Merge branch 'main' into refactor/model-manager-2

Author: Lincoln Stein

docs/index.md

@@ -198,6 +198,7 @@ The list of schedulers has been completely revamped and brought up to date:
 | **dpmpp_2m**   | DPMSolverMultistepScheduler     | original noise scnedule     |
 | **dpmpp_2m_k** | DPMSolverMultistepScheduler     | using karras noise schedule |
 | **unipc**      | UniPCMultistepScheduler         | CPU only                    |
+| **lcm**        | LCMScheduler                    |                             |
 
 Please see [3.0.0 Release Notes](https://github.com/invoke-ai/InvokeAI/releases/tag/v3.0.0) for further details.
 

invokeai/app/api/sockets.py

@@ -34,4 +34,4 @@ async def _handle_sub_queue(self, sid, data, *args, **kwargs):
 
     async def _handle_unsub_queue(self, sid, data, *args, **kwargs):
         if "queue_id" in data:
-            await self.__sio.enter_room(sid, data["queue_id"])
+            await self.__sio.leave_room(sid, data["queue_id"])

invokeai/app/invocations/baseinvocation.py

@@ -16,6 +16,7 @@
 from pydantic_core import PydanticUndefined
 
 from invokeai.app.services.config.config_default import InvokeAIAppConfig
+from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.app.util.misc import uuid_string
 
 if TYPE_CHECKING:
@@ -30,74 +31,6 @@ class InvalidFieldError(TypeError):
     pass
 
 
-class FieldDescriptions:
-    denoising_start = "When to start denoising, expressed a percentage of total steps"
-    denoising_end = "When to stop denoising, expressed a percentage of total steps"
-    cfg_scale = "Classifier-Free Guidance scale"
-    scheduler = "Scheduler to use during inference"
-    positive_cond = "Positive conditioning tensor"
-    negative_cond = "Negative conditioning tensor"
-    noise = "Noise tensor"
-    clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
-    unet = "UNet (scheduler, LoRAs)"
-    vae = "VAE"
-    cond = "Conditioning tensor"
-    controlnet_model = "ControlNet model to load"
-    vae_model = "VAE model to load"
-    lora_model = "LoRA model to load"
-    main_model = "Main model (UNet, VAE, CLIP) to load"
-    sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
-    sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
-    onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
-    lora_weight = "The weight at which the LoRA is applied to each model"
-    compel_prompt = "Prompt to be parsed by Compel to create a conditioning tensor"
-    raw_prompt = "Raw prompt text (no parsing)"
-    sdxl_aesthetic = "The aesthetic score to apply to the conditioning tensor"
-    skipped_layers = "Number of layers to skip in text encoder"
-    seed = "Seed for random number generation"
-    steps = "Number of steps to run"
-    width = "Width of output (px)"
-    height = "Height of output (px)"
-    control = "ControlNet(s) to apply"
-    ip_adapter = "IP-Adapter to apply"
-    t2i_adapter = "T2I-Adapter(s) to apply"
-    denoised_latents = "Denoised latents tensor"
-    latents = "Latents tensor"
-    strength = "Strength of denoising (proportional to steps)"
-    metadata = "Optional metadata to be saved with the image"
-    metadata_collection = "Collection of Metadata"
-    metadata_item_polymorphic = "A single metadata item or collection of metadata items"
-    metadata_item_label = "Label for this metadata item"
-    metadata_item_value = "The value for this metadata item (may be any type)"
-    workflow = "Optional workflow to be saved with the image"
-    interp_mode = "Interpolation mode"
-    torch_antialias = "Whether or not to apply antialiasing (bilinear or bicubic only)"
-    fp32 = "Whether or not to use full float32 precision"
-    precision = "Precision to use"
-    tiled = "Processing using overlapping tiles (reduce memory consumption)"
-    detect_res = "Pixel resolution for detection"
-    image_res = "Pixel resolution for output image"
-    safe_mode = "Whether or not to use safe mode"
-    scribble_mode = "Whether or not to use scribble mode"
-    scale_factor = "The factor by which to scale"
-    blend_alpha = (
-        "Blending factor. 0.0 = use input A only, 1.0 = use input B only, 0.5 = 50% mix of input A and input B."
-    )
-    num_1 = "The first number"
-    num_2 = "The second number"
-    mask = "The mask to use for the operation"
-    board = "The board to save the image to"
-    image = "The image to process"
-    tile_size = "Tile size"
-    inclusive_low = "The inclusive low value"
-    exclusive_high = "The exclusive high value"
-    decimal_places = "The number of decimal places to round to"
-    freeu_s1 = 'Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
-    freeu_s2 = 'Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to mitigate the "oversmoothing effect" in the enhanced denoising process.'
-    freeu_b1 = "Scaling factor for stage 1 to amplify the contributions of backbone features."
-    freeu_b2 = "Scaling factor for stage 2 to amplify the contributions of backbone features."
-
-
 class Input(str, Enum):
     """
     The type of input a field accepts.

invokeai/app/invocations/compel.py

@@ -7,6 +7,7 @@
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 
 from invokeai.app.invocations.primitives import ConditioningField, ConditioningOutput
+from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ExtraConditioningInfo,
@@ -19,7 +20,6 @@
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
     Input,
     InputField,
     InvocationContext,

invokeai/app/invocations/controlnet_image_processors.py

@@ -28,12 +28,12 @@
 
 from invokeai.app.invocations.primitives import ImageField, ImageOutput
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.shared.fields import FieldDescriptions
 
 from ...backend.model_management import BaseModelType
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
     Input,
     InputField,
     InvocationContext,

invokeai/app/invocations/image.py

@@ -9,19 +9,11 @@
 
 from invokeai.app.invocations.primitives import BoardField, ColorField, ImageField, ImageOutput
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.backend.image_util.invisible_watermark import InvisibleWatermark
 from invokeai.backend.image_util.safety_checker import SafetyChecker
 
-from .baseinvocation import (
-    BaseInvocation,
-    FieldDescriptions,
-    Input,
-    InputField,
-    InvocationContext,
-    WithMetadata,
-    WithWorkflow,
-    invocation,
-)
+from .baseinvocation import BaseInvocation, Input, InputField, InvocationContext, WithMetadata, WithWorkflow, invocation
 
 
 @invocation("show_image", title="Show Image", tags=["image"], category="image", version="1.0.0")

invokeai/app/invocations/ip_adapter.py

@@ -7,7 +7,6 @@
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
     Input,
     InputField,
     InvocationContext,
@@ -17,6 +16,7 @@
     invocation_output,
 )
 from invokeai.app.invocations.primitives import ImageField
+from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.backend.model_management.models.base import BaseModelType, ModelType
 from invokeai.backend.model_management.models.ip_adapter import get_ip_adapter_image_encoder_model_id
 

invokeai/app/invocations/latent.py

@@ -10,7 +10,7 @@
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.models.adapter import FullAdapterXL, T2IAdapter
+from diffusers.models.adapter import T2IAdapter
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
     LoRAAttnProcessor2_0,
@@ -34,6 +34,7 @@
 )
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
 from invokeai.app.services.image_records.image_records_common import ImageCategory, ResourceOrigin
+from invokeai.app.shared.fields import FieldDescriptions
 from invokeai.app.util.controlnet_utils import prepare_control_image
 from invokeai.app.util.step_callback import stable_diffusion_step_callback
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter, IPAdapterPlus
@@ -57,7 +58,6 @@
 from .baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
     Input,
     InputField,
     InvocationContext,
@@ -562,10 +562,6 @@ def run_t2i_adapters(
             t2i_adapter_model: T2IAdapter
             with t2i_adapter_model_info as t2i_adapter_model:
                 total_downscale_factor = t2i_adapter_model.total_downscale_factor
-                if isinstance(t2i_adapter_model.adapter, FullAdapterXL):
-                    # HACK(ryand): Work around a bug in FullAdapterXL. This is being addressed upstream in diffusers by
-                    # this PR: https://github.com/huggingface/diffusers/pull/5134.
-                    total_downscale_factor = total_downscale_factor // 2
 
                 # Resize the T2I-Adapter input image.
                 # We select the resize dimensions so that after the T2I-Adapter's total_downscale_factor is applied, the

invokeai/app/invocations/math.py

@@ -6,8 +6,9 @@
 from pydantic import ValidationInfo, field_validator
 
 from invokeai.app.invocations.primitives import FloatOutput, IntegerOutput
+from invokeai.app.shared.fields import FieldDescriptions
 
-from .baseinvocation import BaseInvocation, FieldDescriptions, InputField, InvocationContext, invocation
+from .baseinvocation import BaseInvocation, InputField, InvocationContext, invocation
 
 
 @invocation("add", title="Add Integers", tags=["math", "add"], category="math", version="1.0.0")

invokeai/app/invocations/metadata.py

@@ -5,7 +5,6 @@
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
     BaseInvocationOutput,
-    FieldDescriptions,
     InputField,
     InvocationContext,
     MetadataField,
@@ -19,6 +18,7 @@
 from invokeai.app.invocations.model import LoRAModelField, MainModelField, VAEModelField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.t2i_adapter import T2IAdapterField
+from invokeai.app.shared.fields import FieldDescriptions
 
 from ...version import __version__