mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
tidy(nodes): use canonical capitalizations
This commit is contained in:
psychedelicious
parent
c57f6ee885
commit
132790eebe
@ -20,7 +20,7 @@ from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
|
||||
from invokeai.backend.util.devices import torch_dtype
|
||||
|
||||
from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
|
||||
from .model import ClipField
|
||||
from .model import CLIPField
|
||||
|
||||
# unconditioned: Optional[torch.Tensor]
|
||||
|
||||
@ -46,7 +46,7 @@ class CompelInvocation(BaseInvocation):
|
||||
description=FieldDescriptions.compel_prompt,
|
||||
ui_component=UIComponent.Textarea,
|
||||
)
|
||||
clip: ClipField = InputField(
|
||||
clip: CLIPField = InputField(
|
||||
title="CLIP",
|
||||
description=FieldDescriptions.clip,
|
||||
input=Input.Connection,
|
||||
@ -127,7 +127,7 @@ class SDXLPromptInvocationBase:
|
||||
def run_clip_compel(
|
||||
self,
|
||||
context: InvocationContext,
|
||||
clip_field: ClipField,
|
||||
clip_field: CLIPField,
|
||||
prompt: str,
|
||||
get_pooled: bool,
|
||||
lora_prefix: str,
|
||||
@ -253,8 +253,8 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
|
||||
crop_left: int = InputField(default=0, description="")
|
||||
target_width: int = InputField(default=1024, description="")
|
||||
target_height: int = InputField(default=1024, description="")
|
||||
clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
|
||||
clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
|
||||
clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
|
||||
clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
|
||||
|
||||
@torch.no_grad()
|
||||
def invoke(self, context: InvocationContext) -> ConditioningOutput:
|
||||
@ -340,7 +340,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
|
||||
crop_top: int = InputField(default=0, description="")
|
||||
crop_left: int = InputField(default=0, description="")
|
||||
aesthetic_score: float = InputField(default=6.0, description=FieldDescriptions.sdxl_aesthetic)
|
||||
clip2: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
|
||||
clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection)
|
||||
|
||||
@torch.no_grad()
|
||||
def invoke(self, context: InvocationContext) -> ConditioningOutput:
|
||||
@ -370,10 +370,10 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
|
||||
|
||||
|
||||
@invocation_output("clip_skip_output")
|
||||
class ClipSkipInvocationOutput(BaseInvocationOutput):
|
||||
"""Clip skip node output"""
|
||||
class CLIPSkipInvocationOutput(BaseInvocationOutput):
|
||||
"""CLIP skip node output"""
|
||||
|
||||
clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
|
||||
clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
|
||||
|
||||
|
||||
@invocation(
|
||||
@ -383,15 +383,15 @@ class ClipSkipInvocationOutput(BaseInvocationOutput):
|
||||
category="conditioning",
|
||||
version="1.0.0",
|
||||
)
|
||||
class ClipSkipInvocation(BaseInvocation):
|
||||
class CLIPSkipInvocation(BaseInvocation):
|
||||
"""Skip layers in clip text_encoder model."""
|
||||
|
||||
clip: ClipField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
|
||||
clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP")
|
||||
skipped_layers: int = InputField(default=0, ge=0, description=FieldDescriptions.skipped_layers)
|
||||
|
||||
def invoke(self, context: InvocationContext) -> ClipSkipInvocationOutput:
|
||||
def invoke(self, context: InvocationContext) -> CLIPSkipInvocationOutput:
|
||||
self.clip.skipped_layers += self.skipped_layers
|
||||
return ClipSkipInvocationOutput(
|
||||
return CLIPSkipInvocationOutput(
|
||||
clip=self.clip,
|
||||
)
|
||||
|
||||
|
||||
@ -76,7 +76,7 @@ from .baseinvocation import (
|
||||
invocation_output,
|
||||
)
|
||||
from .controlnet_image_processors import ControlField
|
||||
from .model import ModelField, UNetField, VaeField
|
||||
from .model import ModelField, UNetField, VAEField
|
||||
|
||||
if choose_torch_device() == torch.device("mps"):
|
||||
from torch import mps
|
||||
@ -119,7 +119,7 @@ class SchedulerInvocation(BaseInvocation):
|
||||
class CreateDenoiseMaskInvocation(BaseInvocation):
|
||||
"""Creates mask for denoising model run."""
|
||||
|
||||
vae: VaeField = InputField(description=FieldDescriptions.vae, input=Input.Connection, ui_order=0)
|
||||
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)
|
||||
@ -832,7 +832,7 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
|
||||
description=FieldDescriptions.latents,
|
||||
input=Input.Connection,
|
||||
)
|
||||
vae: VaeField = InputField(
|
||||
vae: VAEField = InputField(
|
||||
description=FieldDescriptions.vae,
|
||||
input=Input.Connection,
|
||||
)
|
||||
@ -1010,7 +1010,7 @@ class ImageToLatentsInvocation(BaseInvocation):
|
||||
image: ImageField = InputField(
|
||||
description="The image to encode",
|
||||
)
|
||||
vae: VaeField = InputField(
|
||||
vae: VAEField = InputField(
|
||||
description=FieldDescriptions.vae,
|
||||
input=Input.Connection,
|
||||
)
|
||||
|
||||
@ -29,20 +29,19 @@ class LoRAField(BaseModel):
|
||||
class UNetField(BaseModel):
|
||||
unet: ModelField = Field(description="Info to load unet submodel")
|
||||
scheduler: ModelField = Field(description="Info to load scheduler submodel")
|
||||
loras: List[LoRAField] = Field(description="Loras to apply on model loading")
|
||||
loras: List[LoRAField] = 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')
|
||||
freeu_config: Optional[FreeUConfig] = Field(default=None, description="FreeU configuration")
|
||||
|
||||
|
||||
class ClipField(BaseModel):
|
||||
class CLIPField(BaseModel):
|
||||
tokenizer: ModelField = Field(description="Info to load tokenizer submodel")
|
||||
text_encoder: ModelField = Field(description="Info to load text_encoder submodel")
|
||||
skipped_layers: int = Field(description="Number of skipped layers in text_encoder")
|
||||
loras: List[LoRAField] = Field(description="Loras to apply on model loading")
|
||||
loras: List[LoRAField] = Field(description="LoRAs to apply on model loading")
|
||||
|
||||
|
||||
class VaeField(BaseModel):
|
||||
# TODO: better naming?
|
||||
class VAEField(BaseModel):
|
||||
vae: ModelField = Field(description="Info to load vae submodel")
|
||||
seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
|
||||
|
||||
@ -58,14 +57,14 @@ class UNetOutput(BaseInvocationOutput):
|
||||
class VAEOutput(BaseInvocationOutput):
|
||||
"""Base class for invocations that output a VAE field"""
|
||||
|
||||
vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
|
||||
vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
|
||||
|
||||
|
||||
@invocation_output("clip_output")
|
||||
class CLIPOutput(BaseInvocationOutput):
|
||||
"""Base class for invocations that output a CLIP field"""
|
||||
|
||||
clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP")
|
||||
clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP")
|
||||
|
||||
|
||||
@invocation_output("model_loader_output")
|
||||
@ -101,21 +100,21 @@ class MainModelLoaderInvocation(BaseInvocation):
|
||||
|
||||
return ModelLoaderOutput(
|
||||
unet=UNetField(unet=unet, scheduler=scheduler, loras=[]),
|
||||
clip=ClipField(tokenizer=tokenizer, text_encoder=text_encoder, loras=[], skipped_layers=0),
|
||||
vae=VaeField(vae=vae),
|
||||
clip=CLIPField(tokenizer=tokenizer, text_encoder=text_encoder, loras=[], skipped_layers=0),
|
||||
vae=VAEField(vae=vae),
|
||||
)
|
||||
|
||||
|
||||
@invocation_output("lora_loader_output")
|
||||
class LoraLoaderOutput(BaseInvocationOutput):
|
||||
class LoRALoaderOutput(BaseInvocationOutput):
|
||||
"""Model loader output"""
|
||||
|
||||
unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
|
||||
clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
|
||||
clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP")
|
||||
|
||||
|
||||
@invocation("lora_loader", title="LoRA", tags=["model"], category="model", version="1.0.1")
|
||||
class LoraLoaderInvocation(BaseInvocation):
|
||||
class LoRALoaderInvocation(BaseInvocation):
|
||||
"""Apply selected lora to unet and text_encoder."""
|
||||
|
||||
lora: ModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
|
||||
@ -126,26 +125,26 @@ class LoraLoaderInvocation(BaseInvocation):
|
||||
input=Input.Connection,
|
||||
title="UNet",
|
||||
)
|
||||
clip: Optional[ClipField] = InputField(
|
||||
clip: Optional[CLIPField] = InputField(
|
||||
default=None,
|
||||
description=FieldDescriptions.clip,
|
||||
input=Input.Connection,
|
||||
title="CLIP",
|
||||
)
|
||||
|
||||
def invoke(self, context: InvocationContext) -> LoraLoaderOutput:
|
||||
def invoke(self, context: InvocationContext) -> LoRALoaderOutput:
|
||||
lora_key = self.lora.key
|
||||
|
||||
if not context.models.exists(lora_key):
|
||||
raise Exception(f"Unkown lora: {lora_key}!")
|
||||
|
||||
if self.unet is not None and any(lora.lora.key == lora_key for lora in self.unet.loras):
|
||||
raise Exception(f'Lora "{lora_key}" already applied to unet')
|
||||
raise Exception(f'LoRA "{lora_key}" already applied to unet')
|
||||
|
||||
if self.clip is not None and any(lora.lora.key == lora_key for lora in self.clip.loras):
|
||||
raise Exception(f'Lora "{lora_key}" already applied to clip')
|
||||
raise Exception(f'LoRA "{lora_key}" already applied to clip')
|
||||
|
||||
output = LoraLoaderOutput()
|
||||
output = LoRALoaderOutput()
|
||||
|
||||
if self.unet is not None:
|
||||
output.unet = self.unet.model_copy(deep=True)
|
||||
@ -169,12 +168,12 @@ class LoraLoaderInvocation(BaseInvocation):
|
||||
|
||||
|
||||
@invocation_output("sdxl_lora_loader_output")
|
||||
class SDXLLoraLoaderOutput(BaseInvocationOutput):
|
||||
class SDXLLoRALoaderOutput(BaseInvocationOutput):
|
||||
"""SDXL LoRA Loader Output"""
|
||||
|
||||
unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
|
||||
clip: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 1")
|
||||
clip2: Optional[ClipField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
|
||||
clip: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 1")
|
||||
clip2: Optional[CLIPField] = OutputField(default=None, description=FieldDescriptions.clip, title="CLIP 2")
|
||||
|
||||
|
||||
@invocation(
|
||||
@ -184,7 +183,7 @@ class SDXLLoraLoaderOutput(BaseInvocationOutput):
|
||||
category="model",
|
||||
version="1.0.1",
|
||||
)
|
||||
class SDXLLoraLoaderInvocation(BaseInvocation):
|
||||
class SDXLLoRALoaderInvocation(BaseInvocation):
|
||||
"""Apply selected lora to unet and text_encoder."""
|
||||
|
||||
lora: ModelField = InputField(description=FieldDescriptions.lora_model, input=Input.Direct, title="LoRA")
|
||||
@ -195,35 +194,35 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
|
||||
input=Input.Connection,
|
||||
title="UNet",
|
||||
)
|
||||
clip: Optional[ClipField] = InputField(
|
||||
clip: Optional[CLIPField] = InputField(
|
||||
default=None,
|
||||
description=FieldDescriptions.clip,
|
||||
input=Input.Connection,
|
||||
title="CLIP 1",
|
||||
)
|
||||
clip2: Optional[ClipField] = InputField(
|
||||
clip2: Optional[CLIPField] = InputField(
|
||||
default=None,
|
||||
description=FieldDescriptions.clip,
|
||||
input=Input.Connection,
|
||||
title="CLIP 2",
|
||||
)
|
||||
|
||||
def invoke(self, context: InvocationContext) -> SDXLLoraLoaderOutput:
|
||||
def invoke(self, context: InvocationContext) -> SDXLLoRALoaderOutput:
|
||||
lora_key = self.lora.key
|
||||
|
||||
if not context.models.exists(lora_key):
|
||||
raise Exception(f"Unknown lora: {lora_key}!")
|
||||
|
||||
if self.unet is not None and any(lora.lora.key == lora_key for lora in self.unet.loras):
|
||||
raise Exception(f'Lora "{lora_key}" already applied to unet')
|
||||
raise Exception(f'LoRA "{lora_key}" already applied to unet')
|
||||
|
||||
if self.clip is not None and any(lora.lora.key == lora_key for lora in self.clip.loras):
|
||||
raise Exception(f'Lora "{lora_key}" already applied to clip')
|
||||
raise Exception(f'LoRA "{lora_key}" already applied to clip')
|
||||
|
||||
if self.clip2 is not None and any(lora.lora.key == lora_key for lora in self.clip2.loras):
|
||||
raise Exception(f'Lora "{lora_key}" already applied to clip2')
|
||||
raise Exception(f'LoRA "{lora_key}" already applied to clip2')
|
||||
|
||||
output = SDXLLoraLoaderOutput()
|
||||
output = SDXLLoRALoaderOutput()
|
||||
|
||||
if self.unet is not None:
|
||||
output.unet = self.unet.model_copy(deep=True)
|
||||
@ -256,7 +255,7 @@ class SDXLLoraLoaderInvocation(BaseInvocation):
|
||||
|
||||
|
||||
@invocation("vae_loader", title="VAE", tags=["vae", "model"], category="model", version="1.0.1")
|
||||
class VaeLoaderInvocation(BaseInvocation):
|
||||
class VAELoaderInvocation(BaseInvocation):
|
||||
"""Loads a VAE model, outputting a VaeLoaderOutput"""
|
||||
|
||||
vae_model: ModelField = InputField(
|
||||
@ -271,7 +270,7 @@ class VaeLoaderInvocation(BaseInvocation):
|
||||
if not context.models.exists(key):
|
||||
raise Exception(f"Unkown vae: {key}!")
|
||||
|
||||
return VAEOutput(vae=VaeField(vae=self.vae_model))
|
||||
return VAEOutput(vae=VAEField(vae=self.vae_model))
|
||||
|
||||
|
||||
@invocation_output("seamless_output")
|
||||
@ -279,7 +278,7 @@ class SeamlessModeOutput(BaseInvocationOutput):
|
||||
"""Modified Seamless Model output"""
|
||||
|
||||
unet: Optional[UNetField] = OutputField(default=None, description=FieldDescriptions.unet, title="UNet")
|
||||
vae: Optional[VaeField] = OutputField(default=None, description=FieldDescriptions.vae, title="VAE")
|
||||
vae: Optional[VAEField] = OutputField(default=None, description=FieldDescriptions.vae, title="VAE")
|
||||
|
||||
|
||||
@invocation(
|
||||
@ -298,7 +297,7 @@ class SeamlessModeInvocation(BaseInvocation):
|
||||
input=Input.Connection,
|
||||
title="UNet",
|
||||
)
|
||||
vae: Optional[VaeField] = InputField(
|
||||
vae: Optional[VAEField] = InputField(
|
||||
default=None,
|
||||
description=FieldDescriptions.vae_model,
|
||||
input=Input.Connection,
|
||||
|
||||
@ -8,7 +8,7 @@ from .baseinvocation import (
|
||||
invocation,
|
||||
invocation_output,
|
||||
)
|
||||
from .model import ClipField, ModelField, UNetField, VaeField
|
||||
from .model import CLIPField, ModelField, UNetField, VAEField
|
||||
|
||||
|
||||
@invocation_output("sdxl_model_loader_output")
|
||||
@ -16,9 +16,9 @@ class SDXLModelLoaderOutput(BaseInvocationOutput):
|
||||
"""SDXL base model loader output"""
|
||||
|
||||
unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
|
||||
clip: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 1")
|
||||
clip2: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
|
||||
vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
|
||||
clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP 1")
|
||||
clip2: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
|
||||
vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
|
||||
|
||||
|
||||
@invocation_output("sdxl_refiner_model_loader_output")
|
||||
@ -26,8 +26,8 @@ class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
|
||||
"""SDXL refiner model loader output"""
|
||||
|
||||
unet: UNetField = OutputField(description=FieldDescriptions.unet, title="UNet")
|
||||
clip2: ClipField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
|
||||
vae: VaeField = OutputField(description=FieldDescriptions.vae, title="VAE")
|
||||
clip2: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP 2")
|
||||
vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
|
||||
|
||||
|
||||
@invocation("sdxl_model_loader", title="SDXL Main Model", tags=["model", "sdxl"], category="model", version="1.0.1")
|
||||
@ -56,9 +56,9 @@ class SDXLModelLoaderInvocation(BaseInvocation):
|
||||
|
||||
return SDXLModelLoaderOutput(
|
||||
unet=UNetField(unet=unet, scheduler=scheduler, loras=[]),
|
||||
clip=ClipField(tokenizer=tokenizer, text_encoder=text_encoder, loras=[], skipped_layers=0),
|
||||
clip2=ClipField(tokenizer=tokenizer2, text_encoder=text_encoder2, loras=[], skipped_layers=0),
|
||||
vae=VaeField(vae=vae),
|
||||
clip=CLIPField(tokenizer=tokenizer, text_encoder=text_encoder, loras=[], skipped_layers=0),
|
||||
clip2=CLIPField(tokenizer=tokenizer2, text_encoder=text_encoder2, loras=[], skipped_layers=0),
|
||||
vae=VAEField(vae=vae),
|
||||
)
|
||||
|
||||
|
||||
@ -92,6 +92,6 @@ class SDXLRefinerModelLoaderInvocation(BaseInvocation):
|
||||
|
||||
return SDXLRefinerModelLoaderOutput(
|
||||
unet=UNetField(unet=unet, scheduler=scheduler, loras=[]),
|
||||
clip2=ClipField(tokenizer=tokenizer2, text_encoder=text_encoder2, loras=[], skipped_layers=0),
|
||||
vae=VaeField(vae=vae),
|
||||
clip2=CLIPField(tokenizer=tokenizer2, text_encoder=text_encoder2, loras=[], skipped_layers=0),
|
||||
vae=VAEField(vae=vae),
|
||||
)
|
||||
|
||||
@ -310,7 +310,7 @@ class IPAdapterConfig(ModelConfigBase):
|
||||
|
||||
|
||||
class CLIPVisionDiffusersConfig(ModelConfigBase):
|
||||
"""Model config for ClipVision."""
|
||||
"""Model config for CLIPVision."""
|
||||
|
||||
type: Literal[ModelType.CLIPVision] = ModelType.CLIPVision
|
||||
format: Literal[ModelFormat.Diffusers]
|
||||
|
||||
@ -24,7 +24,7 @@ from .. import ModelLoader, ModelLoaderRegistry
|
||||
|
||||
@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.LoRA, format=ModelFormat.Diffusers)
|
||||
@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.LoRA, format=ModelFormat.LyCORIS)
|
||||
class LoraLoader(ModelLoader):
|
||||
class LoRALoader(ModelLoader):
|
||||
"""Class to load LoRA models."""
|
||||
|
||||
# We cheat a little bit to get access to the model base
|
||||
|
||||
@ -23,7 +23,7 @@ from .generic_diffusers import GenericDiffusersLoader
|
||||
@ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.VAE, format=ModelFormat.Diffusers)
|
||||
@ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion1, type=ModelType.VAE, format=ModelFormat.Checkpoint)
|
||||
@ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion2, type=ModelType.VAE, format=ModelFormat.Checkpoint)
|
||||
class VaeLoader(GenericDiffusersLoader):
|
||||
class VAELoader(GenericDiffusersLoader):
|
||||
"""Class to load VAE models."""
|
||||
|
||||
def _needs_conversion(self, config: AnyModelConfig, model_path: Path, dest_path: Path) -> bool:
|
||||
|
||||
@ -33,15 +33,15 @@ from invokeai.app.invocations.fields import (
|
||||
from invokeai.app.invocations.latent import SchedulerOutput
|
||||
from invokeai.app.invocations.metadata import MetadataItemField, MetadataItemOutput, MetadataOutput
|
||||
from invokeai.app.invocations.model import (
|
||||
ClipField,
|
||||
CLIPField,
|
||||
CLIPOutput,
|
||||
LoraLoaderOutput,
|
||||
LoRALoaderOutput,
|
||||
ModelField,
|
||||
ModelLoaderOutput,
|
||||
SDXLLoraLoaderOutput,
|
||||
SDXLLoRALoaderOutput,
|
||||
UNetField,
|
||||
UNetOutput,
|
||||
VaeField,
|
||||
VAEField,
|
||||
VAEOutput,
|
||||
)
|
||||
from invokeai.app.invocations.primitives import (
|
||||
@ -116,14 +116,14 @@ __all__ = [
|
||||
# invokeai.app.invocations.model
|
||||
"ModelField",
|
||||
"UNetField",
|
||||
"ClipField",
|
||||
"VaeField",
|
||||
"CLIPField",
|
||||
"VAEField",
|
||||
"UNetOutput",
|
||||
"VAEOutput",
|
||||
"CLIPOutput",
|
||||
"ModelLoaderOutput",
|
||||
"LoraLoaderOutput",
|
||||
"SDXLLoraLoaderOutput",
|
||||
"LoRALoaderOutput",
|
||||
"SDXLLoRALoaderOutput",
|
||||
# invokeai.app.invocations.primitives
|
||||
"BooleanCollectionOutput",
|
||||
"BooleanOutput",
|
||||
|
||||
Loading…
Reference in New Issue
Block a user