InvokeAI 4.0.3__tar.gz → 4.1.0__tar.gz

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/InvokeAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.0.3
+Version: 4.1.0
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/InvokeAI.egg-info/SOURCES.txt

@@ -39,6 +39,7 @@ invokeai/app/invocations/image.py
 invokeai/app/invocations/infill.py
 invokeai/app/invocations/ip_adapter.py
 invokeai/app/invocations/latent.py
+invokeai/app/invocations/mask.py
 invokeai/app/invocations/math.py
 invokeai/app/invocations/metadata.py
 invokeai/app/invocations/model.py
@@ -224,11 +225,9 @@ invokeai/backend/image_util/infill_methods/tile.py
 invokeai/backend/image_util/realesrgan/__init__.py
 invokeai/backend/image_util/realesrgan/realesrgan.py
 invokeai/backend/ip_adapter/__init__.py
-invokeai/backend/ip_adapter/attention_processor.py
 invokeai/backend/ip_adapter/ip_adapter.py
 invokeai/backend/ip_adapter/ip_attention_weights.py
 invokeai/backend/ip_adapter/resampler.py
-invokeai/backend/ip_adapter/unet_patcher.py
 invokeai/backend/model_hash/model_hash.py
 invokeai/backend/model_manager/__init__.py
 invokeai/backend/model_manager/config.py
@@ -275,8 +274,11 @@ invokeai/backend/stable_diffusion/diffusers_pipeline.py
 invokeai/backend/stable_diffusion/seamless.py
 invokeai/backend/stable_diffusion/diffusion/__init__.py
 invokeai/backend/stable_diffusion/diffusion/conditioning_data.py
-invokeai/backend/stable_diffusion/diffusion/cross_attention_control.py
+invokeai/backend/stable_diffusion/diffusion/custom_atttention.py
+invokeai/backend/stable_diffusion/diffusion/regional_ip_data.py
+invokeai/backend/stable_diffusion/diffusion/regional_prompt_data.py
 invokeai/backend/stable_diffusion/diffusion/shared_invokeai_diffusion.py
+invokeai/backend/stable_diffusion/diffusion/unet_attention_patcher.py
 invokeai/backend/stable_diffusion/schedulers/__init__.py
 invokeai/backend/stable_diffusion/schedulers/schedulers.py
 invokeai/backend/tiles/__init__.py
@@ -288,6 +290,7 @@ invokeai/backend/util/db_maintenance.py
 invokeai/backend/util/devices.py
 invokeai/backend/util/hotfixes.py
 invokeai/backend/util/logging.py
+invokeai/backend/util/mask.py
 invokeai/backend/util/mps_fixes.py
 invokeai/backend/util/silence_warnings.py
 invokeai/backend/util/test_utils.py
@@ -314,11 +317,11 @@ invokeai/frontend/install/__init__.py
 invokeai/frontend/install/import_images.py
 invokeai/frontend/web/__init__.py
 invokeai/frontend/web/dist/index.html
-invokeai/frontend/web/dist/assets/App-BLcNMYZP.js
 invokeai/frontend/web/dist/assets/App-DI6oCUg0.css
+invokeai/frontend/web/dist/assets/App-nR2gvd20.js
 invokeai/frontend/web/dist/assets/ThemeLocaleProvider-Bsx7ESc2.css
-invokeai/frontend/web/dist/assets/ThemeLocaleProvider-DKJ1LbAm.js
-invokeai/frontend/web/dist/assets/index-MDF-DOT9.js
+invokeai/frontend/web/dist/assets/ThemeLocaleProvider-KzMt_S5B.js
+invokeai/frontend/web/dist/assets/index-CB6ZmbOE.js
 invokeai/frontend/web/dist/assets/inter-cyrillic-ext-wght-normal-DIEz8p5i.woff2
 invokeai/frontend/web/dist/assets/inter-cyrillic-wght-normal-BmJJXa8e.woff2
 invokeai/frontend/web/dist/assets/inter-greek-ext-wght-normal-D5AYLNiq.woff2
@@ -326,6 +329,7 @@ invokeai/frontend/web/dist/assets/inter-greek-wght-normal-DyIDNIyN.woff2
 invokeai/frontend/web/dist/assets/inter-latin-ext-wght-normal-CN1pIXkb.woff2
 invokeai/frontend/web/dist/assets/inter-latin-wght-normal-BgVq2Tq4.woff2
 invokeai/frontend/web/dist/assets/inter-vietnamese-wght-normal-_GQuwPVU.woff2
+invokeai/frontend/web/dist/assets/images/invoke-alert-favicon.svg
 invokeai/frontend/web/dist/assets/images/invoke-avatar-circle.svg
 invokeai/frontend/web/dist/assets/images/invoke-avatar-square.svg
 invokeai/frontend/web/dist/assets/images/invoke-favicon.png

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/InvokeAI.egg-info/requires.txt

@@ -1,4 +1,4 @@
-accelerate==0.28.0
+accelerate==0.29.2
 clip_anytorch==2.5.2
 compel==2.0.2
 controlnet-aux==0.0.7
@@ -12,14 +12,14 @@ opencv-python==4.9.0.80
 pytorch-lightning==2.1.3
 safetensors==0.4.2
 timm==0.6.13
-torch==2.2.1
+torch==2.2.2
 torchmetrics==0.11.4
 torchsde==0.2.6
-torchvision==0.17.1
-transformers==4.39.1
+torchvision==0.17.2
+transformers==4.39.3
 fastapi-events==0.11.0
 fastapi==0.110.0
-huggingface-hub==0.21.4
+huggingface-hub==0.22.2
 pydantic-settings==2.2.1
 pydantic==2.6.3
 python-socketio==5.11.1
@@ -96,7 +96,7 @@ httpx
 [xformers]
 
 [xformers:sys_platform != "darwin"]
-xformers==0.0.25
+xformers==0.0.25post1
 
 [xformers:sys_platform == "linux"]
 triton

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.0.3
+Version: 4.1.0
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/invokeai/app/api_app.py

@@ -28,7 +28,7 @@ from invokeai.app.api.no_cache_staticfiles import NoCacheStaticFiles
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.services.config.config_default import get_config
 from invokeai.app.services.session_processor.session_processor_common import ProgressImage
-from invokeai.backend.util.devices import get_torch_device_name
+from invokeai.backend.util.devices import TorchDevice
 
 from ..backend.util.logging import InvokeAILogger
 from .api.dependencies import ApiDependencies
@@ -63,7 +63,7 @@ logger = InvokeAILogger.get_logger(config=app_config)
 mimetypes.add_type("application/javascript", ".js")
 mimetypes.add_type("text/css", ".css")
 
-torch_device_name = get_torch_device_name()
+torch_device_name = TorchDevice.get_torch_device_name()
 logger.info(f"Using torch device: {torch_device_name}")
 
 

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/invokeai/app/invocations/compel.py

@@ -5,7 +5,15 @@ from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIComponent
+from invokeai.app.invocations.fields import (
+    ConditioningField,
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    TensorField,
+    UIComponent,
+)
 from invokeai.app.invocations.primitives import ConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.ti_utils import generate_ti_list
@@ -14,10 +22,9 @@ from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ConditioningFieldData,
-    ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
-from invokeai.backend.util.devices import torch_dtype
+from invokeai.backend.util.devices import TorchDevice
 
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from .model import CLIPField
@@ -36,7 +43,7 @@ from .model import CLIPField
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.1.1",
+    version="1.2.0",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -51,6 +58,9 @@ class CompelInvocation(BaseInvocation):
         description=FieldDescriptions.clip,
         input=Input.Connection,
     )
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this conditioning prompt applies to."
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -89,7 +99,7 @@ class CompelInvocation(BaseInvocation):
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
-                dtype_for_device_getter=torch_dtype,
+                dtype_for_device_getter=TorchDevice.choose_torch_dtype,
                 truncate_long_prompts=False,
             )
 
@@ -98,27 +108,19 @@ class CompelInvocation(BaseInvocation):
             if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
-
-            ec = ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                cross_attention_control_args=options.get("cross_attention_control", None),
-            )
+            c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
 
         c = c.detach().to("cpu")
 
-        conditioning_data = ConditioningFieldData(
-            conditionings=[
-                BasicConditioningInfo(
-                    embeds=c,
-                    extra_conditioning=ec,
-                )
-            ]
-        )
+        conditioning_data = ConditioningFieldData(conditionings=[BasicConditioningInfo(embeds=c)])
 
         conditioning_name = context.conditioning.save(conditioning_data)
-
-        return ConditioningOutput.build(conditioning_name)
+        return ConditioningOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+                mask=self.mask,
+            )
+        )
 
 
 class SDXLPromptInvocationBase:
@@ -132,7 +134,7 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
         tokenizer_info = context.models.load(clip_field.tokenizer)
         tokenizer_model = tokenizer_info.model
         assert isinstance(tokenizer_model, CLIPTokenizer)
@@ -159,7 +161,7 @@ class SDXLPromptInvocationBase:
                 )
             else:
                 c_pooled = None
-            return c, c_pooled, None
+            return c, c_pooled
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
@@ -191,7 +193,7 @@ class SDXLPromptInvocationBase:
                 tokenizer=tokenizer,
                 text_encoder=text_encoder,
                 textual_inversion_manager=ti_manager,
-                dtype_for_device_getter=torch_dtype,
+                dtype_for_device_getter=TorchDevice.choose_torch_dtype,
                 truncate_long_prompts=False,  # TODO:
                 returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,  # TODO: clip skip
                 requires_pooled=get_pooled,
@@ -204,17 +206,12 @@ class SDXLPromptInvocationBase:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             # TODO: ask for optimizations? to not run text_encoder twice
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+            c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
             if get_pooled:
                 c_pooled = compel.conditioning_provider.get_pooled_embeddings([prompt])
             else:
                 c_pooled = None
 
-            ec = ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                cross_attention_control_args=options.get("cross_attention_control", None),
-            )
-
         del tokenizer
         del text_encoder
         del tokenizer_info
@@ -224,7 +221,7 @@ class SDXLPromptInvocationBase:
         if c_pooled is not None:
             c_pooled = c_pooled.detach().to("cpu")
 
-        return c, c_pooled, ec
+        return c, c_pooled
 
 
 @invocation(
@@ -232,7 +229,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.1.1",
+    version="1.2.0",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -255,20 +252,19 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     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")
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this conditioning prompt applies to."
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        c1, c1_pooled, ec1 = self.run_clip_compel(
-            context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True
-        )
+        c1, c1_pooled = self.run_clip_compel(context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True)
         if self.style.strip() == "":
-            c2, c2_pooled, ec2 = self.run_clip_compel(
+            c2, c2_pooled = self.run_clip_compel(
                 context, self.clip2, self.prompt, True, "lora_te2_", zero_on_empty=True
             )
         else:
-            c2, c2_pooled, ec2 = self.run_clip_compel(
-                context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True
-            )
+            c2, c2_pooled = self.run_clip_compel(context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True)
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -307,17 +303,19 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
-                    embeds=torch.cat([c1, c2], dim=-1),
-                    pooled_embeds=c2_pooled,
-                    add_time_ids=add_time_ids,
-                    extra_conditioning=ec1,
+                    embeds=torch.cat([c1, c2], dim=-1), pooled_embeds=c2_pooled, add_time_ids=add_time_ids
                 )
             ]
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput.build(conditioning_name)
+        return ConditioningOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+                mask=self.mask,
+            )
+        )
 
 
 @invocation(
@@ -345,7 +343,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         # TODO: if there will appear lora for refiner - write proper prefix
-        c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
+        c2, c2_pooled = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -354,14 +352,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
-            conditionings=[
-                SDXLConditioningInfo(
-                    embeds=c2,
-                    pooled_embeds=c2_pooled,
-                    add_time_ids=add_time_ids,
-                    extra_conditioning=ec2,  # or None
-                )
-            ]
+            conditionings=[SDXLConditioningInfo(embeds=c2, pooled_embeds=c2_pooled, add_time_ids=add_time_ids)]
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/invokeai/app/invocations/fields.py

@@ -203,6 +203,12 @@ class DenoiseMaskField(BaseModel):
     gradient: bool = Field(default=False, description="Used for gradient inpainting")
 
 
+class TensorField(BaseModel):
+    """A tensor primitive field."""
+
+    tensor_name: str = Field(description="The name of a tensor.")
+
+
 class LatentsField(BaseModel):
     """A latents tensor primitive field"""
 
@@ -226,7 +232,11 @@ class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 
     conditioning_name: str = Field(description="The name of conditioning tensor")
-    # endregion
+    mask: Optional[TensorField] = Field(
+        default=None,
+        description="The mask associated with this conditioning tensor. Excluded regions should be set to False, "
+        "included regions should be set to True.",
+    )
 
 
 class MetadataField(RootModel[dict[str, Any]]):

{InvokeAI-4.0.3 → InvokeAI-4.1.0}/invokeai/app/invocations/ip_adapter.py

@@ -1,11 +1,11 @@
 from builtins import float
-from typing import List, Literal, Union
+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, UIType
+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
@@ -23,13 +23,19 @@ class IPAdapterField(BaseModel):
     image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
     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 ControlNet")
+    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)"
     )
     end_step_percent: float = Field(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
+    mask: Optional[TensorField] = Field(
+        default=None,
+        description="The bool mask associated with this IP-Adapter. Excluded regions should be set to False, included "
+        "regions should be set to True.",
+    )
 
     @field_validator("weight")
     @classmethod
@@ -52,7 +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="1.2.2")
+@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."""
 
@@ -67,18 +73,24 @@ class IPAdapterInvocation(BaseInvocation):
     )
     clip_vision_model: Literal["ViT-H", "ViT-G"] = InputField(
         description="CLIP Vision model to use. Overrides model settings. Mandatory for checkpoint models.",
-        default="auto",
+        default="ViT-H",
         ui_order=2,
     )
     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)"
     )
     end_step_percent: float = InputField(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this IP-Adapter applies to."
+    )
 
     @field_validator("weight")
     @classmethod
@@ -104,14 +116,35 @@ 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,
             ),
         )