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/batch-graphs

Browse Source
This commit is contained in:
Mary Hipp Rogers 2023-08-29 09:07:18 -04:00 committed by GitHub
commit 6d5403e19d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
45 changed files with 1692 additions and 413 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
invokeai/app/invocations/image.py
View File

@ -375,6 +375,9 @@ class ImageResizeInvocation(BaseInvocation):
width: int = InputField(default=512, ge=64, multiple_of=8, description="The width to resize to (px)")
height: int = InputField(default=512, ge=64, multiple_of=8, description="The height to resize to (px)")
resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
metadata: Optional[CoreMetadata] = InputField(
default=None, description=FieldDescriptions.core_metadata, ui_hidden=True
)
def invoke(self, context: InvocationContext) -> ImageOutput:
image = context.services.images.get_pil_image(self.image.image_name)
@ -393,6 +396,7 @@ class ImageResizeInvocation(BaseInvocation):
node_id=self.id,
session_id=context.graph_execution_state_id,
is_intermediate=self.is_intermediate,
metadata=self.metadata.dict() if self.metadata else None,
)
return ImageOutput(

160
invokeai/app/invocations/latent.py
View File

@ -21,6 +21,8 @@ from torchvision.transforms.functional import resize as tv_resize
from invokeai.app.invocations.metadata import CoreMetadata
from invokeai.app.invocations.primitives import (
DenoiseMaskField,
DenoiseMaskOutput,
ImageField,
ImageOutput,
LatentsField,
@ -31,8 +33,9 @@ from invokeai.app.util.controlnet_utils import prepare_control_image
from invokeai.app.util.step_callback import stable_diffusion_step_callback
from invokeai.backend.model_management.models import ModelType, SilenceWarnings
from ...backend.model_management.models import BaseModelType
from ...backend.model_management.lora import ModelPatcher
from ...backend.model_management.seamless import set_seamless
from ...backend.model_management.models import BaseModelType
from ...backend.stable_diffusion import PipelineIntermediateState
from ...backend.stable_diffusion.diffusers_pipeline import (
ConditioningData,
@ -44,16 +47,7 @@ from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import Post
from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
from ...backend.util.devices import choose_precision, choose_torch_device
from ..models.image import ImageCategory, ResourceOrigin
from .baseinvocation import (
BaseInvocation,
FieldDescriptions,
Input,
InputField,
InvocationContext,
UIType,
tags,
title,
)
from .baseinvocation import BaseInvocation, FieldDescriptions, Input, InputField, InvocationContext, UIType, tags, title
from .compel import ConditioningField
from .controlnet_image_processors import ControlField
from .model import ModelInfo, UNetField, VaeField
@ -64,6 +58,72 @@ DEFAULT_PRECISION = choose_precision(choose_torch_device())
SAMPLER_NAME_VALUES = Literal[tuple(list(SCHEDULER_MAP.keys()))]
@title("Create Denoise Mask")
@tags("mask", "denoise")
class CreateDenoiseMaskInvocation(BaseInvocation):
"""Creates mask for denoising model run."""
# Metadata
type: Literal["create_denoise_mask"] = "create_denoise_mask"
# Inputs
vae: VaeField = InputField(description=FieldDescriptions.vae, input=Input.Connection, ui_order=0)
image: Optional[ImageField] = InputField(default=None, description="Image which will be masked", ui_order=1)
mask: ImageField = InputField(description="The mask to use when pasting", ui_order=2)
tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=3)
fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32, ui_order=4)
def prep_mask_tensor(self, mask_image):
if mask_image.mode != "L":
mask_image = mask_image.convert("L")
mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
if mask_tensor.dim() == 3:
mask_tensor = mask_tensor.unsqueeze(0)
# if shape is not None:
# mask_tensor = tv_resize(mask_tensor, shape, T.InterpolationMode.BILINEAR)
return mask_tensor
@torch.no_grad()
def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
if self.image is not None:
image = context.services.images.get_pil_image(self.image.image_name)
image = image_resized_to_grid_as_tensor(image.convert("RGB"))
if image.dim() == 3:
image = image.unsqueeze(0)
else:
image = None
mask = self.prep_mask_tensor(
context.services.images.get_pil_image(self.mask.image_name),
)
if image is not None:
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
context=context,
)
img_mask = tv_resize(mask, image.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
masked_image = image * torch.where(img_mask < 0.5, 0.0, 1.0)
# TODO:
masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
masked_latents_name = f"{context.graph_execution_state_id}__{self.id}_masked_latents"
context.services.latents.save(masked_latents_name, masked_latents)
else:
masked_latents_name = None
mask_name = f"{context.graph_execution_state_id}__{self.id}_mask"
context.services.latents.save(mask_name, mask)
return DenoiseMaskOutput(
denoise_mask=DenoiseMaskField(
mask_name=mask_name,
masked_latents_name=masked_latents_name,
),
)
def get_scheduler(
context: InvocationContext,
scheduler_info: ModelInfo,
@ -126,10 +186,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
control: Union[ControlField, list[ControlField]] = InputField(
default=None, description=FieldDescriptions.control, input=Input.Connection, ui_order=5
)
latents: Optional[LatentsField] = InputField(
description=FieldDescriptions.latents, input=Input.Connection, ui_order=4
)
mask: Optional[ImageField] = InputField(
latents: Optional[LatentsField] = InputField(description=FieldDescriptions.latents, input=Input.Connection)
denoise_mask: Optional[DenoiseMaskField] = InputField(
default=None,
description=FieldDescriptions.mask,
)
@ -342,19 +400,18 @@ class DenoiseLatentsInvocation(BaseInvocation):
return num_inference_steps, timesteps, init_timestep
def prep_mask_tensor(self, mask, context, lantents):
if mask is None:
return None
def prep_inpaint_mask(self, context, latents):
if self.denoise_mask is None:
return None, None
mask_image = context.services.images.get_pil_image(mask.image_name)
if mask_image.mode != "L":
# FIXME: why do we get passed an RGB image here? We can only use single-channel.
mask_image = mask_image.convert("L")
mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
if mask_tensor.dim() == 3:
mask_tensor = mask_tensor.unsqueeze(0)
mask_tensor = tv_resize(mask_tensor, lantents.shape[-2:], T.InterpolationMode.BILINEAR)
return 1 - mask_tensor
mask = context.services.latents.get(self.denoise_mask.mask_name)
mask = tv_resize(mask, latents.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
if self.denoise_mask.masked_latents_name is not None:
masked_latents = context.services.latents.get(self.denoise_mask.masked_latents_name)
else:
masked_latents = None
return 1 - mask, masked_latents
@torch.no_grad()
def invoke(self, context: InvocationContext) -> LatentsOutput:
@ -375,7 +432,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
if seed is None:
seed = 0
mask = self.prep_mask_tensor(self.mask, context, latents)
mask, masked_latents = self.prep_inpaint_mask(context, latents)
# Get the source node id (we are invoking the prepared node)
graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
@ -400,12 +457,14 @@ class DenoiseLatentsInvocation(BaseInvocation):
)
with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
unet_info.context.model, _lora_loader()
), unet_info as unet:
), set_seamless(unet_info.context.model, self.unet.seamless_axes), unet_info as unet:
latents = latents.to(device=unet.device, dtype=unet.dtype)
if noise is not None:
noise = noise.to(device=unet.device, dtype=unet.dtype)
if mask is not None:
mask = mask.to(device=unet.device, dtype=unet.dtype)
if masked_latents is not None:
masked_latents = masked_latents.to(device=unet.device, dtype=unet.dtype)
scheduler = get_scheduler(
context=context,
@ -442,6 +501,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
noise=noise,
seed=seed,
mask=mask,
masked_latents=masked_latents,
num_inference_steps=num_inference_steps,
conditioning_data=conditioning_data,
control_data=control_data, # list[ControlNetData]
@ -490,7 +550,7 @@ class LatentsToImageInvocation(BaseInvocation):
context=context,
)
with vae_info as vae:
with set_seamless(vae_info.context.model, self.vae.seamless_axes), vae_info as vae:
latents = latents.to(vae.device)
if self.fp32:
vae.to(dtype=torch.float32)
@ -663,26 +723,11 @@ class ImageToLatentsInvocation(BaseInvocation):
tiled: bool = InputField(default=False, description=FieldDescriptions.tiled)
fp32: bool = InputField(default=DEFAULT_PRECISION == "float32", description=FieldDescriptions.fp32)
@torch.no_grad()
def invoke(self, context: InvocationContext) -> LatentsOutput:
# image = context.services.images.get(
# self.image.image_type, self.image.image_name
# )
image = context.services.images.get_pil_image(self.image.image_name)
# vae_info = context.services.model_manager.get_model(**self.vae.vae.dict())
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
context=context,
)
image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
if image_tensor.dim() == 3:
image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
@staticmethod
def vae_encode(vae_info, upcast, tiled, image_tensor):
with vae_info as vae:
orig_dtype = vae.dtype
if self.fp32:
if upcast:
vae.to(dtype=torch.float32)
use_torch_2_0_or_xformers = isinstance(
@ -707,7 +752,7 @@ class ImageToLatentsInvocation(BaseInvocation):
vae.to(dtype=torch.float16)
# latents = latents.half()
if self.tiled:
if tiled:
vae.enable_tiling()
else:
vae.disable_tiling()
@ -721,6 +766,23 @@ class ImageToLatentsInvocation(BaseInvocation):
latents = vae.config.scaling_factor * latents
latents = latents.to(dtype=orig_dtype)
return latents
@torch.no_grad()
def invoke(self, context: InvocationContext) -> LatentsOutput:
image = context.services.images.get_pil_image(self.image.image_name)
vae_info = context.services.model_manager.get_model(
**self.vae.vae.dict(),
context=context,
)
image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
if image_tensor.dim() == 3:
image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
latents = self.vae_encode(vae_info, self.fp32, self.tiled, image_tensor)
name = f"{context.graph_execution_state_id}__{self.id}"
latents = latents.to("cpu")
context.services.latents.save(name, latents)

51
invokeai/app/invocations/model.py
View File

@ -8,8 +8,8 @@ from .baseinvocation import (
BaseInvocation,
BaseInvocationOutput,
FieldDescriptions,
InputField,
Input,
InputField,
InvocationContext,
OutputField,
UIType,
@ -33,6 +33,7 @@ class UNetField(BaseModel):
unet: ModelInfo = Field(description="Info to load unet submodel")
scheduler: ModelInfo = Field(description="Info to load scheduler submodel")
loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
class ClipField(BaseModel):
@ -45,6 +46,7 @@ class ClipField(BaseModel):
class VaeField(BaseModel):
# TODO: better naming?
vae: ModelInfo = Field(description="Info to load vae submodel")
seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
class ModelLoaderOutput(BaseInvocationOutput):
@ -388,3 +390,50 @@ class VaeLoaderInvocation(BaseInvocation):
)
)
)
class SeamlessModeOutput(BaseInvocationOutput):
"""Modified Seamless Model output"""
type: Literal["seamless_output"] = "seamless_output"
# Outputs
unet: Optional[UNetField] = OutputField(description=FieldDescriptions.unet, title="UNet")
vae: Optional[VaeField] = OutputField(description=FieldDescriptions.vae, title="VAE")
@title("Seamless")
@tags("seamless", "model")
class SeamlessModeInvocation(BaseInvocation):
"""Applies the seamless transformation to the Model UNet and VAE."""
type: Literal["seamless"] = "seamless"
# Inputs
unet: Optional[UNetField] = InputField(
default=None, description=FieldDescriptions.unet, input=Input.Connection, title="UNet"
)
vae: Optional[VaeField] = InputField(
default=None, description=FieldDescriptions.vae_model, input=Input.Connection, title="VAE"
)
seamless_y: bool = InputField(default=True, input=Input.Any, description="Specify whether Y axis is seamless")
seamless_x: bool = InputField(default=True, input=Input.Any, description="Specify whether X axis is seamless")
def invoke(self, context: InvocationContext) -> SeamlessModeOutput:
# Conditionally append 'x' and 'y' based on seamless_x and seamless_y
unet = copy.deepcopy(self.unet)
vae = copy.deepcopy(self.vae)
seamless_axes_list = []
if self.seamless_x:
seamless_axes_list.append("x")
if self.seamless_y:
seamless_axes_list.append("y")
if unet is not None:
unet.seamless_axes = seamless_axes_list
if vae is not None:
vae.seamless_axes = seamless_axes_list
return SeamlessModeOutput(unet=unet, vae=vae)

19
invokeai/app/invocations/primitives.py
View File

@ -294,6 +294,25 @@ class ImageCollectionInvocation(BaseInvocation):
return ImageCollectionOutput(collection=self.collection)
# endregion
# region DenoiseMask
class DenoiseMaskField(BaseModel):
"""An inpaint mask field"""
mask_name: str = Field(description="The name of the mask image")
masked_latents_name: Optional[str] = Field(description="The name of the masked image latents")
class DenoiseMaskOutput(BaseInvocationOutput):
"""Base class for nodes that output a single image"""
type: Literal["denoise_mask_output"] = "denoise_mask_output"
denoise_mask: DenoiseMaskField = OutputField(description="Mask for denoise model run")
# endregion
# region Latents

3
invokeai/backend/image_util/seamless.py
View File

@ -20,7 +20,8 @@ def _conv_forward_asymmetric(self, input, weight, bias):
def configure_model_padding(model, seamless, seamless_axes):
"""
Modifies the 2D convolution layers to use a circular padding mode based on the `seamless` and `seamless_axes` options.
Modifies the 2D convolution layers to use a circular padding mode based on
the `seamless` and `seamless_axes` options.
"""
# TODO: get an explicit interface for this in diffusers: https://github.com/huggingface/diffusers/issues/556
for m in model.modules():

103
invokeai/backend/model_management/seamless.py Normal file
View File

@ -0,0 +1,103 @@
from __future__ import annotations
from contextlib import contextmanager
from typing import List, Union
import torch.nn as nn
from diffusers.models import AutoencoderKL, UNet2DConditionModel
def _conv_forward_asymmetric(self, input, weight, bias):
"""
Patch for Conv2d._conv_forward that supports asymmetric padding
"""
working = nn.functional.pad(input, self.asymmetric_padding["x"], mode=self.asymmetric_padding_mode["x"])
working = nn.functional.pad(working, self.asymmetric_padding["y"], mode=self.asymmetric_padding_mode["y"])
return nn.functional.conv2d(
working,
weight,
bias,
self.stride,
nn.modules.utils._pair(0),
self.dilation,
self.groups,
)
@contextmanager
def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL], seamless_axes: List[str]):
try:
to_restore = []
for m_name, m in model.named_modules():
if isinstance(model, UNet2DConditionModel):
if ".attentions." in m_name:
continue
if ".resnets." in m_name:
if ".conv2" in m_name:
continue
if ".conv_shortcut" in m_name:
continue
"""
if isinstance(model, UNet2DConditionModel):
if False and ".upsamplers." in m_name:
continue
if False and ".downsamplers." in m_name:
continue
if True and ".resnets." in m_name:
if True and ".conv1" in m_name:
if False and "down_blocks" in m_name:
continue
if False and "mid_block" in m_name:
continue
if False and "up_blocks" in m_name:
continue
if True and ".conv2" in m_name:
continue
if True and ".conv_shortcut" in m_name:
continue
if True and ".attentions." in m_name:
continue
if False and m_name in ["conv_in", "conv_out"]:
continue
"""
if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
print(f"applied - {m_name}")
m.asymmetric_padding_mode = {}
m.asymmetric_padding = {}
m.asymmetric_padding_mode["x"] = "circular" if ("x" in seamless_axes) else "constant"
m.asymmetric_padding["x"] = (
m._reversed_padding_repeated_twice[0],
m._reversed_padding_repeated_twice[1],
0,
0,
)
m.asymmetric_padding_mode["y"] = "circular" if ("y" in seamless_axes) else "constant"
m.asymmetric_padding["y"] = (
0,
0,
m._reversed_padding_repeated_twice[2],
m._reversed_padding_repeated_twice[3],
)
to_restore.append((m, m._conv_forward))
m._conv_forward = _conv_forward_asymmetric.__get__(m, nn.Conv2d)
yield
finally:
for module, orig_conv_forward in to_restore:
module._conv_forward = orig_conv_forward
if hasattr(m, "asymmetric_padding_mode"):
del m.asymmetric_padding_mode
if hasattr(m, "asymmetric_padding"):
del m.asymmetric_padding

41
invokeai/backend/stable_diffusion/diffusers_pipeline.py
View File

@ -144,7 +144,7 @@ def image_resized_to_grid_as_tensor(image: PIL.Image.Image, normalize: bool = Tr
w, h = trim_to_multiple_of(*image.size, multiple_of=multiple_of)
transformation = T.Compose(
[
T.Resize((h, w), T.InterpolationMode.LANCZOS),
T.Resize((h, w), T.InterpolationMode.LANCZOS, antialias=True),
T.ToTensor(),
]
)
@ -358,6 +358,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
callback: Callable[[PipelineIntermediateState], None] = None,
control_data: List[ControlNetData] = None,
mask: Optional[torch.Tensor] = None,
masked_latents: Optional[torch.Tensor] = None,
seed: Optional[int] = None,
) -> tuple[torch.Tensor, Optional[AttentionMapSaver]]:
if init_timestep.shape[0] == 0:
@ -376,28 +377,28 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
latents = self.scheduler.add_noise(latents, noise, batched_t)
if mask is not None:
# if no noise provided, noisify unmasked area based on seed(or 0 as fallback)
if noise is None:
noise = torch.randn(
orig_latents.shape,
dtype=torch.float32,
device="cpu",
generator=torch.Generator(device="cpu").manual_seed(seed or 0),
).to(device=orig_latents.device, dtype=orig_latents.dtype)
latents = self.scheduler.add_noise(latents, noise, batched_t)
latents = torch.lerp(
orig_latents, latents.to(dtype=orig_latents.dtype), mask.to(dtype=orig_latents.dtype)
)
if is_inpainting_model(self.unet):
# You'd think the inpainting model wouldn't be paying attention to the area it is going to repaint
# (that's why there's a mask!) but it seems to really want that blanked out.
# masked_latents = latents * torch.where(mask < 0.5, 1, 0) TODO: inpaint/outpaint/infill
if masked_latents is None:
raise Exception("Source image required for inpaint mask when inpaint model used!")
# TODO: we should probably pass this in so we don't have to try/finally around setting it.
self.invokeai_diffuser.model_forward_callback = AddsMaskLatents(self._unet_forward, mask, orig_latents)
self.invokeai_diffuser.model_forward_callback = AddsMaskLatents(
self._unet_forward, mask, masked_latents
)
else:
# if no noise provided, noisify unmasked area based on seed(or 0 as fallback)
if noise is None:
noise = torch.randn(
orig_latents.shape,
dtype=torch.float32,
device="cpu",
generator=torch.Generator(device="cpu").manual_seed(seed or 0),
).to(device=orig_latents.device, dtype=orig_latents.dtype)
latents = self.scheduler.add_noise(latents, noise, batched_t)
latents = torch.lerp(
orig_latents, latents.to(dtype=orig_latents.dtype), mask.to(dtype=orig_latents.dtype)
)
additional_guidance.append(AddsMaskGuidance(mask, orig_latents, self.scheduler, noise))
try:

15
invokeai/backend/util/hotfixes.py
View File

@ -761,3 +761,18 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
diffusers.ControlNetModel = ControlNetModel
diffusers.models.controlnet.ControlNetModel = ControlNetModel
# patch LoRACompatibleConv to use original Conv2D forward function
# this needed to make work seamless patch
# NOTE: with this patch, torch.compile crashes on 2.0 torch(already fixed in nightly)
# https://github.com/huggingface/diffusers/pull/4315
# https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/lora.py#L96C18-L96C18
def new_LoRACompatibleConv_forward(self, x):
if self.lora_layer is None:
return super(diffusers.models.lora.LoRACompatibleConv, self).forward(x)
else:
return super(diffusers.models.lora.LoRACompatibleConv, self).forward(x) + self.lora_layer(x)
diffusers.models.lora.LoRACompatibleConv.forward = new_LoRACompatibleConv_forward

16
invokeai/frontend/web/src/app/components/App.tsx
View File

@ -14,6 +14,7 @@ import i18n from 'i18n';
import { size } from 'lodash-es';
import { ReactNode, memo, useCallback, useEffect } from 'react';
import { ErrorBoundary } from 'react-error-boundary';
import { usePreselectedImage } from '../../features/parameters/hooks/usePreselectedImage';
import AppErrorBoundaryFallback from './AppErrorBoundaryFallback';
import GlobalHotkeys from './GlobalHotkeys';
import Toaster from './Toaster';
@ -23,13 +24,22 @@ const DEFAULT_CONFIG = {};
interface Props {
config?: PartialAppConfig;
headerComponent?: ReactNode;
selectedImage?: {
imageName: string;
action: 'sendToImg2Img' | 'sendToCanvas' | 'useAllParameters';
};
}
const App = ({ config = DEFAULT_CONFIG, headerComponent }: Props) => {
const App = ({
config = DEFAULT_CONFIG,
headerComponent,
selectedImage,
}: Props) => {
const language = useAppSelector(languageSelector);
const logger = useLogger('system');
const dispatch = useAppDispatch();
const { handlePreselectedImage } = usePreselectedImage();
const handleReset = useCallback(() => {
localStorage.clear();
location.reload();
@ -51,6 +61,10 @@ const App = ({ config = DEFAULT_CONFIG, headerComponent }: Props) => {
dispatch(appStarted());
}, [dispatch]);
useEffect(() => {
handlePreselectedImage(selectedImage);
}, [handlePreselectedImage, selectedImage]);
return (
<ErrorBoundary
onReset={handleReset}

11
invokeai/frontend/web/src/app/components/InvokeAIUI.tsx
View File

@ -26,6 +26,10 @@ interface Props extends PropsWithChildren {
headerComponent?: ReactNode;
middleware?: Middleware[];
projectId?: string;
selectedImage?: {
imageName: string;
action: 'sendToImg2Img' | 'sendToCanvas' | 'useAllParameters';
};
}
const InvokeAIUI = ({
@ -35,6 +39,7 @@ const InvokeAIUI = ({
headerComponent,
middleware,
projectId,
selectedImage,
}: Props) => {
useEffect(() => {
// configure API client token
@ -81,7 +86,11 @@ const InvokeAIUI = ({
<React.Suspense fallback={<Loading />}>
<ThemeLocaleProvider>
<AppDndContext>
<App config={config} headerComponent={headerComponent} />
<App
config={config}
headerComponent={headerComponent}
selectedImage={selectedImage}
/>
</AppDndContext>
</ThemeLocaleProvider>
</React.Suspense>

2
invokeai/frontend/web/src/features/gallery/components/ImageGrid/GalleryImage.tsx
View File

@ -8,7 +8,7 @@ import {
ImageDraggableData,
TypesafeDraggableData,
} from 'features/dnd/types';
import { useMultiselect } from 'features/gallery/hooks/useMultiselect.ts';
import { useMultiselect } from 'features/gallery/hooks/useMultiselect';
import { MouseEvent, memo, useCallback, useMemo, useState } from 'react';
import { FaTrash } from 'react-icons/fa';
import { MdStar, MdStarBorder } from 'react-icons/md';

0
invokeai/frontend/web/src/features/gallery/hooks/useMultiselect.ts.ts → invokeai/frontend/web/src/features/gallery/hooks/useMultiselect.ts
View File

124
invokeai/frontend/web/src/features/nodes/components/flow/nodes/CurrentImage/CurrentImageNode.tsx
View File

@ -1,13 +1,15 @@
import { Flex, Image, Text } from '@chakra-ui/react';
import { useState, PropsWithChildren, memo } from 'react';
import { useSelector } from 'react-redux';
import { createSelector } from '@reduxjs/toolkit';
import { stateSelector } from 'app/store/store';
import { Flex, Image, Text } from '@chakra-ui/react';
import { motion } from 'framer-motion';
import { NodeProps } from 'reactflow';
import NodeWrapper from '../common/NodeWrapper';
import NextPrevImageButtons from 'features/gallery/components/NextPrevImageButtons';
import IAIDndImage from 'common/components/IAIDndImage';
import { IAINoContentFallback } from 'common/components/IAIImageFallback';
import { DRAG_HANDLE_CLASSNAME } from 'features/nodes/types/constants';
import { PropsWithChildren, memo } from 'react';
import { useSelector } from 'react-redux';
import { NodeProps } from 'reactflow';
import NodeWrapper from '../common/NodeWrapper';
import { stateSelector } from 'app/store/store';
const selector = createSelector(stateSelector, ({ system, gallery }) => {
const imageDTO = gallery.selection[gallery.selection.length - 1];
@ -54,44 +56,90 @@ const CurrentImageNode = (props: NodeProps) => {
export default memo(CurrentImageNode);
const Wrapper = (props: PropsWithChildren<{ nodeProps: NodeProps }>) => (
<NodeWrapper
nodeId={props.nodeProps.data.id}
selected={props.nodeProps.selected}
width={384}
>
<Flex
className={DRAG_HANDLE_CLASSNAME}
sx={{
flexDirection: 'column',
}}
const Wrapper = (props: PropsWithChildren<{ nodeProps: NodeProps }>) => {
const [isHovering, setIsHovering] = useState(false);
const handleMouseEnter = () => {
setIsHovering(true);
};
const handleMouseLeave = () => {
setIsHovering(false);
};
return (
<NodeWrapper
nodeId={props.nodeProps.id}
selected={props.nodeProps.selected}
width={384}
>
<Flex
layerStyle="nodeHeader"
onMouseEnter={handleMouseEnter}
onMouseLeave={handleMouseLeave}
className={DRAG_HANDLE_CLASSNAME}
sx={{
borderTopRadius: 'base',
alignItems: 'center',
justifyContent: 'center',
h: 8,
position: 'relative',
flexDirection: 'column',
}}
>
<Text
<Flex
layerStyle="nodeHeader"
sx={{
fontSize: 'sm',
fontWeight: 600,
color: 'base.700',
_dark: { color: 'base.200' },
borderTopRadius: 'base',
alignItems: 'center',
justifyContent: 'center',
h: 8,
}}
>
Current Image
</Text>
<Text
sx={{
fontSize: 'sm',
fontWeight: 600,
color: 'base.700',
_dark: { color: 'base.200' },
}}
>
Current Image
</Text>
</Flex>
<Flex
layerStyle="nodeBody"
sx={{
w: 'full',
h: 'full',
borderBottomRadius: 'base',
p: 2,
}}
>
{props.children}
{isHovering && (
<motion.div
key="nextPrevButtons"
initial={{
opacity: 0,
}}
animate={{
opacity: 1,
transition: { duration: 0.1 },
}}
exit={{
opacity: 0,
transition: { duration: 0.1 },
}}
style={{
position: 'absolute',
top: 40,
left: -2,
right: -2,
bottom: 0,
pointerEvents: 'none',
}}
>
<NextPrevImageButtons />
</motion.div>
)}
</Flex>
</Flex>
<Flex
layerStyle="nodeBody"
sx={{ w: 'full', h: 'full', borderBottomRadius: 'base', p: 2 }}
>
{props.children}
</Flex>
</Flex>
</NodeWrapper>
);
</NodeWrapper>
);
};

14
invokeai/frontend/web/src/features/nodes/components/flow/nodes/Invocation/fields/InputFieldRenderer.tsx
View File

@ -10,6 +10,7 @@ import ColorInputField from './inputs/ColorInputField';
import ConditioningInputField from './inputs/ConditioningInputField';
import ControlInputField from './inputs/ControlInputField';
import ControlNetModelInputField from './inputs/ControlNetModelInputField';
import DenoiseMaskInputField from './inputs/DenoiseMaskInputField';
import EnumInputField from './inputs/EnumInputField';
import ImageCollectionInputField from './inputs/ImageCollectionInputField';
import ImageInputField from './inputs/ImageInputField';
@ -105,6 +106,19 @@ const InputFieldRenderer = ({ nodeId, fieldName }: InputFieldProps) => {
);
}
if (
field?.type === 'DenoiseMaskField' &&
fieldTemplate?.type === 'DenoiseMaskField'
) {
return (
<DenoiseMaskInputField
nodeId={nodeId}
field={field}
fieldTemplate={fieldTemplate}
/>
);
}
if (
field?.type === 'ConditioningField' &&
fieldTemplate?.type === 'ConditioningField'

17
invokeai/frontend/web/src/features/nodes/components/flow/nodes/Invocation/fields/inputs/DenoiseMaskInputField.tsx Normal file
View File

@ -0,0 +1,17 @@
import {
DenoiseMaskInputFieldTemplate,
DenoiseMaskInputFieldValue,
FieldComponentProps,
} from 'features/nodes/types/types';
import { memo } from 'react';
const DenoiseMaskInputFieldComponent = (
_props: FieldComponentProps<
DenoiseMaskInputFieldValue,
DenoiseMaskInputFieldTemplate
>
) => {
return null;
};
export default memo(DenoiseMaskInputFieldComponent);

5
invokeai/frontend/web/src/features/nodes/types/constants.ts
View File

@ -59,6 +59,11 @@ export const FIELDS: Record<FieldType, FieldUIConfig> = {
description: 'Images may be passed between nodes.',
color: 'purple.500',
},
DenoiseMaskField: {
title: 'Denoise Mask',
description: 'Denoise Mask may be passed between nodes',
color: 'red.700',
},
LatentsField: {
title: 'Latents',
description: 'Latents may be passed between nodes.',

22
invokeai/frontend/web/src/features/nodes/types/types.ts
View File

@ -64,6 +64,7 @@ export const zFieldType = z.enum([
'string',
'array',
'ImageField',
'DenoiseMaskField',
'LatentsField',
'ConditioningField',
'ControlField',
@ -120,6 +121,7 @@ export type InputFieldTemplate =
| StringInputFieldTemplate
| BooleanInputFieldTemplate
| ImageInputFieldTemplate
| DenoiseMaskInputFieldTemplate
| LatentsInputFieldTemplate
| ConditioningInputFieldTemplate
| UNetInputFieldTemplate
@ -205,6 +207,12 @@ export const zConditioningField = z.object({
});
export type ConditioningField = z.infer<typeof zConditioningField>;
export const zDenoiseMaskField = z.object({
mask_name: z.string().trim().min(1),
masked_latents_name: z.string().trim().min(1).optional(),
});
export type DenoiseMaskFieldValue = z.infer<typeof zDenoiseMaskField>;
export const zIntegerInputFieldValue = zInputFieldValueBase.extend({
type: z.literal('integer'),
value: z.number().optional(),
@ -241,6 +249,14 @@ export const zLatentsInputFieldValue = zInputFieldValueBase.extend({
});
export type LatentsInputFieldValue = z.infer<typeof zLatentsInputFieldValue>;
export const zDenoiseMaskInputFieldValue = zInputFieldValueBase.extend({
type: z.literal('DenoiseMaskField'),
value: zDenoiseMaskField.optional(),
});
export type DenoiseMaskInputFieldValue = z.infer<
typeof zDenoiseMaskInputFieldValue
>;
export const zConditioningInputFieldValue = zInputFieldValueBase.extend({
type: z.literal('ConditioningField'),
value: zConditioningField.optional(),
@ -459,6 +475,7 @@ export const zInputFieldValue = z.discriminatedUnion('type', [
zBooleanInputFieldValue,
zImageInputFieldValue,
zLatentsInputFieldValue,
zDenoiseMaskInputFieldValue,
zConditioningInputFieldValue,
zUNetInputFieldValue,
zClipInputFieldValue,
@ -532,6 +549,11 @@ export type ImageCollectionInputFieldTemplate = InputFieldTemplateBase & {
type: 'ImageCollection';
};
export type DenoiseMaskInputFieldTemplate = InputFieldTemplateBase & {
default: undefined;
type: 'DenoiseMaskField';
};
export type LatentsInputFieldTemplate = InputFieldTemplateBase & {
default: string;
type: 'LatentsField';

20
invokeai/frontend/web/src/features/nodes/util/fieldTemplateBuilders.ts
View File

@ -8,6 +8,7 @@ import {
ConditioningInputFieldTemplate,
ControlInputFieldTemplate,
ControlNetModelInputFieldTemplate,
DenoiseMaskInputFieldTemplate,
EnumInputFieldTemplate,
FieldType,
FloatInputFieldTemplate,
@ -263,6 +264,19 @@ const buildImageCollectionInputFieldTemplate = ({
return template;
};
const buildDenoiseMaskInputFieldTemplate = ({
schemaObject,
baseField,
}: BuildInputFieldArg): DenoiseMaskInputFieldTemplate => {
const template: DenoiseMaskInputFieldTemplate = {
...baseField,
type: 'DenoiseMaskField',
default: schemaObject.default ?? undefined,
};
return template;
};
const buildLatentsInputFieldTemplate = ({
schemaObject,
baseField,
@ -498,6 +512,12 @@ export const buildInputFieldTemplate = (
baseField,
});
}
if (fieldType === 'DenoiseMaskField') {
return buildDenoiseMaskInputFieldTemplate({
schemaObject: fieldSchema,
baseField,
});
}
if (fieldType === 'LatentsField') {
return buildLatentsInputFieldTemplate({
schemaObject: fieldSchema,

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

@ -49,6 +49,10 @@ export const buildInputFieldValue = (
fieldValue.value = [];
}
if (template.type === 'DenoiseMaskField') {
fieldValue.value = undefined;
}
if (template.type === 'LatentsField') {
fieldValue.value = undefined;
}

2
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addDynamicPromptsToGraph.ts
View File

@ -63,7 +63,7 @@ export const addDynamicPromptsToGraph = (
{
source: {
node_id: DYNAMIC_PROMPT,
field: 'prompt_collection',
field: 'collection',
},
destination: {
node_id: ITERATE,

23
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addSDXLLoRAstoGraph.ts
View File

@ -11,9 +11,11 @@ import {
METADATA_ACCUMULATOR,
NEGATIVE_CONDITIONING,
POSITIVE_CONDITIONING,
REFINER_SEAMLESS,
SDXL_CANVAS_INPAINT_GRAPH,
SDXL_CANVAS_OUTPAINT_GRAPH,
SDXL_MODEL_LOADER,
SEAMLESS,
} from './constants';
export const addSDXLLoRAsToGraph = (
@ -36,20 +38,25 @@ export const addSDXLLoRAsToGraph = (
| MetadataAccumulatorInvocation
| undefined;
// Handle Seamless Plugs
const unetLoaderId = modelLoaderNodeId;
let clipLoaderId = modelLoaderNodeId;
if ([SEAMLESS, REFINER_SEAMLESS].includes(modelLoaderNodeId)) {
clipLoaderId = SDXL_MODEL_LOADER;
}
if (loraCount > 0) {
// Remove modelLoaderNodeId unet/clip/clip2 connections to feed it to LoRAs
graph.edges = graph.edges.filter(
(e) =>
!(
e.source.node_id === modelLoaderNodeId &&
['unet'].includes(e.source.field)
e.source.node_id === unetLoaderId && ['unet'].includes(e.source.field)
) &&
!(
e.source.node_id === modelLoaderNodeId &&
['clip'].includes(e.source.field)
e.source.node_id === clipLoaderId && ['clip'].includes(e.source.field)
) &&
!(
e.source.node_id === modelLoaderNodeId &&
e.source.node_id === clipLoaderId &&
['clip2'].includes(e.source.field)
)
);
@ -88,7 +95,7 @@ export const addSDXLLoRAsToGraph = (
// first lora = start the lora chain, attach directly to model loader
graph.edges.push({
source: {
node_id: modelLoaderNodeId,
node_id: unetLoaderId,
field: 'unet',
},
destination: {
@ -99,7 +106,7 @@ export const addSDXLLoRAsToGraph = (
graph.edges.push({
source: {
node_id: modelLoaderNodeId,
node_id: clipLoaderId,
field: 'clip',
},
destination: {
@ -110,7 +117,7 @@ export const addSDXLLoRAsToGraph = (
graph.edges.push({
source: {
node_id: modelLoaderNodeId,
node_id: clipLoaderId,
field: 'clip2',
},
destination: {

60
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addSDXLRefinerToGraph.ts
View File

@ -1,11 +1,15 @@
import { RootState } from 'app/store/store';
import { MetadataAccumulatorInvocation } from 'services/api/types';
import {
MetadataAccumulatorInvocation,
SeamlessModeInvocation,
} from 'services/api/types';
import { NonNullableGraph } from '../../types/types';
import {
CANVAS_OUTPUT,
LATENTS_TO_IMAGE,
MASK_BLUR,
METADATA_ACCUMULATOR,
REFINER_SEAMLESS,
SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH,
SDXL_CANVAS_INPAINT_GRAPH,
SDXL_CANVAS_OUTPAINT_GRAPH,
@ -21,7 +25,8 @@ import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
export const addSDXLRefinerToGraph = (
state: RootState,
graph: NonNullableGraph,
baseNodeId: string
baseNodeId: string,
modelLoaderNodeId?: string
): void => {
const {
refinerModel,
@ -33,6 +38,8 @@ export const addSDXLRefinerToGraph = (
refinerStart,
} = state.sdxl;
const { seamlessXAxis, seamlessYAxis } = state.generation;
if (!refinerModel) {
return;
}
@ -53,6 +60,10 @@ export const addSDXLRefinerToGraph = (
metadataAccumulator.refiner_steps = refinerSteps;
}
const modelLoaderId = modelLoaderNodeId
? modelLoaderNodeId
: SDXL_MODEL_LOADER;
// Construct Style Prompt
const { craftedPositiveStylePrompt, craftedNegativeStylePrompt } =
craftSDXLStylePrompt(state, true);
@ -65,10 +76,7 @@ export const addSDXLRefinerToGraph = (
graph.edges = graph.edges.filter(
(e) =>
!(
e.source.node_id === SDXL_MODEL_LOADER &&
['vae'].includes(e.source.field)
)
!(e.source.node_id === modelLoaderId && ['vae'].includes(e.source.field))
);
graph.nodes[SDXL_REFINER_MODEL_LOADER] = {
@ -98,8 +106,39 @@ export const addSDXLRefinerToGraph = (
denoising_end: 1,
};
graph.edges.push(
{
// Add Seamless To Refiner
if (seamlessXAxis || seamlessYAxis) {
graph.nodes[REFINER_SEAMLESS] = {
id: REFINER_SEAMLESS,
type: 'seamless',
seamless_x: seamlessXAxis,
seamless_y: seamlessYAxis,
} as SeamlessModeInvocation;
graph.edges.push(
{
source: {
node_id: SDXL_REFINER_MODEL_LOADER,
field: 'unet',
},
destination: {
node_id: REFINER_SEAMLESS,
field: 'unet',
},
},
{
source: {
node_id: REFINER_SEAMLESS,
field: 'unet',
},
destination: {
node_id: SDXL_REFINER_DENOISE_LATENTS,
field: 'unet',
},
}
);
} else {
graph.edges.push({
source: {
node_id: SDXL_REFINER_MODEL_LOADER,
field: 'unet',
@ -108,7 +147,10 @@ export const addSDXLRefinerToGraph = (
node_id: SDXL_REFINER_DENOISE_LATENTS,
field: 'unet',
},
},
});
}
graph.edges.push(
{
source: {
node_id: SDXL_REFINER_MODEL_LOADER,

109
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addSeamlessToLinearGraph.ts Normal file
View File

@ -0,0 +1,109 @@
import { RootState } from 'app/store/store';
import { SeamlessModeInvocation } from 'services/api/types';
import { NonNullableGraph } from '../../types/types';
import {
CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_INPAINT_GRAPH,
CANVAS_OUTPAINT_GRAPH,
DENOISE_LATENTS,
SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH,
SDXL_CANVAS_INPAINT_GRAPH,
SDXL_CANVAS_OUTPAINT_GRAPH,
SDXL_CANVAS_TEXT_TO_IMAGE_GRAPH,
SDXL_DENOISE_LATENTS,
SDXL_IMAGE_TO_IMAGE_GRAPH,
SDXL_TEXT_TO_IMAGE_GRAPH,
SEAMLESS,
} from './constants';
export const addSeamlessToLinearGraph = (
state: RootState,
graph: NonNullableGraph,
modelLoaderNodeId: string
): void => {
// Remove Existing UNet Connections
const { seamlessXAxis, seamlessYAxis } = state.generation;
graph.nodes[SEAMLESS] = {
id: SEAMLESS,
type: 'seamless',
seamless_x: seamlessXAxis,
seamless_y: seamlessYAxis,
} as SeamlessModeInvocation;
let denoisingNodeId = DENOISE_LATENTS;
if (
graph.id === SDXL_TEXT_TO_IMAGE_GRAPH ||
graph.id === SDXL_IMAGE_TO_IMAGE_GRAPH ||
graph.id === SDXL_CANVAS_TEXT_TO_IMAGE_GRAPH ||
graph.id === SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH ||
graph.id === SDXL_CANVAS_INPAINT_GRAPH ||
graph.id === SDXL_CANVAS_OUTPAINT_GRAPH
) {
denoisingNodeId = SDXL_DENOISE_LATENTS;
}
graph.edges = graph.edges.filter(
(e) =>
!(
e.source.node_id === modelLoaderNodeId &&
['unet'].includes(e.source.field)
) &&
!(
e.source.node_id === modelLoaderNodeId &&
['vae'].includes(e.source.field)
)
);
graph.edges.push(
{
source: {
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
node_id: SEAMLESS,
field: 'unet',
},
},
{
source: {
node_id: modelLoaderNodeId,
field: 'vae',
},
destination: {
node_id: SEAMLESS,
field: 'vae',
},
},
{
source: {
node_id: SEAMLESS,
field: 'unet',
},
destination: {
node_id: denoisingNodeId,
field: 'unet',
},
}
);
if (
graph.id == CANVAS_INPAINT_GRAPH ||
graph.id === CANVAS_OUTPAINT_GRAPH ||
graph.id === SDXL_CANVAS_INPAINT_GRAPH ||
graph.id === SDXL_CANVAS_OUTPAINT_GRAPH
) {
graph.edges.push({
source: {
node_id: SEAMLESS,
field: 'unet',
},
destination: {
node_id: CANVAS_COHERENCE_DENOISE_LATENTS,
field: 'unet',
},
});
}
};

18
invokeai/frontend/web/src/features/nodes/util/graphBuilders/addVAEToGraph.ts
View File

@ -9,6 +9,7 @@ import {
CANVAS_TEXT_TO_IMAGE_GRAPH,
IMAGE_TO_IMAGE_GRAPH,
IMAGE_TO_LATENTS,
INPAINT_CREATE_MASK,
INPAINT_IMAGE,
LATENTS_TO_IMAGE,
MAIN_MODEL_LOADER,
@ -30,6 +31,11 @@ export const addVAEToGraph = (
modelLoaderNodeId: string = MAIN_MODEL_LOADER
): void => {
const { vae } = state.generation;
const { boundingBoxScaleMethod } = state.canvas;
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
const isAutoVae = !vae;
const metadataAccumulator = graph.nodes[METADATA_ACCUMULATOR] as
@ -76,7 +82,7 @@ export const addVAEToGraph = (
field: isAutoVae && isOnnxModel ? 'vae_decoder' : 'vae',
},
destination: {
node_id: CANVAS_OUTPUT,
node_id: isUsingScaledDimensions ? LATENTS_TO_IMAGE : CANVAS_OUTPUT,
field: 'vae',
},
});
@ -117,6 +123,16 @@ export const addVAEToGraph = (
field: 'vae',
},
},
{
source: {
node_id: isAutoVae ? modelLoaderNodeId : VAE_LOADER,
field: isAutoVae && isOnnxModel ? 'vae_decoder' : 'vae',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'vae',
},
},
{
source: {
node_id: isAutoVae ? modelLoaderNodeId : VAE_LOADER,

182
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasImageToImageGraph.ts
View File

@ -2,15 +2,12 @@ import { logger } from 'app/logging/logger';
import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types';
import { initialGenerationState } from 'features/parameters/store/generationSlice';
import {
ImageDTO,
ImageResizeInvocation,
ImageToLatentsInvocation,
} from 'services/api/types';
import { ImageDTO, ImageToLatentsInvocation } from 'services/api/types';
import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addLoRAsToGraph } from './addLoRAsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
@ -19,12 +16,14 @@ import {
CLIP_SKIP,
DENOISE_LATENTS,
IMAGE_TO_LATENTS,
IMG2IMG_RESIZE,
LATENTS_TO_IMAGE,
MAIN_MODEL_LOADER,
METADATA_ACCUMULATOR,
NEGATIVE_CONDITIONING,
NOISE,
POSITIVE_CONDITIONING,
RESIZE,
SEAMLESS,
} from './constants';
/**
@ -43,21 +42,34 @@ export const buildCanvasImageToImageGraph = (
scheduler,
steps,
img2imgStrength: strength,
vaePrecision,
clipSkip,
shouldUseCpuNoise,
shouldUseNoiseSettings,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
// The bounding box determines width and height, not the width and height params
const { width, height } = state.canvas.boundingBoxDimensions;
const { shouldAutoSave } = state.canvas;
const {
scaledBoundingBoxDimensions,
boundingBoxScaleMethod,
shouldAutoSave,
} = state.canvas;
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
if (!model) {
log.error('No model found in state');
throw new Error('No model found in state');
}
let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: initialGenerationState.shouldUseCpuNoise;
@ -75,9 +87,9 @@ export const buildCanvasImageToImageGraph = (
const graph: NonNullableGraph = {
id: CANVAS_IMAGE_TO_IMAGE_GRAPH,
nodes: {
[MAIN_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'main_model_loader',
id: MAIN_MODEL_LOADER,
id: modelLoaderNodeId,
is_intermediate: true,
model,
},
@ -104,15 +116,17 @@ export const buildCanvasImageToImageGraph = (
id: NOISE,
is_intermediate: true,
use_cpu,
width: !isUsingScaledDimensions
? width
: scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
},
[IMAGE_TO_LATENTS]: {
type: 'i2l',
id: IMAGE_TO_LATENTS,
is_intermediate: true,
// must be set manually later, bc `fit` parameter may require a resize node inserted
// image: {
// image_name: initialImage.image_name,
// },
},
[DENOISE_LATENTS]: {
type: 'denoise_latents',
@ -134,7 +148,7 @@ export const buildCanvasImageToImageGraph = (
// Connect Model Loader to CLIP Skip and UNet
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -144,7 +158,7 @@ export const buildCanvasImageToImageGraph = (
},
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -214,82 +228,84 @@ export const buildCanvasImageToImageGraph = (
field: 'latents',
},
},
// Decode the denoised latents to an image
],
};
// Decode Latents To Image & Handle Scaled Before Processing
if (isUsingScaledDimensions) {
graph.nodes[IMG2IMG_RESIZE] = {
id: IMG2IMG_RESIZE,
type: 'img_resize',
is_intermediate: true,
image: initialImage,
width: scaledBoundingBoxDimensions.width,
height: scaledBoundingBoxDimensions.height,
};
graph.nodes[LATENTS_TO_IMAGE] = {
id: LATENTS_TO_IMAGE,
type: 'l2i',
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
};
graph.nodes[CANVAS_OUTPUT] = {
id: CANVAS_OUTPUT,
type: 'img_resize',
is_intermediate: !shouldAutoSave,
width: width,
height: height,
};
graph.edges.push(
{
source: {
node_id: IMG2IMG_RESIZE,
field: 'image',
},
destination: {
node_id: IMAGE_TO_LATENTS,
field: 'image',
},
},
{
source: {
node_id: DENOISE_LATENTS,
field: 'latents',
},
destination: {
node_id: CANVAS_OUTPUT,
node_id: LATENTS_TO_IMAGE,
field: 'latents',
},
},
],
};
// handle `fit`
if (initialImage.width !== width || initialImage.height !== height) {
// The init image needs to be resized to the specified width and height before being passed to `IMAGE_TO_LATENTS`
// Create a resize node, explicitly setting its image
const resizeNode: ImageResizeInvocation = {
id: RESIZE,
type: 'img_resize',
image: {
image_name: initialImage.image_name,
},
is_intermediate: true,
width,
height,
};
graph.nodes[RESIZE] = resizeNode;
// The `RESIZE` node then passes its image to `IMAGE_TO_LATENTS`
graph.edges.push({
source: { node_id: RESIZE, field: 'image' },
destination: {
node_id: IMAGE_TO_LATENTS,
field: 'image',
},
});
// The `RESIZE` node also passes its width and height to `NOISE`
graph.edges.push({
source: { node_id: RESIZE, field: 'width' },
destination: {
node_id: NOISE,
field: 'width',
},
});
graph.edges.push({
source: { node_id: RESIZE, field: 'height' },
destination: {
node_id: NOISE,
field: 'height',
},
});
{
source: {
node_id: LATENTS_TO_IMAGE,
field: 'image',
},
destination: {
node_id: CANVAS_OUTPUT,
field: 'image',
},
}
);
} else {
// We are not resizing, so we need to set the image on the `IMAGE_TO_LATENTS` node explicitly
(graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image = {
image_name: initialImage.image_name,
graph.nodes[CANVAS_OUTPUT] = {
type: 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false,
};
// Pass the image's dimensions to the `NOISE` node
(graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image =
initialImage;
graph.edges.push({
source: { node_id: IMAGE_TO_LATENTS, field: 'width' },
destination: {
node_id: NOISE,
field: 'width',
source: {
node_id: DENOISE_LATENTS,
field: 'latents',
},
});
graph.edges.push({
source: { node_id: IMAGE_TO_LATENTS, field: 'height' },
destination: {
node_id: NOISE,
field: 'height',
node_id: CANVAS_OUTPUT,
field: 'latents',
},
});
}
@ -300,8 +316,10 @@ export const buildCanvasImageToImageGraph = (
type: 'metadata_accumulator',
generation_mode: 'img2img',
cfg_scale,
height,
width,
width: !isUsingScaledDimensions ? width : scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
positive_prompt: '', // set in addDynamicPromptsToGraph
negative_prompt: negativePrompt,
model,
@ -328,11 +346,17 @@ export const buildCanvasImageToImageGraph = (
},
});
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// add LoRA support
addLoRAsToGraph(state, graph, DENOISE_LATENTS);
// optionally add custom VAE
addVAEToGraph(state, graph, MAIN_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add dynamic prompts - also sets up core iteration and seed
addDynamicPromptsToGraph(state, graph);

65
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasInpaintGraph.ts
View File

@ -2,6 +2,7 @@ import { logger } from 'app/logging/logger';
import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types';
import {
CreateDenoiseMaskInvocation,
ImageBlurInvocation,
ImageDTO,
ImageToLatentsInvocation,
@ -12,16 +13,18 @@ import {
import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addLoRAsToGraph } from './addLoRAsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
CANVAS_INPAINT_GRAPH,
CANVAS_OUTPUT,
CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_INPAINT_GRAPH,
CANVAS_OUTPUT,
CLIP_SKIP,
DENOISE_LATENTS,
INPAINT_CREATE_MASK,
INPAINT_IMAGE,
INPAINT_IMAGE_RESIZE_DOWN,
INPAINT_IMAGE_RESIZE_UP,
@ -36,6 +39,7 @@ import {
POSITIVE_CONDITIONING,
RANDOM_INT,
RANGE_OF_SIZE,
SEAMLESS,
} from './constants';
/**
@ -66,6 +70,8 @@ export const buildCanvasInpaintGraph = (
canvasCoherenceSteps,
canvasCoherenceStrength,
clipSkip,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
if (!model) {
@ -83,6 +89,8 @@ export const buildCanvasInpaintGraph = (
shouldAutoSave,
} = state.canvas;
let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: shouldUseCpuNoise;
@ -90,9 +98,9 @@ export const buildCanvasInpaintGraph = (
const graph: NonNullableGraph = {
id: CANVAS_INPAINT_GRAPH,
nodes: {
[MAIN_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'main_model_loader',
id: MAIN_MODEL_LOADER,
id: modelLoaderNodeId,
is_intermediate: true,
model,
},
@ -127,6 +135,12 @@ export const buildCanvasInpaintGraph = (
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
},
[INPAINT_CREATE_MASK]: {
type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK,
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
},
[NOISE]: {
type: 'noise',
id: NOISE,
@ -196,7 +210,7 @@ export const buildCanvasInpaintGraph = (
// Connect Model Loader to CLIP Skip and UNet
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -206,7 +220,7 @@ export const buildCanvasInpaintGraph = (
},
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -276,16 +290,27 @@ export const buildCanvasInpaintGraph = (
field: 'latents',
},
},
// Create Inpaint Mask
{
source: {
node_id: MASK_BLUR,
field: 'image',
},
destination: {
node_id: DENOISE_LATENTS,
node_id: INPAINT_CREATE_MASK,
field: 'mask',
},
},
{
source: {
node_id: INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: DENOISE_LATENTS,
field: 'denoise_mask',
},
},
// Iterate
{
source: {
@ -330,7 +355,7 @@ export const buildCanvasInpaintGraph = (
},
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -459,6 +484,16 @@ export const buildCanvasInpaintGraph = (
field: 'image',
},
},
{
source: {
node_id: INPAINT_IMAGE_RESIZE_UP,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Color Correct The Inpainted Result
{
source: {
@ -516,6 +551,10 @@ export const buildCanvasInpaintGraph = (
...(graph.nodes[MASK_BLUR] as ImageBlurInvocation),
image: canvasMaskImage,
};
graph.nodes[INPAINT_CREATE_MASK] = {
...(graph.nodes[INPAINT_CREATE_MASK] as CreateDenoiseMaskInvocation),
image: canvasInitImage,
};
graph.edges.push(
// Color Correct The Inpainted Result
@ -562,11 +601,17 @@ export const buildCanvasInpaintGraph = (
(graph.nodes[RANGE_OF_SIZE] as RangeOfSizeInvocation).start = seed;
}
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add VAE
addVAEToGraph(state, graph, MAIN_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addLoRAsToGraph(state, graph, DENOISE_LATENTS, MAIN_MODEL_LOADER);
addLoRAsToGraph(state, graph, DENOISE_LATENTS, modelLoaderNodeId);
// add controlnet, mutating `graph`
addControlNetToLinearGraph(state, graph, DENOISE_LATENTS);

70
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasOutpaintGraph.ts
View File

@ -14,16 +14,18 @@ import {
import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addLoRAsToGraph } from './addLoRAsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
CANVAS_OUTPAINT_GRAPH,
CANVAS_OUTPUT,
CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_OUTPAINT_GRAPH,
CANVAS_OUTPUT,
CLIP_SKIP,
DENOISE_LATENTS,
INPAINT_CREATE_MASK,
INPAINT_IMAGE,
INPAINT_IMAGE_RESIZE_DOWN,
INPAINT_IMAGE_RESIZE_UP,
@ -42,6 +44,7 @@ import {
POSITIVE_CONDITIONING,
RANDOM_INT,
RANGE_OF_SIZE,
SEAMLESS,
} from './constants';
/**
@ -74,6 +77,8 @@ export const buildCanvasOutpaintGraph = (
tileSize,
infillMethod,
clipSkip,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
if (!model) {
@ -91,6 +96,8 @@ export const buildCanvasOutpaintGraph = (
shouldAutoSave,
} = state.canvas;
let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: shouldUseCpuNoise;
@ -98,9 +105,9 @@ export const buildCanvasOutpaintGraph = (
const graph: NonNullableGraph = {
id: CANVAS_OUTPAINT_GRAPH,
nodes: {
[MAIN_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'main_model_loader',
id: MAIN_MODEL_LOADER,
id: modelLoaderNodeId,
is_intermediate: true,
model,
},
@ -153,6 +160,12 @@ export const buildCanvasOutpaintGraph = (
use_cpu,
is_intermediate: true,
},
[INPAINT_CREATE_MASK]: {
type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK,
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
},
[DENOISE_LATENTS]: {
type: 'denoise_latents',
id: DENOISE_LATENTS,
@ -215,7 +228,7 @@ export const buildCanvasOutpaintGraph = (
// Connect Model Loader To UNet & Clip Skip
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -225,7 +238,7 @@ export const buildCanvasOutpaintGraph = (
},
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -317,16 +330,27 @@ export const buildCanvasOutpaintGraph = (
field: 'latents',
},
},
// Create Inpaint Mask
{
source: {
node_id: MASK_BLUR,
field: 'image',
},
destination: {
node_id: DENOISE_LATENTS,
node_id: INPAINT_CREATE_MASK,
field: 'mask',
},
},
{
source: {
node_id: INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: DENOISE_LATENTS,
field: 'denoise_mask',
},
},
// Iterate
{
source: {
@ -371,7 +395,7 @@ export const buildCanvasOutpaintGraph = (
},
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -522,6 +546,16 @@ export const buildCanvasOutpaintGraph = (
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
{
source: {
@ -640,6 +674,16 @@ export const buildCanvasOutpaintGraph = (
field: 'image',
},
},
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Color Correct The Inpainted Result
{
source: {
@ -694,11 +738,17 @@ export const buildCanvasOutpaintGraph = (
(graph.nodes[RANGE_OF_SIZE] as RangeOfSizeInvocation).start = seed;
}
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add VAE
addVAEToGraph(state, graph, MAIN_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addLoRAsToGraph(state, graph, DENOISE_LATENTS, MAIN_MODEL_LOADER);
addLoRAsToGraph(state, graph, DENOISE_LATENTS, modelLoaderNodeId);
// add controlnet, mutating `graph`
addControlNetToLinearGraph(state, graph, DENOISE_LATENTS);

200
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLImageToImageGraph.ts
View File

@ -2,29 +2,29 @@ import { logger } from 'app/logging/logger';
import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types';
import { initialGenerationState } from 'features/parameters/store/generationSlice';
import {
ImageDTO,
ImageResizeInvocation,
ImageToLatentsInvocation,
} from 'services/api/types';
import { ImageDTO, ImageToLatentsInvocation } from 'services/api/types';
import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSDXLLoRAsToGraph } from './addSDXLLoRAstoGraph';
import { addSDXLRefinerToGraph } from './addSDXLRefinerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
CANVAS_OUTPUT,
IMAGE_TO_LATENTS,
IMG2IMG_RESIZE,
LATENTS_TO_IMAGE,
METADATA_ACCUMULATOR,
NEGATIVE_CONDITIONING,
NOISE,
POSITIVE_CONDITIONING,
RESIZE,
REFINER_SEAMLESS,
SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH,
SDXL_DENOISE_LATENTS,
SDXL_MODEL_LOADER,
SEAMLESS,
} from './constants';
import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
@ -47,6 +47,8 @@ export const buildCanvasSDXLImageToImageGraph = (
clipSkip,
shouldUseCpuNoise,
shouldUseNoiseSettings,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
const {
@ -59,13 +61,24 @@ export const buildCanvasSDXLImageToImageGraph = (
// The bounding box determines width and height, not the width and height params
const { width, height } = state.canvas.boundingBoxDimensions;
const { shouldAutoSave } = state.canvas;
const {
scaledBoundingBoxDimensions,
boundingBoxScaleMethod,
shouldAutoSave,
} = state.canvas;
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
if (!model) {
log.error('No model found in state');
throw new Error('No model found in state');
}
// Model Loader ID
let modelLoaderNodeId = SDXL_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: initialGenerationState.shouldUseCpuNoise;
@ -87,9 +100,9 @@ export const buildCanvasSDXLImageToImageGraph = (
const graph: NonNullableGraph = {
id: SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH,
nodes: {
[SDXL_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'sdxl_model_loader',
id: SDXL_MODEL_LOADER,
id: modelLoaderNodeId,
model,
},
[POSITIVE_CONDITIONING]: {
@ -109,16 +122,18 @@ export const buildCanvasSDXLImageToImageGraph = (
id: NOISE,
is_intermediate: true,
use_cpu,
width: !isUsingScaledDimensions
? width
: scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
},
[IMAGE_TO_LATENTS]: {
type: 'i2l',
id: IMAGE_TO_LATENTS,
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
// must be set manually later, bc `fit` parameter may require a resize node inserted
// image: {
// image_name: initialImage.image_name,
// },
},
[SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents',
@ -132,18 +147,12 @@ export const buildCanvasSDXLImageToImageGraph = (
: 1 - strength,
denoising_end: shouldUseSDXLRefiner ? refinerStart : 1,
},
[CANVAS_OUTPUT]: {
type: 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false,
},
},
edges: [
// Connect Model Loader To UNet & CLIP
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -153,7 +162,7 @@ export const buildCanvasSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -163,7 +172,7 @@ export const buildCanvasSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -173,7 +182,7 @@ export const buildCanvasSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -183,7 +192,7 @@ export const buildCanvasSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -232,82 +241,84 @@ export const buildCanvasSDXLImageToImageGraph = (
field: 'latents',
},
},
// Decode denoised latents to an image
],
};
// Decode Latents To Image & Handle Scaled Before Processing
if (isUsingScaledDimensions) {
graph.nodes[IMG2IMG_RESIZE] = {
id: IMG2IMG_RESIZE,
type: 'img_resize',
is_intermediate: true,
image: initialImage,
width: scaledBoundingBoxDimensions.width,
height: scaledBoundingBoxDimensions.height,
};
graph.nodes[LATENTS_TO_IMAGE] = {
id: LATENTS_TO_IMAGE,
type: 'l2i',
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
};
graph.nodes[CANVAS_OUTPUT] = {
id: CANVAS_OUTPUT,
type: 'img_resize',
is_intermediate: !shouldAutoSave,
width: width,
height: height,
};
graph.edges.push(
{
source: {
node_id: IMG2IMG_RESIZE,
field: 'image',
},
destination: {
node_id: IMAGE_TO_LATENTS,
field: 'image',
},
},
{
source: {
node_id: SDXL_DENOISE_LATENTS,
field: 'latents',
},
destination: {
node_id: CANVAS_OUTPUT,
node_id: LATENTS_TO_IMAGE,
field: 'latents',
},
},
],
};
// handle `fit`
if (initialImage.width !== width || initialImage.height !== height) {
// The init image needs to be resized to the specified width and height before being passed to `IMAGE_TO_LATENTS`
// Create a resize node, explicitly setting its image
const resizeNode: ImageResizeInvocation = {
id: RESIZE,
type: 'img_resize',
image: {
image_name: initialImage.image_name,
},
is_intermediate: true,
width,
height,
};
graph.nodes[RESIZE] = resizeNode;
// The `RESIZE` node then passes its image to `IMAGE_TO_LATENTS`
graph.edges.push({
source: { node_id: RESIZE, field: 'image' },
destination: {
node_id: IMAGE_TO_LATENTS,
field: 'image',
},
});
// The `RESIZE` node also passes its width and height to `NOISE`
graph.edges.push({
source: { node_id: RESIZE, field: 'width' },
destination: {
node_id: NOISE,
field: 'width',
},
});
graph.edges.push({
source: { node_id: RESIZE, field: 'height' },
destination: {
node_id: NOISE,
field: 'height',
},
});
{
source: {
node_id: LATENTS_TO_IMAGE,
field: 'image',
},
destination: {
node_id: CANVAS_OUTPUT,
field: 'image',
},
}
);
} else {
// We are not resizing, so we need to set the image on the `IMAGE_TO_LATENTS` node explicitly
(graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image = {
image_name: initialImage.image_name,
graph.nodes[CANVAS_OUTPUT] = {
type: 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false,
};
// Pass the image's dimensions to the `NOISE` node
(graph.nodes[IMAGE_TO_LATENTS] as ImageToLatentsInvocation).image =
initialImage;
graph.edges.push({
source: { node_id: IMAGE_TO_LATENTS, field: 'width' },
destination: {
node_id: NOISE,
field: 'width',
source: {
node_id: SDXL_DENOISE_LATENTS,
field: 'latents',
},
});
graph.edges.push({
source: { node_id: IMAGE_TO_LATENTS, field: 'height' },
destination: {
node_id: NOISE,
field: 'height',
node_id: CANVAS_OUTPUT,
field: 'latents',
},
});
}
@ -318,8 +329,10 @@ export const buildCanvasSDXLImageToImageGraph = (
type: 'metadata_accumulator',
generation_mode: 'img2img',
cfg_scale,
height,
width,
width: !isUsingScaledDimensions ? width : scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
positive_prompt: '', // set in addDynamicPromptsToGraph
negative_prompt: negativePrompt,
model,
@ -346,16 +359,23 @@ export const buildCanvasSDXLImageToImageGraph = (
},
});
// add LoRA support
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, SDXL_MODEL_LOADER);
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add Refiner if enabled
if (shouldUseSDXLRefiner) {
addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS);
modelLoaderNodeId = REFINER_SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, SDXL_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
// add dynamic prompts - also sets up core iteration and seed
addDynamicPromptsToGraph(state, graph);

78
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLInpaintGraph.ts
View File

@ -2,6 +2,7 @@ import { logger } from 'app/logging/logger';
import { RootState } from 'app/store/store';
import { NonNullableGraph } from 'features/nodes/types/types';
import {
CreateDenoiseMaskInvocation,
ImageBlurInvocation,
ImageDTO,
ImageToLatentsInvocation,
@ -13,13 +14,15 @@ import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSDXLLoRAsToGraph } from './addSDXLLoRAstoGraph';
import { addSDXLRefinerToGraph } from './addSDXLRefinerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
CANVAS_OUTPUT,
CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_OUTPUT,
INPAINT_CREATE_MASK,
INPAINT_IMAGE,
INPAINT_IMAGE_RESIZE_DOWN,
INPAINT_IMAGE_RESIZE_UP,
@ -33,9 +36,11 @@ import {
POSITIVE_CONDITIONING,
RANDOM_INT,
RANGE_OF_SIZE,
REFINER_SEAMLESS,
SDXL_CANVAS_INPAINT_GRAPH,
SDXL_DENOISE_LATENTS,
SDXL_MODEL_LOADER,
SEAMLESS,
} from './constants';
import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
@ -65,6 +70,8 @@ export const buildCanvasSDXLInpaintGraph = (
maskBlurMethod,
canvasCoherenceSteps,
canvasCoherenceStrength,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
const {
@ -89,6 +96,8 @@ export const buildCanvasSDXLInpaintGraph = (
shouldAutoSave,
} = state.canvas;
let modelLoaderNodeId = SDXL_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: shouldUseCpuNoise;
@ -100,9 +109,9 @@ export const buildCanvasSDXLInpaintGraph = (
const graph: NonNullableGraph = {
id: SDXL_CANVAS_INPAINT_GRAPH,
nodes: {
[SDXL_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'sdxl_model_loader',
id: SDXL_MODEL_LOADER,
id: modelLoaderNodeId,
model,
},
[POSITIVE_CONDITIONING]: {
@ -136,6 +145,12 @@ export const buildCanvasSDXLInpaintGraph = (
use_cpu,
is_intermediate: true,
},
[INPAINT_CREATE_MASK]: {
type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK,
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
},
[SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents',
id: SDXL_DENOISE_LATENTS,
@ -201,7 +216,7 @@ export const buildCanvasSDXLInpaintGraph = (
// Connect Model Loader to UNet and CLIP
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -211,7 +226,7 @@ export const buildCanvasSDXLInpaintGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -221,7 +236,7 @@ export const buildCanvasSDXLInpaintGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -231,7 +246,7 @@ export const buildCanvasSDXLInpaintGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -241,7 +256,7 @@ export const buildCanvasSDXLInpaintGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -290,16 +305,27 @@ export const buildCanvasSDXLInpaintGraph = (
field: 'latents',
},
},
// Create Inpaint Mask
{
source: {
node_id: MASK_BLUR,
field: 'image',
},
destination: {
node_id: SDXL_DENOISE_LATENTS,
node_id: INPAINT_CREATE_MASK,
field: 'mask',
},
},
{
source: {
node_id: INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: SDXL_DENOISE_LATENTS,
field: 'denoise_mask',
},
},
// Iterate
{
source: {
@ -344,7 +370,7 @@ export const buildCanvasSDXLInpaintGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -473,6 +499,16 @@ export const buildCanvasSDXLInpaintGraph = (
field: 'image',
},
},
{
source: {
node_id: INPAINT_IMAGE_RESIZE_UP,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Color Correct The Inpainted Result
{
source: {
@ -530,6 +566,10 @@ export const buildCanvasSDXLInpaintGraph = (
...(graph.nodes[MASK_BLUR] as ImageBlurInvocation),
image: canvasMaskImage,
};
graph.nodes[INPAINT_CREATE_MASK] = {
...(graph.nodes[INPAINT_CREATE_MASK] as CreateDenoiseMaskInvocation),
image: canvasInitImage,
};
graph.edges.push(
// Color Correct The Inpainted Result
@ -576,16 +616,28 @@ export const buildCanvasSDXLInpaintGraph = (
(graph.nodes[RANGE_OF_SIZE] as RangeOfSizeInvocation).start = seed;
}
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add Refiner if enabled
if (shouldUseSDXLRefiner) {
addSDXLRefinerToGraph(state, graph, CANVAS_COHERENCE_DENOISE_LATENTS);
addSDXLRefinerToGraph(
state,
graph,
CANVAS_COHERENCE_DENOISE_LATENTS,
modelLoaderNodeId
);
modelLoaderNodeId = REFINER_SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, SDXL_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, SDXL_MODEL_LOADER);
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
// add controlnet, mutating `graph`
addControlNetToLinearGraph(state, graph, SDXL_DENOISE_LATENTS);

67
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLOutpaintGraph.ts
View File

@ -15,13 +15,15 @@ import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSDXLLoRAsToGraph } from './addSDXLLoRAstoGraph';
import { addSDXLRefinerToGraph } from './addSDXLRefinerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
CANVAS_OUTPUT,
CANVAS_COHERENCE_DENOISE_LATENTS,
CANVAS_COHERENCE_NOISE,
CANVAS_COHERENCE_NOISE_INCREMENT,
CANVAS_OUTPUT,
INPAINT_CREATE_MASK,
INPAINT_IMAGE,
INPAINT_IMAGE_RESIZE_DOWN,
INPAINT_IMAGE_RESIZE_UP,
@ -39,9 +41,11 @@ import {
POSITIVE_CONDITIONING,
RANDOM_INT,
RANGE_OF_SIZE,
REFINER_SEAMLESS,
SDXL_CANVAS_OUTPAINT_GRAPH,
SDXL_DENOISE_LATENTS,
SDXL_MODEL_LOADER,
SEAMLESS,
} from './constants';
import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
@ -73,6 +77,8 @@ export const buildCanvasSDXLOutpaintGraph = (
canvasCoherenceStrength,
tileSize,
infillMethod,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
const {
@ -97,6 +103,8 @@ export const buildCanvasSDXLOutpaintGraph = (
shouldAutoSave,
} = state.canvas;
let modelLoaderNodeId = SDXL_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: shouldUseCpuNoise;
@ -156,6 +164,12 @@ export const buildCanvasSDXLOutpaintGraph = (
use_cpu,
is_intermediate: true,
},
[INPAINT_CREATE_MASK]: {
type: 'create_denoise_mask',
id: INPAINT_CREATE_MASK,
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
},
[SDXL_DENOISE_LATENTS]: {
type: 'denoise_latents',
id: SDXL_DENOISE_LATENTS,
@ -331,16 +345,27 @@ export const buildCanvasSDXLOutpaintGraph = (
field: 'latents',
},
},
// Create Inpaint Mask
{
source: {
node_id: MASK_BLUR,
field: 'image',
},
destination: {
node_id: SDXL_DENOISE_LATENTS,
node_id: INPAINT_CREATE_MASK,
field: 'mask',
},
},
{
source: {
node_id: INPAINT_CREATE_MASK,
field: 'denoise_mask',
},
destination: {
node_id: SDXL_DENOISE_LATENTS,
field: 'denoise_mask',
},
},
// Iterate
{
source: {
@ -537,6 +562,16 @@ export const buildCanvasSDXLOutpaintGraph = (
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
{
source: {
@ -655,6 +690,16 @@ export const buildCanvasSDXLOutpaintGraph = (
field: 'image',
},
},
{
source: {
node_id: INPAINT_INFILL,
field: 'image',
},
destination: {
node_id: INPAINT_CREATE_MASK,
field: 'image',
},
},
// Color Correct The Inpainted Result
{
source: {
@ -709,16 +754,28 @@ export const buildCanvasSDXLOutpaintGraph = (
(graph.nodes[RANGE_OF_SIZE] as RangeOfSizeInvocation).start = seed;
}
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add Refiner if enabled
if (shouldUseSDXLRefiner) {
addSDXLRefinerToGraph(state, graph, CANVAS_COHERENCE_DENOISE_LATENTS);
addSDXLRefinerToGraph(
state,
graph,
CANVAS_COHERENCE_DENOISE_LATENTS,
modelLoaderNodeId
);
modelLoaderNodeId = REFINER_SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, SDXL_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, SDXL_MODEL_LOADER);
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
// add controlnet, mutating `graph`
addControlNetToLinearGraph(state, graph, SDXL_DENOISE_LATENTS);

101
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasSDXLTextToImageGraph.ts
View File

@ -11,18 +11,22 @@ import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSDXLLoRAsToGraph } from './addSDXLLoRAstoGraph';
import { addSDXLRefinerToGraph } from './addSDXLRefinerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
CANVAS_OUTPUT,
LATENTS_TO_IMAGE,
METADATA_ACCUMULATOR,
NEGATIVE_CONDITIONING,
NOISE,
ONNX_MODEL_LOADER,
POSITIVE_CONDITIONING,
REFINER_SEAMLESS,
SDXL_CANVAS_TEXT_TO_IMAGE_GRAPH,
SDXL_DENOISE_LATENTS,
SDXL_MODEL_LOADER,
SEAMLESS,
} from './constants';
import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
@ -44,12 +48,22 @@ export const buildCanvasSDXLTextToImageGraph = (
clipSkip,
shouldUseCpuNoise,
shouldUseNoiseSettings,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
// The bounding box determines width and height, not the width and height params
const { width, height } = state.canvas.boundingBoxDimensions;
const { shouldAutoSave } = state.canvas;
const {
scaledBoundingBoxDimensions,
boundingBoxScaleMethod,
shouldAutoSave,
} = state.canvas;
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
const { shouldUseSDXLRefiner, refinerStart, shouldConcatSDXLStylePrompt } =
state.sdxl;
@ -65,7 +79,7 @@ export const buildCanvasSDXLTextToImageGraph = (
const isUsingOnnxModel = model.model_type === 'onnx';
const modelLoaderNodeId = isUsingOnnxModel
let modelLoaderNodeId = isUsingOnnxModel
? ONNX_MODEL_LOADER
: SDXL_MODEL_LOADER;
@ -136,17 +150,15 @@ export const buildCanvasSDXLTextToImageGraph = (
type: 'noise',
id: NOISE,
is_intermediate: true,
width,
height,
width: !isUsingScaledDimensions
? width
: scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
use_cpu,
},
[t2lNode.id]: t2lNode,
[CANVAS_OUTPUT]: {
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false,
},
},
edges: [
// Connect Model Loader to UNet and CLIP
@ -231,19 +243,67 @@ export const buildCanvasSDXLTextToImageGraph = (
field: 'noise',
},
},
// Decode Denoised Latents To Image
],
};
// Decode Latents To Image & Handle Scaled Before Processing
if (isUsingScaledDimensions) {
graph.nodes[LATENTS_TO_IMAGE] = {
id: LATENTS_TO_IMAGE,
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
};
graph.nodes[CANVAS_OUTPUT] = {
id: CANVAS_OUTPUT,
type: 'img_resize',
is_intermediate: !shouldAutoSave,
width: width,
height: height,
};
graph.edges.push(
{
source: {
node_id: SDXL_DENOISE_LATENTS,
field: 'latents',
},
destination: {
node_id: CANVAS_OUTPUT,
node_id: LATENTS_TO_IMAGE,
field: 'latents',
},
},
],
};
{
source: {
node_id: LATENTS_TO_IMAGE,
field: 'image',
},
destination: {
node_id: CANVAS_OUTPUT,
field: 'image',
},
}
);
} else {
graph.nodes[CANVAS_OUTPUT] = {
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false,
};
graph.edges.push({
source: {
node_id: SDXL_DENOISE_LATENTS,
field: 'latents',
},
destination: {
node_id: CANVAS_OUTPUT,
field: 'latents',
},
});
}
// add metadata accumulator, which is only mostly populated - some fields are added later
graph.nodes[METADATA_ACCUMULATOR] = {
@ -251,8 +311,10 @@ export const buildCanvasSDXLTextToImageGraph = (
type: 'metadata_accumulator',
generation_mode: 'txt2img',
cfg_scale,
height,
width,
width: !isUsingScaledDimensions ? width : scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
positive_prompt: '', // set in addDynamicPromptsToGraph
negative_prompt: negativePrompt,
model,
@ -277,9 +339,16 @@ export const buildCanvasSDXLTextToImageGraph = (
},
});
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add Refiner if enabled
if (shouldUseSDXLRefiner) {
addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS);
modelLoaderNodeId = REFINER_SEAMLESS;
}
// add LoRA support

99
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildCanvasTextToImageGraph.ts
View File

@ -10,6 +10,7 @@ import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addLoRAsToGraph } from './addLoRAsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
@ -17,12 +18,14 @@ import {
CANVAS_TEXT_TO_IMAGE_GRAPH,
CLIP_SKIP,
DENOISE_LATENTS,
LATENTS_TO_IMAGE,
MAIN_MODEL_LOADER,
METADATA_ACCUMULATOR,
NEGATIVE_CONDITIONING,
NOISE,
ONNX_MODEL_LOADER,
POSITIVE_CONDITIONING,
SEAMLESS,
} from './constants';
/**
@ -39,15 +42,26 @@ export const buildCanvasTextToImageGraph = (
cfgScale: cfg_scale,
scheduler,
steps,
vaePrecision,
clipSkip,
shouldUseCpuNoise,
shouldUseNoiseSettings,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
// The bounding box determines width and height, not the width and height params
const { width, height } = state.canvas.boundingBoxDimensions;
const { shouldAutoSave } = state.canvas;
const {
scaledBoundingBoxDimensions,
boundingBoxScaleMethod,
shouldAutoSave,
} = state.canvas;
const isUsingScaledDimensions = ['auto', 'manual'].includes(
boundingBoxScaleMethod
);
if (!model) {
log.error('No model found in state');
@ -60,7 +74,7 @@ export const buildCanvasTextToImageGraph = (
const isUsingOnnxModel = model.model_type === 'onnx';
const modelLoaderNodeId = isUsingOnnxModel
let modelLoaderNodeId = isUsingOnnxModel
? ONNX_MODEL_LOADER
: MAIN_MODEL_LOADER;
@ -131,16 +145,15 @@ export const buildCanvasTextToImageGraph = (
type: 'noise',
id: NOISE,
is_intermediate: true,
width,
height,
width: !isUsingScaledDimensions
? width
: scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
use_cpu,
},
[t2lNode.id]: t2lNode,
[CANVAS_OUTPUT]: {
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
},
},
edges: [
// Connect Model Loader to UNet & CLIP Skip
@ -216,19 +229,67 @@ export const buildCanvasTextToImageGraph = (
field: 'noise',
},
},
// Decode denoised latents to image
],
};
// Decode Latents To Image & Handle Scaled Before Processing
if (isUsingScaledDimensions) {
graph.nodes[LATENTS_TO_IMAGE] = {
id: LATENTS_TO_IMAGE,
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
is_intermediate: true,
fp32: vaePrecision === 'fp32' ? true : false,
};
graph.nodes[CANVAS_OUTPUT] = {
id: CANVAS_OUTPUT,
type: 'img_resize',
is_intermediate: !shouldAutoSave,
width: width,
height: height,
};
graph.edges.push(
{
source: {
node_id: DENOISE_LATENTS,
field: 'latents',
},
destination: {
node_id: CANVAS_OUTPUT,
node_id: LATENTS_TO_IMAGE,
field: 'latents',
},
},
],
};
{
source: {
node_id: LATENTS_TO_IMAGE,
field: 'image',
},
destination: {
node_id: CANVAS_OUTPUT,
field: 'image',
},
}
);
} else {
graph.nodes[CANVAS_OUTPUT] = {
type: isUsingOnnxModel ? 'l2i_onnx' : 'l2i',
id: CANVAS_OUTPUT,
is_intermediate: !shouldAutoSave,
fp32: vaePrecision === 'fp32' ? true : false,
};
graph.edges.push({
source: {
node_id: DENOISE_LATENTS,
field: 'latents',
},
destination: {
node_id: CANVAS_OUTPUT,
field: 'latents',
},
});
}
// add metadata accumulator, which is only mostly populated - some fields are added later
graph.nodes[METADATA_ACCUMULATOR] = {
@ -236,8 +297,10 @@ export const buildCanvasTextToImageGraph = (
type: 'metadata_accumulator',
generation_mode: 'txt2img',
cfg_scale,
height,
width,
width: !isUsingScaledDimensions ? width : scaledBoundingBoxDimensions.width,
height: !isUsingScaledDimensions
? height
: scaledBoundingBoxDimensions.height,
positive_prompt: '', // set in addDynamicPromptsToGraph
negative_prompt: negativePrompt,
model,
@ -262,6 +325,12 @@ export const buildCanvasTextToImageGraph = (
},
});
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, modelLoaderNodeId);

24
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearImageToImageGraph.ts
View File

@ -10,6 +10,7 @@ import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addLoRAsToGraph } from './addLoRAsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
@ -24,6 +25,7 @@ import {
NOISE,
POSITIVE_CONDITIONING,
RESIZE,
SEAMLESS,
} from './constants';
/**
@ -49,6 +51,8 @@ export const buildLinearImageToImageGraph = (
shouldUseCpuNoise,
shouldUseNoiseSettings,
vaePrecision,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
// TODO: add batch functionality
@ -80,6 +84,8 @@ export const buildLinearImageToImageGraph = (
throw new Error('No model found in state');
}
let modelLoaderNodeId = MAIN_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: initialGenerationState.shouldUseCpuNoise;
@ -88,9 +94,9 @@ export const buildLinearImageToImageGraph = (
const graph: NonNullableGraph = {
id: IMAGE_TO_IMAGE_GRAPH,
nodes: {
[MAIN_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'main_model_loader',
id: MAIN_MODEL_LOADER,
id: modelLoaderNodeId,
model,
},
[CLIP_SKIP]: {
@ -141,7 +147,7 @@ export const buildLinearImageToImageGraph = (
// Connect Model Loader to UNet and CLIP Skip
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -151,7 +157,7 @@ export const buildLinearImageToImageGraph = (
},
{
source: {
node_id: MAIN_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -338,11 +344,17 @@ export const buildLinearImageToImageGraph = (
},
});
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, MAIN_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addLoRAsToGraph(state, graph, DENOISE_LATENTS);
addLoRAsToGraph(state, graph, DENOISE_LATENTS, modelLoaderNodeId);
// add dynamic prompts - also sets up core iteration and seed
addDynamicPromptsToGraph(state, graph);

34
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearSDXLImageToImageGraph.ts
View File

@ -11,6 +11,7 @@ import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSDXLLoRAsToGraph } from './addSDXLLoRAstoGraph';
import { addSDXLRefinerToGraph } from './addSDXLRefinerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
@ -20,10 +21,12 @@ import {
NEGATIVE_CONDITIONING,
NOISE,
POSITIVE_CONDITIONING,
REFINER_SEAMLESS,
RESIZE,
SDXL_DENOISE_LATENTS,
SDXL_IMAGE_TO_IMAGE_GRAPH,
SDXL_MODEL_LOADER,
SEAMLESS,
} from './constants';
import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
@ -49,6 +52,8 @@ export const buildLinearSDXLImageToImageGraph = (
shouldUseCpuNoise,
shouldUseNoiseSettings,
vaePrecision,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
const {
@ -79,6 +84,9 @@ export const buildLinearSDXLImageToImageGraph = (
throw new Error('No model found in state');
}
// Model Loader ID
let modelLoaderNodeId = SDXL_MODEL_LOADER;
const use_cpu = shouldUseNoiseSettings
? shouldUseCpuNoise
: initialGenerationState.shouldUseCpuNoise;
@ -91,9 +99,9 @@ export const buildLinearSDXLImageToImageGraph = (
const graph: NonNullableGraph = {
id: SDXL_IMAGE_TO_IMAGE_GRAPH,
nodes: {
[SDXL_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'sdxl_model_loader',
id: SDXL_MODEL_LOADER,
id: modelLoaderNodeId,
model,
},
[POSITIVE_CONDITIONING]: {
@ -143,7 +151,7 @@ export const buildLinearSDXLImageToImageGraph = (
// Connect Model Loader to UNet, CLIP & VAE
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -153,7 +161,7 @@ export const buildLinearSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -163,7 +171,7 @@ export const buildLinearSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -173,7 +181,7 @@ export const buildLinearSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -183,7 +191,7 @@ export const buildLinearSDXLImageToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -351,15 +359,23 @@ export const buildLinearSDXLImageToImageGraph = (
},
});
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, SDXL_MODEL_LOADER);
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add Refiner if enabled
if (shouldUseSDXLRefiner) {
addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS);
modelLoaderNodeId = REFINER_SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, SDXL_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// Add LoRA Support
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
// add controlnet, mutating `graph`
addControlNetToLinearGraph(state, graph, SDXL_DENOISE_LATENTS);

33
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearSDXLTextToImageGraph.ts
View File

@ -7,6 +7,7 @@ import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSDXLLoRAsToGraph } from './addSDXLLoRAstoGraph';
import { addSDXLRefinerToGraph } from './addSDXLRefinerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
@ -15,9 +16,11 @@ import {
NEGATIVE_CONDITIONING,
NOISE,
POSITIVE_CONDITIONING,
REFINER_SEAMLESS,
SDXL_DENOISE_LATENTS,
SDXL_MODEL_LOADER,
SDXL_TEXT_TO_IMAGE_GRAPH,
SEAMLESS,
} from './constants';
import { craftSDXLStylePrompt } from './helpers/craftSDXLStylePrompt';
@ -38,6 +41,8 @@ export const buildLinearSDXLTextToImageGraph = (
shouldUseCpuNoise,
shouldUseNoiseSettings,
vaePrecision,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
const {
@ -61,6 +66,9 @@ export const buildLinearSDXLTextToImageGraph = (
const { craftedPositiveStylePrompt, craftedNegativeStylePrompt } =
craftSDXLStylePrompt(state, shouldConcatSDXLStylePrompt);
// Model Loader ID
let modelLoaderNodeId = SDXL_MODEL_LOADER;
/**
* The easiest way to build linear graphs is to do it in the node editor, then copy and paste the
* full graph here as a template. Then use the parameters from app state and set friendlier node
@ -74,9 +82,9 @@ export const buildLinearSDXLTextToImageGraph = (
const graph: NonNullableGraph = {
id: SDXL_TEXT_TO_IMAGE_GRAPH,
nodes: {
[SDXL_MODEL_LOADER]: {
[modelLoaderNodeId]: {
type: 'sdxl_model_loader',
id: SDXL_MODEL_LOADER,
id: modelLoaderNodeId,
model,
},
[POSITIVE_CONDITIONING]: {
@ -117,7 +125,7 @@ export const buildLinearSDXLTextToImageGraph = (
// Connect Model Loader to UNet, VAE & CLIP
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'unet',
},
destination: {
@ -127,7 +135,7 @@ export const buildLinearSDXLTextToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -137,7 +145,7 @@ export const buildLinearSDXLTextToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -147,7 +155,7 @@ export const buildLinearSDXLTextToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip',
},
destination: {
@ -157,7 +165,7 @@ export const buildLinearSDXLTextToImageGraph = (
},
{
source: {
node_id: SDXL_MODEL_LOADER,
node_id: modelLoaderNodeId,
field: 'clip2',
},
destination: {
@ -244,16 +252,23 @@ export const buildLinearSDXLTextToImageGraph = (
},
});
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// Add Refiner if enabled
if (shouldUseSDXLRefiner) {
addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS);
modelLoaderNodeId = REFINER_SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, SDXL_MODEL_LOADER);
addVAEToGraph(state, graph, modelLoaderNodeId);
// add LoRA support
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, SDXL_MODEL_LOADER);
addSDXLLoRAsToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
// add controlnet, mutating `graph`
addControlNetToLinearGraph(state, graph, SDXL_DENOISE_LATENTS);

12
invokeai/frontend/web/src/features/nodes/util/graphBuilders/buildLinearTextToImageGraph.ts
View File

@ -10,6 +10,7 @@ import { addControlNetToLinearGraph } from './addControlNetToLinearGraph';
import { addDynamicPromptsToGraph } from './addDynamicPromptsToGraph';
import { addLoRAsToGraph } from './addLoRAsToGraph';
import { addNSFWCheckerToGraph } from './addNSFWCheckerToGraph';
import { addSeamlessToLinearGraph } from './addSeamlessToLinearGraph';
import { addVAEToGraph } from './addVAEToGraph';
import { addWatermarkerToGraph } from './addWatermarkerToGraph';
import {
@ -22,6 +23,7 @@ import {
NOISE,
ONNX_MODEL_LOADER,
POSITIVE_CONDITIONING,
SEAMLESS,
TEXT_TO_IMAGE_GRAPH,
} from './constants';
@ -42,6 +44,8 @@ export const buildLinearTextToImageGraph = (
shouldUseCpuNoise,
shouldUseNoiseSettings,
vaePrecision,
seamlessXAxis,
seamlessYAxis,
} = state.generation;
const use_cpu = shouldUseNoiseSettings
@ -55,7 +59,7 @@ export const buildLinearTextToImageGraph = (
const isUsingOnnxModel = model.model_type === 'onnx';
const modelLoaderNodeId = isUsingOnnxModel
let modelLoaderNodeId = isUsingOnnxModel
? ONNX_MODEL_LOADER
: MAIN_MODEL_LOADER;
@ -258,6 +262,12 @@ export const buildLinearTextToImageGraph = (
},
});
// Add Seamless To Graph
if (seamlessXAxis || seamlessYAxis) {
addSeamlessToLinearGraph(state, graph, modelLoaderNodeId);
modelLoaderNodeId = SEAMLESS;
}
// optionally add custom VAE
addVAEToGraph(state, graph, modelLoaderNodeId);

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

@ -17,6 +17,7 @@ export const CLIP_SKIP = 'clip_skip';
export const IMAGE_TO_LATENTS = 'image_to_latents';
export const LATENTS_TO_LATENTS = 'latents_to_latents';
export const RESIZE = 'resize_image';
export const IMG2IMG_RESIZE = 'img2img_resize';
export const CANVAS_OUTPUT = 'canvas_output';
export const INPAINT_IMAGE = 'inpaint_image';
export const SCALED_INPAINT_IMAGE = 'scaled_inpaint_image';
@ -25,6 +26,7 @@ export const INPAINT_IMAGE_RESIZE_DOWN = 'inpaint_image_resize_down';
export const INPAINT_INFILL = 'inpaint_infill';
export const INPAINT_INFILL_RESIZE_DOWN = 'inpaint_infill_resize_down';
export const INPAINT_FINAL_IMAGE = 'inpaint_final_image';
export const INPAINT_CREATE_MASK = 'inpaint_create_mask';
export const CANVAS_COHERENCE_DENOISE_LATENTS =
'canvas_coherence_denoise_latents';
export const CANVAS_COHERENCE_NOISE = 'canvas_coherence_noise';
@ -54,6 +56,8 @@ export const SDXL_REFINER_POSITIVE_CONDITIONING =
export const SDXL_REFINER_NEGATIVE_CONDITIONING =
'sdxl_refiner_negative_conditioning';
export const SDXL_REFINER_DENOISE_LATENTS = 'sdxl_refiner_denoise_latents';
export const SEAMLESS = 'seamless';
export const REFINER_SEAMLESS = 'refiner_seamless';
// friendly graph ids
export const TEXT_TO_IMAGE_GRAPH = 'text_to_image_graph';

81
invokeai/frontend/web/src/features/parameters/hooks/usePreselectedImage.ts Normal file
View File

@ -0,0 +1,81 @@
import { skipToken } from '@reduxjs/toolkit/dist/query';
import { t } from 'i18next';
import { useCallback, useState } from 'react';
import { useAppToaster } from '../../../app/components/Toaster';
import { useAppDispatch } from '../../../app/store/storeHooks';
import {
useGetImageDTOQuery,
useGetImageMetadataQuery,
} from '../../../services/api/endpoints/images';
import { setInitialCanvasImage } from '../../canvas/store/canvasSlice';
import { setActiveTab } from '../../ui/store/uiSlice';
import { initialImageSelected } from '../store/actions';
import { useRecallParameters } from './useRecallParameters';
type SelectedImage = {
imageName: string;
action: 'sendToImg2Img' | 'sendToCanvas' | 'useAllParameters';
};
export const usePreselectedImage = () => {
const dispatch = useAppDispatch();
const [imageNameForDto, setImageNameForDto] = useState<string | undefined>();
const [imageNameForMetadata, setImageNameForMetadata] = useState<
string | undefined
>();
const { recallAllParameters } = useRecallParameters();
const toaster = useAppToaster();
const { currentData: selectedImageDto } = useGetImageDTOQuery(
imageNameForDto ?? skipToken
);
const { currentData: selectedImageMetadata } = useGetImageMetadataQuery(
imageNameForMetadata ?? skipToken
);
const handlePreselectedImage = useCallback(
(selectedImage?: SelectedImage) => {
if (!selectedImage) {
return;
}
if (selectedImage.action === 'sendToCanvas') {
setImageNameForDto(selectedImage?.imageName);
if (selectedImageDto) {
dispatch(setInitialCanvasImage(selectedImageDto));
dispatch(setActiveTab('unifiedCanvas'));
toaster({
title: t('toast.sentToUnifiedCanvas'),
status: 'info',
duration: 2500,
isClosable: true,
});
}
}
if (selectedImage.action === 'sendToImg2Img') {
setImageNameForDto(selectedImage?.imageName);
if (selectedImageDto) {
dispatch(initialImageSelected(selectedImageDto));
}
}
if (selectedImage.action === 'useAllParameters') {
setImageNameForMetadata(selectedImage?.imageName);
if (selectedImageMetadata) {
recallAllParameters(selectedImageMetadata.metadata);
}
}
},
[
dispatch,
selectedImageDto,
selectedImageMetadata,
recallAllParameters,
toaster,
]
);
return { handlePreselectedImage };
};

2
invokeai/frontend/web/src/features/sdxl/components/SDXLImageToImageTabParameters.tsx
View File

@ -2,6 +2,7 @@ import ParamDynamicPromptsCollapse from 'features/dynamicPrompts/components/Para
import ParamLoraCollapse from 'features/lora/components/ParamLoraCollapse';
import ParamControlNetCollapse from 'features/parameters/components/Parameters/ControlNet/ParamControlNetCollapse';
import ParamNoiseCollapse from 'features/parameters/components/Parameters/Noise/ParamNoiseCollapse';
import ParamSeamlessCollapse from 'features/parameters/components/Parameters/Seamless/ParamSeamlessCollapse';
import { memo } from 'react';
import ParamSDXLPromptArea from './ParamSDXLPromptArea';
import ParamSDXLRefinerCollapse from './ParamSDXLRefinerCollapse';
@ -17,6 +18,7 @@ const SDXLImageToImageTabParameters = () => {
<ParamLoraCollapse />
<ParamDynamicPromptsCollapse />
<ParamNoiseCollapse />
<ParamSeamlessCollapse />
</>
);
};

2
invokeai/frontend/web/src/features/sdxl/components/SDXLTextToImageTabParameters.tsx
View File

@ -2,6 +2,7 @@ import ParamDynamicPromptsCollapse from 'features/dynamicPrompts/components/Para
import ParamLoraCollapse from 'features/lora/components/ParamLoraCollapse';
import ParamControlNetCollapse from 'features/parameters/components/Parameters/ControlNet/ParamControlNetCollapse';
import ParamNoiseCollapse from 'features/parameters/components/Parameters/Noise/ParamNoiseCollapse';
import ParamSeamlessCollapse from 'features/parameters/components/Parameters/Seamless/ParamSeamlessCollapse';
import TextToImageTabCoreParameters from 'features/ui/components/tabs/TextToImage/TextToImageTabCoreParameters';
import { memo } from 'react';
import ParamSDXLPromptArea from './ParamSDXLPromptArea';
@ -17,6 +18,7 @@ const SDXLTextToImageTabParameters = () => {
<ParamLoraCollapse />
<ParamDynamicPromptsCollapse />
<ParamNoiseCollapse />
<ParamSeamlessCollapse />
</>
);
};

2
invokeai/frontend/web/src/features/sdxl/components/SDXLUnifiedCanvasTabParameters.tsx
View File

@ -5,6 +5,7 @@ import ParamMaskAdjustmentCollapse from 'features/parameters/components/Paramete
import ParamCanvasCoherencePassCollapse from 'features/parameters/components/Parameters/Canvas/SeamPainting/ParamCanvasCoherencePassCollapse';
import ParamControlNetCollapse from 'features/parameters/components/Parameters/ControlNet/ParamControlNetCollapse';
import ParamNoiseCollapse from 'features/parameters/components/Parameters/Noise/ParamNoiseCollapse';
import ParamSeamlessCollapse from 'features/parameters/components/Parameters/Seamless/ParamSeamlessCollapse';
import ParamSDXLPromptArea from './ParamSDXLPromptArea';
import ParamSDXLRefinerCollapse from './ParamSDXLRefinerCollapse';
import SDXLUnifiedCanvasTabCoreParameters from './SDXLUnifiedCanvasTabCoreParameters';
@ -22,6 +23,7 @@ export default function SDXLUnifiedCanvasTabParameters() {
<ParamMaskAdjustmentCollapse />
<ParamInfillAndScalingCollapse />
<ParamCanvasCoherencePassCollapse />
<ParamSeamlessCollapse />
</>
);
}

1
invokeai/frontend/web/src/features/system/store/configSlice.ts
View File

@ -9,7 +9,6 @@ export const initialConfigState: AppConfig = {
disabledFeatures: ['lightbox', 'faceRestore', 'batches'],
disabledSDFeatures: [
'variation',
'seamless',
'symmetry',
'hires',
'perlinNoise',

2
invokeai/frontend/web/src/features/ui/components/tabs/UnifiedCanvas/UnifiedCanvasParameters.tsx
View File

@ -6,6 +6,7 @@ import ParamMaskAdjustmentCollapse from 'features/parameters/components/Paramete
import ParamCanvasCoherencePassCollapse from 'features/parameters/components/Parameters/Canvas/SeamPainting/ParamCanvasCoherencePassCollapse';
import ParamControlNetCollapse from 'features/parameters/components/Parameters/ControlNet/ParamControlNetCollapse';
import ParamPromptArea from 'features/parameters/components/Parameters/Prompt/ParamPromptArea';
import ParamSeamlessCollapse from 'features/parameters/components/Parameters/Seamless/ParamSeamlessCollapse';
import ParamSymmetryCollapse from 'features/parameters/components/Parameters/Symmetry/ParamSymmetryCollapse';
import { memo } from 'react';
import UnifiedCanvasCoreParameters from './UnifiedCanvasCoreParameters';
@ -22,6 +23,7 @@ const UnifiedCanvasParameters = () => {
<ParamMaskAdjustmentCollapse />
<ParamInfillAndScalingCollapse />
<ParamCanvasCoherencePassCollapse />
<ParamSeamlessCollapse />
<ParamAdvancedCollapse />
</>
);

201
invokeai/frontend/web/src/services/api/schema.d.ts vendored
View File

File diff suppressed because one or more lines are too long

2
invokeai/frontend/web/src/services/api/types.ts
View File

@ -111,6 +111,7 @@ export type ImageBlurInvocation = s['ImageBlurInvocation'];
export type ImageScaleInvocation = s['ImageScaleInvocation'];
export type InfillPatchMatchInvocation = s['InfillPatchMatchInvocation'];
export type InfillTileInvocation = s['InfillTileInvocation'];
export type CreateDenoiseMaskInvocation = s['CreateDenoiseMaskInvocation'];
export type RandomIntInvocation = s['RandomIntInvocation'];
export type CompelInvocation = s['CompelInvocation'];
export type DynamicPromptInvocation = s['DynamicPromptInvocation'];
@ -129,6 +130,7 @@ export type ESRGANInvocation = s['ESRGANInvocation'];
export type DivideInvocation = s['DivideInvocation'];
export type ImageNSFWBlurInvocation = s['ImageNSFWBlurInvocation'];
export type ImageWatermarkInvocation = s['ImageWatermarkInvocation'];
export type SeamlessModeInvocation = s['SeamlessModeInvocation'];
// ControlNet Nodes
export type ControlNetInvocation = s['ControlNetInvocation'];