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

Merge branch 'main' into feat/ip-adapter

Browse Source
This commit is contained in:
blessedcoolant 2023-09-05 15:22:15 +12:00
commit f44496a579
37 changed files with 1298 additions and 450 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
docs/nodes/communityNodes.md
View File

@ -109,6 +109,73 @@ a Text-Generation-Webui instance (might work remotely too, but I never tried it)
This node works best with SDXL models, especially as the style can be described independantly of the LLM's output. This node works best with SDXL models, especially as the style can be described independantly of the LLM's output.
--------------------------------
### Depth Map from Wavefront OBJ
**Description:** Render depth maps from Wavefront .obj files (triangulated) using this simple 3D renderer utilizing numpy and matplotlib to compute and color the scene. There are simple parameters to change the FOV, camera position, and model orientation.
To be imported, an .obj must use triangulated meshes, so make sure to enable that option if exporting from a 3D modeling program. This renderer makes each triangle a solid color based on its average depth, so it will cause anomalies if your .obj has large triangles. In Blender, the Remesh modifier can be helpful to subdivide a mesh into small pieces that work well given these limitations.
**Node Link:** https://github.com/dwringer/depth-from-obj-node
**Example Usage:**
![depth from obj usage graph](https://raw.githubusercontent.com/dwringer/depth-from-obj-node/main/depth_from_obj_usage.jpg)
--------------------------------
### Enhance Image (simple adjustments)
**Description:** Boost or reduce color saturation, contrast, brightness, sharpness, or invert colors of any image at any stage with this simple wrapper for pillow [PIL]'s ImageEnhance module.
Color inversion is toggled with a simple switch, while each of the four enhancer modes are activated by entering a value other than 1 in each corresponding input field. Values less than 1 will reduce the corresponding property, while values greater than 1 will enhance it.
**Node Link:** https://github.com/dwringer/image-enhance-node
**Example Usage:**
![enhance image usage graph](https://raw.githubusercontent.com/dwringer/image-enhance-node/main/image_enhance_usage.jpg)
--------------------------------
### Generative Grammar-Based Prompt Nodes
**Description:** This set of 3 nodes generates prompts from simple user-defined grammar rules (loaded from custom files - examples provided below). The prompts are made by recursively expanding a special template string, replacing nonterminal "parts-of-speech" until no more nonterminal terms remain in the string.
This includes 3 Nodes:
- *Lookup Table from File* - loads a YAML file "prompt" section (or of a whole folder of YAML's) into a JSON-ified dictionary (Lookups output)
- *Lookups Entry from Prompt* - places a single entry in a new Lookups output under the specified heading
- *Prompt from Lookup Table* - uses a Collection of Lookups as grammar rules from which to randomly generate prompts.
**Node Link:** https://github.com/dwringer/generative-grammar-prompt-nodes
**Example Usage:**
![lookups usage example graph](https://raw.githubusercontent.com/dwringer/generative-grammar-prompt-nodes/main/lookuptables_usage.jpg)
--------------------------------
### Image and Mask Composition Pack
**Description:** This is a pack of nodes for composing masks and images, including a simple text mask creator and both image and latent offset nodes. The offsets wrap around, so these can be used in conjunction with the Seamless node to progressively generate centered on different parts of the seamless tiling.
This includes 4 Nodes:
- *Text Mask (simple 2D)* - create and position a white on black (or black on white) line of text using any font locally available to Invoke.
- *Image Compositor* - Take a subject from an image with a flat backdrop and layer it on another image using a chroma key or flood select background removal.
- *Offset Latents* - Offset a latents tensor in the vertical and/or horizontal dimensions, wrapping it around.
- *Offset Image* - Offset an image in the vertical and/or horizontal dimensions, wrapping it around.
**Node Link:** https://github.com/dwringer/composition-nodes
**Example Usage:**
![composition nodes usage graph](https://raw.githubusercontent.com/dwringer/composition-nodes/main/composition_nodes_usage.jpg)
--------------------------------
### Size Stepper Nodes
**Description:** This is a set of nodes for calculating the necessary size increments for doing upscaling workflows. Use the *Final Size & Orientation* node to enter your full size dimensions and orientation (portrait/landscape/random), then plug that and your initial generation dimensions into the *Ideal Size Stepper* and get 1, 2, or 3 intermediate pairs of dimensions for upscaling. Note this does not output the initial size or full size dimensions: the 1, 2, or 3 outputs of this node are only the intermediate sizes.
A third node is included, *Random Switch (Integers)*, which is just a generic version of Final Size with no orientation selection.
**Node Link:** https://github.com/dwringer/size-stepper-nodes
**Example Usage:**
![size stepper usage graph](https://raw.githubusercontent.com/dwringer/size-stepper-nodes/main/size_nodes_usage.jpg)
-------------------------------- --------------------------------
### Example Node Template ### Example Node Template

4
docs/nodes/defaultNodes.md
View File

@ -35,13 +35,13 @@ The table below contains a list of the default nodes shipped with InvokeAI and t
|Inverse Lerp Image | Inverse linear interpolation of all pixels of an image| |Inverse Lerp Image | Inverse linear interpolation of all pixels of an image|
|Image Primitive | An image primitive value| |Image Primitive | An image primitive value|
|Lerp Image | Linear interpolation of all pixels of an image| |Lerp Image | Linear interpolation of all pixels of an image|
|Image Luminosity Adjustment | Adjusts the Luminosity (Value) of an image.| |Offset Image Channel | Add to or subtract from an image color channel by a uniform value.|
|Multiply Image Channel | Multiply or Invert an image color channel by a scalar value.|
|Multiply Images | Multiplies two images together using `PIL.ImageChops.multiply()`.| |Multiply Images | Multiplies two images together using `PIL.ImageChops.multiply()`.|
|Blur NSFW Image | Add blur to NSFW-flagged images| |Blur NSFW Image | Add blur to NSFW-flagged images|
|Paste Image | Pastes an image into another image.| |Paste Image | Pastes an image into another image.|
|ImageProcessor | Base class for invocations that preprocess images for ControlNet| |ImageProcessor | Base class for invocations that preprocess images for ControlNet|
|Resize Image | Resizes an image to specific dimensions| |Resize Image | Resizes an image to specific dimensions|
|Image Saturation Adjustment | Adjusts the Saturation of an image.|
|Scale Image | Scales an image by a factor| |Scale Image | Scales an image by a factor|
|Image to Latents | Encodes an image into latents.| |Image to Latents | Encodes an image into latents.|
|Add Invisible Watermark | Add an invisible watermark to an image| |Add Invisible Watermark | Add an invisible watermark to an image|

12
invokeai/app/api/routers/app_info.py
View File

@ -1,19 +1,19 @@
import typing import typing
from enum import Enum from enum import Enum
from pathlib import Path
from fastapi import Body from fastapi import Body
from fastapi.routing import APIRouter from fastapi.routing import APIRouter
from pathlib import Path
from pydantic import BaseModel, Field from pydantic import BaseModel, Field
from invokeai.app.invocations.upscale import ESRGAN_MODELS
from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
from invokeai.backend.image_util.patchmatch import PatchMatch from invokeai.backend.image_util.patchmatch import PatchMatch
from invokeai.backend.image_util.safety_checker import SafetyChecker from invokeai.backend.image_util.safety_checker import SafetyChecker
from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark from invokeai.backend.util.logging import logging
from invokeai.app.invocations.upscale import ESRGAN_MODELS
from invokeai.version import __version__ from invokeai.version import __version__
from ..dependencies import ApiDependencies from ..dependencies import ApiDependencies
from invokeai.backend.util.logging import logging
class LogLevel(int, Enum): class LogLevel(int, Enum):
@ -55,7 +55,7 @@ async def get_version() -> AppVersion:
@app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig) @app_router.get("/config", operation_id="get_config", status_code=200, response_model=AppConfig)
async def get_config() -> AppConfig: async def get_config() -> AppConfig:
infill_methods = ["tile", "lama"] infill_methods = ["tile", "lama", "cv2"]
if PatchMatch.patchmatch_available(): if PatchMatch.patchmatch_available():
infill_methods.append("patchmatch") infill_methods.append("patchmatch")

161
invokeai/app/invocations/image.py
View File

@ -563,7 +563,7 @@ class MaskEdgeInvocation(BaseInvocation):
) )
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
mask = context.services.images.get_pil_image(self.image.image_name) mask = context.services.images.get_pil_image(self.image.image_name).convert("L")
npimg = numpy.asarray(mask, dtype=numpy.uint8) npimg = numpy.asarray(mask, dtype=numpy.uint8)
npgradient = numpy.uint8(255 * (1.0 - numpy.floor(numpy.abs(0.5 - numpy.float32(npimg) / 255.0) * 2.0))) npgradient = numpy.uint8(255 * (1.0 - numpy.floor(numpy.abs(0.5 - numpy.float32(npimg) / 255.0) * 2.0)))
@ -700,8 +700,13 @@ class ColorCorrectInvocation(BaseInvocation):
# Blur the mask out (into init image) by specified amount # Blur the mask out (into init image) by specified amount
if self.mask_blur_radius > 0: if self.mask_blur_radius > 0:
nm = numpy.asarray(pil_init_mask, dtype=numpy.uint8) nm = numpy.asarray(pil_init_mask, dtype=numpy.uint8)
inverted_nm = 255 - nm
dilation_size = int(round(self.mask_blur_radius) + 20)
dilating_kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (dilation_size, dilation_size))
inverted_dilated_nm = cv2.dilate(inverted_nm, dilating_kernel)
dilated_nm = 255 - inverted_dilated_nm
nmd = cv2.erode( nmd = cv2.erode(
nm, dilated_nm,
kernel=numpy.ones((3, 3), dtype=numpy.uint8), kernel=numpy.ones((3, 3), dtype=numpy.uint8),
iterations=int(self.mask_blur_radius / 2), iterations=int(self.mask_blur_radius / 2),
) )
@ -773,39 +778,95 @@ class ImageHueAdjustmentInvocation(BaseInvocation):
) )
COLOR_CHANNELS = Literal[
"Red (RGBA)",
"Green (RGBA)",
"Blue (RGBA)",
"Alpha (RGBA)",
"Cyan (CMYK)",
"Magenta (CMYK)",
"Yellow (CMYK)",
"Black (CMYK)",
"Hue (HSV)",
"Saturation (HSV)",
"Value (HSV)",
"Luminosity (LAB)",
"A (LAB)",
"B (LAB)",
"Y (YCbCr)",
"Cb (YCbCr)",
"Cr (YCbCr)",
]
CHANNEL_FORMATS = {
"Red (RGBA)": ("RGBA", 0),
"Green (RGBA)": ("RGBA", 1),
"Blue (RGBA)": ("RGBA", 2),
"Alpha (RGBA)": ("RGBA", 3),
"Cyan (CMYK)": ("CMYK", 0),
"Magenta (CMYK)": ("CMYK", 1),
"Yellow (CMYK)": ("CMYK", 2),
"Black (CMYK)": ("CMYK", 3),
"Hue (HSV)": ("HSV", 0),
"Saturation (HSV)": ("HSV", 1),
"Value (HSV)": ("HSV", 2),
"Luminosity (LAB)": ("LAB", 0),
"A (LAB)": ("LAB", 1),
"B (LAB)": ("LAB", 2),
"Y (YCbCr)": ("YCbCr", 0),
"Cb (YCbCr)": ("YCbCr", 1),
"Cr (YCbCr)": ("YCbCr", 2),
}
@invocation( @invocation(
"img_luminosity_adjust", "img_channel_offset",
title="Adjust Image Luminosity", title="Offset Image Channel",
tags=["image", "luminosity", "hsl"], tags=[
"image",
"offset",
"red",
"green",
"blue",
"alpha",
"cyan",
"magenta",
"yellow",
"black",
"hue",
"saturation",
"luminosity",
"value",
],
category="image", category="image",
version="1.0.0", version="1.0.0",
) )
class ImageLuminosityAdjustmentInvocation(BaseInvocation): class ImageChannelOffsetInvocation(BaseInvocation):
"""Adjusts the Luminosity (Value) of an image.""" """Add or subtract a value from a specific color channel of an image."""
image: ImageField = InputField(description="The image to adjust") image: ImageField = InputField(description="The image to adjust")
luminosity: float = InputField( channel: COLOR_CHANNELS = InputField(description="Which channel to adjust")
default=1.0, ge=0, le=1, description="The factor by which to adjust the luminosity (value)" offset: int = InputField(default=0, ge=-255, le=255, description="The amount to adjust the channel by")
)
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
pil_image = context.services.images.get_pil_image(self.image.image_name) pil_image = context.services.images.get_pil_image(self.image.image_name)
# Convert PIL image to OpenCV format (numpy array), note color channel # extract the channel and mode from the input and reference tuple
# ordering is changed from RGB to BGR mode = CHANNEL_FORMATS[self.channel][0]
image = numpy.array(pil_image.convert("RGB"))[:, :, ::-1] channel_number = CHANNEL_FORMATS[self.channel][1]
# Convert image to HSV color space # Convert PIL image to new format
hsv_image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) converted_image = numpy.array(pil_image.convert(mode)).astype(int)
image_channel = converted_image[:, :, channel_number]
# Adjust the luminosity (value) # Adjust the value, clipping to 0..255
hsv_image[:, :, 2] = numpy.clip(hsv_image[:, :, 2] * self.luminosity, 0, 255) image_channel = numpy.clip(image_channel + self.offset, 0, 255)
# Convert image back to BGR color space # Put the channel back into the image
image = cv2.cvtColor(hsv_image, cv2.COLOR_HSV2BGR) converted_image[:, :, channel_number] = image_channel
# Convert back to PIL format and to original color mode # Convert back to RGBA format and output
pil_image = Image.fromarray(image[:, :, ::-1], "RGB").convert("RGBA") pil_image = Image.fromarray(converted_image.astype(numpy.uint8), mode=mode).convert("RGBA")
image_dto = context.services.images.create( image_dto = context.services.images.create(
image=pil_image, image=pil_image,
@ -827,36 +888,60 @@ class ImageLuminosityAdjustmentInvocation(BaseInvocation):
@invocation( @invocation(
"img_saturation_adjust", "img_channel_multiply",
title="Adjust Image Saturation", title="Multiply Image Channel",
tags=["image", "saturation", "hsl"], tags=[
"image",
"invert",
"scale",
"multiply",
"red",
"green",
"blue",
"alpha",
"cyan",
"magenta",
"yellow",
"black",
"hue",
"saturation",
"luminosity",
"value",
],
category="image", category="image",
version="1.0.0", version="1.0.0",
) )
class ImageSaturationAdjustmentInvocation(BaseInvocation): class ImageChannelMultiplyInvocation(BaseInvocation):
"""Adjusts the Saturation of an image.""" """Scale a specific color channel of an image."""
image: ImageField = InputField(description="The image to adjust") image: ImageField = InputField(description="The image to adjust")
saturation: float = InputField(default=1.0, ge=0, le=1, description="The factor by which to adjust the saturation") channel: COLOR_CHANNELS = InputField(description="Which channel to adjust")
scale: float = InputField(default=1.0, ge=0.0, description="The amount to scale the channel by.")
invert_channel: bool = InputField(default=False, description="Invert the channel after scaling")
def invoke(self, context: InvocationContext) -> ImageOutput: def invoke(self, context: InvocationContext) -> ImageOutput:
pil_image = context.services.images.get_pil_image(self.image.image_name) pil_image = context.services.images.get_pil_image(self.image.image_name)
# Convert PIL image to OpenCV format (numpy array), note color channel # extract the channel and mode from the input and reference tuple
# ordering is changed from RGB to BGR mode = CHANNEL_FORMATS[self.channel][0]
image = numpy.array(pil_image.convert("RGB"))[:, :, ::-1] channel_number = CHANNEL_FORMATS[self.channel][1]
# Convert image to HSV color space # Convert PIL image to new format
hsv_image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) converted_image = numpy.array(pil_image.convert(mode)).astype(float)
image_channel = converted_image[:, :, channel_number]
# Adjust the saturation # Adjust the value, clipping to 0..255
hsv_image[:, :, 1] = numpy.clip(hsv_image[:, :, 1] * self.saturation, 0, 255) image_channel = numpy.clip(image_channel * self.scale, 0, 255)
# Convert image back to BGR color space # Invert the channel if requested
image = cv2.cvtColor(hsv_image, cv2.COLOR_HSV2BGR) if self.invert_channel:
image_channel = 255 - image_channel
# Convert back to PIL format and to original color mode # Put the channel back into the image
pil_image = Image.fromarray(image[:, :, ::-1], "RGB").convert("RGBA") converted_image[:, :, channel_number] = image_channel
# Convert back to RGBA format and output
pil_image = Image.fromarray(converted_image.astype(numpy.uint8), mode=mode).convert("RGBA")
image_dto = context.services.images.create( image_dto = context.services.images.create(
image=pil_image, image=pil_image,

63
invokeai/app/invocations/infill.py
View File

@ -8,19 +8,17 @@ from PIL import Image, ImageOps
from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput from invokeai.app.invocations.primitives import ColorField, ImageField, ImageOutput
from invokeai.app.util.misc import SEED_MAX, get_random_seed from invokeai.app.util.misc import SEED_MAX, get_random_seed
from invokeai.backend.image_util.cv2_inpaint import cv2_inpaint
from invokeai.backend.image_util.lama import LaMA from invokeai.backend.image_util.lama import LaMA
from invokeai.backend.image_util.patchmatch import PatchMatch from invokeai.backend.image_util.patchmatch import PatchMatch
from ..models.image import ImageCategory, ResourceOrigin from ..models.image import ImageCategory, ResourceOrigin
from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
from .image import PIL_RESAMPLING_MAP, PIL_RESAMPLING_MODES
def infill_methods() -> list[str]: def infill_methods() -> list[str]:
methods = [ methods = ["tile", "solid", "lama", "cv2"]
"tile",
"solid",
"lama",
]
if PatchMatch.patchmatch_available(): if PatchMatch.patchmatch_available():
methods.insert(0, "patchmatch") methods.insert(0, "patchmatch")
return methods return methods
@ -49,6 +47,10 @@ def infill_patchmatch(im: Image.Image) -> Image.Image:
return im_patched return im_patched
def infill_cv2(im: Image.Image) -> Image.Image:
return cv2_inpaint(im)
def get_tile_images(image: np.ndarray, width=8, height=8): def get_tile_images(image: np.ndarray, width=8, height=8):
_nrows, _ncols, depth = image.shape _nrows, _ncols, depth = image.shape
_strides = image.strides _strides = image.strides
@ -194,15 +196,35 @@ class InfillPatchMatchInvocation(BaseInvocation):
"""Infills transparent areas of an image using the PatchMatch algorithm""" """Infills transparent areas of an image using the PatchMatch algorithm"""
image: ImageField = InputField(description="The image to infill") image: ImageField = InputField(description="The image to infill")
downscale: float = InputField(default=2.0, gt=0, description="Run patchmatch on downscaled image to speedup infill")
resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
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).convert("RGBA")
resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
infill_image = image.copy()
width = int(image.width / self.downscale)
height = int(image.height / self.downscale)
infill_image = infill_image.resize(
(width, height),
resample=resample_mode,
)
if PatchMatch.patchmatch_available(): if PatchMatch.patchmatch_available():
infilled = infill_patchmatch(image.copy()) infilled = infill_patchmatch(infill_image)
else: else:
raise ValueError("PatchMatch is not available on this system") raise ValueError("PatchMatch is not available on this system")
infilled = infilled.resize(
(image.width, image.height),
resample=resample_mode,
)
infilled.paste(image, (0, 0), mask=image.split()[-1])
# image.paste(infilled, (0, 0), mask=image.split()[-1])
image_dto = context.services.images.create( image_dto = context.services.images.create(
image=infilled, image=infilled,
image_origin=ResourceOrigin.INTERNAL, image_origin=ResourceOrigin.INTERNAL,
@ -245,3 +267,30 @@ class LaMaInfillInvocation(BaseInvocation):
width=image_dto.width, width=image_dto.width,
height=image_dto.height, height=image_dto.height,
) )
@invocation("infill_cv2", title="CV2 Infill", tags=["image", "inpaint"], category="inpaint")
class CV2InfillInvocation(BaseInvocation):
"""Infills transparent areas of an image using OpenCV Inpainting"""
image: ImageField = InputField(description="The image to infill")
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
infilled = infill_cv2(image.copy())
image_dto = context.services.images.create(
image=infilled,
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,
)

20
invokeai/backend/image_util/cv2_inpaint.py Normal file
View File

@ -0,0 +1,20 @@
import cv2
import numpy as np
from PIL import Image
def cv2_inpaint(image: Image.Image) -> Image.Image:
# Prepare Image
image_array = np.array(image.convert("RGB"))
image_cv = cv2.cvtColor(image_array, cv2.COLOR_RGB2BGR)
# Prepare Mask From Alpha Channel
mask = image.split()[3].convert("RGB")
mask_array = np.array(mask)
mask_cv = cv2.cvtColor(mask_array, cv2.COLOR_BGR2GRAY)
mask_inv = cv2.bitwise_not(mask_cv)
# Inpaint Image
inpainted_result = cv2.inpaint(image_cv, mask_inv, 3, cv2.INPAINT_TELEA)
inpainted_image = Image.fromarray(cv2.cvtColor(inpainted_result, cv2.COLOR_BGR2RGB))
return inpainted_image

4
invokeai/backend/image_util/lama.py
View File

@ -5,6 +5,7 @@ import numpy as np
import torch import torch
from PIL import Image from PIL import Image
import invokeai.backend.util.logging as logger
from invokeai.app.services.config import get_invokeai_config from invokeai.app.services.config import get_invokeai_config
from invokeai.backend.util.devices import choose_torch_device from invokeai.backend.util.devices import choose_torch_device
@ -19,7 +20,7 @@ def norm_img(np_img):
def load_jit_model(url_or_path, device): def load_jit_model(url_or_path, device):
model_path = url_or_path model_path = url_or_path
print(f"Loading model from: {model_path}") logger.info(f"Loading model from: {model_path}")
model = torch.jit.load(model_path, map_location="cpu").to(device) model = torch.jit.load(model_path, map_location="cpu").to(device)
model.eval() model.eval()
return model return model
@ -52,5 +53,6 @@ class LaMA:
del model del model
gc.collect() gc.collect()
torch.cuda.empty_cache()
return infilled_image return infilled_image

11
invokeai/backend/install/invokeai_configure.py
View File

@ -290,9 +290,20 @@ def download_realesrgan():
download_with_progress_bar(model["url"], config.models_path / model["dest"], model["description"]) download_with_progress_bar(model["url"], config.models_path / model["dest"], model["description"])
# ---------------------------------------------
def download_lama():
logger.info("Installing lama infill model")
download_with_progress_bar(
"https://github.com/Sanster/models/releases/download/add_big_lama/big-lama.pt",
config.models_path / "core/misc/lama/lama.pt",
"lama infill model",
)
# --------------------------------------------- # ---------------------------------------------
def download_support_models(): def download_support_models():
download_realesrgan() download_realesrgan()
download_lama()
download_conversion_models() download_conversion_models()

2
invokeai/frontend/web/public/locales/en.json
View File

@ -511,6 +511,7 @@
"maskBlur": "Blur", "maskBlur": "Blur",
"maskBlurMethod": "Blur Method", "maskBlurMethod": "Blur Method",
"coherencePassHeader": "Coherence Pass", "coherencePassHeader": "Coherence Pass",
"coherenceMode": "Mode",
"coherenceSteps": "Steps", "coherenceSteps": "Steps",
"coherenceStrength": "Strength", "coherenceStrength": "Strength",
"seamLowThreshold": "Low", "seamLowThreshold": "Low",
@ -520,6 +521,7 @@
"scaledHeight": "Scaled H", "scaledHeight": "Scaled H",
"infillMethod": "Infill Method", "infillMethod": "Infill Method",
"tileSize": "Tile Size", "tileSize": "Tile Size",
"patchmatchDownScaleSize": "Downscale",
"boundingBoxHeader": "Bounding Box", "boundingBoxHeader": "Bounding Box",
"seamCorrectionHeader": "Seam Correction", "seamCorrectionHeader": "Seam Correction",
"infillScalingHeader": "Infill and Scaling", "infillScalingHeader": "Infill and Scaling",

80
invokeai/frontend/web/src/common/hooks/useIsReadyToInvoke.ts
View File

@ -31,52 +31,54 @@ const selector = createSelector(
reasons.push('No initial image selected'); reasons.push('No initial image selected');
} }
if (activeTabName === 'nodes' && nodes.shouldValidateGraph) { if (activeTabName === 'nodes') {
if (!nodes.nodes.length) { if (nodes.shouldValidateGraph) {
reasons.push('No nodes in graph'); if (!nodes.nodes.length) {
} reasons.push('No nodes in graph');
nodes.nodes.forEach((node) => {
if (!isInvocationNode(node)) {
return;
} }
const nodeTemplate = nodes.nodeTemplates[node.data.type]; nodes.nodes.forEach((node) => {
if (!isInvocationNode(node)) {
if (!nodeTemplate) {
// Node type not found
reasons.push('Missing node template');
return;
}
const connectedEdges = getConnectedEdges([node], nodes.edges);
forEach(node.data.inputs, (field) => {
const fieldTemplate = nodeTemplate.inputs[field.name];
const hasConnection = connectedEdges.some(
(edge) =>
edge.target === node.id && edge.targetHandle === field.name
);
if (!fieldTemplate) {
reasons.push('Missing field template');
return; return;
} }
if ( const nodeTemplate = nodes.nodeTemplates[node.data.type];
fieldTemplate.required &&
field.value === undefined && if (!nodeTemplate) {
!hasConnection // Node type not found
) { reasons.push('Missing node template');
reasons.push( return;
`${node.data.label || nodeTemplate.title} -> ${ }
field.label || fieldTemplate.title
} missing input` const connectedEdges = getConnectedEdges([node], nodes.edges);
forEach(node.data.inputs, (field) => {
const fieldTemplate = nodeTemplate.inputs[field.name];
const hasConnection = connectedEdges.some(
(edge) =>
edge.target === node.id && edge.targetHandle === field.name
); );
return;
} if (!fieldTemplate) {
reasons.push('Missing field template');
return;
}
if (
fieldTemplate.required &&
field.value === undefined &&
!hasConnection
) {
reasons.push(
`${node.data.label || nodeTemplate.title} -> ${
field.label || fieldTemplate.title
} missing input`
);
return;
}
});
}); });
}); }
} else { } else {
if (!model) { if (!model) {
reasons.push('No model selected'); reasons.push('No model selected');

6
invokeai/frontend/web/src/features/canvas/components/IAICanvasToolbar/IAICanvasToolChooserOptions.tsx
View File

@ -118,7 +118,11 @@ const IAICanvasToolChooserOptions = () => {
useHotkeys( useHotkeys(
['BracketLeft'], ['BracketLeft'],
() => { () => {
dispatch(setBrushSize(Math.max(brushSize - 5, 5))); if (brushSize - 5 <= 5) {
dispatch(setBrushSize(Math.max(brushSize - 1, 1)));
} else {
dispatch(setBrushSize(Math.max(brushSize - 5, 1)));
}
}, },
{ {
enabled: () => !isStaging, enabled: () => !isStaging,

9
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addSDXLRefinerToGraph.ts
View File

@ -10,7 +10,8 @@ import {
CANVAS_OUTPUT, CANVAS_OUTPUT,
INPAINT_IMAGE_RESIZE_UP, INPAINT_IMAGE_RESIZE_UP,
LATENTS_TO_IMAGE, LATENTS_TO_IMAGE,
MASK_BLUR, MASK_COMBINE,
MASK_RESIZE_UP,
METADATA_ACCUMULATOR, METADATA_ACCUMULATOR,
SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH, SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH,
SDXL_CANVAS_INPAINT_GRAPH, SDXL_CANVAS_INPAINT_GRAPH,
@ -46,6 +47,8 @@ export const addSDXLRefinerToGraph = (
const { seamlessXAxis, seamlessYAxis, vaePrecision } = state.generation; const { seamlessXAxis, seamlessYAxis, vaePrecision } = state.generation;
const { boundingBoxScaleMethod } = state.canvas; const { boundingBoxScaleMethod } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes( const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod boundingBoxScaleMethod
); );
@ -231,7 +234,7 @@ export const addSDXLRefinerToGraph = (
type: 'create_denoise_mask', type: 'create_denoise_mask',
id: SDXL_REFINER_INPAINT_CREATE_MASK, id: SDXL_REFINER_INPAINT_CREATE_MASK,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
if (isUsingScaledDimensions) { if (isUsingScaledDimensions) {
@ -257,7 +260,7 @@ export const addSDXLRefinerToGraph = (
graph.edges.push( graph.edges.push(
{ {
source: { source: {
node_id: MASK_BLUR, node_id: isUsingScaledDimensions ? MASK_RESIZE_UP : MASK_COMBINE,
field: 'image', field: 'image',
}, },
destination: { destination: {

17
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addVAEToGraph.ts
View File

@ -2,6 +2,7 @@ import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types'; import { NonNullableGraph } from 'features/nodes/types/types';
import { MetadataAccumulatorInvocation } from 'services/api/types'; import { MetadataAccumulatorInvocation } from 'services/api/types';
import { import {
CANVAS_COHERENCE_INPAINT_CREATE_MASK,
CANVAS_IMAGE_TO_IMAGE_GRAPH, CANVAS_IMAGE_TO_IMAGE_GRAPH,
CANVAS_INPAINT_GRAPH, CANVAS_INPAINT_GRAPH,
CANVAS_OUTPAINT_GRAPH, CANVAS_OUTPAINT_GRAPH,
@ -31,7 +32,7 @@ export const addVAEToGraph = (
graph: NonNullableGraph, graph: NonNullableGraph,
modelLoaderNodeId: string = MAIN_MODEL_LOADER modelLoaderNodeId: string = MAIN_MODEL_LOADER
): void => { ): void => {
const { vae } = state.generation; const { vae, canvasCoherenceMode } = state.generation;
const { boundingBoxScaleMethod } = state.canvas; const { boundingBoxScaleMethod } = state.canvas;
const { shouldUseSDXLRefiner } = state.sdxl; const { shouldUseSDXLRefiner } = state.sdxl;
@ -146,6 +147,20 @@ export const addVAEToGraph = (
}, },
} }
); );
// Handle Coherence Mode
if (canvasCoherenceMode !== 'unmasked') {
graph.edges.push({
source: {
node_id: isAutoVae ? modelLoaderNodeId : VAE_LOADER,
field: isAutoVae && isOnnxModel ? 'vae_decoder' : 'vae',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'vae',
},
});
}
} }
if (shouldUseSDXLRefiner) { if (shouldUseSDXLRefiner) {

6
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasImageToImageGraph.ts
View File

@ -59,6 +59,8 @@ export const buildCanvasImageToImageGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes( const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod boundingBoxScaleMethod
); );
@ -245,7 +247,7 @@ export const buildCanvasImageToImageGraph = (
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
type: 'l2i', type: 'l2i',
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
graph.nodes[CANVAS_OUTPUT] = { graph.nodes[CANVAS_OUTPUT] = {
id: CANVAS_OUTPUT, id: CANVAS_OUTPUT,
@ -292,7 +294,7 @@ export const buildCanvasImageToImageGraph = (
type: 'l2i', type: 'l2i',
id: CANVAS_OUTPUT, id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave, is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
(graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image = (graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image =

140
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasInpaintGraph.ts
View File

@ -6,6 +6,7 @@ import {
ImageBlurInvocation, ImageBlurInvocation,
ImageDTO, ImageDTO,
ImageToLatentsInvocation, ImageToLatentsInvocation,
MaskEdgeInvocation,
NoiseInvocation, NoiseInvocation,
RandomIntInvocation, RandomIntInvocation,
RangeOfSizeInvocation, RangeOfSizeInvocation,
@ -18,6 +19,8 @@ import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph'; import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import { import {
CANVAS_COHERENCE_DENOISE_LATENTS, CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_INPAINT_CREATE_MASK,
CANVAS_COHERENCE_MASK_EDGE,
CANVAS_COHERENCE_NOISE, CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT, CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_INPAINT_GRAPH, CANVAS_INPAINT_GRAPH,
@ -67,6 +70,7 @@ export const buildCanvasInpaintGraph = (
shouldUseCpuNoise, shouldUseCpuNoise,
maskBlur, maskBlur,
maskBlurMethod, maskBlurMethod,
canvasCoherenceMode,
canvasCoherenceSteps, canvasCoherenceSteps,
canvasCoherenceStrength, canvasCoherenceStrength,
clipSkip, clipSkip,
@ -89,6 +93,12 @@ export const buildCanvasInpaintGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
let modelLoaderNodeId = MAIN_MODEL_LOADER; let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings const use_cpu = shouldUseNoiseSettings
@ -133,13 +143,7 @@ export const buildCanvasInpaintGraph = (
type: 'i2l', type: 'i2l',
id: INPAINT_IMAGE, id: INPAINT_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
},
[INPAINT_CREATE_MASK]: {
type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK,
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
}, },
[NOISE]: { [NOISE]: {
type: 'noise', type: 'noise',
@ -147,6 +151,12 @@ export const buildCanvasInpaintGraph = (
use_cpu, use_cpu,
is_intermediate: true, is_intermediate: true,
}, },
[INPAINT_CREATE_MASK]: {
type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK,
is_intermediate: true,
fp32,
},
[DENOISE_LATENTS]: { [DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
id: DENOISE_LATENTS, id: DENOISE_LATENTS,
@ -171,7 +181,7 @@ export const buildCanvasInpaintGraph = (
}, },
[CANVAS_COHERENCE_DENOISE_LATENTS]: { [CANVAS_COHERENCE_DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
id: DENOISE_LATENTS, id: CANVAS_COHERENCE_DENOISE_LATENTS,
is_intermediate: true, is_intermediate: true,
steps: canvasCoherenceSteps, steps: canvasCoherenceSteps,
cfg_scale: cfg_scale, cfg_scale: cfg_scale,
@ -183,7 +193,7 @@ export const buildCanvasInpaintGraph = (
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[CANVAS_OUTPUT]: { [CANVAS_OUTPUT]: {
type: 'color_correct', type: 'color_correct',
@ -418,7 +428,7 @@ export const buildCanvasInpaintGraph = (
}; };
// Handle Scale Before Processing // Handle Scale Before Processing
if (['auto', 'manual'].includes(boundingBoxScaleMethod)) { if (isUsingScaledDimensions) {
const scaledWidth: number = scaledBoundingBoxDimensions.width; const scaledWidth: number = scaledBoundingBoxDimensions.width;
const scaledHeight: number = scaledBoundingBoxDimensions.height; const scaledHeight: number = scaledBoundingBoxDimensions.height;
@ -581,6 +591,116 @@ export const buildCanvasInpaintGraph = (
); );
} }
// Handle Coherence Mode
if (canvasCoherenceMode !== 'unmasked') {
// Create Mask If Coherence Mode Is Not Full
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
type: 'create_denoise_mask',
id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
is_intermediate: true,
fp32,
};
// Handle Image Input For Mask Creation
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: INPAINT_IMAGE_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'image',
},
});
} else {
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
...(graph.nodes[
CANVAS_COHERENCE_INPAINT_CREATE_MASK
] as CreateDenoiseMaskInvocation),
image: canvasInitImage,
};
}
// Create Mask If Coherence Mode Is Mask
if (canvasCoherenceMode === 'mask') {
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
} else {
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
...(graph.nodes[
CANVAS_COHERENCE_INPAINT_CREATE_MASK
] as CreateDenoiseMaskInvocation),
mask: canvasMaskImage,
};
}
}
// Create Mask Edge If Coherence Mode Is Edge
if (canvasCoherenceMode === 'edge') {
graph.nodes[CANVAS_COHERENCE_MASK_EDGE] = {
type: 'mask_edge',
id: CANVAS_COHERENCE_MASK_EDGE,
is_intermediate: true,
edge_blur: maskBlur,
edge_size: maskBlur * 2,
low_threshold: 100,
high_threshold: 200,
};
// Handle Scaled Dimensions For Mask Edge
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
});
} else {
graph.nodes[CANVAS_COHERENCE_MASK_EDGE] = {
...(graph.nodes[CANVAS_COHERENCE_MASK_EDGE] as MaskEdgeInvocation),
image: canvasMaskImage,
};
}
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
}
// Plug Denoise Mask To Coherence Denoise Latents
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: CANVAS_COHERENCE_DENOISE_LATENTS,
field: 'denoise_mask',
},
});
}
// Handle Seed // Handle Seed
if (shouldRandomizeSeed) { if (shouldRandomizeSeed) {
// Random int node to generate the starting seed // Random int node to generate the starting seed

209
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasOutpaintGraph.ts
View File

@ -2,7 +2,6 @@ import { logger } from 'app/logging/logger';
import { RootState } from 'app/store/store'; import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types'; import { NonNullableGraph } from 'features/nodes/types/types';
import { import {
ImageBlurInvocation,
ImageDTO, ImageDTO,
ImageToLatentsInvocation, ImageToLatentsInvocation,
InfillPatchMatchInvocation, InfillPatchMatchInvocation,
@ -19,6 +18,8 @@ import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph'; import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import { import {
CANVAS_COHERENCE_DENOISE_LATENTS, CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_INPAINT_CREATE_MASK,
CANVAS_COHERENCE_MASK_EDGE,
CANVAS_COHERENCE_NOISE, CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT, CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_OUTPAINT_GRAPH, CANVAS_OUTPAINT_GRAPH,
@ -34,7 +35,6 @@ import {
ITERATE, ITERATE,
LATENTS_TO_IMAGE, LATENTS_TO_IMAGE,
MAIN_MODEL_LOADER, MAIN_MODEL_LOADER,
MASK_BLUR,
MASK_COMBINE, MASK_COMBINE,
MASK_FROM_ALPHA, MASK_FROM_ALPHA,
MASK_RESIZE_DOWN, MASK_RESIZE_DOWN,
@ -71,10 +71,11 @@ export const buildCanvasOutpaintGraph = (
shouldUseNoiseSettings, shouldUseNoiseSettings,
shouldUseCpuNoise, shouldUseCpuNoise,
maskBlur, maskBlur,
maskBlurMethod, canvasCoherenceMode,
canvasCoherenceSteps, canvasCoherenceSteps,
canvasCoherenceStrength, canvasCoherenceStrength,
tileSize, infillTileSize,
infillPatchmatchDownscaleSize,
infillMethod, infillMethod,
clipSkip, clipSkip,
seamlessXAxis, seamlessXAxis,
@ -96,6 +97,12 @@ export const buildCanvasOutpaintGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
let modelLoaderNodeId = MAIN_MODEL_LOADER; let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings const use_cpu = shouldUseNoiseSettings
@ -141,18 +148,11 @@ export const buildCanvasOutpaintGraph = (
is_intermediate: true, is_intermediate: true,
mask2: canvasMaskImage, mask2: canvasMaskImage,
}, },
[MASK_BLUR]: {
type: 'img_blur',
id: MASK_BLUR,
is_intermediate: true,
radius: maskBlur,
blur_type: maskBlurMethod,
},
[INPAINT_IMAGE]: { [INPAINT_IMAGE]: {
type: 'i2l', type: 'i2l',
id: INPAINT_IMAGE, id: INPAINT_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[NOISE]: { [NOISE]: {
type: 'noise', type: 'noise',
@ -164,7 +164,7 @@ export const buildCanvasOutpaintGraph = (
type: 'create_denoise_mask', type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK, id: INPAINT_CREATE_MASK,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[DENOISE_LATENTS]: { [DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
@ -202,7 +202,7 @@ export const buildCanvasOutpaintGraph = (
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[CANVAS_OUTPUT]: { [CANVAS_OUTPUT]: {
type: 'color_correct', type: 'color_correct',
@ -333,7 +333,7 @@ export const buildCanvasOutpaintGraph = (
// Create Inpaint Mask // Create Inpaint Mask
{ {
source: { source: {
node_id: MASK_BLUR, node_id: isUsingScaledDimensions ? MASK_RESIZE_UP : MASK_COMBINE,
field: 'image', field: 'image',
}, },
destination: { destination: {
@ -443,6 +443,16 @@ export const buildCanvasOutpaintGraph = (
field: 'latents', field: 'latents',
}, },
}, },
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Decode the result from Inpaint // Decode the result from Inpaint
{ {
source: { source: {
@ -463,6 +473,7 @@ export const buildCanvasOutpaintGraph = (
type: 'infill_patchmatch', type: 'infill_patchmatch',
id: INPAINT_INFILL, id: INPAINT_INFILL,
is_intermediate: true, is_intermediate: true,
downscale: infillPatchmatchDownscaleSize,
}; };
} }
@ -474,17 +485,25 @@ export const buildCanvasOutpaintGraph = (
}; };
} }
if (infillMethod === 'cv2') {
graph.nodes[INPAINT_INFILL] = {
type: 'infill_cv2',
id: INPAINT_INFILL,
is_intermediate: true,
};
}
if (infillMethod === 'tile') { if (infillMethod === 'tile') {
graph.nodes[INPAINT_INFILL] = { graph.nodes[INPAINT_INFILL] = {
type: 'infill_tile', type: 'infill_tile',
id: INPAINT_INFILL, id: INPAINT_INFILL,
is_intermediate: true, is_intermediate: true,
tile_size: tileSize, tile_size: infillTileSize,
}; };
} }
// Handle Scale Before Processing // Handle Scale Before Processing
if (['auto', 'manual'].includes(boundingBoxScaleMethod)) { if (isUsingScaledDimensions) {
const scaledWidth: number = scaledBoundingBoxDimensions.width; const scaledWidth: number = scaledBoundingBoxDimensions.width;
const scaledHeight: number = scaledBoundingBoxDimensions.height; const scaledHeight: number = scaledBoundingBoxDimensions.height;
@ -546,16 +565,6 @@ export const buildCanvasOutpaintGraph = (
field: 'image', field: 'image',
}, },
}, },
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Take combined mask and resize and then blur // Take combined mask and resize and then blur
{ {
source: { source: {
@ -567,16 +576,7 @@ export const buildCanvasOutpaintGraph = (
field: 'image', field: 'image',
}, },
}, },
{
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: MASK_BLUR,
field: 'image',
},
},
// Resize Results Down // Resize Results Down
{ {
source: { source: {
@ -658,32 +658,8 @@ export const buildCanvasOutpaintGraph = (
...(graph.nodes[INPAINT_IMAGE] as ImageToLatentsInvocation), ...(graph.nodes[INPAINT_IMAGE] as ImageToLatentsInvocation),
image: canvasInitImage, image: canvasInitImage,
}; };
graph.nodes[MASK_BLUR] = {
...(graph.nodes[MASK_BLUR] as ImageBlurInvocation),
};
graph.edges.push( graph.edges.push(
// Take combined mask and plug it to blur
{
source: {
node_id: MASK_COMBINE,
field: 'image',
},
destination: {
node_id: MASK_BLUR,
field: 'image',
},
},
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Color Correct The Inpainted Result // Color Correct The Inpainted Result
{ {
source: { source: {
@ -707,7 +683,7 @@ export const buildCanvasOutpaintGraph = (
}, },
{ {
source: { source: {
node_id: MASK_BLUR, node_id: MASK_COMBINE,
field: 'image', field: 'image',
}, },
destination: { destination: {
@ -718,6 +694,115 @@ export const buildCanvasOutpaintGraph = (
); );
} }
// Handle Coherence Mode
if (canvasCoherenceMode !== 'unmasked') {
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
type: 'create_denoise_mask',
id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
is_intermediate: true,
fp32,
};
// Handle Image Input For Mask Creation
graph.edges.push({
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'image',
},
});
// Create Mask If Coherence Mode Is Mask
if (canvasCoherenceMode === 'mask') {
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
} else {
graph.edges.push({
source: {
node_id: MASK_COMBINE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
}
}
if (canvasCoherenceMode === 'edge') {
graph.nodes[CANVAS_COHERENCE_MASK_EDGE] = {
type: 'mask_edge',
id: CANVAS_COHERENCE_MASK_EDGE,
is_intermediate: true,
edge_blur: maskBlur,
edge_size: maskBlur * 2,
low_threshold: 100,
high_threshold: 200,
};
// Handle Scaled Dimensions For Mask Edge
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
});
} else {
graph.edges.push({
source: {
node_id: MASK_COMBINE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
});
}
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
}
// Plug Denoise Mask To Coherence Denoise Latents
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: CANVAS_COHERENCE_DENOISE_LATENTS,
field: 'denoise_mask',
},
});
}
// Handle Seed // Handle Seed
if (shouldRandomizeSeed) { if (shouldRandomizeSeed) {
// Random int node to generate the starting seed // Random int node to generate the starting seed

8
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLImageToImageGraph.ts
View File

@ -67,6 +67,8 @@ export const buildCanvasSDXLImageToImageGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes( const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod boundingBoxScaleMethod
); );
@ -133,7 +135,7 @@ export const buildCanvasSDXLImageToImageGraph = (
type: 'i2l', type: 'i2l',
id: IMAGE_TO_LATENTS, id: IMAGE_TO_LATENTS,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[SDXL_DENOISE_LATENTS]: { [SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
@ -258,7 +260,7 @@ export const buildCanvasSDXLImageToImageGraph = (
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
type: 'l2i', type: 'l2i',
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
graph.nodes[CANVAS_OUTPUT] = { graph.nodes[CANVAS_OUTPUT] = {
id: CANVAS_OUTPUT, id: CANVAS_OUTPUT,
@ -305,7 +307,7 @@ export const buildCanvasSDXLImageToImageGraph = (
type: 'l2i', type: 'l2i',
id: CANVAS_OUTPUT, id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave, is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
(graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image = (graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image =

130
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLInpaintGraph.ts
View File

@ -6,6 +6,7 @@ import {
ImageBlurInvocation, ImageBlurInvocation,
ImageDTO, ImageDTO,
ImageToLatentsInvocation, ImageToLatentsInvocation,
MaskEdgeInvocation,
NoiseInvocation, NoiseInvocation,
RandomIntInvocation, RandomIntInvocation,
RangeOfSizeInvocation, RangeOfSizeInvocation,
@ -19,6 +20,8 @@ import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph'; import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import { import {
CANVAS_COHERENCE_DENOISE_LATENTS, CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_INPAINT_CREATE_MASK,
CANVAS_COHERENCE_MASK_EDGE,
CANVAS_COHERENCE_NOISE, CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT, CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_OUTPUT, CANVAS_OUTPUT,
@ -68,6 +71,7 @@ export const buildCanvasSDXLInpaintGraph = (
shouldUseCpuNoise, shouldUseCpuNoise,
maskBlur, maskBlur,
maskBlurMethod, maskBlurMethod,
canvasCoherenceMode,
canvasCoherenceSteps, canvasCoherenceSteps,
canvasCoherenceStrength, canvasCoherenceStrength,
seamlessXAxis, seamlessXAxis,
@ -96,6 +100,12 @@ export const buildCanvasSDXLInpaintGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
let modelLoaderNodeId = SDXL_MODEL_LOADER; let modelLoaderNodeId = SDXL_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings const use_cpu = shouldUseNoiseSettings
@ -137,7 +147,7 @@ export const buildCanvasSDXLInpaintGraph = (
type: 'i2l', type: 'i2l',
id: INPAINT_IMAGE, id: INPAINT_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[NOISE]: { [NOISE]: {
type: 'noise', type: 'noise',
@ -149,7 +159,7 @@ export const buildCanvasSDXLInpaintGraph = (
type: 'create_denoise_mask', type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK, id: INPAINT_CREATE_MASK,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[SDXL_DENOISE_LATENTS]: { [SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
@ -177,7 +187,7 @@ export const buildCanvasSDXLInpaintGraph = (
}, },
[CANVAS_COHERENCE_DENOISE_LATENTS]: { [CANVAS_COHERENCE_DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
id: SDXL_DENOISE_LATENTS, id: CANVAS_COHERENCE_DENOISE_LATENTS,
is_intermediate: true, is_intermediate: true,
steps: canvasCoherenceSteps, steps: canvasCoherenceSteps,
cfg_scale: cfg_scale, cfg_scale: cfg_scale,
@ -189,7 +199,7 @@ export const buildCanvasSDXLInpaintGraph = (
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[CANVAS_OUTPUT]: { [CANVAS_OUTPUT]: {
type: 'color_correct', type: 'color_correct',
@ -433,7 +443,7 @@ export const buildCanvasSDXLInpaintGraph = (
}; };
// Handle Scale Before Processing // Handle Scale Before Processing
if (['auto', 'manual'].includes(boundingBoxScaleMethod)) { if (isUsingScaledDimensions) {
const scaledWidth: number = scaledBoundingBoxDimensions.width; const scaledWidth: number = scaledBoundingBoxDimensions.width;
const scaledHeight: number = scaledBoundingBoxDimensions.height; const scaledHeight: number = scaledBoundingBoxDimensions.height;
@ -596,6 +606,116 @@ export const buildCanvasSDXLInpaintGraph = (
); );
} }
// Handle Coherence Mode
if (canvasCoherenceMode !== 'unmasked') {
// Create Mask If Coherence Mode Is Not Full
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
type: 'create_denoise_mask',
id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
is_intermediate: true,
fp32,
};
// Handle Image Input For Mask Creation
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: INPAINT_IMAGE_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'image',
},
});
} else {
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
...(graph.nodes[
CANVAS_COHERENCE_INPAINT_CREATE_MASK
] as CreateDenoiseMaskInvocation),
image: canvasInitImage,
};
}
// Create Mask If Coherence Mode Is Mask
if (canvasCoherenceMode === 'mask') {
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
} else {
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
...(graph.nodes[
CANVAS_COHERENCE_INPAINT_CREATE_MASK
] as CreateDenoiseMaskInvocation),
mask: canvasMaskImage,
};
}
}
// Create Mask Edge If Coherence Mode Is Edge
if (canvasCoherenceMode === 'edge') {
graph.nodes[CANVAS_COHERENCE_MASK_EDGE] = {
type: 'mask_edge',
id: CANVAS_COHERENCE_MASK_EDGE,
is_intermediate: true,
edge_blur: maskBlur,
edge_size: maskBlur * 2,
low_threshold: 100,
high_threshold: 200,
};
// Handle Scaled Dimensions For Mask Edge
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
});
} else {
graph.nodes[CANVAS_COHERENCE_MASK_EDGE] = {
...(graph.nodes[CANVAS_COHERENCE_MASK_EDGE] as MaskEdgeInvocation),
image: canvasMaskImage,
};
}
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
}
// Plug Denoise Mask To Coherence Denoise Latents
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: CANVAS_COHERENCE_DENOISE_LATENTS,
field: 'denoise_mask',
},
});
}
// Handle Seed // Handle Seed
if (shouldRandomizeSeed) { if (shouldRandomizeSeed) {
// Random int node to generate the starting seed // Random int node to generate the starting seed

215
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLOutpaintGraph.ts
View File

@ -2,7 +2,6 @@ import { logger } from 'app/logging/logger';
import { RootState } from 'app/store/store'; import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types'; import { NonNullableGraph } from 'features/nodes/types/types';
import { import {
ImageBlurInvocation,
ImageDTO, ImageDTO,
ImageToLatentsInvocation, ImageToLatentsInvocation,
InfillPatchMatchInvocation, InfillPatchMatchInvocation,
@ -20,6 +19,8 @@ import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph'; import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import { import {
CANVAS_COHERENCE_DENOISE_LATENTS, CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_INPAINT_CREATE_MASK,
CANVAS_COHERENCE_MASK_EDGE,
CANVAS_COHERENCE_NOISE, CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT, CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_OUTPUT, CANVAS_OUTPUT,
@ -31,7 +32,6 @@ import {
INPAINT_INFILL_RESIZE_DOWN, INPAINT_INFILL_RESIZE_DOWN,
ITERATE, ITERATE,
LATENTS_TO_IMAGE, LATENTS_TO_IMAGE,
MASK_BLUR,
MASK_COMBINE, MASK_COMBINE,
MASK_FROM_ALPHA, MASK_FROM_ALPHA,
MASK_RESIZE_DOWN, MASK_RESIZE_DOWN,
@ -72,10 +72,11 @@ export const buildCanvasSDXLOutpaintGraph = (
shouldUseNoiseSettings, shouldUseNoiseSettings,
shouldUseCpuNoise, shouldUseCpuNoise,
maskBlur, maskBlur,
maskBlurMethod, canvasCoherenceMode,
canvasCoherenceSteps, canvasCoherenceSteps,
canvasCoherenceStrength, canvasCoherenceStrength,
tileSize, infillTileSize,
infillPatchmatchDownscaleSize,
infillMethod, infillMethod,
seamlessXAxis, seamlessXAxis,
seamlessYAxis, seamlessYAxis,
@ -103,6 +104,12 @@ export const buildCanvasSDXLOutpaintGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
let modelLoaderNodeId = SDXL_MODEL_LOADER; let modelLoaderNodeId = SDXL_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings const use_cpu = shouldUseNoiseSettings
@ -145,18 +152,11 @@ export const buildCanvasSDXLOutpaintGraph = (
is_intermediate: true, is_intermediate: true,
mask2: canvasMaskImage, mask2: canvasMaskImage,
}, },
[MASK_BLUR]: {
type: 'img_blur',
id: MASK_BLUR,
is_intermediate: true,
radius: maskBlur,
blur_type: maskBlurMethod,
},
[INPAINT_IMAGE]: { [INPAINT_IMAGE]: {
type: 'i2l', type: 'i2l',
id: INPAINT_IMAGE, id: INPAINT_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[NOISE]: { [NOISE]: {
type: 'noise', type: 'noise',
@ -168,7 +168,7 @@ export const buildCanvasSDXLOutpaintGraph = (
type: 'create_denoise_mask', type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK, id: INPAINT_CREATE_MASK,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[SDXL_DENOISE_LATENTS]: { [SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
@ -208,7 +208,7 @@ export const buildCanvasSDXLOutpaintGraph = (
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[CANVAS_OUTPUT]: { [CANVAS_OUTPUT]: {
type: 'color_correct', type: 'color_correct',
@ -348,7 +348,7 @@ export const buildCanvasSDXLOutpaintGraph = (
// Create Inpaint Mask // Create Inpaint Mask
{ {
source: { source: {
node_id: MASK_BLUR, node_id: isUsingScaledDimensions ? MASK_RESIZE_UP : MASK_COMBINE,
field: 'image', field: 'image',
}, },
destination: { destination: {
@ -410,7 +410,7 @@ export const buildCanvasSDXLOutpaintGraph = (
}, },
{ {
source: { source: {
node_id: SDXL_MODEL_LOADER, node_id: modelLoaderNodeId,
field: 'unet', field: 'unet',
}, },
destination: { destination: {
@ -458,6 +458,16 @@ export const buildCanvasSDXLOutpaintGraph = (
field: 'latents', field: 'latents',
}, },
}, },
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Decode inpainted latents to image // Decode inpainted latents to image
{ {
source: { source: {
@ -473,12 +483,12 @@ export const buildCanvasSDXLOutpaintGraph = (
}; };
// Add Infill Nodes // Add Infill Nodes
if (infillMethod === 'patchmatch') { if (infillMethod === 'patchmatch') {
graph.nodes[INPAINT_INFILL] = { graph.nodes[INPAINT_INFILL] = {
type: 'infill_patchmatch', type: 'infill_patchmatch',
id: INPAINT_INFILL, id: INPAINT_INFILL,
is_intermediate: true, is_intermediate: true,
downscale: infillPatchmatchDownscaleSize,
}; };
} }
@ -490,17 +500,25 @@ export const buildCanvasSDXLOutpaintGraph = (
}; };
} }
if (infillMethod === 'cv2') {
graph.nodes[INPAINT_INFILL] = {
type: 'infill_cv2',
id: INPAINT_INFILL,
is_intermediate: true,
};
}
if (infillMethod === 'tile') { if (infillMethod === 'tile') {
graph.nodes[INPAINT_INFILL] = { graph.nodes[INPAINT_INFILL] = {
type: 'infill_tile', type: 'infill_tile',
id: INPAINT_INFILL, id: INPAINT_INFILL,
is_intermediate: true, is_intermediate: true,
tile_size: tileSize, tile_size: infillTileSize,
}; };
} }
// Handle Scale Before Processing // Handle Scale Before Processing
if (['auto', 'manual'].includes(boundingBoxScaleMethod)) { if (isUsingScaledDimensions) {
const scaledWidth: number = scaledBoundingBoxDimensions.width; const scaledWidth: number = scaledBoundingBoxDimensions.width;
const scaledHeight: number = scaledBoundingBoxDimensions.height; const scaledHeight: number = scaledBoundingBoxDimensions.height;
@ -562,16 +580,7 @@ export const buildCanvasSDXLOutpaintGraph = (
field: 'image', field: 'image',
}, },
}, },
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Take combined mask and resize and then blur // Take combined mask and resize and then blur
{ {
source: { source: {
@ -583,16 +592,7 @@ export const buildCanvasSDXLOutpaintGraph = (
field: 'image', field: 'image',
}, },
}, },
{
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: MASK_BLUR,
field: 'image',
},
},
// Resize Results Down // Resize Results Down
{ {
source: { source: {
@ -674,32 +674,8 @@ export const buildCanvasSDXLOutpaintGraph = (
...(graph.nodes[INPAINT_IMAGE] as ImageToLatentsInvocation), ...(graph.nodes[INPAINT_IMAGE] as ImageToLatentsInvocation),
image: canvasInitImage, image: canvasInitImage,
}; };
graph.nodes[MASK_BLUR] = {
...(graph.nodes[MASK_BLUR] as ImageBlurInvocation),
};
graph.edges.push( graph.edges.push(
// Take combined mask and plug it to blur
{
source: {
node_id: MASK_COMBINE,
field: 'image',
},
destination: {
node_id: MASK_BLUR,
field: 'image',
},
},
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Color Correct The Inpainted Result // Color Correct The Inpainted Result
{ {
source: { source: {
@ -723,7 +699,7 @@ export const buildCanvasSDXLOutpaintGraph = (
}, },
{ {
source: { source: {
node_id: MASK_BLUR, node_id: MASK_COMBINE,
field: 'image', field: 'image',
}, },
destination: { destination: {
@ -734,7 +710,116 @@ export const buildCanvasSDXLOutpaintGraph = (
); );
} }
// Handle seed // Handle Coherence Mode
if (canvasCoherenceMode !== 'unmasked') {
graph.nodes[CANVAS_COHERENCE_INPAINT_CREATE_MASK] = {
type: 'create_denoise_mask',
id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
is_intermediate: true,
fp32,
};
// Handle Image Input For Mask Creation
graph.edges.push({
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'image',
},
});
// Create Mask If Coherence Mode Is Mask
if (canvasCoherenceMode === 'mask') {
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
} else {
graph.edges.push({
source: {
node_id: MASK_COMBINE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
}
}
if (canvasCoherenceMode === 'edge') {
graph.nodes[CANVAS_COHERENCE_MASK_EDGE] = {
type: 'mask_edge',
id: CANVAS_COHERENCE_MASK_EDGE,
is_intermediate: true,
edge_blur: maskBlur,
edge_size: maskBlur * 2,
low_threshold: 100,
high_threshold: 200,
};
// Handle Scaled Dimensions For Mask Edge
if (isUsingScaledDimensions) {
graph.edges.push({
source: {
node_id: MASK_RESIZE_UP,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
});
} else {
graph.edges.push({
source: {
node_id: MASK_COMBINE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
});
}
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_MASK_EDGE,
field: 'image',
},
destination: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'mask',
},
});
}
// Plug Denoise Mask To Coherence Denoise Latents
graph.edges.push({
source: {
node_id: CANVAS_COHERENCE_INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: CANVAS_COHERENCE_DENOISE_LATENTS,
field: 'denoise_mask',
},
});
}
// Handle Seed
if (shouldRandomizeSeed) { if (shouldRandomizeSeed) {
// Random int node to generate the starting seed // Random int node to generate the starting seed
const randomIntNode: RandomIntInvocation = { const randomIntNode: RandomIntInvocation = {

6
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLTextToImageGraph.ts
View File

@ -61,6 +61,8 @@ export const buildCanvasSDXLTextToImageGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes( const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod boundingBoxScaleMethod
); );
@ -252,7 +254,7 @@ export const buildCanvasSDXLTextToImageGraph = (
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i', type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
graph.nodes[CANVAS_OUTPUT] = { graph.nodes[CANVAS_OUTPUT] = {
@ -290,7 +292,7 @@ export const buildCanvasSDXLTextToImageGraph = (
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i', type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: CANVAS_OUTPUT, id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave, is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
graph.edges.push({ graph.edges.push({

6
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasTextToImageGraph.ts
View File

@ -59,6 +59,8 @@ export const buildCanvasTextToImageGraph = (
shouldAutoSave, shouldAutoSave,
} = state.canvas; } = state.canvas;
const fp32 = vaePrecision === 'fp32';
const isUsingScaledDimensions = ['auto', 'manual'].includes( const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod boundingBoxScaleMethod
); );
@ -238,7 +240,7 @@ export const buildCanvasTextToImageGraph = (
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i', type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
is_intermediate: true, is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
graph.nodes[CANVAS_OUTPUT] = { graph.nodes[CANVAS_OUTPUT] = {
@ -276,7 +278,7 @@ export const buildCanvasTextToImageGraph = (
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i', type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: CANVAS_OUTPUT, id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave, is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}; };
graph.edges.push({ graph.edges.push({

6
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearImageToImageGraph.ts
View File

@ -84,6 +84,8 @@ export const buildLinearImageToImageGraph = (
throw new Error('No model found in state'); throw new Error('No model found in state');
} }
const fp32 = vaePrecision === 'fp32';
let modelLoaderNodeId = MAIN_MODEL_LOADER; let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings const use_cpu = shouldUseNoiseSettings
@ -122,7 +124,7 @@ export const buildLinearImageToImageGraph = (
[LATENTS_TO_IMAGE]: { [LATENTS_TO_IMAGE]: {
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[DENOISE_LATENTS]: { [DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
@ -140,7 +142,7 @@ export const buildLinearImageToImageGraph = (
// image: { // image: {
// image_name: initialImage.image_name, // image_name: initialImage.image_name,
// }, // },
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
}, },
edges: [ edges: [

6
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearSDXLImageToImageGraph.ts
View File

@ -84,6 +84,8 @@ export const buildLinearSDXLImageToImageGraph = (
throw new Error('No model found in state'); throw new Error('No model found in state');
} }
const fp32 = vaePrecision === 'fp32';
// Model Loader ID // Model Loader ID
let modelLoaderNodeId = SDXL_MODEL_LOADER; let modelLoaderNodeId = SDXL_MODEL_LOADER;
@ -124,7 +126,7 @@ export const buildLinearSDXLImageToImageGraph = (
[LATENTS_TO_IMAGE]: { [LATENTS_TO_IMAGE]: {
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
[SDXL_DENOISE_LATENTS]: { [SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents', type: 'denoise_latents',
@ -144,7 +146,7 @@ export const buildLinearSDXLImageToImageGraph = (
// image: { // image: {
// image_name: initialImage.image_name, // image_name: initialImage.image_name,
// }, // },
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
}, },
edges: [ edges: [

4
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearSDXLTextToImageGraph.ts
View File

@ -62,6 +62,8 @@ export const buildLinearSDXLTextToImageGraph = (
throw new Error('No model found in state'); throw new Error('No model found in state');
} }
const fp32 = vaePrecision === 'fp32';
// Construct Style Prompt // Construct Style Prompt
const { craftedPositiveStylePrompt, craftedNegativeStylePrompt } = const { craftedPositiveStylePrompt, craftedNegativeStylePrompt } =
craftSDXLStylePrompt(state, shouldConcatSDXLStylePrompt); craftSDXLStylePrompt(state, shouldConcatSDXLStylePrompt);
@ -118,7 +120,7 @@ export const buildLinearSDXLTextToImageGraph = (
[LATENTS_TO_IMAGE]: { [LATENTS_TO_IMAGE]: {
type: 'l2i', type: 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
}, },
edges: [ edges: [

4
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearTextToImageGraph.ts
View File

@ -57,6 +57,8 @@ export const buildLinearTextToImageGraph = (
throw new Error('No model found in state'); throw new Error('No model found in state');
} }
const fp32 = vaePrecision === 'fp32';
const isUsingOnnxModel = model.model_type === 'onnx'; const isUsingOnnxModel = model.model_type === 'onnx';
let modelLoaderNodeId = isUsingOnnxModel let modelLoaderNodeId = isUsingOnnxModel
@ -139,7 +141,7 @@ export const buildLinearTextToImageGraph = (
[LATENTS_TO_IMAGE]: { [LATENTS_TO_IMAGE]: {
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i', type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: LATENTS_TO_IMAGE, id: LATENTS_TO_IMAGE,
fp32: vaePrecision === 'fp32' ? true : false, fp32,
}, },
}, },
edges: [ edges: [

4
invokeai/frontend/web/src/features/nodes/util/graphBuilders/constants.ts
View File

@ -27,11 +27,15 @@ export const INPAINT_INFILL = 'inpaint_infill';
export const INPAINT_INFILL_RESIZE_DOWN = 'inpaint_infill_resize_down'; export const INPAINT_INFILL_RESIZE_DOWN = 'inpaint_infill_resize_down';
export const INPAINT_FINAL_IMAGE = 'inpaint_final_image'; export const INPAINT_FINAL_IMAGE = 'inpaint_final_image';
export const INPAINT_CREATE_MASK = 'inpaint_create_mask'; export const INPAINT_CREATE_MASK = 'inpaint_create_mask';
export const INPAINT_MASK = 'inpaint_mask';
export const CANVAS_COHERENCE_DENOISE_LATENTS = export const CANVAS_COHERENCE_DENOISE_LATENTS =
'canvas_coherence_denoise_latents'; 'canvas_coherence_denoise_latents';
export const CANVAS_COHERENCE_NOISE = 'canvas_coherence_noise'; export const CANVAS_COHERENCE_NOISE = 'canvas_coherence_noise';
export const CANVAS_COHERENCE_NOISE_INCREMENT = export const CANVAS_COHERENCE_NOISE_INCREMENT =
'canvas_coherence_noise_increment'; 'canvas_coherence_noise_increment';
export const CANVAS_COHERENCE_MASK_EDGE = 'canvas_coherence_mask_edge';
export const CANVAS_COHERENCE_INPAINT_CREATE_MASK =
'canvas_coherence_inpaint_create_mask';
export const MASK_FROM_ALPHA = 'tomask'; export const MASK_FROM_ALPHA = 'tomask';
export const MASK_EDGE = 'mask_edge'; export const MASK_EDGE = 'mask_edge';
export const MASK_BLUR = 'mask_blur'; export const MASK_BLUR = 'mask_blur';

42
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/Compositing/CoherencePass/ParamCanvasCoherenceMode.tsx Normal file
View File

@ -0,0 +1,42 @@
import type { RootState } from 'app/store/store';
import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import { IAISelectDataType } from 'common/components/IAIMantineSearchableSelect';
import IAIMantineSelect from 'common/components/IAIMantineSelect';
import { setCanvasCoherenceMode } from 'features/parameters/store/generationSlice';
import { CanvasCoherenceModeParam } from 'features/parameters/types/parameterSchemas';
import { memo } from 'react';
import { useTranslation } from 'react-i18next';
const coherenceModeSelectData: IAISelectDataType[] = [
{ label: 'Unmasked', value: 'unmasked' },
{ label: 'Mask', value: 'mask' },
{ label: 'Mask Edge', value: 'edge' },
];
const ParamCanvasCoherenceMode = () => {
const dispatch = useAppDispatch();
const canvasCoherenceMode = useAppSelector(
(state: RootState) => state.generation.canvasCoherenceMode
);
const { t } = useTranslation();
const handleCoherenceModeChange = (v: string | null) => {
if (!v) {
return;
}
dispatch(setCanvasCoherenceMode(v as CanvasCoherenceModeParam));
};
return (
<IAIMantineSelect
label={t('parameters.coherenceMode')}
data={coherenceModeSelectData}
value={canvasCoherenceMode}
onChange={handleCoherenceModeChange}
/>
);
};
export default memo(ParamCanvasCoherenceMode);

12
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/Compositing/ParamCompositingSettingsCollapse.tsx
View File

@ -3,6 +3,7 @@ import IAICollapse from 'common/components/IAICollapse';
import { memo } from 'react'; import { memo } from 'react';
import { useTranslation } from 'react-i18next'; import { useTranslation } from 'react-i18next';
import SubParametersWrapper from '../../SubParametersWrapper'; import SubParametersWrapper from '../../SubParametersWrapper';
import ParamCanvasCoherenceMode from './CoherencePass/ParamCanvasCoherenceMode';
import ParamCanvasCoherenceSteps from './CoherencePass/ParamCanvasCoherenceSteps'; import ParamCanvasCoherenceSteps from './CoherencePass/ParamCanvasCoherenceSteps';
import ParamCanvasCoherenceStrength from './CoherencePass/ParamCanvasCoherenceStrength'; import ParamCanvasCoherenceStrength from './CoherencePass/ParamCanvasCoherenceStrength';
import ParamMaskBlur from './MaskAdjustment/ParamMaskBlur'; import ParamMaskBlur from './MaskAdjustment/ParamMaskBlur';
@ -14,15 +15,16 @@ const ParamCompositingSettingsCollapse = () => {
return ( return (
<IAICollapse label={t('parameters.compositingSettingsHeader')}> <IAICollapse label={t('parameters.compositingSettingsHeader')}>
<Flex sx={{ flexDirection: 'column', gap: 2 }}> <Flex sx={{ flexDirection: 'column', gap: 2 }}>
<SubParametersWrapper label={t('parameters.coherencePassHeader')}>
<ParamCanvasCoherenceMode />
<ParamCanvasCoherenceSteps />
<ParamCanvasCoherenceStrength />
</SubParametersWrapper>
<Divider />
<SubParametersWrapper label={t('parameters.maskAdjustmentsHeader')}> <SubParametersWrapper label={t('parameters.maskAdjustmentsHeader')}>
<ParamMaskBlur /> <ParamMaskBlur />
<ParamMaskBlurMethod /> <ParamMaskBlurMethod />
</SubParametersWrapper> </SubParametersWrapper>
<Divider />
<SubParametersWrapper label={t('parameters.coherencePassHeader')}>
<ParamCanvasCoherenceSteps />
<ParamCanvasCoherenceStrength />
</SubParametersWrapper>
</Flex> </Flex>
</IAICollapse> </IAICollapse>
); );

4
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/InfillAndScaling/ParamInfillAndScalingCollapse.tsx
View File

@ -5,7 +5,7 @@ import { useTranslation } from 'react-i18next';
import IAICollapse from 'common/components/IAICollapse'; import IAICollapse from 'common/components/IAICollapse';
import SubParametersWrapper from '../../SubParametersWrapper'; import SubParametersWrapper from '../../SubParametersWrapper';
import ParamInfillMethod from './ParamInfillMethod'; import ParamInfillMethod from './ParamInfillMethod';
import ParamInfillTilesize from './ParamInfillTilesize'; import ParamInfillOptions from './ParamInfillOptions';
import ParamScaleBeforeProcessing from './ParamScaleBeforeProcessing'; import ParamScaleBeforeProcessing from './ParamScaleBeforeProcessing';
import ParamScaledHeight from './ParamScaledHeight'; import ParamScaledHeight from './ParamScaledHeight';
import ParamScaledWidth from './ParamScaledWidth'; import ParamScaledWidth from './ParamScaledWidth';
@ -18,7 +18,7 @@ const ParamInfillCollapse = () => {
<Flex sx={{ gap: 2, flexDirection: 'column' }}> <Flex sx={{ gap: 2, flexDirection: 'column' }}>
<SubParametersWrapper> <SubParametersWrapper>
<ParamInfillMethod /> <ParamInfillMethod />
<ParamInfillTilesize /> <ParamInfillOptions />
</SubParametersWrapper> </SubParametersWrapper>
<Divider /> <Divider />
<SubParametersWrapper> <SubParametersWrapper>

4
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/InfillAndScaling/ParamInfillMethod.tsx
View File

@ -27,9 +27,7 @@ const ParamInfillMethod = () => {
const { data: appConfigData, isLoading } = useGetAppConfigQuery(); const { data: appConfigData, isLoading } = useGetAppConfigQuery();
const infill_methods = appConfigData?.infill_methods.filter( const infill_methods = appConfigData?.infill_methods;
(method) => method !== 'lama'
);
const { t } = useTranslation(); const { t } = useTranslation();

29
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/InfillAndScaling/ParamInfillOptions.tsx Normal file
View File

@ -0,0 +1,29 @@
import { Flex } from '@chakra-ui/react';
import { createSelector } from '@reduxjs/toolkit';
import { useAppSelector } from 'app/store/storeHooks';
import { defaultSelectorOptions } from 'app/store/util/defaultMemoizeOptions';
import { generationSelector } from 'features/parameters/store/generationSelectors';
import ParamInfillPatchmatchDownscaleSize from './ParamInfillPatchmatchDownscaleSize';
import ParamInfillTilesize from './ParamInfillTilesize';
const selector = createSelector(
[generationSelector],
(parameters) => {
const { infillMethod } = parameters;
return {
infillMethod,
};
},
defaultSelectorOptions
);
export default function ParamInfillOptions() {
const { infillMethod } = useAppSelector(selector);
return (
<Flex>
{infillMethod === 'tile' && <ParamInfillTilesize />}
{infillMethod === 'patchmatch' && <ParamInfillPatchmatchDownscaleSize />}
</Flex>
);
}

58
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/InfillAndScaling/ParamInfillPatchmatchDownscaleSize.tsx Normal file
View File

@ -0,0 +1,58 @@
import { createSelector } from '@reduxjs/toolkit';
import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import { defaultSelectorOptions } from 'app/store/util/defaultMemoizeOptions';
import IAISlider from 'common/components/IAISlider';
import { generationSelector } from 'features/parameters/store/generationSelectors';
import { setInfillPatchmatchDownscaleSize } from 'features/parameters/store/generationSlice';
import { memo, useCallback } from 'react';
import { useTranslation } from 'react-i18next';
const selector = createSelector(
[generationSelector],
(parameters) => {
const { infillPatchmatchDownscaleSize, infillMethod } = parameters;
return {
infillPatchmatchDownscaleSize,
infillMethod,
};
},
defaultSelectorOptions
);
const ParamInfillPatchmatchDownscaleSize = () => {
const dispatch = useAppDispatch();
const { infillPatchmatchDownscaleSize, infillMethod } =
useAppSelector(selector);
const { t } = useTranslation();
const handleChange = useCallback(
(v: number) => {
dispatch(setInfillPatchmatchDownscaleSize(v));
},
[dispatch]
);
const handleReset = useCallback(() => {
dispatch(setInfillPatchmatchDownscaleSize(2));
}, [dispatch]);
return (
<IAISlider
isDisabled={infillMethod !== 'patchmatch'}
label={t('parameters.patchmatchDownScaleSize')}
min={1}
max={10}
value={infillPatchmatchDownscaleSize}
onChange={handleChange}
withInput
withSliderMarks
withReset
handleReset={handleReset}
/>
);
};
export default memo(ParamInfillPatchmatchDownscaleSize);

14
invokeai/frontend/web/src/features/parameters/components/Parameters/Canvas/InfillAndScaling/ParamInfillTilesize.tsx
View File

@ -3,7 +3,7 @@ import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
import { defaultSelectorOptions } from 'app/store/util/defaultMemoizeOptions'; import { defaultSelectorOptions } from 'app/store/util/defaultMemoizeOptions';
import IAISlider from 'common/components/IAISlider'; import IAISlider from 'common/components/IAISlider';
import { generationSelector } from 'features/parameters/store/generationSelectors'; import { generationSelector } from 'features/parameters/store/generationSelectors';
import { setTileSize } from 'features/parameters/store/generationSlice'; import { setInfillTileSize } from 'features/parameters/store/generationSlice';
import { memo, useCallback } from 'react'; import { memo, useCallback } from 'react';
import { useTranslation } from 'react-i18next'; import { useTranslation } from 'react-i18next';
@ -11,10 +11,10 @@ import { useTranslation } from 'react-i18next';
const selector = createSelector( const selector = createSelector(
[generationSelector], [generationSelector],
(parameters) => { (parameters) => {
const { tileSize, infillMethod } = parameters; const { infillTileSize, infillMethod } = parameters;
return { return {
tileSize, infillTileSize,
infillMethod, infillMethod,
}; };
}, },
@ -23,19 +23,19 @@ const selector = createSelector(
const ParamInfillTileSize = () => { const ParamInfillTileSize = () => {
const dispatch = useAppDispatch(); const dispatch = useAppDispatch();
const { tileSize, infillMethod } = useAppSelector(selector); const { infillTileSize, infillMethod } = useAppSelector(selector);
const { t } = useTranslation(); const { t } = useTranslation();
const handleChange = useCallback( const handleChange = useCallback(
(v: number) => { (v: number) => {
dispatch(setTileSize(v)); dispatch(setInfillTileSize(v));
}, },
[dispatch] [dispatch]
); );
const handleReset = useCallback(() => { const handleReset = useCallback(() => {
dispatch(setTileSize(32)); dispatch(setInfillTileSize(32));
}, [dispatch]); }, [dispatch]);
return ( return (
@ -45,7 +45,7 @@ const ParamInfillTileSize = () => {
min={16} min={16}
max={64} max={64}
sliderNumberInputProps={{ max: 256 }} sliderNumberInputProps={{ max: 256 }}
value={tileSize} value={infillTileSize}
onChange={handleChange} onChange={handleChange}
withInput withInput
withSliderMarks withSliderMarks

31
invokeai/frontend/web/src/features/parameters/store/generationSlice.ts
View File

@ -7,6 +7,7 @@ import { ImageDTO } from 'services/api/types';
import { clipSkipMap } from '../types/constants'; import { clipSkipMap } from '../types/constants';
import { import {
CanvasCoherenceModeParam,
CfgScaleParam, CfgScaleParam,
HeightParam, HeightParam,
MainModelParam, MainModelParam,
@ -37,6 +38,7 @@ export interface GenerationState {
scheduler: SchedulerParam; scheduler: SchedulerParam;
maskBlur: number; maskBlur: number;
maskBlurMethod: MaskBlurMethodParam; maskBlurMethod: MaskBlurMethodParam;
canvasCoherenceMode: CanvasCoherenceModeParam;
canvasCoherenceSteps: number; canvasCoherenceSteps: number;
canvasCoherenceStrength: StrengthParam; canvasCoherenceStrength: StrengthParam;
seed: SeedParam; seed: SeedParam;
@ -47,7 +49,8 @@ export interface GenerationState {
shouldUseNoiseSettings: boolean; shouldUseNoiseSettings: boolean;
steps: StepsParam; steps: StepsParam;
threshold: number; threshold: number;
tileSize: number; infillTileSize: number;
infillPatchmatchDownscaleSize: number;
variationAmount: number; variationAmount: number;
width: WidthParam; width: WidthParam;
shouldUseSymmetry: boolean; shouldUseSymmetry: boolean;
@ -77,6 +80,7 @@ export const initialGenerationState: GenerationState = {
scheduler: 'euler', scheduler: 'euler',
maskBlur: 16, maskBlur: 16,
maskBlurMethod: 'box', maskBlurMethod: 'box',
canvasCoherenceMode: 'edge',
canvasCoherenceSteps: 20, canvasCoherenceSteps: 20,
canvasCoherenceStrength: 0.3, canvasCoherenceStrength: 0.3,
seed: 0, seed: 0,
@ -87,7 +91,8 @@ export const initialGenerationState: GenerationState = {
shouldUseNoiseSettings: false, shouldUseNoiseSettings: false,
steps: 50, steps: 50,
threshold: 0, threshold: 0,
tileSize: 32, infillTileSize: 32,
infillPatchmatchDownscaleSize: 1,
variationAmount: 0.1, variationAmount: 0.1,
width: 512, width: 512,
shouldUseSymmetry: false, shouldUseSymmetry: false,
@ -206,18 +211,30 @@ export const generationSlice = createSlice({
setMaskBlurMethod: (state, action: PayloadAction<MaskBlurMethodParam>) => { setMaskBlurMethod: (state, action: PayloadAction<MaskBlurMethodParam>) => {
state.maskBlurMethod = action.payload; state.maskBlurMethod = action.payload;
}, },
setCanvasCoherenceMode: (
state,
action: PayloadAction<CanvasCoherenceModeParam>
) => {
state.canvasCoherenceMode = action.payload;
},
setCanvasCoherenceSteps: (state, action: PayloadAction<number>) => { setCanvasCoherenceSteps: (state, action: PayloadAction<number>) => {
state.canvasCoherenceSteps = action.payload; state.canvasCoherenceSteps = action.payload;
}, },
setCanvasCoherenceStrength: (state, action: PayloadAction<number>) => { setCanvasCoherenceStrength: (state, action: PayloadAction<number>) => {
state.canvasCoherenceStrength = action.payload; state.canvasCoherenceStrength = action.payload;
}, },
setTileSize: (state, action: PayloadAction<number>) => {
state.tileSize = action.payload;
},
setInfillMethod: (state, action: PayloadAction<string>) => { setInfillMethod: (state, action: PayloadAction<string>) => {
state.infillMethod = action.payload; state.infillMethod = action.payload;
}, },
setInfillTileSize: (state, action: PayloadAction<number>) => {
state.infillTileSize = action.payload;
},
setInfillPatchmatchDownscaleSize: (
state,
action: PayloadAction<number>
) => {
state.infillPatchmatchDownscaleSize = action.payload;
},
setShouldUseSymmetry: (state, action: PayloadAction<boolean>) => { setShouldUseSymmetry: (state, action: PayloadAction<boolean>) => {
state.shouldUseSymmetry = action.payload; state.shouldUseSymmetry = action.payload;
}, },
@ -323,6 +340,7 @@ export const {
setScheduler, setScheduler,
setMaskBlur, setMaskBlur,
setMaskBlurMethod, setMaskBlurMethod,
setCanvasCoherenceMode,
setCanvasCoherenceSteps, setCanvasCoherenceSteps,
setCanvasCoherenceStrength, setCanvasCoherenceStrength,
setSeed, setSeed,
@ -332,7 +350,8 @@ export const {
setShouldRandomizeSeed, setShouldRandomizeSeed,
setSteps, setSteps,
setThreshold, setThreshold,
setTileSize, setInfillTileSize,
setInfillPatchmatchDownscaleSize,
setVariationAmount, setVariationAmount,
setShouldUseSymmetry, setShouldUseSymmetry,
setHorizontalSymmetrySteps, setHorizontalSymmetrySteps,

16
invokeai/frontend/web/src/features/parameters/types/parameterSchemas.ts
View File

@ -418,6 +418,22 @@ export const isValidMaskBlurMethod = (
val: unknown val: unknown
): val is MaskBlurMethodParam => zMaskBlurMethod.safeParse(val).success; ): val is MaskBlurMethodParam => zMaskBlurMethod.safeParse(val).success;
/**
* Zod schema for a Canvas Coherence Mode method parameter
*/
export const zCanvasCoherenceMode = z.enum(['unmasked', 'mask', 'edge']);
/**
* Type alias for Canvas Coherence Mode parameter, inferred from its zod schema
*/
export type CanvasCoherenceModeParam = z.infer<typeof zCanvasCoherenceMode>;
/**
* Validates/type-guards a value as a mask blur method parameter
*/
export const isValidCoherenceModeParam = (
val: unknown
): val is CanvasCoherenceModeParam =>
zCanvasCoherenceMode.safeParse(val).success;
// /** // /**
// * Zod schema for BaseModelType // * Zod schema for BaseModelType
// */ // */

337
invokeai/frontend/web/src/services/api/schema.d.ts vendored
View File

File diff suppressed because one or more lines are too long

1
invokeai/frontend/web/src/services/api/types.ts
View File

@ -112,6 +112,7 @@ export type ImageScaleInvocation = s['ImageScaleInvocation'];
export type InfillPatchMatchInvocation = s['InfillPatchMatchInvocation']; export type InfillPatchMatchInvocation = s['InfillPatchMatchInvocation'];
export type InfillTileInvocation = s['InfillTileInvocation']; export type InfillTileInvocation = s['InfillTileInvocation'];
export type CreateDenoiseMaskInvocation = s['CreateDenoiseMaskInvocation']; export type CreateDenoiseMaskInvocation = s['CreateDenoiseMaskInvocation'];
export type MaskEdgeInvocation = s['MaskEdgeInvocation'];
export type RandomIntInvocation = s['RandomIntInvocation']; export type RandomIntInvocation = s['RandomIntInvocation'];
export type CompelInvocation = s['CompelInvocation']; export type CompelInvocation = s['CompelInvocation'];
export type DynamicPromptInvocation = s['DynamicPromptInvocation']; export type DynamicPromptInvocation = s['DynamicPromptInvocation'];