InvokeAI 4.2.9.dev4__tar.gz → 4.2.9.dev6__tar.gz

{InvokeAI-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/InvokeAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.2.9.dev4
+Version: 4.2.9.dev6
 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-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/InvokeAI.egg-info/SOURCES.txt

@@ -40,6 +40,8 @@ invokeai/app/invocations/cv.py
 invokeai/app/invocations/denoise_latents.py
 invokeai/app/invocations/facetools.py
 invokeai/app/invocations/fields.py
+invokeai/app/invocations/flux_text_encoder.py
+invokeai/app/invocations/flux_text_to_image.py
 invokeai/app/invocations/grounding_dino.py
 invokeai/app/invocations/ideal_size.py
 invokeai/app/invocations/image.py
@@ -219,6 +221,7 @@ invokeai/app/services/workflow_records/workflow_records_common.py
 invokeai/app/services/workflow_records/workflow_records_sqlite.py
 invokeai/app/services/workflow_records/default_workflows/ESRGAN Upscaling with Canny ControlNet.json
 invokeai/app/services/workflow_records/default_workflows/Face Detailer with IP-Adapter & Canny (See Note in Details).json
+invokeai/app/services/workflow_records/default_workflows/Flux Text to Image.json
 invokeai/app/services/workflow_records/default_workflows/Multi ControlNet (Canny & Depth).json
 invokeai/app/services/workflow_records/default_workflows/MultiDiffusion SD1.5.json
 invokeai/app/services/workflow_records/default_workflows/MultiDiffusion SDXL.json
@@ -247,6 +250,13 @@ invokeai/backend/model_patcher.py
 invokeai/backend/raw_model.py
 invokeai/backend/spandrel_image_to_image_model.py
 invokeai/backend/textual_inversion.py
+invokeai/backend/flux/math.py
+invokeai/backend/flux/model.py
+invokeai/backend/flux/sampling.py
+invokeai/backend/flux/util.py
+invokeai/backend/flux/modules/autoencoder.py
+invokeai/backend/flux/modules/conditioner.py
+invokeai/backend/flux/modules/layers.py
 invokeai/backend/image_util/__init__.py
 invokeai/backend/image_util/canny.py
 invokeai/backend/image_util/hed.py
@@ -303,6 +313,7 @@ invokeai/backend/model_manager/load/model_cache/model_cache_default.py
 invokeai/backend/model_manager/load/model_cache/model_locker.py
 invokeai/backend/model_manager/load/model_loaders/__init__.py
 invokeai/backend/model_manager/load/model_loaders/controlnet.py
+invokeai/backend/model_manager/load/model_loaders/flux.py
 invokeai/backend/model_manager/load/model_loaders/generic_diffusers.py
 invokeai/backend/model_manager/load/model_loaders/ip_adapter.py
 invokeai/backend/model_manager/load/model_loaders/lora.py
@@ -320,6 +331,12 @@ invokeai/backend/model_manager/util/libc_util.py
 invokeai/backend/model_manager/util/model_util.py
 invokeai/backend/model_manager/util/select_hf_files.py
 invokeai/backend/onnx/onnx_runtime.py
+invokeai/backend/quantization/__init__.py
+invokeai/backend/quantization/bnb_llm_int8.py
+invokeai/backend/quantization/bnb_nf4.py
+invokeai/backend/quantization/scripts/load_flux_model_bnb_llm_int8.py
+invokeai/backend/quantization/scripts/load_flux_model_bnb_nf4.py
+invokeai/backend/quantization/scripts/quantize_t5_xxl_bnb_llm_int8.py
 invokeai/backend/stable_diffusion/__init__.py
 invokeai/backend/stable_diffusion/denoise_context.py
 invokeai/backend/stable_diffusion/diffusers_pipeline.py
@@ -387,10 +404,10 @@ invokeai/frontend/install/import_images.py
 invokeai/frontend/web/__init__.py
 invokeai/frontend/web/dist/index.html
 invokeai/frontend/web/dist/assets/App-DEu4J2pT.css
-invokeai/frontend/web/dist/assets/App-Dp3a5nk3.js
+invokeai/frontend/web/dist/assets/App-vCM7oRzD.js
 invokeai/frontend/web/dist/assets/ThemeLocaleProvider-B2NxUfIp.css
-invokeai/frontend/web/dist/assets/ThemeLocaleProvider-oaIduhpQ.js
-invokeai/frontend/web/dist/assets/index-hqV6JEH_.js
+invokeai/frontend/web/dist/assets/ThemeLocaleProvider-C04frtGG.js
+invokeai/frontend/web/dist/assets/index-do3ah3Ti.js
 invokeai/frontend/web/dist/assets/inter-cyrillic-ext-wght-normal-B2xhLi22.woff2
 invokeai/frontend/web/dist/assets/inter-cyrillic-wght-normal-CMZtQduZ.woff2
 invokeai/frontend/web/dist/assets/inter-greek-ext-wght-normal-CGAr0uHJ.woff2

{InvokeAI-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/InvokeAI.egg-info/requires.txt

@@ -11,6 +11,7 @@ onnxruntime==1.16.3
 opencv-python==4.9.0.80
 pytorch-lightning==2.1.3
 safetensors==0.4.3
+sentencepiece==0.2.0
 spandrel==0.3.4
 timm==0.6.13
 torch==2.2.2
@@ -52,6 +53,9 @@ scikit-image~=0.21.0
 semver~=3.0.1
 test-tube~=0.7.5
 
+[:sys_platform != "darwin"]
+bitsandbytes==0.43.3
+
 [:sys_platform == "win32"]
 windows-curses
 

{InvokeAI-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.2.9.dev4
+Version: 4.2.9.dev6
 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-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/invokeai/app/invocations/baseinvocation.py

@@ -20,7 +20,6 @@ from typing import (
     Type,
     TypeVar,
     Union,
-    cast,
 )
 
 import semver
@@ -80,7 +79,7 @@ class UIConfigBase(BaseModel):
     version: str = Field(
         description='The node\'s version. Should be a valid semver string e.g. "1.0.0" or "3.8.13".',
     )
-    node_pack: Optional[str] = Field(default=None, description="Whether or not this is a custom node")
+    node_pack: str = Field(description="The node pack that this node belongs to, will be 'invokeai' for built-in nodes")
     classification: Classification = Field(default=Classification.Stable, description="The node's classification")
 
     model_config = ConfigDict(
@@ -230,18 +229,16 @@ class BaseInvocation(ABC, BaseModel):
     @staticmethod
     def json_schema_extra(schema: dict[str, Any], model_class: Type[BaseInvocation]) -> None:
         """Adds various UI-facing attributes to the invocation's OpenAPI schema."""
-        uiconfig = cast(UIConfigBase | None, getattr(model_class, "UIConfig", None))
-        if uiconfig is not None:
-            if uiconfig.title is not None:
-                schema["title"] = uiconfig.title
-            if uiconfig.tags is not None:
-                schema["tags"] = uiconfig.tags
-            if uiconfig.category is not None:
-                schema["category"] = uiconfig.category
-            if uiconfig.node_pack is not None:
-                schema["node_pack"] = uiconfig.node_pack
-            schema["classification"] = uiconfig.classification
-            schema["version"] = uiconfig.version
+        if title := model_class.UIConfig.title:
+            schema["title"] = title
+        if tags := model_class.UIConfig.tags:
+            schema["tags"] = tags
+        if category := model_class.UIConfig.category:
+            schema["category"] = category
+        if node_pack := model_class.UIConfig.node_pack:
+            schema["node_pack"] = node_pack
+        schema["classification"] = model_class.UIConfig.classification
+        schema["version"] = model_class.UIConfig.version
         if "required" not in schema or not isinstance(schema["required"], list):
             schema["required"] = []
         schema["class"] = "invocation"
@@ -312,7 +309,7 @@ class BaseInvocation(ABC, BaseModel):
         json_schema_extra={"field_kind": FieldKind.NodeAttribute},
     )
 
-    UIConfig: ClassVar[Type[UIConfigBase]]
+    UIConfig: ClassVar[UIConfigBase]
 
     model_config = ConfigDict(
         protected_namespaces=(),
@@ -441,30 +438,25 @@ def invocation(
         validate_fields(cls.model_fields, invocation_type)
 
         # Add OpenAPI schema extras
-        uiconfig_name = cls.__qualname__ + ".UIConfig"
-        if not hasattr(cls, "UIConfig") or cls.UIConfig.__qualname__ != uiconfig_name:
-            cls.UIConfig = type(uiconfig_name, (UIConfigBase,), {})
-        cls.UIConfig.title = title
-        cls.UIConfig.tags = tags
-        cls.UIConfig.category = category
-        cls.UIConfig.classification = classification
-
-        # Grab the node pack's name from the module name, if it's a custom node
-        is_custom_node = cls.__module__.rsplit(".", 1)[0] == "invokeai.app.invocations"
-        if is_custom_node:
-            cls.UIConfig.node_pack = cls.__module__.split(".")[0]
-        else:
-            cls.UIConfig.node_pack = None
+        uiconfig: dict[str, Any] = {}
+        uiconfig["title"] = title
+        uiconfig["tags"] = tags
+        uiconfig["category"] = category
+        uiconfig["classification"] = classification
+        # The node pack is the module name - will be "invokeai" for built-in nodes
+        uiconfig["node_pack"] = cls.__module__.split(".")[0]
 
         if version is not None:
             try:
                 semver.Version.parse(version)
             except ValueError as e:
                 raise InvalidVersionError(f'Invalid version string for node "{invocation_type}": "{version}"') from e
-            cls.UIConfig.version = version
+            uiconfig["version"] = version
         else:
             logger.warn(f'No version specified for node "{invocation_type}", using "1.0.0"')
-            cls.UIConfig.version = "1.0.0"
+            uiconfig["version"] = "1.0.0"
+
+        cls.UIConfig = UIConfigBase(**uiconfig)
 
         if use_cache is not None:
             cls.model_fields["use_cache"].default = use_cache

{InvokeAI-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/invokeai/app/invocations/fields.py

@@ -40,6 +40,7 @@ class UIType(str, Enum, metaclass=MetaEnum):
 
     # region Model Field Types
     MainModel = "MainModelField"
+    FluxMainModel = "FluxMainModelField"
     SDXLMainModel = "SDXLMainModelField"
     SDXLRefinerModel = "SDXLRefinerModelField"
     ONNXModel = "ONNXModelField"
@@ -48,6 +49,7 @@ class UIType(str, Enum, metaclass=MetaEnum):
     ControlNetModel = "ControlNetModelField"
     IPAdapterModel = "IPAdapterModelField"
     T2IAdapterModel = "T2IAdapterModelField"
+    T5EncoderModel = "T5EncoderModelField"
     SpandrelImageToImageModel = "SpandrelImageToImageModelField"
     # endregion
 
@@ -125,13 +127,16 @@ class FieldDescriptions:
     negative_cond = "Negative conditioning tensor"
     noise = "Noise tensor"
     clip = "CLIP (tokenizer, text encoder, LoRAs) and skipped layer count"
+    t5_encoder = "T5 tokenizer and text encoder"
     unet = "UNet (scheduler, LoRAs)"
+    transformer = "Transformer"
     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"
+    flux_model = "Flux model (Transformer) 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"
@@ -231,6 +236,12 @@ class ColorField(BaseModel):
         return (self.r, self.g, self.b, self.a)
 
 
+class FluxConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+
+
 class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 

InvokeAI-4.2.9.dev6/invokeai/app/invocations/flux_text_encoder.py

@@ -0,0 +1,86 @@
+from typing import Literal
+
+import torch
+from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField
+from invokeai.app.invocations.model import CLIPField, T5EncoderField
+from invokeai.app.invocations.primitives import FluxConditioningOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.flux.modules.conditioner import HFEncoder
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningFieldData, FLUXConditioningInfo
+
+
+@invocation(
+    "flux_text_encoder",
+    title="FLUX Text Encoding",
+    tags=["prompt", "conditioning", "flux"],
+    category="conditioning",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class FluxTextEncoderInvocation(BaseInvocation):
+    """Encodes and preps a prompt for a flux image."""
+
+    clip: CLIPField = InputField(
+        title="CLIP",
+        description=FieldDescriptions.clip,
+        input=Input.Connection,
+    )
+    t5_encoder: T5EncoderField = InputField(
+        title="T5Encoder",
+        description=FieldDescriptions.t5_encoder,
+        input=Input.Connection,
+    )
+    t5_max_seq_len: Literal[256, 512] = InputField(
+        description="Max sequence length for the T5 encoder. Expected to be 256 for FLUX schnell models and 512 for FLUX dev models."
+    )
+    prompt: str = InputField(description="Text prompt to encode.")
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> FluxConditioningOutput:
+        t5_embeddings, clip_embeddings = self._encode_prompt(context)
+        conditioning_data = ConditioningFieldData(
+            conditionings=[FLUXConditioningInfo(clip_embeds=clip_embeddings, t5_embeds=t5_embeddings)]
+        )
+
+        conditioning_name = context.conditioning.save(conditioning_data)
+        return FluxConditioningOutput.build(conditioning_name)
+
+    def _encode_prompt(self, context: InvocationContext) -> tuple[torch.Tensor, torch.Tensor]:
+        # Load CLIP.
+        clip_tokenizer_info = context.models.load(self.clip.tokenizer)
+        clip_text_encoder_info = context.models.load(self.clip.text_encoder)
+
+        # Load T5.
+        t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer)
+        t5_text_encoder_info = context.models.load(self.t5_encoder.text_encoder)
+
+        prompt = [self.prompt]
+
+        with (
+            t5_text_encoder_info as t5_text_encoder,
+            t5_tokenizer_info as t5_tokenizer,
+        ):
+            assert isinstance(t5_text_encoder, T5EncoderModel)
+            assert isinstance(t5_tokenizer, T5Tokenizer)
+
+            t5_encoder = HFEncoder(t5_text_encoder, t5_tokenizer, False, self.t5_max_seq_len)
+
+            prompt_embeds = t5_encoder(prompt)
+
+        with (
+            clip_text_encoder_info as clip_text_encoder,
+            clip_tokenizer_info as clip_tokenizer,
+        ):
+            assert isinstance(clip_text_encoder, CLIPTextModel)
+            assert isinstance(clip_tokenizer, CLIPTokenizer)
+
+            clip_encoder = HFEncoder(clip_text_encoder, clip_tokenizer, True, 77)
+
+            pooled_prompt_embeds = clip_encoder(prompt)
+
+        assert isinstance(prompt_embeds, torch.Tensor)
+        assert isinstance(pooled_prompt_embeds, torch.Tensor)
+        return prompt_embeds, pooled_prompt_embeds

InvokeAI-4.2.9.dev6/invokeai/app/invocations/flux_text_to_image.py

@@ -0,0 +1,172 @@
+import torch
+from einops import rearrange
+from PIL import Image
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    FluxConditioningField,
+    Input,
+    InputField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import TransformerField, VAEField
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.session_processor.session_processor_common import CanceledException
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.flux.model import Flux
+from invokeai.backend.flux.modules.autoencoder import AutoEncoder
+from invokeai.backend.flux.sampling import denoise, get_noise, get_schedule, prepare_latent_img_patches, unpack
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import FLUXConditioningInfo
+from invokeai.backend.util.devices import TorchDevice
+
+
+@invocation(
+    "flux_text_to_image",
+    title="FLUX Text to Image",
+    tags=["image", "flux"],
+    category="image",
+    version="1.0.0",
+    classification=Classification.Prototype,
+)
+class FluxTextToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Text-to-image generation using a FLUX model."""
+
+    transformer: TransformerField = InputField(
+        description=FieldDescriptions.flux_model,
+        input=Input.Connection,
+        title="Transformer",
+    )
+    vae: VAEField = InputField(
+        description=FieldDescriptions.vae,
+        input=Input.Connection,
+    )
+    positive_text_conditioning: FluxConditioningField = InputField(
+        description=FieldDescriptions.positive_cond, input=Input.Connection
+    )
+    width: int = InputField(default=1024, multiple_of=16, description="Width of the generated image.")
+    height: int = InputField(default=1024, multiple_of=16, description="Height of the generated image.")
+    num_steps: int = InputField(
+        default=4, description="Number of diffusion steps. Recommend values are schnell: 4, dev: 50."
+    )
+    guidance: float = InputField(
+        default=4.0,
+        description="The guidance strength. Higher values adhere more strictly to the prompt, and will produce less diverse images. FLUX dev only, ignored for schnell.",
+    )
+    seed: int = InputField(default=0, description="Randomness seed for reproducibility.")
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(self.positive_text_conditioning.conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        flux_conditioning = cond_data.conditionings[0]
+        assert isinstance(flux_conditioning, FLUXConditioningInfo)
+
+        latents = self._run_diffusion(context, flux_conditioning.clip_embeds, flux_conditioning.t5_embeds)
+        image = self._run_vae_decoding(context, latents)
+        image_dto = context.images.save(image=image)
+        return ImageOutput.build(image_dto)
+
+    def _run_diffusion(
+        self,
+        context: InvocationContext,
+        clip_embeddings: torch.Tensor,
+        t5_embeddings: torch.Tensor,
+    ):
+        transformer_info = context.models.load(self.transformer.transformer)
+        inference_dtype = torch.bfloat16
+
+        # Prepare input noise.
+        x = get_noise(
+            num_samples=1,
+            height=self.height,
+            width=self.width,
+            device=TorchDevice.choose_torch_device(),
+            dtype=inference_dtype,
+            seed=self.seed,
+        )
+
+        img, img_ids = prepare_latent_img_patches(x)
+
+        is_schnell = "schnell" in transformer_info.config.config_path
+
+        timesteps = get_schedule(
+            num_steps=self.num_steps,
+            image_seq_len=img.shape[1],
+            shift=not is_schnell,
+        )
+
+        bs, t5_seq_len, _ = t5_embeddings.shape
+        txt_ids = torch.zeros(bs, t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device())
+
+        # HACK(ryand): Manually empty the cache. Currently we don't check the size of the model before loading it from
+        # disk. Since the transformer model is large (24GB), there's a good chance that it will OOM on 32GB RAM systems
+        # if the cache is not empty.
+        context.models._services.model_manager.load.ram_cache.make_room(24 * 2**30)
+
+        with transformer_info as transformer:
+            assert isinstance(transformer, Flux)
+
+            def step_callback() -> None:
+                if context.util.is_canceled():
+                    raise CanceledException
+
+                # TODO: Make this look like the image before re-enabling
+                # latent_image = unpack(img.float(), self.height, self.width)
+                # latent_image = latent_image.squeeze()  # Remove unnecessary dimensions
+                # flattened_tensor = latent_image.reshape(-1)  # Flatten to shape [48*128*128]
+
+                # # Create a new tensor of the required shape [255, 255, 3]
+                # latent_image = flattened_tensor[: 255 * 255 * 3].reshape(255, 255, 3)  # Reshape to RGB format
+
+                # # Convert to a NumPy array and then to a PIL Image
+                # image = Image.fromarray(latent_image.cpu().numpy().astype(np.uint8))
+
+                # (width, height) = image.size
+                # width *= 8
+                # height *= 8
+
+                # dataURL = image_to_dataURL(image, image_format="JPEG")
+
+                # # TODO: move this whole function to invocation context to properly reference these variables
+                # context._services.events.emit_invocation_denoise_progress(
+                #     context._data.queue_item,
+                #     context._data.invocation,
+                #     state,
+                #     ProgressImage(dataURL=dataURL, width=width, height=height),
+                # )
+
+            x = denoise(
+                model=transformer,
+                img=img,
+                img_ids=img_ids,
+                txt=t5_embeddings,
+                txt_ids=txt_ids,
+                vec=clip_embeddings,
+                timesteps=timesteps,
+                step_callback=step_callback,
+                guidance=self.guidance,
+            )
+
+        x = unpack(x.float(), self.height, self.width)
+
+        return x
+
+    def _run_vae_decoding(
+        self,
+        context: InvocationContext,
+        latents: torch.Tensor,
+    ) -> Image.Image:
+        vae_info = context.models.load(self.vae.vae)
+        with vae_info as vae:
+            assert isinstance(vae, AutoEncoder)
+            latents = latents.to(dtype=TorchDevice.choose_torch_dtype())
+            img = vae.decode(latents)
+
+        img = img.clamp(-1, 1)
+        img = rearrange(img[0], "c h w -> h w c")
+        img_pil = Image.fromarray((127.5 * (img + 1.0)).byte().cpu().numpy())
+
+        return img_pil

{InvokeAI-4.2.9.dev4 → InvokeAI-4.2.9.dev6}/invokeai/app/invocations/model.py

@@ -1,5 +1,5 @@
 import copy
-from typing import List, Optional
+from typing import List, Literal, Optional
 
 from pydantic import BaseModel, Field
 
@@ -13,7 +13,14 @@ from invokeai.app.invocations.baseinvocation import (
 from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.shared.models import FreeUConfig
-from invokeai.backend.model_manager.config import AnyModelConfig, BaseModelType, ModelType, SubModelType
+from invokeai.backend.flux.util import max_seq_lengths
+from invokeai.backend.model_manager.config import (
+    AnyModelConfig,
+    BaseModelType,
+    CheckpointConfigBase,
+    ModelType,
+    SubModelType,
+)
 
 
 class ModelIdentifierField(BaseModel):
@@ -60,6 +67,15 @@ class CLIPField(BaseModel):
     loras: List[LoRAField] = Field(description="LoRAs to apply on model loading")
 
 
+class TransformerField(BaseModel):
+    transformer: ModelIdentifierField = Field(description="Info to load Transformer submodel")
+
+
+class T5EncoderField(BaseModel):
+    tokenizer: ModelIdentifierField = Field(description="Info to load tokenizer submodel")
+    text_encoder: ModelIdentifierField = Field(description="Info to load text_encoder submodel")
+
+
 class VAEField(BaseModel):
     vae: ModelIdentifierField = Field(description="Info to load vae submodel")
     seamless_axes: List[str] = Field(default_factory=list, description='Axes("x" and "y") to which apply seamless')
@@ -122,6 +138,112 @@ class ModelIdentifierInvocation(BaseInvocation):
         return ModelIdentifierOutput(model=self.model)
 
 
+@invocation_output("flux_model_loader_output")
+class FluxModelLoaderOutput(BaseInvocationOutput):
+    """Flux base model loader output"""
+
+    transformer: TransformerField = OutputField(description=FieldDescriptions.transformer, title="Transformer")
+    clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP")
+    t5_encoder: T5EncoderField = OutputField(description=FieldDescriptions.t5_encoder, title="T5 Encoder")
+    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    max_seq_len: Literal[256, 512] = OutputField(
+        description="The max sequence length to used for the T5 encoder. (256 for schnell transformer, 512 for dev transformer)",
+        title="Max Seq Length",
+    )
+
+
+@invocation(
+    "flux_model_loader",
+    title="Flux Main Model",
+    tags=["model", "flux"],
+    category="model",
+    version="1.0.3",
+    classification=Classification.Prototype,
+)
+class FluxModelLoaderInvocation(BaseInvocation):
+    """Loads a flux base model, outputting its submodels."""
+
+    model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.flux_model,
+        ui_type=UIType.FluxMainModel,
+        input=Input.Direct,
+    )
+
+    t5_encoder: ModelIdentifierField = InputField(
+        description=FieldDescriptions.t5_encoder,
+        ui_type=UIType.T5EncoderModel,
+        input=Input.Direct,
+    )
+
+    def invoke(self, context: InvocationContext) -> FluxModelLoaderOutput:
+        model_key = self.model.key
+
+        if not context.models.exists(model_key):
+            raise ValueError(f"Unknown model: {model_key}")
+        transformer = self._get_model(context, SubModelType.Transformer)
+        tokenizer = self._get_model(context, SubModelType.Tokenizer)
+        tokenizer2 = self._get_model(context, SubModelType.Tokenizer2)
+        clip_encoder = self._get_model(context, SubModelType.TextEncoder)
+        t5_encoder = self._get_model(context, SubModelType.TextEncoder2)
+        vae = self._get_model(context, SubModelType.VAE)
+        transformer_config = context.models.get_config(transformer)
+        assert isinstance(transformer_config, CheckpointConfigBase)
+
+        return FluxModelLoaderOutput(
+            transformer=TransformerField(transformer=transformer),
+            clip=CLIPField(tokenizer=tokenizer, text_encoder=clip_encoder, loras=[], skipped_layers=0),
+            t5_encoder=T5EncoderField(tokenizer=tokenizer2, text_encoder=t5_encoder),
+            vae=VAEField(vae=vae),
+            max_seq_len=max_seq_lengths[transformer_config.config_path],
+        )
+
+    def _get_model(self, context: InvocationContext, submodel: SubModelType) -> ModelIdentifierField:
+        match submodel:
+            case SubModelType.Transformer:
+                return self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
+            case SubModelType.VAE:
+                return self._pull_model_from_mm(
+                    context,
+                    SubModelType.VAE,
+                    "FLUX.1-schnell_ae",
+                    ModelType.VAE,
+                    BaseModelType.Flux,
+                )
+            case submodel if submodel in [SubModelType.Tokenizer, SubModelType.TextEncoder]:
+                return self._pull_model_from_mm(
+                    context,
+                    submodel,
+                    "clip-vit-large-patch14",
+                    ModelType.CLIPEmbed,
+                    BaseModelType.Any,
+                )
+            case submodel if submodel in [SubModelType.Tokenizer2, SubModelType.TextEncoder2]:
+                return self._pull_model_from_mm(
+                    context,
+                    submodel,
+                    self.t5_encoder.name,
+                    ModelType.T5Encoder,
+                    BaseModelType.Any,
+                )
+            case _:
+                raise Exception(f"{submodel.value} is not a supported submodule for a flux model")
+
+    def _pull_model_from_mm(
+        self,
+        context: InvocationContext,
+        submodel: SubModelType,
+        name: str,
+        type: ModelType,
+        base: BaseModelType,
+    ):
+        if models := context.models.search_by_attrs(name=name, base=base, type=type):
+            if len(models) != 1:
+                raise Exception(f"Multiple models detected for selected model with name {name}")
+            return ModelIdentifierField.from_config(models[0]).model_copy(update={"submodel_type": submodel})
+        else:
+            raise ValueError(f"Please install the {base}:{type} model named {name} via starter models")
+
+
 @invocation(
     "main_model_loader",
     title="Main Model",