image_processors.py
View File

@ -1,43 +1,25 @@
# Invocations for ControlNet image preprocessors # Invocations for ControlNet image preprocessors
# initial implementation by Gregg Helt, 2023 # initial implementation by Gregg Helt, 2023
# heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux # heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
from builtins import float, bool from builtins import bool, float
from typing import Dict, List, Literal, Optional, Union
import cv2 import cv2
import numpy as np import numpy as np
from typing import Literal, Optional, Union, List, Dict from controlnet_aux import (CannyDetector, ContentShuffleDetector, HEDdetector,
LeresDetector, LineartAnimeDetector,
LineartDetector, MediapipeFaceDetector,
MidasDetector, MLSDdetector, NormalBaeDetector,
OpenposeDetector, PidiNetDetector, SamDetector,
ZoeDetector)
from controlnet_aux.util import HWC3, ade_palette
from PIL import Image from PIL import Image
from pydantic import BaseModel, Field, validator from pydantic import BaseModel, Field, validator
from ...backend.model_management import BaseModelType, ModelType from ...backend.model_management import BaseModelType, ModelType
from ..models.image import ImageField, ImageCategory, ResourceOrigin from ..models.image import ImageCategory, ImageField, ResourceOrigin
from .baseinvocation import ( from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
BaseInvocation, InvocationConfig, InvocationContext)
BaseInvocationOutput,
InvocationContext,
InvocationConfig,
)
from controlnet_aux import (
CannyDetector,
HEDdetector,
LineartDetector,
LineartAnimeDetector,
MidasDetector,
MLSDdetector,
NormalBaeDetector,
OpenposeDetector,
PidiNetDetector,
ContentShuffleDetector,
ZoeDetector,
MediapipeFaceDetector,
SamDetector,
LeresDetector,
)
from controlnet_aux.util import HWC3, ade_palette
from .image import ImageOutput, PILInvocationConfig from .image import ImageOutput, PILInvocationConfig
CONTROLNET_DEFAULT_MODELS = [ CONTROLNET_DEFAULT_MODELS = [
@ -75,33 +57,34 @@ CONTROLNET_DEFAULT_MODELS = [
"lllyasviel/control_v11e_sd15_ip2p", "lllyasviel/control_v11e_sd15_ip2p",
"lllyasviel/control_v11f1e_sd15_tile", "lllyasviel/control_v11f1e_sd15_tile",
################################################# #################################################
# thibaud sd v2.1 models (ControlNet v1.0? or v1.1? # thibaud sd v2.1 models (ControlNet v1.0? or v1.1?
################################################## ##################################################
"thibaud/controlnet-sd21-openpose-diffusers", "thibaud/controlnet-sd21-openpose-diffusers",
"thibaud/controlnet-sd21-canny-diffusers", "thibaud/controlnet-sd21-canny-diffusers",
"thibaud/controlnet-sd21-depth-diffusers", "thibaud/controlnet-sd21-depth-diffusers",
"thibaud/controlnet-sd21-scribble-diffusers", "thibaud/controlnet-sd21-scribble-diffusers",
"thibaud/controlnet-sd21-hed-diffusers", "thibaud/controlnet-sd21-hed-diffusers",
"thibaud/controlnet-sd21-zoedepth-diffusers", "thibaud/controlnet-sd21-zoedepth-diffusers",
"thibaud/controlnet-sd21-color-diffusers", "thibaud/controlnet-sd21-color-diffusers",
"thibaud/controlnet-sd21-openposev2-diffusers", "thibaud/controlnet-sd21-openposev2-diffusers",
"thibaud/controlnet-sd21-lineart-diffusers", "thibaud/controlnet-sd21-lineart-diffusers",
"thibaud/controlnet-sd21-normalbae-diffusers", "thibaud/controlnet-sd21-normalbae-diffusers",
"thibaud/controlnet-sd21-ade20k-diffusers", "thibaud/controlnet-sd21-ade20k-diffusers",
############################################## ##############################################
# ControlNetMediaPipeface, ControlNet v1.1 # ControlNetMediaPipeface, ControlNet v1.1
############################################## ##############################################
# ["CrucibleAI/ControlNetMediaPipeFace", "diffusion_sd15"], # SD 1.5 # ["CrucibleAI/ControlNetMediaPipeFace", "diffusion_sd15"], # SD 1.5
# diffusion_sd15 needs to be passed to from_pretrained() as subfolder arg # diffusion_sd15 needs to be passed to from_pretrained() as subfolder arg
# hacked t2l to split to model & subfolder if format is "model,subfolder" # hacked t2l to split to model & subfolder if format is "model,subfolder"
"CrucibleAI/ControlNetMediaPipeFace,diffusion_sd15", # SD 1.5 "CrucibleAI/ControlNetMediaPipeFace,diffusion_sd15", # SD 1.5
"CrucibleAI/ControlNetMediaPipeFace", # SD 2.1? "CrucibleAI/ControlNetMediaPipeFace", # SD 2.1?
] ]
CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)] CONTROLNET_NAME_VALUES = Literal[tuple(CONTROLNET_DEFAULT_MODELS)]
CONTROLNET_MODE_VALUES = Literal[tuple(["balanced", "more_prompt", "more_control", "unbalanced"])] CONTROLNET_MODE_VALUES = Literal[tuple(
["balanced", "more_prompt", "more_control", "unbalanced"])]
# crop and fill options not ready yet # crop and fill options not ready yet
# CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])] # CONTROLNET_RESIZE_VALUES = Literal[tuple(["just_resize", "crop_resize", "fill_resize"])]
@ -112,16 +95,22 @@ class ControlNetModelField(BaseModel):
model_name: str = Field(description="Name of the ControlNet model") model_name: str = Field(description="Name of the ControlNet model")
base_model: BaseModelType = Field(description="Base model") base_model: BaseModelType = Field(description="Base model")
class ControlField(BaseModel): class ControlField(BaseModel):
image: ImageField = Field(default=None, description="The control image") image: ImageField = Field(default=None, description="The control image")
control_model: Optional[ControlNetModelField] = Field(default=None, description="The ControlNet model to use") control_model: Optional[ControlNetModelField] = Field(
default=None, description="The ControlNet model to use")
# control_weight: Optional[float] = Field(default=1, description="weight given to controlnet") # control_weight: Optional[float] = Field(default=1, description="weight given to controlnet")
control_weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet") control_weight: Union[float, List[float]] = Field(
begin_step_percent: float = Field(default=0, ge=0, le=1, default=1, description="The weight given to the ControlNet")
description="When the ControlNet is first applied (% of total steps)") begin_step_percent: float = Field(
end_step_percent: float = Field(default=1, ge=0, le=1, default=0, ge=0, le=1,
description="When the ControlNet is last applied (% of total steps)") description="When the ControlNet is first applied (% of total steps)")
control_mode: CONTROLNET_MODE_VALUES = Field(default="balanced", description="The control mode to use") end_step_percent: float = Field(
default=1, ge=0, le=1,
description="When the ControlNet is last applied (% of total steps)")
control_mode: CONTROLNET_MODE_VALUES = Field(
default="balanced", description="The control mode to use")
# resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use") # resize_mode: CONTROLNET_RESIZE_VALUES = Field(default="just_resize", description="The resize mode to use")
@validator("control_weight") @validator("control_weight")
@ -130,11 +119,13 @@ class ControlField(BaseModel):
if isinstance(v, list): if isinstance(v, list):
for i in v: for i in v:
if i < -1 or i > 2: if i < -1 or i > 2:
raise ValueError('Control weights must be within -1 to 2 range') raise ValueError(
'Control weights must be within -1 to 2 range')
else: else:
if v < -1 or v > 2: if v < -1 or v > 2:
raise ValueError('Control weights must be within -1 to 2 range') raise ValueError('Control weights must be within -1 to 2 range')
return v return v
class Config: class Config:
schema_extra = { schema_extra = {
"required": ["image", "control_model", "control_weight", "begin_step_percent", "end_step_percent"], "required": ["image", "control_model", "control_weight", "begin_step_percent", "end_step_percent"],
@ -175,13 +166,14 @@ class ControlNetInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"tags": ["latents"], "title": "ControlNet",
"tags": ["controlnet", "latents"],
"type_hints": { "type_hints": {
"model": "model", "model": "model",
"control": "control", "control": "control",
# "cfg_scale": "float", # "cfg_scale": "float",
"cfg_scale": "number", "cfg_scale": "number",
"control_weight": "float", "control_weight": "float",
} }
}, },
} }
@ -208,6 +200,13 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
image: ImageField = Field(default=None, description="The image to process") image: ImageField = Field(default=None, description="The image to process")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Image Processor",
"tags": ["image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
# superclass just passes through image without processing # superclass just passes through image without processing
@ -239,14 +238,15 @@ class ImageProcessorInvocation(BaseInvocation, PILInvocationConfig):
return ImageOutput( return ImageOutput(
image=processed_image_field, image=processed_image_field,
# width=processed_image.width, # width=processed_image.width,
width = image_dto.width, width=image_dto.width,
# height=processed_image.height, # height=processed_image.height,
height = image_dto.height, height=image_dto.height,
# mode=processed_image.mode, # mode=processed_image.mode,
) )
class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class CannyImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Canny edge detection for ControlNet""" """Canny edge detection for ControlNet"""
# fmt: off # fmt: off
type: Literal["canny_image_processor"] = "canny_image_processor" type: Literal["canny_image_processor"] = "canny_image_processor"
@ -255,13 +255,23 @@ class CannyImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfi
high_threshold: int = Field(default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)") high_threshold: int = Field(default=200, ge=0, le=255, description="The high threshold of the Canny pixel gradient (0-255)")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Canny Processor",
"tags": ["controlnet", "canny", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
canny_processor = CannyDetector() canny_processor = CannyDetector()
processed_image = canny_processor(image, self.low_threshold, self.high_threshold) processed_image = canny_processor(
image, self.low_threshold, self.high_threshold)
return processed_image return processed_image
class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class HedImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies HED edge detection to image""" """Applies HED edge detection to image"""
# fmt: off # fmt: off
type: Literal["hed_image_processor"] = "hed_image_processor" type: Literal["hed_image_processor"] = "hed_image_processor"
@ -273,6 +283,14 @@ class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig)
scribble: bool = Field(default=False, description="Whether to use scribble mode") scribble: bool = Field(default=False, description="Whether to use scribble mode")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Softedge(HED) Processor",
"tags": ["controlnet", "softedge", "hed", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators") hed_processor = HEDdetector.from_pretrained("lllyasviel/Annotators")
processed_image = hed_processor(image, processed_image = hed_processor(image,
@ -285,7 +303,8 @@ class HedImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig)
return processed_image return processed_image
class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class LineartImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies line art processing to image""" """Applies line art processing to image"""
# fmt: off # fmt: off
type: Literal["lineart_image_processor"] = "lineart_image_processor" type: Literal["lineart_image_processor"] = "lineart_image_processor"
@ -295,16 +314,25 @@ class LineartImageProcessorInvocation(ImageProcessorInvocation, PILInvocationCon
coarse: bool = Field(default=False, description="Whether to use coarse mode") coarse: bool = Field(default=False, description="Whether to use coarse mode")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Lineart Processor",
"tags": ["controlnet", "lineart", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
lineart_processor = LineartDetector.from_pretrained("lllyasviel/Annotators") lineart_processor = LineartDetector.from_pretrained(
processed_image = lineart_processor(image, "lllyasviel/Annotators")
detect_resolution=self.detect_resolution, processed_image = lineart_processor(
image_resolution=self.image_resolution, image, detect_resolution=self.detect_resolution,
coarse=self.coarse) image_resolution=self.image_resolution, coarse=self.coarse)
return processed_image return processed_image
class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class LineartAnimeImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies line art anime processing to image""" """Applies line art anime processing to image"""
# fmt: off # fmt: off
type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor" type: Literal["lineart_anime_image_processor"] = "lineart_anime_image_processor"
@ -313,8 +341,17 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocati
image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image") image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Lineart Anime Processor",
"tags": ["controlnet", "lineart", "anime", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
processor = LineartAnimeDetector.from_pretrained("lllyasviel/Annotators") processor = LineartAnimeDetector.from_pretrained(
"lllyasviel/Annotators")
processed_image = processor(image, processed_image = processor(image,
detect_resolution=self.detect_resolution, detect_resolution=self.detect_resolution,
image_resolution=self.image_resolution, image_resolution=self.image_resolution,
@ -322,7 +359,8 @@ class LineartAnimeImageProcessorInvocation(ImageProcessorInvocation, PILInvocati
return processed_image return processed_image
class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class OpenposeImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies Openpose processing to image""" """Applies Openpose processing to image"""
# fmt: off # fmt: off
type: Literal["openpose_image_processor"] = "openpose_image_processor" type: Literal["openpose_image_processor"] = "openpose_image_processor"
@ -332,17 +370,26 @@ class OpenposeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationCo
image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image") image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Openpose Processor",
"tags": ["controlnet", "openpose", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
openpose_processor = OpenposeDetector.from_pretrained("lllyasviel/Annotators") openpose_processor = OpenposeDetector.from_pretrained(
processed_image = openpose_processor(image, "lllyasviel/Annotators")
detect_resolution=self.detect_resolution, processed_image = openpose_processor(
image_resolution=self.image_resolution, image, detect_resolution=self.detect_resolution,
hand_and_face=self.hand_and_face, image_resolution=self.image_resolution,
) hand_and_face=self.hand_and_face,)
return processed_image return processed_image
class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class MidasDepthImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies Midas depth processing to image""" """Applies Midas depth processing to image"""
# fmt: off # fmt: off
type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor" type: Literal["midas_depth_image_processor"] = "midas_depth_image_processor"
@ -353,6 +400,14 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocation
# depth_and_normal: bool = Field(default=False, description="whether to use depth and normal mode") # depth_and_normal: bool = Field(default=False, description="whether to use depth and normal mode")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Midas (Depth) Processor",
"tags": ["controlnet", "midas", "depth", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators") midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
processed_image = midas_processor(image, processed_image = midas_processor(image,
@ -364,7 +419,8 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocation
return processed_image return processed_image
class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class NormalbaeImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies NormalBae processing to image""" """Applies NormalBae processing to image"""
# fmt: off # fmt: off
type: Literal["normalbae_image_processor"] = "normalbae_image_processor" type: Literal["normalbae_image_processor"] = "normalbae_image_processor"
@ -373,15 +429,25 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation, PILInvocationC
image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image") image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Normal BAE Processor",
"tags": ["controlnet", "normal", "bae", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators") normalbae_processor = NormalBaeDetector.from_pretrained(
processed_image = normalbae_processor(image, "lllyasviel/Annotators")
detect_resolution=self.detect_resolution, processed_image = normalbae_processor(
image_resolution=self.image_resolution) image, detect_resolution=self.detect_resolution,
image_resolution=self.image_resolution)
return processed_image return processed_image
class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class MlsdImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies MLSD processing to image""" """Applies MLSD processing to image"""
# fmt: off # fmt: off
type: Literal["mlsd_image_processor"] = "mlsd_image_processor" type: Literal["mlsd_image_processor"] = "mlsd_image_processor"
@ -392,17 +458,25 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig
thr_d: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_d`") thr_d: float = Field(default=0.1, ge=0, description="MLSD parameter `thr_d`")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "MLSD Processor",
"tags": ["controlnet", "mlsd", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators") mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
processed_image = mlsd_processor(image, processed_image = mlsd_processor(
detect_resolution=self.detect_resolution, image, detect_resolution=self.detect_resolution,
image_resolution=self.image_resolution, image_resolution=self.image_resolution, thr_v=self.thr_v,
thr_v=self.thr_v, thr_d=self.thr_d)
thr_d=self.thr_d)
return processed_image return processed_image
class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class PidiImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies PIDI processing to image""" """Applies PIDI processing to image"""
# fmt: off # fmt: off
type: Literal["pidi_image_processor"] = "pidi_image_processor" type: Literal["pidi_image_processor"] = "pidi_image_processor"
@ -413,17 +487,26 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig
scribble: bool = Field(default=False, description="Whether to use scribble mode") scribble: bool = Field(default=False, description="Whether to use scribble mode")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "PIDI Processor",
"tags": ["controlnet", "pidi", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators") pidi_processor = PidiNetDetector.from_pretrained(
processed_image = pidi_processor(image, "lllyasviel/Annotators")
detect_resolution=self.detect_resolution, processed_image = pidi_processor(
image_resolution=self.image_resolution, image, detect_resolution=self.detect_resolution,
safe=self.safe, image_resolution=self.image_resolution, safe=self.safe,
scribble=self.scribble) scribble=self.scribble)
return processed_image return processed_image
class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class ContentShuffleImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies content shuffle processing to image""" """Applies content shuffle processing to image"""
# fmt: off # fmt: off
type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor" type: Literal["content_shuffle_image_processor"] = "content_shuffle_image_processor"
@ -435,6 +518,14 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvoca
f: Optional[int] = Field(default=256, ge=0, description="Content shuffle `f` parameter") f: Optional[int] = Field(default=256, ge=0, description="Content shuffle `f` parameter")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Content Shuffle Processor",
"tags": ["controlnet", "contentshuffle", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
content_shuffle_processor = ContentShuffleDetector() content_shuffle_processor = ContentShuffleDetector()
processed_image = content_shuffle_processor(image, processed_image = content_shuffle_processor(image,
@ -448,19 +539,30 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation, PILInvoca
# should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13 # should work with controlnet_aux >= 0.0.4 and timm <= 0.6.13
class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class ZoeDepthImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies Zoe depth processing to image""" """Applies Zoe depth processing to image"""
# fmt: off # fmt: off
type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor" type: Literal["zoe_depth_image_processor"] = "zoe_depth_image_processor"
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Zoe (Depth) Processor",
"tags": ["controlnet", "zoe", "depth", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators") zoe_depth_processor = ZoeDetector.from_pretrained(
"lllyasviel/Annotators")
processed_image = zoe_depth_processor(image) processed_image = zoe_depth_processor(image)
return processed_image return processed_image
class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class MediapipeFaceProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies mediapipe face processing to image""" """Applies mediapipe face processing to image"""
# fmt: off # fmt: off
type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor" type: Literal["mediapipe_face_processor"] = "mediapipe_face_processor"
@ -469,16 +571,27 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation, PILInvocationCo
min_confidence: float = Field(default=0.5, ge=0, le=1, description="Minimum confidence for face detection") min_confidence: float = Field(default=0.5, ge=0, le=1, description="Minimum confidence for face detection")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Mediapipe Processor",
"tags": ["controlnet", "mediapipe", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
# MediaPipeFaceDetector throws an error if image has alpha channel # MediaPipeFaceDetector throws an error if image has alpha channel
# so convert to RGB if needed # so convert to RGB if needed
if image.mode == 'RGBA': if image.mode == 'RGBA':
image = image.convert('RGB') image = image.convert('RGB')
mediapipe_face_processor = MediapipeFaceDetector() mediapipe_face_processor = MediapipeFaceDetector()
processed_image = mediapipe_face_processor(image, max_faces=self.max_faces, min_confidence=self.min_confidence) processed_image = mediapipe_face_processor(
image, max_faces=self.max_faces, min_confidence=self.min_confidence)
return processed_image return processed_image
class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
class LeresImageProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
"""Applies leres processing to image""" """Applies leres processing to image"""
# fmt: off # fmt: off
type: Literal["leres_image_processor"] = "leres_image_processor" type: Literal["leres_image_processor"] = "leres_image_processor"
@ -490,18 +603,25 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation, PILInvocationConfi
image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image") image_resolution: int = Field(default=512, ge=0, description="The pixel resolution for the output image")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Leres (Depth) Processor",
"tags": ["controlnet", "leres", "depth", "image", "processor"]
},
}
def run_processor(self, image): def run_processor(self, image):
leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators") leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
processed_image = leres_processor(image, processed_image = leres_processor(
thr_a=self.thr_a, image, thr_a=self.thr_a, thr_b=self.thr_b, boost=self.boost,
thr_b=self.thr_b, detect_resolution=self.detect_resolution,
boost=self.boost, image_resolution=self.image_resolution)
detect_resolution=self.detect_resolution,
image_resolution=self.image_resolution)
return processed_image return processed_image
class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig): class TileResamplerProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
# fmt: off # fmt: off
type: Literal["tile_image_processor"] = "tile_image_processor" type: Literal["tile_image_processor"] = "tile_image_processor"
@ -510,6 +630,14 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationCo
down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate") down_sampling_rate: float = Field(default=1.0, ge=1.0, le=8.0, description="Down sampling rate")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Tile Resample Processor",
"tags": ["controlnet", "tile", "resample", "image", "processor"]
},
}
# tile_resample copied from sd-webui-controlnet/scripts/processor.py # tile_resample copied from sd-webui-controlnet/scripts/processor.py
def tile_resample(self, def tile_resample(self,
np_img: np.ndarray, np_img: np.ndarray,
@ -528,28 +656,33 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation, PILInvocationCo
def run_processor(self, img): def run_processor(self, img):
np_img = np.array(img, dtype=np.uint8) np_img = np.array(img, dtype=np.uint8)
processed_np_image = self.tile_resample(np_img, processed_np_image = self.tile_resample(np_img,
#res=self.tile_size, # res=self.tile_size,
down_sampling_rate=self.down_sampling_rate down_sampling_rate=self.down_sampling_rate
) )
processed_image = Image.fromarray(processed_np_image) processed_image = Image.fromarray(processed_np_image)
return processed_image return processed_image
class SegmentAnythingProcessorInvocation(
ImageProcessorInvocation, PILInvocationConfig):
class SegmentAnythingProcessorInvocation(ImageProcessorInvocation, PILInvocationConfig):
"""Applies segment anything processing to image""" """Applies segment anything processing to image"""
# fmt: off # fmt: off
type: Literal["segment_anything_processor"] = "segment_anything_processor" type: Literal["segment_anything_processor"] = "segment_anything_processor"
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {"ui": {"title": "Segment Anything Processor", "tags": [
"controlnet", "segment", "anything", "sam", "image", "processor"]}, }
def run_processor(self, image): def run_processor(self, image):
# segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints") # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
segment_anything_processor = SamDetectorReproducibleColors.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints") segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(
"ybelkada/segment-anything", subfolder="checkpoints")
np_img = np.array(image, dtype=np.uint8) np_img = np.array(image, dtype=np.uint8)
processed_image = segment_anything_processor(np_img) processed_image = segment_anything_processor(np_img)
return processed_image return processed_image
class SamDetectorReproducibleColors(SamDetector): class SamDetectorReproducibleColors(SamDetector):
# overriding SamDetector.show_anns() method to use reproducible colors for segmentation image # overriding SamDetector.show_anns() method to use reproducible colors for segmentation image
@ -561,7 +694,8 @@ class SamDetectorReproducibleColors(SamDetector):
return return
sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True) sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
h, w = anns[0]['segmentation'].shape h, w = anns[0]['segmentation'].shape
final_img = Image.fromarray(np.zeros((h, w, 3), dtype=np.uint8), mode="RGB") final_img = Image.fromarray(
np.zeros((h, w, 3), dtype=np.uint8), mode="RGB")
palette = ade_palette() palette = ade_palette()
for i, ann in enumerate(sorted_anns): for i, ann in enumerate(sorted_anns):
m = ann['segmentation'] m = ann['segmentation']
@ -569,5 +703,8 @@ class SamDetectorReproducibleColors(SamDetector):
# doing modulo just in case number of annotated regions exceeds number of colors in palette # doing modulo just in case number of annotated regions exceeds number of colors in palette
ann_color = palette[i % len(palette)] ann_color = palette[i % len(palette)]
img[:, :] = ann_color img[:, :] = ann_color
final_img.paste(Image.fromarray(img, mode="RGB"), (0, 0), Image.fromarray(np.uint8(m * 255))) final_img.paste(
Image.fromarray(img, mode="RGB"),
(0, 0),
Image.fromarray(np.uint8(m * 255)))
return np.array(final_img, dtype=np.uint8) return np.array(final_img, dtype=np.uint8)

8
invokeai/app/invocations/cv.py
View File

@ -35,6 +35,14 @@ class CvInpaintInvocation(BaseInvocation, CvInvocationConfig):
mask: ImageField = Field(default=None, description="The mask to use when inpainting") mask: ImageField = Field(default=None, description="The mask to use when inpainting")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "OpenCV Inpaint",
"tags": ["opencv", "inpaint"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
mask = context.services.images.get_pil_image(self.mask.image_name) mask = context.services.images.get_pil_image(self.mask.image_name)

1
invokeai/app/invocations/generate.py
View File

@ -130,6 +130,7 @@ class InpaintInvocation(BaseInvocation):
schema_extra = { schema_extra = {
"ui": { "ui": {
"tags": ["stable-diffusion", "image"], "tags": ["stable-diffusion", "image"],
"title": "Inpaint"
}, },
} }

105
invokeai/app/invocations/image.py
View File

@ -71,6 +71,15 @@ class LoadImageInvocation(BaseInvocation):
default=None, description="The image to load" default=None, description="The image to load"
) )
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Load Image",
"tags": ["image", "load"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -91,6 +100,14 @@ class ShowImageInvocation(BaseInvocation):
default=None, description="The image to show" default=None, description="The image to show"
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Show Image",
"tags": ["image", "show"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
if image: if image:
@ -119,6 +136,14 @@ class ImageCropInvocation(BaseInvocation, PILInvocationConfig):
height: int = Field(default=512, gt=0, description="The height of the crop rectangle") height: int = Field(default=512, gt=0, description="The height of the crop rectangle")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Crop Image",
"tags": ["image", "crop"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -157,6 +182,14 @@ class ImagePasteInvocation(BaseInvocation, PILInvocationConfig):
y: int = Field(default=0, description="The top y 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 # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Paste Image",
"tags": ["image", "paste"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
base_image = context.services.images.get_pil_image(self.base_image.image_name) base_image = context.services.images.get_pil_image(self.base_image.image_name)
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -207,6 +240,14 @@ class MaskFromAlphaInvocation(BaseInvocation, PILInvocationConfig):
invert: bool = Field(default=False, description="Whether or not to invert the mask") invert: bool = Field(default=False, description="Whether or not to invert the mask")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Mask From Alpha",
"tags": ["image", "mask", "alpha"]
},
}
def invoke(self, context: InvocationContext) -> MaskOutput: def invoke(self, context: InvocationContext) -> MaskOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -241,6 +282,14 @@ class ImageMultiplyInvocation(BaseInvocation, PILInvocationConfig):
image2: Optional[ImageField] = Field(default=None, description="The second image to multiply") image2: Optional[ImageField] = Field(default=None, description="The second image to multiply")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Multiply Images",
"tags": ["image", "multiply"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image1 = context.services.images.get_pil_image(self.image1.image_name) image1 = context.services.images.get_pil_image(self.image1.image_name)
image2 = context.services.images.get_pil_image(self.image2.image_name) image2 = context.services.images.get_pil_image(self.image2.image_name)
@ -277,6 +326,14 @@ class ImageChannelInvocation(BaseInvocation, PILInvocationConfig):
channel: IMAGE_CHANNELS = Field(default="A", description="The channel to get") channel: IMAGE_CHANNELS = Field(default="A", description="The channel to get")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Image Channel",
"tags": ["image", "channel"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -312,6 +369,14 @@ class ImageConvertInvocation(BaseInvocation, PILInvocationConfig):
mode: IMAGE_MODES = Field(default="L", description="The mode to convert to") mode: IMAGE_MODES = Field(default="L", description="The mode to convert to")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Convert Image",
"tags": ["image", "convert"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -345,6 +410,14 @@ class ImageBlurInvocation(BaseInvocation, PILInvocationConfig):
blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur") blur_type: Literal["gaussian", "box"] = Field(default="gaussian", description="The type of blur")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Blur Image",
"tags": ["image", "blur"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -404,6 +477,14 @@ class ImageResizeInvocation(BaseInvocation, PILInvocationConfig):
resample_mode: PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode") resample_mode: PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Resize Image",
"tags": ["image", "resize"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -442,6 +523,14 @@ class ImageScaleInvocation(BaseInvocation, PILInvocationConfig):
resample_mode: PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode") resample_mode: PIL_RESAMPLING_MODES = Field(default="bicubic", description="The resampling mode")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Scale Image",
"tags": ["image", "scale"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -482,6 +571,14 @@ class ImageLerpInvocation(BaseInvocation, PILInvocationConfig):
max: int = Field(default=255, ge=0, le=255, description="The maximum output value") max: int = Field(default=255, ge=0, le=255, description="The maximum output value")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Image Linear Interpolation",
"tags": ["image", "linear", "interpolation", "lerp"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -518,6 +615,14 @@ class ImageInverseLerpInvocation(BaseInvocation, PILInvocationConfig):
max: int = Field(default=255, ge=0, le=255, description="The maximum input value") max: int = Field(default=255, ge=0, le=255, description="The maximum input value")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Image Inverse Linear Interpolation",
"tags": ["image", "linear", "interpolation", "inverse"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)

25
invokeai/app/invocations/infill.py
View File

@ -14,6 +14,7 @@ from invokeai.backend.image_util.patchmatch import PatchMatch
from ..models.image import ColorField, ImageCategory, ImageField, ResourceOrigin from ..models.image import ColorField, ImageCategory, ImageField, ResourceOrigin
from .baseinvocation import ( from .baseinvocation import (
BaseInvocation, BaseInvocation,
InvocationConfig,
InvocationContext, InvocationContext,
) )
@ -133,6 +134,14 @@ class InfillColorInvocation(BaseInvocation):
description="The color to use to infill", description="The color to use to infill",
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Color Infill",
"tags": ["image", "inpaint", "color", "infill"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -173,6 +182,14 @@ class InfillTileInvocation(BaseInvocation):
default_factory=get_random_seed, default_factory=get_random_seed,
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Tile Infill",
"tags": ["image", "inpaint", "tile", "infill"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
@ -206,6 +223,14 @@ class InfillPatchMatchInvocation(BaseInvocation):
default=None, description="The image to infill" default=None, description="The image to infill"
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Patch Match Infill",
"tags": ["image", "inpaint", "patchmatch", "infill"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)

22
invokeai/app/invocations/latent.py
View File

@ -139,6 +139,7 @@ class TextToLatentsInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"title": "Text To Latents",
"tags": ["latents"], "tags": ["latents"],
"type_hints": { "type_hints": {
"model": "model", "model": "model",
@ -389,6 +390,7 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"title": "Latent To Latents",
"tags": ["latents"], "tags": ["latents"],
"type_hints": { "type_hints": {
"model": "model", "model": "model",
@ -498,6 +500,7 @@ class LatentsToImageInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"title": "Latents To Image",
"tags": ["latents", "image"], "tags": ["latents", "image"],
}, },
} }
@ -596,6 +599,14 @@ class ResizeLatentsInvocation(BaseInvocation):
default=False, default=False,
description="Whether or not to antialias (applied in bilinear and bicubic modes only)") description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Resize Latents",
"tags": ["latents", "resize"]
},
}
def invoke(self, context: InvocationContext) -> LatentsOutput: def invoke(self, context: InvocationContext) -> LatentsOutput:
latents = context.services.latents.get(self.latents.latents_name) latents = context.services.latents.get(self.latents.latents_name)
@ -634,6 +645,14 @@ class ScaleLatentsInvocation(BaseInvocation):
default=False, default=False,
description="Whether or not to antialias (applied in bilinear and bicubic modes only)") description="Whether or not to antialias (applied in bilinear and bicubic modes only)")
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Scale Latents",
"tags": ["latents", "scale"]
},
}
def invoke(self, context: InvocationContext) -> LatentsOutput: def invoke(self, context: InvocationContext) -> LatentsOutput:
latents = context.services.latents.get(self.latents.latents_name) latents = context.services.latents.get(self.latents.latents_name)
@ -675,7 +694,8 @@ class ImageToLatentsInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"tags": ["latents", "image"], "title": "Image To Latents",
"tags": ["latents", "image"]
}, },
} }

41
invokeai/app/invocations/math.py
View File

@ -52,6 +52,14 @@ class AddInvocation(BaseInvocation, MathInvocationConfig):
b: int = Field(default=0, description="The second number") b: int = Field(default=0, description="The second number")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Add",
"tags": ["math", "add"]
},
}
def invoke(self, context: InvocationContext) -> IntOutput: def invoke(self, context: InvocationContext) -> IntOutput:
return IntOutput(a=self.a + self.b) return IntOutput(a=self.a + self.b)
@ -65,6 +73,14 @@ class SubtractInvocation(BaseInvocation, MathInvocationConfig):
b: int = Field(default=0, description="The second number") b: int = Field(default=0, description="The second number")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Subtract",
"tags": ["math", "subtract"]
},
}
def invoke(self, context: InvocationContext) -> IntOutput: def invoke(self, context: InvocationContext) -> IntOutput:
return IntOutput(a=self.a - self.b) return IntOutput(a=self.a - self.b)
@ -78,6 +94,14 @@ class MultiplyInvocation(BaseInvocation, MathInvocationConfig):
b: int = Field(default=0, description="The second number") b: int = Field(default=0, description="The second number")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Multiply",
"tags": ["math", "multiply"]
},
}
def invoke(self, context: InvocationContext) -> IntOutput: def invoke(self, context: InvocationContext) -> IntOutput:
return IntOutput(a=self.a * self.b) return IntOutput(a=self.a * self.b)
@ -91,6 +115,14 @@ class DivideInvocation(BaseInvocation, MathInvocationConfig):
b: int = Field(default=0, description="The second number") b: int = Field(default=0, description="The second number")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Divide",
"tags": ["math", "divide"]
},
}
def invoke(self, context: InvocationContext) -> IntOutput: def invoke(self, context: InvocationContext) -> IntOutput:
return IntOutput(a=int(self.a / self.b)) return IntOutput(a=int(self.a / self.b))
@ -105,5 +137,14 @@ class RandomIntInvocation(BaseInvocation):
default=np.iinfo(np.int32).max, description="The exclusive high value" default=np.iinfo(np.int32).max, description="The exclusive high value"
) )
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Random Integer",
"tags": ["math", "random", "integer"]
},
}
def invoke(self, context: InvocationContext) -> IntOutput: def invoke(self, context: InvocationContext) -> IntOutput:
return IntOutput(a=np.random.randint(self.low, self.high)) return IntOutput(a=np.random.randint(self.low, self.high))

10
invokeai/app/invocations/metadata.py
View File

@ -3,7 +3,7 @@ from typing import Literal, Optional, Union
from pydantic import BaseModel, Field from pydantic import BaseModel, Field
from invokeai.app.invocations.baseinvocation import (BaseInvocation, from invokeai.app.invocations.baseinvocation import (BaseInvocation,
BaseInvocationOutput, BaseInvocationOutput, InvocationConfig,
InvocationContext) InvocationContext)
from invokeai.app.invocations.controlnet_image_processors import ControlField from invokeai.app.invocations.controlnet_image_processors import ControlField
from invokeai.app.invocations.model import (LoRAModelField, MainModelField, from invokeai.app.invocations.model import (LoRAModelField, MainModelField,
@ -97,6 +97,14 @@ class MetadataAccumulatorInvocation(BaseInvocation):
description="The VAE used for decoding, if the main model's default was not used", description="The VAE used for decoding, if the main model's default was not used",
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Metadata Accumulator",
"tags": ["image", "metadata", "generation"]
},
}
def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput: def invoke(self, context: InvocationContext) -> MetadataAccumulatorOutput:
"""Collects and outputs a CoreMetadata object""" """Collects and outputs a CoreMetadata object"""

1
invokeai/app/invocations/noise.py
View File

@ -112,6 +112,7 @@ class NoiseInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"title": "Noise",
"tags": ["latents", "noise"], "tags": ["latents", "noise"],
}, },
} }

16
invokeai/app/invocations/param_easing.py
View File

@ -43,6 +43,14 @@ class FloatLinearRangeInvocation(BaseInvocation):
stop: float = Field(default=10, description="The last value of the range") stop: float = Field(default=10, description="The last value of the range")
steps: int = Field(default=30, description="number of values to interpolate over (including start and stop)") steps: int = Field(default=30, description="number of values to interpolate over (including start and stop)")
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Linear Range (Float)",
"tags": ["math", "float", "linear", "range"]
},
}
def invoke(self, context: InvocationContext) -> FloatCollectionOutput: def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
param_list = list(np.linspace(self.start, self.stop, self.steps)) param_list = list(np.linspace(self.start, self.stop, self.steps))
return FloatCollectionOutput( return FloatCollectionOutput(
@ -113,6 +121,14 @@ class StepParamEasingInvocation(BaseInvocation):
show_easing_plot: bool = Field(default=False, description="show easing plot") show_easing_plot: bool = Field(default=False, description="show easing plot")
# fmt: on # fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Param Easing By Step",
"tags": ["param", "step", "easing"]
},
}
def invoke(self, context: InvocationContext) -> FloatCollectionOutput: def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
log_diagnostics = False log_diagnostics = False

46
invokeai/app/invocations/params.py
View File

@ -1,9 +1,12 @@
# Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654) # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
from typing import Literal from typing import Literal
from pydantic import Field from pydantic import Field
from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext
from .math import IntOutput, FloatOutput from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
InvocationConfig, InvocationContext)
from .math import FloatOutput, IntOutput
# Pass-through parameter nodes - used by subgraphs # Pass-through parameter nodes - used by subgraphs
@ -14,6 +17,14 @@ class ParamIntInvocation(BaseInvocation):
a: int = Field(default=0, description="The integer value") a: int = Field(default=0, description="The integer value")
#fmt: on #fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"tags": ["param", "integer"],
"title": "Integer Parameter"
},
}
def invoke(self, context: InvocationContext) -> IntOutput: def invoke(self, context: InvocationContext) -> IntOutput:
return IntOutput(a=self.a) return IntOutput(a=self.a)
@ -24,5 +35,36 @@ class ParamFloatInvocation(BaseInvocation):
param: float = Field(default=0.0, description="The float value") param: float = Field(default=0.0, description="The float value")
#fmt: on #fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"tags": ["param", "float"],
"title": "Float Parameter"
},
}
def invoke(self, context: InvocationContext) -> FloatOutput: def invoke(self, context: InvocationContext) -> FloatOutput:
return FloatOutput(param=self.param) return FloatOutput(param=self.param)
class StringOutput(BaseInvocationOutput):
"""A string output"""
type: Literal["string_output"] = "string_output"
text: str = Field(default=None, description="The output string")
class ParamStringInvocation(BaseInvocation):
"""A string parameter"""
type: Literal['param_string'] = 'param_string'
text: str = Field(default='', description='The string value')
class Config(InvocationConfig):
schema_extra = {
"ui": {
"tags": ["param", "string"],
"title": "String Parameter"
},
}
def invoke(self, context: InvocationContext) -> StringOutput:
return StringOutput(text=self.text)

18
invokeai/app/invocations/prompt.py
View File

@ -4,7 +4,7 @@ from typing import Literal, Optional
import numpy as np import numpy as np
from pydantic import Field, validator from pydantic import Field, validator
from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationContext from .baseinvocation import BaseInvocation, BaseInvocationOutput, InvocationConfig, InvocationContext
from dynamicprompts.generators import RandomPromptGenerator, CombinatorialPromptGenerator from dynamicprompts.generators import RandomPromptGenerator, CombinatorialPromptGenerator
class PromptOutput(BaseInvocationOutput): class PromptOutput(BaseInvocationOutput):
@ -48,6 +48,14 @@ class DynamicPromptInvocation(BaseInvocation):
default=False, description="Whether to use the combinatorial generator" default=False, description="Whether to use the combinatorial generator"
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Dynamic Prompt",
"tags": ["prompt", "dynamic"]
},
}
def invoke(self, context: InvocationContext) -> PromptCollectionOutput: def invoke(self, context: InvocationContext) -> PromptCollectionOutput:
if self.combinatorial: if self.combinatorial:
generator = CombinatorialPromptGenerator() generator = CombinatorialPromptGenerator()
@ -72,6 +80,14 @@ class PromptsFromFileInvocation(BaseInvocation):
max_prompts: int = Field(default=1, ge=0, description="Max lines to read from file (0=all)") max_prompts: int = Field(default=1, ge=0, description="Max lines to read from file (0=all)")
#fmt: on #fmt: on
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Prompts From File",
"tags": ["prompt", "file"]
},
}
@validator("file_path") @validator("file_path")
def file_path_exists(cls, v): def file_path_exists(cls, v):
if not exists(v): if not exists(v):

2
invokeai/app/invocations/sdxl.py
View File

@ -233,6 +233,7 @@ class SDXLTextToLatentsInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"title": "SDXL Text To Latents",
"tags": ["latents"], "tags": ["latents"],
"type_hints": { "type_hints": {
"model": "model", "model": "model",
@ -462,6 +463,7 @@ class SDXLLatentsToLatentsInvocation(BaseInvocation):
class Config(InvocationConfig): class Config(InvocationConfig):
schema_extra = { schema_extra = {
"ui": { "ui": {
"title": "SDXL Latents to Latents",
"tags": ["latents"], "tags": ["latents"],
"type_hints": { "type_hints": {
"model": "model", "model": "model",

10
invokeai/app/invocations/upscale.py
View File

@ -11,7 +11,7 @@ from realesrgan import RealESRGANer
from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin from invokeai.app.models.image import ImageCategory, ImageField, ResourceOrigin
from .baseinvocation import BaseInvocation, InvocationContext from .baseinvocation import BaseInvocation, InvocationConfig, InvocationContext
from .image import ImageOutput from .image import ImageOutput
# TODO: Populate this from disk? # TODO: Populate this from disk?
@ -32,6 +32,14 @@ class RealESRGANInvocation(BaseInvocation):
default="RealESRGAN_x4plus.pth", description="The Real-ESRGAN model to use" default="RealESRGAN_x4plus.pth", description="The Real-ESRGAN model to use"
) )
class Config(InvocationConfig):
schema_extra = {
"ui": {
"title": "Upscale (RealESRGAN)",
"tags": ["image", "upscale", "realesrgan"]
},
}
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name) image = context.services.images.get_pil_image(self.image.image_name)
models_path = context.services.configuration.models_path models_path = context.services.configuration.models_path