Merge branch 'main' into lstein/feat/simple-mm2-api

invokeai/app/invocations/ip_adapter.py

@@ -4,20 +4,8 @@ from typing import List, Literal, Optional, Union
 from pydantic import BaseModel, Field, field_validator, model_validator
 from typing_extensions import Self
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.fields import (
-    FieldDescriptions,
-    Input,
-    InputField,
-    OutputField,
-    TensorField,
-    UIType,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, TensorField, UIType
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
@@ -36,6 +24,7 @@ class IPAdapterField(BaseModel):
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model to use.")
     image_encoder_model: ModelIdentifierField = Field(description="The name of the CLIP image encoder model.")
     weight: Union[float, List[float]] = Field(default=1, description="The weight given to the IP-Adapter.")
+    target_blocks: List[str] = Field(default=[], description="The IP Adapter blocks to apply")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
@@ -69,7 +58,7 @@ class IPAdapterOutput(BaseInvocationOutput):
 CLIP_VISION_MODEL_MAP = {"ViT-H": "ip_adapter_sd_image_encoder", "ViT-G": "ip_adapter_sdxl_image_encoder"}
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.3.0")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.4.0")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -90,6 +79,9 @@ class IPAdapterInvocation(BaseInvocation):
     weight: Union[float, List[float]] = InputField(
         default=1, description="The weight given to the IP-Adapter", title="Weight"
     )
+    method: Literal["full", "style", "composition"] = InputField(
+        default="full", description="The method to apply the IP-Adapter"
+    )
     begin_step_percent: float = InputField(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
@@ -124,12 +116,32 @@ class IPAdapterInvocation(BaseInvocation):
 
         image_encoder_model = self._get_image_encoder(context, image_encoder_model_name)
 
+        if self.method == "style":
+            if ip_adapter_info.base == "sd-1":
+                target_blocks = ["up_blocks.1"]
+            elif ip_adapter_info.base == "sdxl":
+                target_blocks = ["up_blocks.0.attentions.1"]
+            else:
+                raise ValueError(f"Unsupported IP-Adapter base type: '{ip_adapter_info.base}'.")
+        elif self.method == "composition":
+            if ip_adapter_info.base == "sd-1":
+                target_blocks = ["down_blocks.2", "mid_block"]
+            elif ip_adapter_info.base == "sdxl":
+                target_blocks = ["down_blocks.2.attentions.1"]
+            else:
+                raise ValueError(f"Unsupported IP-Adapter base type: '{ip_adapter_info.base}'.")
+        elif self.method == "full":
+            target_blocks = ["block"]
+        else:
+            raise ValueError(f"Unexpected IP-Adapter method: '{self.method}'.")
+
         return IPAdapterOutput(
             ip_adapter=IPAdapterField(
                 image=self.image,
                 ip_adapter_model=self.ip_adapter_model,
                 image_encoder_model=ModelIdentifierField.from_config(image_encoder_model),
                 weight=self.weight,
+                target_blocks=target_blocks,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
                 mask=self.mask,

invokeai/app/invocations/latent.py

@@ -679,6 +679,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 IPAdapterData(
                     ip_adapter_model=ip_adapter_model,
                     weight=single_ip_adapter.weight,
+                    target_blocks=single_ip_adapter.target_blocks,
                     begin_step_percent=single_ip_adapter.begin_step_percent,
                     end_step_percent=single_ip_adapter.end_step_percent,
                     ip_adapter_conditioning=IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds),

invokeai/app/invocations/metadata.py

@@ -36,6 +36,7 @@ class IPAdapterMetadataField(BaseModel):
     image: ImageField = Field(description="The IP-Adapter image prompt.")
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model.")
     clip_vision_model: Literal["ViT-H", "ViT-G"] = Field(description="The CLIP Vision model")
+    method: Literal["full", "style", "composition"] = Field(description="Method to apply IP Weights with")
     weight: Union[float, list[float]] = Field(description="The weight given to the IP-Adapter")
     begin_step_percent: float = Field(description="When the IP-Adapter is first applied (% of total steps)")
     end_step_percent: float = Field(description="When the IP-Adapter is last applied (% of total steps)")