Make quantized loading fast for both T5XXL and FLUX transformer.

docs/help/FAQ.md

@@ -196,22 +196,6 @@ tips to reduce the problem:
     === "12GB VRAM GPU"
 
         This should be sufficient to generate larger images up to about 1280x1280.
-		
-## Checkpoint Models Load Slowly or Use Too Much RAM
-
-The difference between diffusers models (a folder containing multiple
-subfolders) and checkpoint models (a file ending with .safetensors or
-.ckpt) is that InvokeAI is able to load diffusers models into memory
-incrementally, while checkpoint models must be loaded all at
-once. With very large models, or systems with limited RAM, you may
-experience slowdowns and other memory-related issues when loading
-checkpoint models.
-
-To solve this, go to the Model Manager tab (the cube), select the
-checkpoint model that's giving you trouble, and press the "Convert"
-button in the upper right of your browser window. This will conver the
-checkpoint into a diffusers model, after which loading should be
-faster and less memory-intensive.
 
 ## Memory Leak (Linux)
 

invokeai/app/api/routers/images.py

@@ -218,8 +218,9 @@ async def get_image_workflow(
         raise HTTPException(status_code=404)
 
 
-@images_router.get(
+@images_router.api_route(
     "/i/{image_name}/full",
+    methods=["GET", "HEAD"],
     operation_id="get_image_full",
     response_class=Response,
     responses={
@@ -230,18 +231,6 @@ async def get_image_workflow(
         404: {"description": "Image not found"},
     },
 )
-@images_router.head(
-    "/i/{image_name}/full",
-    operation_id="get_image_full_head",
-    response_class=Response,
-    responses={
-        200: {
-            "description": "Return the full-resolution image",
-            "content": {"image/png": {}},
-        },
-        404: {"description": "Image not found"},
-    },
-)
 async def get_image_full(
     image_name: str = Path(description="The name of full-resolution image file to get"),
 ) -> Response:
@@ -253,7 +242,6 @@ async def get_image_full(
             content = f.read()
         response = Response(content, media_type="image/png")
         response.headers["Cache-Control"] = f"max-age={IMAGE_MAX_AGE}"
-        response.headers["Content-Disposition"] = f'inline; filename="{image_name}"'
         return response
     except Exception:
         raise HTTPException(status_code=404)

invokeai/app/invocations/controlnet_image_processors.py

@@ -21,8 +21,6 @@ from controlnet_aux import (
 from controlnet_aux.util import HWC3, ade_palette
 from PIL import Image
 from pydantic import BaseModel, Field, field_validator, model_validator
-from transformers import pipeline
-from transformers.pipelines import DepthEstimationPipeline
 
 from invokeai.app.invocations.baseinvocation import (
     BaseInvocation,
@@ -46,12 +44,13 @@ from invokeai.app.invocations.util import validate_begin_end_step, validate_weig
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES, heuristic_resize
 from invokeai.backend.image_util.canny import get_canny_edges
-from invokeai.backend.image_util.depth_anything.depth_anything_pipeline import DepthAnythingPipeline
+from invokeai.backend.image_util.depth_anything import DEPTH_ANYTHING_MODELS, DepthAnythingDetector
 from invokeai.backend.image_util.dw_openpose import DWPOSE_MODELS, DWOpenposeDetector
 from invokeai.backend.image_util.hed import HEDProcessor
 from invokeai.backend.image_util.lineart import LineartProcessor
 from invokeai.backend.image_util.lineart_anime import LineartAnimeProcessor
 from invokeai.backend.image_util.util import np_to_pil, pil_to_np
+from invokeai.backend.util.devices import TorchDevice
 
 
 class ControlField(BaseModel):
@@ -593,14 +592,7 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
         return color_map
 
 
-DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small", "small_v2"]
-# DepthAnything V2 Small model is licensed under Apache 2.0 but not the base and large models.
-DEPTH_ANYTHING_MODELS = {
-    "large": "LiheYoung/depth-anything-large-hf",
-    "base": "LiheYoung/depth-anything-base-hf",
-    "small": "LiheYoung/depth-anything-small-hf",
-    "small_v2": "depth-anything/Depth-Anything-V2-Small-hf",
-}
+DEPTH_ANYTHING_MODEL_SIZES = Literal["large", "base", "small"]
 
 
 @invocation(
@@ -608,33 +600,28 @@ DEPTH_ANYTHING_MODELS = {
     title="Depth Anything Processor",
     tags=["controlnet", "depth", "depth anything"],
     category="controlnet",
-    version="1.1.3",
+    version="1.1.2",
 )
 class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     """Generates a depth map based on the Depth Anything algorithm"""
 
     model_size: DEPTH_ANYTHING_MODEL_SIZES = InputField(
-        default="small_v2", description="The size of the depth model to use"
+        default="small", description="The size of the depth model to use"
     )
     resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
     def run_processor(self, image: Image.Image) -> Image.Image:
-        def load_depth_anything(model_path: Path):
-            depth_anything_pipeline = pipeline(model=str(model_path), task="depth-estimation", local_files_only=True)
-            assert isinstance(depth_anything_pipeline, DepthEstimationPipeline)
-            return DepthAnythingPipeline(depth_anything_pipeline)
+        def loader(model_path: Path):
+            return DepthAnythingDetector.load_model(
+                model_path, model_size=self.model_size, device=TorchDevice.choose_torch_device()
+            )
 
         with self._context.models.load_remote_model(
-            source=DEPTH_ANYTHING_MODELS[self.model_size], loader=load_depth_anything
-        ) as depth_anything_detector:
-            assert isinstance(depth_anything_detector, DepthAnythingPipeline)
-            depth_map = depth_anything_detector.generate_depth(image)
-
-            # Resizing to user target specified size
-            new_height = int(image.size[1] * (self.resolution / image.size[0]))
-            depth_map = depth_map.resize((self.resolution, new_height))
-
-            return depth_map
+            source=DEPTH_ANYTHING_MODELS[self.model_size], loader=loader
+        ) as model:
+            depth_anything_detector = DepthAnythingDetector(model, TorchDevice.choose_torch_device())
+            processed_image = depth_anything_detector(image=image, resolution=self.resolution)
+            return processed_image
 
 
 @invocation(

invokeai/app/invocations/flux_text_to_image.py

@@ -0,0 +1,278 @@
+from pathlib import Path
+from typing import Literal
+
+import torch
+from diffusers import AutoencoderKL, FlowMatchEulerDiscreteScheduler
+from diffusers.models.transformers.transformer_flux import FluxTransformer2DModel
+from diffusers.pipelines.flux.pipeline_flux import FluxPipeline
+from optimum.quanto import qfloat8
+from PIL import Image
+from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5TokenizerFast
+from transformers.models.auto import AutoModelForTextEncoding
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.fields import InputField, WithBoard, WithMetadata
+from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.quantization.fast_quantized_diffusion_model import FastQuantizedDiffusersModel
+from invokeai.backend.quantization.fast_quantized_transformers_model import FastQuantizedTransformersModel
+from invokeai.backend.util.devices import TorchDevice
+
+TFluxModelKeys = Literal["flux-schnell"]
+FLUX_MODELS: dict[TFluxModelKeys, str] = {"flux-schnell": "black-forest-labs/FLUX.1-schnell"}
+
+
+class QuantizedFluxTransformer2DModel(FastQuantizedDiffusersModel):
+    base_class = FluxTransformer2DModel
+
+
+class QuantizedModelForTextEncoding(FastQuantizedTransformersModel):
+    auto_class = AutoModelForTextEncoding
+
+
+@invocation(
+    "flux_text_to_image",
+    title="FLUX Text to Image",
+    tags=["image"],
+    category="image",
+    version="1.0.0",
+)
+class FluxTextToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Text-to-image generation using a FLUX model."""
+
+    model: TFluxModelKeys = InputField(description="The FLUX model to use for text-to-image generation.")
+    use_8bit: bool = InputField(
+        default=False, description="Whether to quantize the transformer model to 8-bit precision."
+    )
+    positive_prompt: str = InputField(description="Positive prompt for text-to-image generation.")
+    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.")
+    guidance: float = InputField(
+        default=4.0,
+        description="The guidance strength. Higher values adhere more strictly to the prompt, and will produce less diverse images.",
+    )
+    seed: int = InputField(default=0, description="Randomness seed for reproducibility.")
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> ImageOutput:
+        model_path = context.models.download_and_cache_model(FLUX_MODELS[self.model])
+
+        t5_embeddings, clip_embeddings = self._encode_prompt(context, model_path)
+        latents = self._run_diffusion(context, model_path, clip_embeddings, t5_embeddings)
+        image = self._run_vae_decoding(context, model_path, latents)
+        image_dto = context.images.save(image=image)
+        return ImageOutput.build(image_dto)
+
+    def _encode_prompt(self, context: InvocationContext, flux_model_dir: Path) -> tuple[torch.Tensor, torch.Tensor]:
+        # Determine the T5 max sequence length based on the model.
+        if self.model == "flux-schnell":
+            max_seq_len = 256
+        # elif self.model == "flux-dev":
+        #     max_seq_len = 512
+        else:
+            raise ValueError(f"Unknown model: {self.model}")
+
+        # Load the CLIP tokenizer.
+        clip_tokenizer_path = flux_model_dir / "tokenizer"
+        clip_tokenizer = CLIPTokenizer.from_pretrained(clip_tokenizer_path, local_files_only=True)
+        assert isinstance(clip_tokenizer, CLIPTokenizer)
+
+        # Load the T5 tokenizer.
+        t5_tokenizer_path = flux_model_dir / "tokenizer_2"
+        t5_tokenizer = T5TokenizerFast.from_pretrained(t5_tokenizer_path, local_files_only=True)
+        assert isinstance(t5_tokenizer, T5TokenizerFast)
+
+        clip_text_encoder_path = flux_model_dir / "text_encoder"
+        t5_text_encoder_path = flux_model_dir / "text_encoder_2"
+        with (
+            context.models.load_local_model(
+                model_path=clip_text_encoder_path, loader=self._load_flux_text_encoder
+            ) as clip_text_encoder,
+            context.models.load_local_model(
+                model_path=t5_text_encoder_path, loader=self._load_flux_text_encoder_2
+            ) as t5_text_encoder,
+        ):
+            assert isinstance(clip_text_encoder, CLIPTextModel)
+            assert isinstance(t5_text_encoder, T5EncoderModel)
+            pipeline = FluxPipeline(
+                scheduler=None,
+                vae=None,
+                text_encoder=clip_text_encoder,
+                tokenizer=clip_tokenizer,
+                text_encoder_2=t5_text_encoder,
+                tokenizer_2=t5_tokenizer,
+                transformer=None,
+            )
+
+            # prompt_embeds: T5 embeddings
+            # pooled_prompt_embeds: CLIP embeddings
+            prompt_embeds, pooled_prompt_embeds, text_ids = pipeline.encode_prompt(
+                prompt=self.positive_prompt,
+                prompt_2=self.positive_prompt,
+                device=TorchDevice.choose_torch_device(),
+                max_sequence_length=max_seq_len,
+            )
+
+        assert isinstance(prompt_embeds, torch.Tensor)
+        assert isinstance(pooled_prompt_embeds, torch.Tensor)
+        return prompt_embeds, pooled_prompt_embeds
+
+    def _run_diffusion(
+        self,
+        context: InvocationContext,
+        flux_model_dir: Path,
+        clip_embeddings: torch.Tensor,
+        t5_embeddings: torch.Tensor,
+    ):
+        scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(flux_model_dir / "scheduler", local_files_only=True)
+
+        # 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)
+
+        transformer_path = flux_model_dir / "transformer"
+        with context.models.load_local_model(
+            model_path=transformer_path, loader=self._load_flux_transformer
+        ) as transformer:
+            assert isinstance(transformer, FluxTransformer2DModel)
+
+            flux_pipeline_with_transformer = FluxPipeline(
+                scheduler=scheduler,
+                vae=None,
+                text_encoder=None,
+                tokenizer=None,
+                text_encoder_2=None,
+                tokenizer_2=None,
+                transformer=transformer,
+            )
+
+            t5_embeddings = t5_embeddings.to(dtype=transformer.dtype)
+            clip_embeddings = clip_embeddings.to(dtype=transformer.dtype)
+
+            latents = flux_pipeline_with_transformer(
+                height=self.height,
+                width=self.width,
+                num_inference_steps=self.num_steps,
+                guidance_scale=self.guidance,
+                generator=torch.Generator().manual_seed(self.seed),
+                prompt_embeds=t5_embeddings,
+                pooled_prompt_embeds=clip_embeddings,
+                output_type="latent",
+                return_dict=False,
+            )[0]
+
+        assert isinstance(latents, torch.Tensor)
+        return latents
+
+    def _run_vae_decoding(
+        self,
+        context: InvocationContext,
+        flux_model_dir: Path,
+        latents: torch.Tensor,
+    ) -> Image.Image:
+        vae_path = flux_model_dir / "vae"
+        with context.models.load_local_model(model_path=vae_path, loader=self._load_flux_vae) as vae:
+            assert isinstance(vae, AutoencoderKL)
+
+            flux_pipeline_with_vae = FluxPipeline(
+                scheduler=None,
+                vae=vae,
+                text_encoder=None,
+                tokenizer=None,
+                text_encoder_2=None,
+                tokenizer_2=None,
+                transformer=None,
+            )
+
+            latents = flux_pipeline_with_vae._unpack_latents(
+                latents, self.height, self.width, flux_pipeline_with_vae.vae_scale_factor
+            )
+            latents = (
+                latents / flux_pipeline_with_vae.vae.config.scaling_factor
+            ) + flux_pipeline_with_vae.vae.config.shift_factor
+            latents = latents.to(dtype=vae.dtype)
+            image = flux_pipeline_with_vae.vae.decode(latents, return_dict=False)[0]
+            image = flux_pipeline_with_vae.image_processor.postprocess(image, output_type="pil")[0]
+
+        assert isinstance(image, Image.Image)
+        return image
+
+    @staticmethod
+    def _load_flux_text_encoder(path: Path) -> CLIPTextModel:
+        model = CLIPTextModel.from_pretrained(path, local_files_only=True)
+        assert isinstance(model, CLIPTextModel)
+        return model
+
+    def _load_flux_text_encoder_2(self, path: Path) -> T5EncoderModel:
+        if self.use_8bit:
+            model_8bit_path = path / "quantized"
+            if model_8bit_path.exists():
+                # The quantized model exists, load it.
+                # TODO(ryand): The requantize(...) operation in from_pretrained(...) is very slow. This seems like
+                # something that we should be able to make much faster.
+                q_model = QuantizedModelForTextEncoding.from_pretrained(model_8bit_path)
+
+                # Access the underlying wrapped model.
+                # We access the wrapped model, even though it is private, because it simplifies the type checking by
+                # always returning a T5EncoderModel from this function.
+                model = q_model._wrapped
+            else:
+                # The quantized model does not exist yet, quantize and save it.
+                # TODO(ryand): dtype?
+                model = T5EncoderModel.from_pretrained(path, local_files_only=True)
+                assert isinstance(model, T5EncoderModel)
+
+                q_model = QuantizedModelForTextEncoding.quantize(model, weights=qfloat8)
+
+                model_8bit_path.mkdir(parents=True, exist_ok=True)
+                q_model.save_pretrained(model_8bit_path)
+
+                # (See earlier comment about accessing the wrapped model.)
+                model = q_model._wrapped
+        else:
+            model = T5EncoderModel.from_pretrained(path, local_files_only=True)
+
+        assert isinstance(model, T5EncoderModel)
+        return model
+
+    def _load_flux_transformer(self, path: Path) -> FluxTransformer2DModel:
+        if self.use_8bit:
+            model_8bit_path = path / "quantized"
+            if model_8bit_path.exists():
+                # The quantized model exists, load it.
+                # TODO(ryand): The requantize(...) operation in from_pretrained(...) is very slow. This seems like
+                # something that we should be able to make much faster.
+                q_model = QuantizedFluxTransformer2DModel.from_pretrained(model_8bit_path)
+
+                # Access the underlying wrapped model.
+                # We access the wrapped model, even though it is private, because it simplifies the type checking by
+                # always returning a FluxTransformer2DModel from this function.
+                model = q_model._wrapped
+            else:
+                # The quantized model does not exist yet, quantize and save it.
+                # TODO(ryand): Loading in float16 and then quantizing seems to result in NaNs. In order to run this on
+                # GPUs that don't support bfloat16, we would need to host the quantized model instead of generating it
+                # here.
+                model = FluxTransformer2DModel.from_pretrained(path, local_files_only=True, torch_dtype=torch.bfloat16)
+                assert isinstance(model, FluxTransformer2DModel)
+
+                q_model = QuantizedFluxTransformer2DModel.quantize(model, weights=qfloat8)
+
+                model_8bit_path.mkdir(parents=True, exist_ok=True)
+                q_model.save_pretrained(model_8bit_path)
+
+                # (See earlier comment about accessing the wrapped model.)
+                model = q_model._wrapped
+        else:
+            model = FluxTransformer2DModel.from_pretrained(path, local_files_only=True, torch_dtype=torch.bfloat16)
+
+        assert isinstance(model, FluxTransformer2DModel)
+        return model
+
+    @staticmethod
+    def _load_flux_vae(path: Path) -> AutoencoderKL:
+        model = AutoencoderKL.from_pretrained(path, local_files_only=True)
+        assert isinstance(model, AutoencoderKL)
+        return model

invokeai/app/util/custom_openapi.py

@@ -81,7 +81,7 @@ def get_openapi_func(
         # Add the output map to the schema
         openapi_schema["components"]["schemas"]["InvocationOutputMap"] = {
             "type": "object",
-            "properties": dict(sorted(invocation_output_map_properties.items())),
+            "properties": invocation_output_map_properties,
             "required": invocation_output_map_required,
         }
 

invokeai/backend/image_util/depth_anything/__init__.py

@@ -0,0 +1,90 @@
+from pathlib import Path
+from typing import Literal
+
+import cv2
+import numpy as np
+import torch
+import torch.nn.functional as F
+from einops import repeat
+from PIL import Image
+from torchvision.transforms import Compose
+
+from invokeai.app.services.config.config_default import get_config
+from invokeai.backend.image_util.depth_anything.model.dpt import DPT_DINOv2
+from invokeai.backend.image_util.depth_anything.utilities.util import NormalizeImage, PrepareForNet, Resize
+from invokeai.backend.util.logging import InvokeAILogger
+
+config = get_config()
+logger = InvokeAILogger.get_logger(config=config)
+
+DEPTH_ANYTHING_MODELS = {
+    "large": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitl14.pth?download=true",
+    "base": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitb14.pth?download=true",
+    "small": "https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vits14.pth?download=true",
+}
+
+
+transform = Compose(
+    [
+        Resize(
+            width=518,
+            height=518,
+            resize_target=False,
+            keep_aspect_ratio=True,
+            ensure_multiple_of=14,
+            resize_method="lower_bound",
+            image_interpolation_method=cv2.INTER_CUBIC,
+        ),
+        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+        PrepareForNet(),
+    ]
+)
+
+
+class DepthAnythingDetector:
+    def __init__(self, model: DPT_DINOv2, device: torch.device) -> None:
+        self.model = model
+        self.device = device
+
+    @staticmethod
+    def load_model(
+        model_path: Path, device: torch.device, model_size: Literal["large", "base", "small"] = "small"
+    ) -> DPT_DINOv2:
+        match model_size:
+            case "small":
+                model = DPT_DINOv2(encoder="vits", features=64, out_channels=[48, 96, 192, 384])
+            case "base":
+                model = DPT_DINOv2(encoder="vitb", features=128, out_channels=[96, 192, 384, 768])
+            case "large":
+                model = DPT_DINOv2(encoder="vitl", features=256, out_channels=[256, 512, 1024, 1024])
+
+        model.load_state_dict(torch.load(model_path.as_posix(), map_location="cpu"))
+        model.eval()
+
+        model.to(device)
+        return model
+
+    def __call__(self, image: Image.Image, resolution: int = 512) -> Image.Image:
+        if not self.model:
+            logger.warn("DepthAnything model was not loaded. Returning original image")
+            return image
+
+        np_image = np.array(image, dtype=np.uint8)
+        np_image = np_image[:, :, ::-1] / 255.0
+
+        image_height, image_width = np_image.shape[:2]
+        np_image = transform({"image": np_image})["image"]
+        tensor_image = torch.from_numpy(np_image).unsqueeze(0).to(self.device)
+
+        with torch.no_grad():
+            depth = self.model(tensor_image)
+            depth = F.interpolate(depth[None], (image_height, image_width), mode="bilinear", align_corners=False)[0, 0]
+            depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
+
+        depth_map = repeat(depth, "h w -> h w 3").cpu().numpy().astype(np.uint8)
+        depth_map = Image.fromarray(depth_map)
+
+        new_height = int(image_height * (resolution / image_width))
+        depth_map = depth_map.resize((resolution, new_height))
+
+        return depth_map

invokeai/backend/image_util/depth_anything/depth_anything_pipeline.py

@@ -1,31 +0,0 @@
-from typing import Optional
-
-import torch
-from PIL import Image
-from transformers.pipelines import DepthEstimationPipeline
-
-from invokeai.backend.raw_model import RawModel
-
-
-class DepthAnythingPipeline(RawModel):
-    """Custom wrapper for the Depth Estimation pipeline from transformers adding compatibility
-    for Invoke's Model Management System"""
-
-    def __init__(self, pipeline: DepthEstimationPipeline) -> None:
-        self._pipeline = pipeline
-
-    def generate_depth(self, image: Image.Image) -> Image.Image:
-        depth_map = self._pipeline(image)["depth"]
-        assert isinstance(depth_map, Image.Image)
-        return depth_map
-
-    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
-        if device is not None and device.type not in {"cpu", "cuda"}:
-            device = None
-        self._pipeline.model.to(device=device, dtype=dtype)
-        self._pipeline.device = self._pipeline.model.device
-
-    def calc_size(self) -> int:
-        from invokeai.backend.model_manager.load.model_util import calc_module_size
-
-        return calc_module_size(self._pipeline.model)

invokeai/backend/image_util/depth_anything/model/blocks.py

@@ -0,0 +1,145 @@
+import torch.nn as nn
+
+
+def _make_scratch(in_shape, out_shape, groups=1, expand=False):
+    scratch = nn.Module()
+
+    out_shape1 = out_shape
+    out_shape2 = out_shape
+    out_shape3 = out_shape
+    if len(in_shape) >= 4:
+        out_shape4 = out_shape
+
+    if expand:
+        out_shape1 = out_shape
+        out_shape2 = out_shape * 2
+        out_shape3 = out_shape * 4
+        if len(in_shape) >= 4:
+            out_shape4 = out_shape * 8
+
+    scratch.layer1_rn = nn.Conv2d(
+        in_shape[0], out_shape1, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
+    )
+    scratch.layer2_rn = nn.Conv2d(
+        in_shape[1], out_shape2, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
+    )
+    scratch.layer3_rn = nn.Conv2d(
+        in_shape[2], out_shape3, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
+    )
+    if len(in_shape) >= 4:
+        scratch.layer4_rn = nn.Conv2d(
+            in_shape[3], out_shape4, kernel_size=3, stride=1, padding=1, bias=False, groups=groups
+        )
+
+    return scratch
+
+
+class ResidualConvUnit(nn.Module):
+    """Residual convolution module."""
+
+    def __init__(self, features, activation, bn):
+        """Init.
+
+        Args:
+            features (int): number of features
+        """
+        super().__init__()
+
+        self.bn = bn
+
+        self.groups = 1
+
+        self.conv1 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
+
+        self.conv2 = nn.Conv2d(features, features, kernel_size=3, stride=1, padding=1, bias=True, groups=self.groups)
+
+        if self.bn:
+            self.bn1 = nn.BatchNorm2d(features)
+            self.bn2 = nn.BatchNorm2d(features)
+
+        self.activation = activation
+
+        self.skip_add = nn.quantized.FloatFunctional()
+
+    def forward(self, x):
+        """Forward pass.
+
+        Args:
+            x (tensor): input
+
+        Returns:
+            tensor: output
+        """
+
+        out = self.activation(x)
+        out = self.conv1(out)
+        if self.bn:
+            out = self.bn1(out)
+
+        out = self.activation(out)
+        out = self.conv2(out)
+        if self.bn:
+            out = self.bn2(out)
+
+        if self.groups > 1:
+            out = self.conv_merge(out)
+
+        return self.skip_add.add(out, x)
+
+
+class FeatureFusionBlock(nn.Module):
+    """Feature fusion block."""
+
+    def __init__(self, features, activation, deconv=False, bn=False, expand=False, align_corners=True, size=None):
+        """Init.
+
+        Args:
+            features (int): number of features
+        """
+        super(FeatureFusionBlock, self).__init__()
+
+        self.deconv = deconv
+        self.align_corners = align_corners
+
+        self.groups = 1
+
+        self.expand = expand
+        out_features = features
+        if self.expand:
+            out_features = features // 2
+
+        self.out_conv = nn.Conv2d(features, out_features, kernel_size=1, stride=1, padding=0, bias=True, groups=1)
+
+        self.resConfUnit1 = ResidualConvUnit(features, activation, bn)
+        self.resConfUnit2 = ResidualConvUnit(features, activation, bn)
+
+        self.skip_add = nn.quantized.FloatFunctional()
+
+        self.size = size
+
+    def forward(self, *xs, size=None):
+        """Forward pass.
+
+        Returns:
+            tensor: output
+        """
+        output = xs[0]
+
+        if len(xs) == 2:
+            res = self.resConfUnit1(xs[1])
+            output = self.skip_add.add(output, res)
+
+        output = self.resConfUnit2(output)
+
+        if (size is None) and (self.size is None):
+            modifier = {"scale_factor": 2}
+        elif size is None:
+            modifier = {"size": self.size}
+        else:
+            modifier = {"size": size}
+
+        output = nn.functional.interpolate(output, **modifier, mode="bilinear", align_corners=self.align_corners)
+
+        output = self.out_conv(output)
+
+        return output

invokeai/backend/image_util/depth_anything/model/dpt.py

@@ -0,0 +1,183 @@
+from pathlib import Path
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from invokeai.backend.image_util.depth_anything.model.blocks import FeatureFusionBlock, _make_scratch
+
+torchhub_path = Path(__file__).parent.parent / "torchhub"
+
+
+def _make_fusion_block(features, use_bn, size=None):
+    return FeatureFusionBlock(
+        features,
+        nn.ReLU(False),
+        deconv=False,
+        bn=use_bn,
+        expand=False,
+        align_corners=True,
+        size=size,
+    )
+
+
+class DPTHead(nn.Module):
+    def __init__(self, nclass, in_channels, features, out_channels, use_bn=False, use_clstoken=False):
+        super(DPTHead, self).__init__()
+
+        self.nclass = nclass
+        self.use_clstoken = use_clstoken
+
+        self.projects = nn.ModuleList(
+            [
+                nn.Conv2d(
+                    in_channels=in_channels,
+                    out_channels=out_channel,
+                    kernel_size=1,
+                    stride=1,
+                    padding=0,
+                )
+                for out_channel in out_channels
+            ]
+        )
+
+        self.resize_layers = nn.ModuleList(
+            [
+                nn.ConvTranspose2d(
+                    in_channels=out_channels[0], out_channels=out_channels[0], kernel_size=4, stride=4, padding=0
+                ),
+                nn.ConvTranspose2d(
+                    in_channels=out_channels[1], out_channels=out_channels[1], kernel_size=2, stride=2, padding=0
+                ),
+                nn.Identity(),
+                nn.Conv2d(
+                    in_channels=out_channels[3], out_channels=out_channels[3], kernel_size=3, stride=2, padding=1
+                ),
+            ]
+        )
+
+        if use_clstoken:
+            self.readout_projects = nn.ModuleList()
+            for _ in range(len(self.projects)):
+                self.readout_projects.append(nn.Sequential(nn.Linear(2 * in_channels, in_channels), nn.GELU()))
+
+        self.scratch = _make_scratch(
+            out_channels,
+            features,
+            groups=1,
+            expand=False,
+        )
+
+        self.scratch.stem_transpose = None
+
+        self.scratch.refinenet1 = _make_fusion_block(features, use_bn)
+        self.scratch.refinenet2 = _make_fusion_block(features, use_bn)
+        self.scratch.refinenet3 = _make_fusion_block(features, use_bn)
+        self.scratch.refinenet4 = _make_fusion_block(features, use_bn)
+
+        head_features_1 = features
+        head_features_2 = 32
+
+        if nclass > 1:
+            self.scratch.output_conv = nn.Sequential(
+                nn.Conv2d(head_features_1, head_features_1, kernel_size=3, stride=1, padding=1),
+                nn.ReLU(True),
+                nn.Conv2d(head_features_1, nclass, kernel_size=1, stride=1, padding=0),
+            )
+        else:
+            self.scratch.output_conv1 = nn.Conv2d(
+                head_features_1, head_features_1 // 2, kernel_size=3, stride=1, padding=1
+            )
+
+            self.scratch.output_conv2 = nn.Sequential(
+                nn.Conv2d(head_features_1 // 2, head_features_2, kernel_size=3, stride=1, padding=1),
+                nn.ReLU(True),
+                nn.Conv2d(head_features_2, 1, kernel_size=1, stride=1, padding=0),
+                nn.ReLU(True),
+                nn.Identity(),
+            )
+
+    def forward(self, out_features, patch_h, patch_w):
+        out = []
+        for i, x in enumerate(out_features):
+            if self.use_clstoken:
+                x, cls_token = x[0], x[1]
+                readout = cls_token.unsqueeze(1).expand_as(x)
+                x = self.readout_projects[i](torch.cat((x, readout), -1))
+            else:
+                x = x[0]
+
+            x = x.permute(0, 2, 1).reshape((x.shape[0], x.shape[-1], patch_h, patch_w))
+
+            x = self.projects[i](x)
+            x = self.resize_layers[i](x)
+
+            out.append(x)
+
+        layer_1, layer_2, layer_3, layer_4 = out
+
+        layer_1_rn = self.scratch.layer1_rn(layer_1)
+        layer_2_rn = self.scratch.layer2_rn(layer_2)
+        layer_3_rn = self.scratch.layer3_rn(layer_3)
+        layer_4_rn = self.scratch.layer4_rn(layer_4)
+
+        path_4 = self.scratch.refinenet4(layer_4_rn, size=layer_3_rn.shape[2:])
+        path_3 = self.scratch.refinenet3(path_4, layer_3_rn, size=layer_2_rn.shape[2:])
+        path_2 = self.scratch.refinenet2(path_3, layer_2_rn, size=layer_1_rn.shape[2:])
+        path_1 = self.scratch.refinenet1(path_2, layer_1_rn)
+
+        out = self.scratch.output_conv1(path_1)
+        out = F.interpolate(out, (int(patch_h * 14), int(patch_w * 14)), mode="bilinear", align_corners=True)
+        out = self.scratch.output_conv2(out)
+
+        return out
+
+
+class DPT_DINOv2(nn.Module):
+    def __init__(
+        self,
+        features,
+        out_channels,
+        encoder="vitl",
+        use_bn=False,
+        use_clstoken=False,
+    ):
+        super(DPT_DINOv2, self).__init__()
+
+        assert encoder in ["vits", "vitb", "vitl"]
+
+        # # in case the Internet connection is not stable, please load the DINOv2 locally
+        # if use_local:
+        #     self.pretrained = torch.hub.load(
+        #         torchhub_path / "facebookresearch_dinov2_main",
+        #         "dinov2_{:}14".format(encoder),
+        #         source="local",
+        #         pretrained=False,
+        #     )
+        # else:
+        #     self.pretrained = torch.hub.load(
+        #         "facebookresearch/dinov2",
+        #         "dinov2_{:}14".format(encoder),
+        #     )
+
+        self.pretrained = torch.hub.load(
+            "facebookresearch/dinov2",
+            "dinov2_{:}14".format(encoder),
+        )
+
+        dim = self.pretrained.blocks[0].attn.qkv.in_features
+
+        self.depth_head = DPTHead(1, dim, features, out_channels=out_channels, use_bn=use_bn, use_clstoken=use_clstoken)
+
+    def forward(self, x):
+        h, w = x.shape[-2:]
+
+        features = self.pretrained.get_intermediate_layers(x, 4, return_class_token=True)
+
+        patch_h, patch_w = h // 14, w // 14
+
+        depth = self.depth_head(features, patch_h, patch_w)
+        depth = F.interpolate(depth, size=(h, w), mode="bilinear", align_corners=True)
+        depth = F.relu(depth)
+
+        return depth.squeeze(1)

invokeai/backend/image_util/depth_anything/utilities/util.py

@@ -0,0 +1,227 @@
+import math
+
+import cv2
+import numpy as np
+import torch
+import torch.nn.functional as F
+
+
+def apply_min_size(sample, size, image_interpolation_method=cv2.INTER_AREA):
+    """Rezise the sample to ensure the given size. Keeps aspect ratio.
+
+    Args:
+        sample (dict): sample
+        size (tuple): image size
+
+    Returns:
+        tuple: new size
+    """
+    shape = list(sample["disparity"].shape)
+
+    if shape[0] >= size[0] and shape[1] >= size[1]:
+        return sample
+
+    scale = [0, 0]
+    scale[0] = size[0] / shape[0]
+    scale[1] = size[1] / shape[1]
+
+    scale = max(scale)
+
+    shape[0] = math.ceil(scale * shape[0])
+    shape[1] = math.ceil(scale * shape[1])
+
+    # resize
+    sample["image"] = cv2.resize(sample["image"], tuple(shape[::-1]), interpolation=image_interpolation_method)
+
+    sample["disparity"] = cv2.resize(sample["disparity"], tuple(shape[::-1]), interpolation=cv2.INTER_NEAREST)
+    sample["mask"] = cv2.resize(
+        sample["mask"].astype(np.float32),
+        tuple(shape[::-1]),
+        interpolation=cv2.INTER_NEAREST,
+    )
+    sample["mask"] = sample["mask"].astype(bool)
+
+    return tuple(shape)
+
+
+class Resize(object):
+    """Resize sample to given size (width, height)."""
+
+    def __init__(
+        self,
+        width,
+        height,
+        resize_target=True,
+        keep_aspect_ratio=False,
+        ensure_multiple_of=1,
+        resize_method="lower_bound",
+        image_interpolation_method=cv2.INTER_AREA,
+    ):
+        """Init.
+
+        Args:
+            width (int): desired output width
+            height (int): desired output height
+            resize_target (bool, optional):
+                True: Resize the full sample (image, mask, target).
+                False: Resize image only.
+                Defaults to True.
+            keep_aspect_ratio (bool, optional):
+                True: Keep the aspect ratio of the input sample.
+                Output sample might not have the given width and height, and
+                resize behaviour depends on the parameter 'resize_method'.
+                Defaults to False.
+            ensure_multiple_of (int, optional):
+                Output width and height is constrained to be multiple of this parameter.
+                Defaults to 1.
+            resize_method (str, optional):
+                "lower_bound": Output will be at least as large as the given size.
+                "upper_bound": Output will be at max as large as the given size. (Output size might be smaller
+                    than given size.)
+                "minimal": Scale as least as possible.  (Output size might be smaller than given size.)
+                Defaults to "lower_bound".
+        """
+        self.__width = width
+        self.__height = height
+
+        self.__resize_target = resize_target
+        self.__keep_aspect_ratio = keep_aspect_ratio
+        self.__multiple_of = ensure_multiple_of
+        self.__resize_method = resize_method
+        self.__image_interpolation_method = image_interpolation_method
+
+    def constrain_to_multiple_of(self, x, min_val=0, max_val=None):
+        y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int)
+
+        if max_val is not None and y > max_val:
+            y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int)
+
+        if y < min_val:
+            y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int)
+
+        return y
+
+    def get_size(self, width, height):
+        # determine new height and width
+        scale_height = self.__height / height
+        scale_width = self.__width / width
+
+        if self.__keep_aspect_ratio:
+            if self.__resize_method == "lower_bound":
+                # scale such that output size is lower bound
+                if scale_width > scale_height:
+                    # fit width
+                    scale_height = scale_width
+                else:
+                    # fit height
+                    scale_width = scale_height
+            elif self.__resize_method == "upper_bound":
+                # scale such that output size is upper bound
+                if scale_width < scale_height:
+                    # fit width
+                    scale_height = scale_width
+                else:
+                    # fit height
+                    scale_width = scale_height
+            elif self.__resize_method == "minimal":
+                # scale as least as possbile
+                if abs(1 - scale_width) < abs(1 - scale_height):
+                    # fit width
+                    scale_height = scale_width
+                else:
+                    # fit height
+                    scale_width = scale_height
+            else:
+                raise ValueError(f"resize_method {self.__resize_method} not implemented")
+
+        if self.__resize_method == "lower_bound":
+            new_height = self.constrain_to_multiple_of(scale_height * height, min_val=self.__height)
+            new_width = self.constrain_to_multiple_of(scale_width * width, min_val=self.__width)
+        elif self.__resize_method == "upper_bound":
+            new_height = self.constrain_to_multiple_of(scale_height * height, max_val=self.__height)
+            new_width = self.constrain_to_multiple_of(scale_width * width, max_val=self.__width)
+        elif self.__resize_method == "minimal":
+            new_height = self.constrain_to_multiple_of(scale_height * height)
+            new_width = self.constrain_to_multiple_of(scale_width * width)
+        else:
+            raise ValueError(f"resize_method {self.__resize_method} not implemented")
+
+        return (new_width, new_height)
+
+    def __call__(self, sample):
+        width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0])
+
+        # resize sample
+        sample["image"] = cv2.resize(
+            sample["image"],
+            (width, height),
+            interpolation=self.__image_interpolation_method,
+        )
+
+        if self.__resize_target:
+            if "disparity" in sample:
+                sample["disparity"] = cv2.resize(
+                    sample["disparity"],
+                    (width, height),
+                    interpolation=cv2.INTER_NEAREST,
+                )
+
+            if "depth" in sample:
+                sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST)
+
+            if "semseg_mask" in sample:
+                # sample["semseg_mask"] = cv2.resize(
+                #     sample["semseg_mask"], (width, height), interpolation=cv2.INTER_NEAREST
+                # )
+                sample["semseg_mask"] = F.interpolate(
+                    torch.from_numpy(sample["semseg_mask"]).float()[None, None, ...], (height, width), mode="nearest"
+                ).numpy()[0, 0]
+
+            if "mask" in sample:
+                sample["mask"] = cv2.resize(
+                    sample["mask"].astype(np.float32),
+                    (width, height),
+                    interpolation=cv2.INTER_NEAREST,
+                )
+                # sample["mask"] = sample["mask"].astype(bool)
+
+        # print(sample['image'].shape, sample['depth'].shape)
+        return sample
+
+
+class NormalizeImage(object):
+    """Normlize image by given mean and std."""
+
+    def __init__(self, mean, std):
+        self.__mean = mean
+        self.__std = std
+
+    def __call__(self, sample):
+        sample["image"] = (sample["image"] - self.__mean) / self.__std
+
+        return sample
+
+
+class PrepareForNet(object):
+    """Prepare sample for usage as network input."""
+
+    def __init__(self):
+        pass
+
+    def __call__(self, sample):
+        image = np.transpose(sample["image"], (2, 0, 1))
+        sample["image"] = np.ascontiguousarray(image).astype(np.float32)
+
+        if "mask" in sample:
+            sample["mask"] = sample["mask"].astype(np.float32)
+            sample["mask"] = np.ascontiguousarray(sample["mask"])
+
+        if "depth" in sample:
+            depth = sample["depth"].astype(np.float32)
+            sample["depth"] = np.ascontiguousarray(depth)
+
+        if "semseg_mask" in sample:
+            sample["semseg_mask"] = sample["semseg_mask"].astype(np.float32)
+            sample["semseg_mask"] = np.ascontiguousarray(sample["semseg_mask"])
+
+        return sample

invokeai/backend/load_flux_model.py

@@ -0,0 +1,129 @@
+import json
+import os
+import time
+from pathlib import Path
+from typing import Union
+
+import torch
+from diffusers.models.model_loading_utils import load_state_dict
+from diffusers.models.transformers.transformer_flux import FluxTransformer2DModel
+from diffusers.utils import (
+    CONFIG_NAME,
+    SAFE_WEIGHTS_INDEX_NAME,
+    SAFETENSORS_WEIGHTS_NAME,
+    _get_checkpoint_shard_files,
+    is_accelerate_available,
+)
+from optimum.quanto import qfloat8
+from optimum.quanto.models import QuantizedDiffusersModel
+from optimum.quanto.models.shared_dict import ShardedStateDict
+
+from invokeai.backend.requantize import requantize
+
+
+class QuantizedFluxTransformer2DModel(QuantizedDiffusersModel):
+    base_class = FluxTransformer2DModel
+
+    @classmethod
+    def from_pretrained(cls, model_name_or_path: Union[str, os.PathLike]):
+        if cls.base_class is None:
+            raise ValueError("The `base_class` attribute needs to be configured.")
+
+        if not is_accelerate_available():
+            raise ValueError("Reloading a quantized diffusers model requires the accelerate library.")
+        from accelerate import init_empty_weights
+
+        if os.path.isdir(model_name_or_path):
+            # Look for a quantization map
+            qmap_path = os.path.join(model_name_or_path, cls._qmap_name())
+            if not os.path.exists(qmap_path):
+                raise ValueError(f"No quantization map found in {model_name_or_path}: is this a quantized model ?")
+
+            # Look for original model config file.
+            model_config_path = os.path.join(model_name_or_path, CONFIG_NAME)
+            if not os.path.exists(model_config_path):
+                raise ValueError(f"{CONFIG_NAME} not found in {model_name_or_path}.")
+
+            with open(qmap_path, "r", encoding="utf-8") as f:
+                qmap = json.load(f)
+
+            with open(model_config_path, "r", encoding="utf-8") as f:
+                original_model_cls_name = json.load(f)["_class_name"]
+            configured_cls_name = cls.base_class.__name__
+            if configured_cls_name != original_model_cls_name:
+                raise ValueError(
+                    f"Configured base class ({configured_cls_name}) differs from what was derived from the provided configuration ({original_model_cls_name})."
+                )
+
+            # Create an empty model
+            config = cls.base_class.load_config(model_name_or_path)
+            with init_empty_weights():
+                model = cls.base_class.from_config(config)
+
+            # Look for the index of a sharded checkpoint
+            checkpoint_file = os.path.join(model_name_or_path, SAFE_WEIGHTS_INDEX_NAME)
+            if os.path.exists(checkpoint_file):
+                # Convert the checkpoint path to a list of shards
+                _, sharded_metadata = _get_checkpoint_shard_files(model_name_or_path, checkpoint_file)
+                # Create a mapping for the sharded safetensor files
+                state_dict = ShardedStateDict(model_name_or_path, sharded_metadata["weight_map"])
+            else:
+                # Look for a single checkpoint file
+                checkpoint_file = os.path.join(model_name_or_path, SAFETENSORS_WEIGHTS_NAME)
+                if not os.path.exists(checkpoint_file):
+                    raise ValueError(f"No safetensor weights found in {model_name_or_path}.")
+                # Get state_dict from model checkpoint
+                state_dict = load_state_dict(checkpoint_file)
+
+            # Requantize and load quantized weights from state_dict
+            requantize(model, state_dict=state_dict, quantization_map=qmap)
+            model.eval()
+            return cls(model)
+        else:
+            raise NotImplementedError("Reloading quantized models directly from the hub is not supported yet.")
+
+
+def load_flux_transformer(path: Path) -> FluxTransformer2DModel:
+    # model = FluxTransformer2DModel.from_pretrained(path, local_files_only=True, torch_dtype=torch.bfloat16)
+    model_8bit_path = path / "quantized"
+    if model_8bit_path.exists():
+        # The quantized model exists, load it.
+        # TODO(ryand): The requantize(...) operation in from_pretrained(...) is very slow. This seems like
+        # something that we should be able to make much faster.
+        q_model = QuantizedFluxTransformer2DModel.from_pretrained(model_8bit_path)
+
+        # Access the underlying wrapped model.
+        # We access the wrapped model, even though it is private, because it simplifies the type checking by
+        # always returning a FluxTransformer2DModel from this function.
+        model = q_model._wrapped
+    else:
+        # The quantized model does not exist yet, quantize and save it.
+        # TODO(ryand): Loading in float16 and then quantizing seems to result in NaNs. In order to run this on
+        # GPUs that don't support bfloat16, we would need to host the quantized model instead of generating it
+        # here.
+        model = FluxTransformer2DModel.from_pretrained(path, local_files_only=True, torch_dtype=torch.bfloat16)
+        assert isinstance(model, FluxTransformer2DModel)
+
+        q_model = QuantizedFluxTransformer2DModel.quantize(model, weights=qfloat8)
+
+        model_8bit_path.mkdir(parents=True, exist_ok=True)
+        q_model.save_pretrained(model_8bit_path)
+
+        # (See earlier comment about accessing the wrapped model.)
+        model = q_model._wrapped
+
+    assert isinstance(model, FluxTransformer2DModel)
+    return model
+
+
+def main():
+    start = time.time()
+    model = load_flux_transformer(
+        Path("/data/invokeai/models/.download_cache/black-forest-labs_flux.1-schnell/FLUX.1-schnell/transformer/")
+    )
+    print(f"Time to load: {time.time() - start}s")
+    print("hi")
+
+
+if __name__ == "__main__":
+    main()

invokeai/backend/lora.py

@@ -220,17 +220,11 @@ class LoKRLayer(LoRALayerBase):
         if self.w1 is None:
             self.w1_a = values["lokr_w1_a"]
             self.w1_b = values["lokr_w1_b"]
-        else:
-            self.w1_b = None
-            self.w1_a = None
 
         self.w2 = values.get("lokr_w2", None)
         if self.w2 is None:
             self.w2_a = values["lokr_w2_a"]
             self.w2_b = values["lokr_w2_b"]
-        else:
-            self.w2_a = None
-            self.w2_b = None
 
         self.t2 = values.get("lokr_t2", None)
 
@@ -378,39 +372,7 @@ class IA3Layer(LoRALayerBase):
         self.on_input = self.on_input.to(device=device, dtype=dtype)
 
 
-class NormLayer(LoRALayerBase):
-    # bias handled in LoRALayerBase(calc_size, to)
-    # weight: torch.Tensor
-    # bias: Optional[torch.Tensor]
-
-    def __init__(
-        self,
-        layer_key: str,
-        values: Dict[str, torch.Tensor],
-    ):
-        super().__init__(layer_key, values)
-
-        self.weight = values["w_norm"]
-        self.bias = values.get("b_norm", None)
-
-        self.rank = None  # unscaled
-        self.check_keys(values, {"w_norm", "b_norm"})
-
-    def get_weight(self, orig_weight: torch.Tensor) -> torch.Tensor:
-        return self.weight
-
-    def calc_size(self) -> int:
-        model_size = super().calc_size()
-        model_size += self.weight.nelement() * self.weight.element_size()
-        return model_size
-
-    def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
-        super().to(device=device, dtype=dtype)
-
-        self.weight = self.weight.to(device=device, dtype=dtype)
-
-
-AnyLoRALayer = Union[LoRALayer, LoHALayer, LoKRLayer, FullLayer, IA3Layer, NormLayer]
+AnyLoRALayer = Union[LoRALayer, LoHALayer, LoKRLayer, FullLayer, IA3Layer]
 
 
 class LoRAModelRaw(RawModel):  # (torch.nn.Module):
@@ -551,10 +513,6 @@ class LoRAModelRaw(RawModel):  # (torch.nn.Module):
             elif "on_input" in values:
                 layer = IA3Layer(layer_key, values)
 
-            # norms
-            elif "w_norm" in values:
-                layer = NormLayer(layer_key, values)
-
             else:
                 print(f">> Encountered unknown lora layer module in {model.name}: {layer_key} - {list(values.keys())}")
                 raise Exception("Unknown lora format!")

invokeai/backend/model_manager/load/model_util.py

@@ -11,7 +11,6 @@ from diffusers.pipelines.pipeline_utils import DiffusionPipeline
 from diffusers.schedulers.scheduling_utils import SchedulerMixin
 from transformers import CLIPTokenizer
 
-from invokeai.backend.image_util.depth_anything.depth_anything_pipeline import DepthAnythingPipeline
 from invokeai.backend.image_util.grounding_dino.grounding_dino_pipeline import GroundingDinoPipeline
 from invokeai.backend.image_util.segment_anything.segment_anything_pipeline import SegmentAnythingPipeline
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
@@ -46,7 +45,6 @@ def calc_model_size_by_data(logger: logging.Logger, model: AnyModel) -> int:
             SpandrelImageToImageModel,
             GroundingDinoPipeline,
             SegmentAnythingPipeline,
-            DepthAnythingPipeline,
         ),
     ):
         return model.calc_size()

invokeai/backend/model_manager/util/select_hf_files.py

@@ -54,6 +54,7 @@ def filter_files(
                 "lora_weights.safetensors",
                 "weights.pb",
                 "onnx_data",
+                "spiece.model", # Added for `black-forest-labs/FLUX.1-schnell`.
             )
         ):
             paths.append(file)
@@ -62,7 +63,7 @@ def filter_files(
         # downloading random checkpoints that might also be in the repo. However there is no guarantee
         # that a checkpoint doesn't contain "model" in its name, and no guarantee that future diffusers models
         # will adhere to this naming convention, so this is an area to be careful of.
-        elif re.search(r"model(\.[^.]+)?\.(safetensors|bin|onnx|xml|pth|pt|ckpt|msgpack)$", file.name):
+        elif re.search(r"model.*\.(safetensors|bin|onnx|xml|pth|pt|ckpt|msgpack)$", file.name):
             paths.append(file)
 
     # limit search to subfolder if requested
@@ -97,7 +98,9 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
             if variant == ModelRepoVariant.Flax:
                 result.add(path)
 
-        elif path.suffix in [".json", ".txt"]:
+        # Note: '.model' was added to support:
+        # https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/768d12a373ed5cc9ef9a9dea7504dc09fcc14842/tokenizer_2/spiece.model
+        elif path.suffix in [".json", ".txt", ".model"]:
             result.add(path)
 
         elif variant in [
@@ -140,6 +143,23 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
             continue
 
     for candidate_list in subfolder_weights.values():
+        # Check if at least one of the files has the explicit fp16 variant.
+        at_least_one_fp16 = False
+        for candidate in candidate_list:
+            if len(candidate.path.suffixes) == 2 and candidate.path.suffixes[0] == ".fp16":
+                at_least_one_fp16 = True
+                break
+
+        if not at_least_one_fp16:
+            # If none of the candidates in this candidate_list have the explicit fp16 variant label, then this
+            # candidate_list probably doesn't adhere to the variant naming convention that we expected. In this case,
+            # we'll simply keep all the candidates. An example of a model that hits this case is
+            # `black-forest-labs/FLUX.1-schnell` (as of commit 012d2fd).
+            for candidate in candidate_list:
+                result.add(candidate.path)
+
+        # The candidate_list seems to have the expected variant naming convention. We'll select the highest scoring
+        # candidate.
         highest_score_candidate = max(candidate_list, key=lambda candidate: candidate.score)
         if highest_score_candidate:
             result.add(highest_score_candidate.path)

invokeai/backend/quantization/fast_quantized_diffusion_model.py

@@ -0,0 +1,77 @@
+import json
+import os
+from typing import Union
+
+from diffusers.models.model_loading_utils import load_state_dict
+from diffusers.utils import (
+    CONFIG_NAME,
+    SAFE_WEIGHTS_INDEX_NAME,
+    SAFETENSORS_WEIGHTS_NAME,
+    _get_checkpoint_shard_files,
+    is_accelerate_available,
+)
+from optimum.quanto.models import QuantizedDiffusersModel
+from optimum.quanto.models.shared_dict import ShardedStateDict
+
+from invokeai.backend.requantize import requantize
+
+
+class FastQuantizedDiffusersModel(QuantizedDiffusersModel):
+    @classmethod
+    def from_pretrained(cls, model_name_or_path: Union[str, os.PathLike]):
+        """We override the `from_pretrained()` method in order to use our custom `requantize()` implementation."""
+        if cls.base_class is None:
+            raise ValueError("The `base_class` attribute needs to be configured.")
+
+        if not is_accelerate_available():
+            raise ValueError("Reloading a quantized diffusers model requires the accelerate library.")
+        from accelerate import init_empty_weights
+
+        if os.path.isdir(model_name_or_path):
+            # Look for a quantization map
+            qmap_path = os.path.join(model_name_or_path, cls._qmap_name())
+            if not os.path.exists(qmap_path):
+                raise ValueError(f"No quantization map found in {model_name_or_path}: is this a quantized model ?")
+
+            # Look for original model config file.
+            model_config_path = os.path.join(model_name_or_path, CONFIG_NAME)
+            if not os.path.exists(model_config_path):
+                raise ValueError(f"{CONFIG_NAME} not found in {model_name_or_path}.")
+
+            with open(qmap_path, "r", encoding="utf-8") as f:
+                qmap = json.load(f)
+
+            with open(model_config_path, "r", encoding="utf-8") as f:
+                original_model_cls_name = json.load(f)["_class_name"]
+            configured_cls_name = cls.base_class.__name__
+            if configured_cls_name != original_model_cls_name:
+                raise ValueError(
+                    f"Configured base class ({configured_cls_name}) differs from what was derived from the provided configuration ({original_model_cls_name})."
+                )
+
+            # Create an empty model
+            config = cls.base_class.load_config(model_name_or_path)
+            with init_empty_weights():
+                model = cls.base_class.from_config(config)
+
+            # Look for the index of a sharded checkpoint
+            checkpoint_file = os.path.join(model_name_or_path, SAFE_WEIGHTS_INDEX_NAME)
+            if os.path.exists(checkpoint_file):
+                # Convert the checkpoint path to a list of shards
+                _, sharded_metadata = _get_checkpoint_shard_files(model_name_or_path, checkpoint_file)
+                # Create a mapping for the sharded safetensor files
+                state_dict = ShardedStateDict(model_name_or_path, sharded_metadata["weight_map"])
+            else:
+                # Look for a single checkpoint file
+                checkpoint_file = os.path.join(model_name_or_path, SAFETENSORS_WEIGHTS_NAME)
+                if not os.path.exists(checkpoint_file):
+                    raise ValueError(f"No safetensor weights found in {model_name_or_path}.")
+                # Get state_dict from model checkpoint
+                state_dict = load_state_dict(checkpoint_file)
+
+            # Requantize and load quantized weights from state_dict
+            requantize(model, state_dict=state_dict, quantization_map=qmap)
+            model.eval()
+            return cls(model)
+        else:
+            raise NotImplementedError("Reloading quantized models directly from the hub is not supported yet.")

invokeai/backend/quantization/fast_quantized_transformers_model.py

@@ -0,0 +1,61 @@
+import json
+import os
+from typing import Union
+
+from optimum.quanto.models import QuantizedTransformersModel
+from optimum.quanto.models.shared_dict import ShardedStateDict
+from transformers import AutoConfig
+from transformers.modeling_utils import get_checkpoint_shard_files, load_state_dict
+from transformers.utils import SAFE_WEIGHTS_INDEX_NAME, SAFE_WEIGHTS_NAME, is_accelerate_available
+
+from invokeai.backend.requantize import requantize
+
+
+class FastQuantizedTransformersModel(QuantizedTransformersModel):
+    @classmethod
+    def from_pretrained(cls, model_name_or_path: Union[str, os.PathLike]):
+        """We override the `from_pretrained()` method in order to use our custom `requantize()` implementation."""
+        if cls.auto_class is None:
+            raise ValueError(
+                "Quantized models cannot be reloaded using {cls}: use a specialized quantized class such as QuantizedModelForCausalLM instead."
+            )
+        if not is_accelerate_available():
+            raise ValueError("Reloading a quantized transformers model requires the accelerate library.")
+        from accelerate import init_empty_weights
+
+        if os.path.isdir(model_name_or_path):
+            # Look for a quantization map
+            qmap_path = os.path.join(model_name_or_path, cls._qmap_name())
+            if not os.path.exists(qmap_path):
+                raise ValueError(f"No quantization map found in {model_name_or_path}: is this a quantized model ?")
+            with open(qmap_path, "r", encoding="utf-8") as f:
+                qmap = json.load(f)
+            # Create an empty model
+            config = AutoConfig.from_pretrained(model_name_or_path)
+            with init_empty_weights():
+                model = cls.auto_class.from_config(config)
+            # Look for the index of a sharded checkpoint
+            checkpoint_file = os.path.join(model_name_or_path, SAFE_WEIGHTS_INDEX_NAME)
+            if os.path.exists(checkpoint_file):
+                # Convert the checkpoint path to a list of shards
+                checkpoint_file, sharded_metadata = get_checkpoint_shard_files(model_name_or_path, checkpoint_file)
+                # Create a mapping for the sharded safetensor files
+                state_dict = ShardedStateDict(model_name_or_path, sharded_metadata["weight_map"])
+            else:
+                # Look for a single checkpoint file
+                checkpoint_file = os.path.join(model_name_or_path, SAFE_WEIGHTS_NAME)
+                if not os.path.exists(checkpoint_file):
+                    raise ValueError(f"No safetensor weights found in {model_name_or_path}.")
+                # Get state_dict from model checkpoint
+                state_dict = load_state_dict(checkpoint_file)
+            # Requantize and load quantized weights from state_dict
+            requantize(model, state_dict=state_dict, quantization_map=qmap)
+            if getattr(model.config, "tie_word_embeddings", True):
+                # Tie output weight embeddings to input weight embeddings
+                # Note that if they were quantized they would NOT be tied
+                model.tie_weights()
+            # Set model in evaluation mode as it is done in transformers
+            model.eval()
+            return cls(model)
+        else:
+            raise NotImplementedError("Reloading quantized models directly from the hub is not supported yet.")

invokeai/backend/requantize.py

@@ -0,0 +1,53 @@
+from typing import Any, Dict
+
+import torch
+from optimum.quanto.quantize import _quantize_submodule
+
+# def custom_freeze(model: torch.nn.Module):
+#     for name, m in model.named_modules():
+#         if isinstance(m, QModuleMixin):
+#             m.weight =
+#             m.freeze()
+
+
+def requantize(
+    model: torch.nn.Module,
+    state_dict: Dict[str, Any],
+    quantization_map: Dict[str, Dict[str, str]],
+    device: torch.device = None,
+):
+    if device is None:
+        device = next(model.parameters()).device
+        if device.type == "meta":
+            device = torch.device("cpu")
+
+    # Quantize the model with parameters from the quantization map
+    for name, m in model.named_modules():
+        qconfig = quantization_map.get(name, None)
+        if qconfig is not None:
+            weights = qconfig["weights"]
+            if weights == "none":
+                weights = None
+            activations = qconfig["activations"]
+            if activations == "none":
+                activations = None
+            _quantize_submodule(model, name, m, weights=weights, activations=activations)
+
+    # Move model parameters and buffers to CPU before materializing quantized weights
+    for name, m in model.named_modules():
+
+        def move_tensor(t, device):
+            if t.device.type == "meta":
+                return torch.empty_like(t, device=device)
+            return t.to(device)
+
+        for name, param in m.named_parameters(recurse=False):
+            setattr(m, name, torch.nn.Parameter(move_tensor(param, "cpu")))
+        for name, param in m.named_buffers(recurse=False):
+            setattr(m, name, move_tensor(param, "cpu"))
+    # Freeze model and move to target device
+    # freeze(model)
+    # model.to(device)
+
+    # Load the quantized model weights
+    model.load_state_dict(state_dict, strict=False)

invokeai/backend/util/hotfixes.py

@@ -3,7 +3,7 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 import diffusers
 import torch
 from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.loaders import FromOriginalControlNetMixin
+from diffusers.loaders.single_file_model import FromOriginalModelMixin
 from diffusers.models.attention_processor import AttentionProcessor, AttnProcessor
 from diffusers.models.controlnet import ControlNetConditioningEmbedding, ControlNetOutput, zero_module
 from diffusers.models.embeddings import (
@@ -32,7 +32,7 @@ from invokeai.backend.util.logging import InvokeAILogger
 logger = InvokeAILogger.get_logger(__name__)
 
 
-class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
+class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
     """
     A ControlNet model.
 

invokeai/frontend/web/package.json

@@ -53,61 +53,61 @@
   },
   "dependencies": {
     "@chakra-ui/react-use-size": "^2.1.0",
-    "@dagrejs/dagre": "^1.1.3",
-    "@dagrejs/graphlib": "^2.2.3",
+    "@dagrejs/dagre": "^1.1.2",
+    "@dagrejs/graphlib": "^2.2.2",
     "@dnd-kit/core": "^6.1.0",
     "@dnd-kit/sortable": "^8.0.0",
     "@dnd-kit/utilities": "^3.2.2",
-    "@fontsource-variable/inter": "^5.0.20",
+    "@fontsource-variable/inter": "^5.0.18",
     "@invoke-ai/ui-library": "^0.0.25",
-    "@nanostores/react": "^0.7.3",
+    "@nanostores/react": "^0.7.2",
     "@reduxjs/toolkit": "2.2.3",
     "@roarr/browser-log-writer": "^1.3.0",
-    "chakra-react-select": "^4.9.1",
-    "compare-versions": "^6.1.1",
+    "chakra-react-select": "^4.7.6",
+    "compare-versions": "^6.1.0",
     "dateformat": "^5.0.3",
-    "fracturedjsonjs": "^4.0.2",
-    "framer-motion": "^11.3.24",
-    "i18next": "^23.12.2",
-    "i18next-http-backend": "^2.5.2",
+    "fracturedjsonjs": "^4.0.1",
+    "framer-motion": "^11.1.8",
+    "i18next": "^23.11.3",
+    "i18next-http-backend": "^2.5.1",
     "idb-keyval": "^6.2.1",
     "jsondiffpatch": "^0.6.0",
-    "konva": "^9.3.14",
+    "konva": "^9.3.6",
     "lodash-es": "^4.17.21",
-    "nanostores": "^0.11.2",
+    "nanostores": "^0.10.3",
     "new-github-issue-url": "^1.0.0",
-    "overlayscrollbars": "^2.10.0",
+    "overlayscrollbars": "^2.7.3",
     "overlayscrollbars-react": "^0.5.6",
-    "query-string": "^9.1.0",
+    "query-string": "^9.0.0",
     "react": "^18.3.1",
     "react-colorful": "^5.6.1",
     "react-dom": "^18.3.1",
     "react-dropzone": "^14.2.3",
     "react-error-boundary": "^4.0.13",
-    "react-hook-form": "^7.52.2",
+    "react-hook-form": "^7.51.4",
     "react-hotkeys-hook": "4.5.0",
-    "react-i18next": "^14.1.3",
-    "react-icons": "^5.2.1",
+    "react-i18next": "^14.1.1",
+    "react-icons": "^5.2.0",
     "react-konva": "^18.2.10",
     "react-redux": "9.1.2",
-    "react-resizable-panels": "^2.0.23",
+    "react-resizable-panels": "^2.0.19",
     "react-select": "5.8.0",
-    "react-use": "^17.5.1",
-    "react-virtuoso": "^4.9.0",
-    "reactflow": "^11.11.4",
+    "react-use": "^17.5.0",
+    "react-virtuoso": "^4.7.10",
+    "reactflow": "^11.11.3",
     "redux-dynamic-middlewares": "^2.2.0",
     "redux-remember": "^5.1.0",
     "redux-undo": "^1.1.0",
-    "rfdc": "^1.4.1",
+    "rfdc": "^1.3.1",
     "roarr": "^7.21.1",
     "serialize-error": "^11.0.3",
     "socket.io-client": "^4.7.5",
-    "use-debounce": "^10.0.2",
+    "use-debounce": "^10.0.0",
     "use-device-pixel-ratio": "^1.1.2",
     "use-image": "^1.1.1",
-    "uuid": "^10.0.0",
-    "zod": "^3.23.8",
-    "zod-validation-error": "^3.3.1"
+    "uuid": "^9.0.1",
+    "zod": "^3.23.6",
+    "zod-validation-error": "^3.2.0"
   },
   "peerDependencies": {
     "@chakra-ui/react": "^2.8.2",
@@ -118,38 +118,38 @@
   "devDependencies": {
     "@invoke-ai/eslint-config-react": "^0.0.14",
     "@invoke-ai/prettier-config-react": "^0.0.7",
-    "@storybook/addon-essentials": "^8.2.8",
-    "@storybook/addon-interactions": "^8.2.8",
-    "@storybook/addon-links": "^8.2.8",
-    "@storybook/addon-storysource": "^8.2.8",
-    "@storybook/manager-api": "^8.2.8",
-    "@storybook/react": "^8.2.8",
-    "@storybook/react-vite": "^8.2.8",
-    "@storybook/theming": "^8.2.8",
+    "@storybook/addon-essentials": "^8.0.10",
+    "@storybook/addon-interactions": "^8.0.10",
+    "@storybook/addon-links": "^8.0.10",
+    "@storybook/addon-storysource": "^8.0.10",
+    "@storybook/manager-api": "^8.0.10",
+    "@storybook/react": "^8.0.10",
+    "@storybook/react-vite": "^8.0.10",
+    "@storybook/theming": "^8.0.10",
     "@types/dateformat": "^5.0.2",
     "@types/lodash-es": "^4.17.12",
-    "@types/node": "^20.14.15",
-    "@types/react": "^18.3.3",
+    "@types/node": "^20.12.10",
+    "@types/react": "^18.3.1",
     "@types/react-dom": "^18.3.0",
-    "@types/uuid": "^10.0.0",
-    "@vitejs/plugin-react-swc": "^3.7.0",
+    "@types/uuid": "^9.0.8",
+    "@vitejs/plugin-react-swc": "^3.6.0",
     "@vitest/coverage-v8": "^1.5.0",
     "@vitest/ui": "^1.5.0",
     "concurrently": "^8.2.2",
     "dpdm": "^3.14.0",
     "eslint": "^8.57.0",
-    "eslint-plugin-i18next": "^6.0.9",
+    "eslint-plugin-i18next": "^6.0.3",
     "eslint-plugin-path": "^1.3.0",
-    "knip": "^5.27.2",
+    "knip": "^5.12.3",
     "openapi-types": "^12.1.3",
-    "openapi-typescript": "^7.3.0",
-    "prettier": "^3.3.3",
+    "openapi-typescript": "^6.7.5",
+    "prettier": "^3.2.5",
     "rollup-plugin-visualizer": "^5.12.0",
-    "storybook": "^8.2.8",
+    "storybook": "^8.0.10",
     "ts-toolbelt": "^9.6.0",
-    "tsafe": "^1.7.2",
-    "typescript": "^5.5.4",
-    "vite": "^5.4.0",
+    "tsafe": "^1.6.6",
+    "typescript": "^5.4.5",
+    "vite": "^5.2.11",
     "vite-plugin-css-injected-by-js": "^3.5.1",
     "vite-plugin-dts": "^3.9.1",
     "vite-plugin-eslint": "^1.8.1",

invokeai/frontend/web/public/locales/en.json

@@ -200,7 +200,6 @@
         "delete": "Delete",
         "depthAnything": "Depth Anything",
         "depthAnythingDescription": "Depth map generation using the Depth Anything technique",
-        "depthAnythingSmallV2": "Small V2",
         "depthMidas": "Depth (Midas)",
         "depthMidasDescription": "Depth map generation using Midas",
         "depthZoe": "Depth (Zoe)",

invokeai/frontend/web/scripts/typegen.js

@@ -1,40 +1,26 @@
 /* eslint-disable no-console */
 import fs from 'node:fs';
 
-import openapiTS, { astToString } from 'openapi-typescript';
-import ts from 'typescript';
+import openapiTS from 'openapi-typescript';
 
 const OPENAPI_URL = 'http://127.0.0.1:9090/openapi.json';
 const OUTPUT_FILE = 'src/services/api/schema.ts';
 
 async function generateTypes(schema) {
   process.stdout.write(`Generating types ${OUTPUT_FILE}...`);
-
-  // Use https://ts-ast-viewer.com to figure out how to create these AST nodes - define a type and use the bottom-left pane's output
-  // `Blob` type
-  const BLOB = ts.factory.createTypeReferenceNode(ts.factory.createIdentifier('Blob'));
-  // `null` type
-  const NULL = ts.factory.createLiteralTypeNode(ts.factory.createNull());
-  // `Record<string, unknown>` type
-  const RECORD_STRING_UNKNOWN = ts.factory.createTypeReferenceNode(ts.factory.createIdentifier('Record'), [
-    ts.factory.createKeywordTypeNode(ts.SyntaxKind.StringKeyword),
-    ts.factory.createKeywordTypeNode(ts.SyntaxKind.UnknownKeyword),
-  ]);
-
   const types = await openapiTS(schema, {
     exportType: true,
     transform: (schemaObject) => {
       if ('format' in schemaObject && schemaObject.format === 'binary') {
-        return schemaObject.nullable ? ts.factory.createUnionTypeNode([BLOB, NULL]) : BLOB;
+        return schemaObject.nullable ? 'Blob | null' : 'Blob';
       }
       if (schemaObject.title === 'MetadataField') {
         // This is `Record<string, never>` by default, but it actually accepts any a dict of any valid JSON value.
-        return RECORD_STRING_UNKNOWN;
+        return 'Record<string, unknown>';
       }
     },
-    defaultNonNullable: false,
   });
-  fs.writeFileSync(OUTPUT_FILE, astToString(types));
+  fs.writeFileSync(OUTPUT_FILE, types);
   process.stdout.write(`\nOK!\r\n`);
 }
 

invokeai/frontend/web/src/features/controlAdapters/components/processors/DepthAnyThingProcessor.tsx

@@ -42,7 +42,6 @@ const DepthAnythingProcessor = (props: Props) => {
 
   const options: { label: string; value: DepthAnythingModelSize }[] = useMemo(
     () => [
-      { label: t('controlnet.depthAnythingSmallV2'), value: 'small_v2' },
       { label: t('controlnet.small'), value: 'small' },
       { label: t('controlnet.base'), value: 'base' },
       { label: t('controlnet.large'), value: 'large' },

invokeai/frontend/web/src/features/controlAdapters/store/constants.ts

@@ -94,7 +94,7 @@ export const CONTROLNET_PROCESSORS: ControlNetProcessorsDict = {
     buildDefaults: (baseModel?: BaseModelType) => ({
       id: 'depth_anything_image_processor',
       type: 'depth_anything_image_processor',
-      model_size: 'small_v2',
+      model_size: 'small',
       resolution: baseModel === 'sdxl' ? 1024 : 512,
     }),
   },

invokeai/frontend/web/src/features/controlAdapters/store/types.ts

@@ -84,7 +84,7 @@ export type RequiredDepthAnythingImageProcessorInvocation = O.Required<
   'type' | 'model_size' | 'resolution' | 'offload'
 >;
 
-const zDepthAnythingModelSize = z.enum(['large', 'base', 'small', 'small_v2']);
+const zDepthAnythingModelSize = z.enum(['large', 'base', 'small']);
 export type DepthAnythingModelSize = z.infer<typeof zDepthAnythingModelSize>;
 export const isDepthAnythingModelSize = (v: unknown): v is DepthAnythingModelSize =>
   zDepthAnythingModelSize.safeParse(v).success;

invokeai/frontend/web/src/features/controlLayers/components/ControlAndIPAdapter/processors/DepthAnythingProcessor.tsx

@@ -24,7 +24,6 @@ export const DepthAnythingProcessor = memo(({ onChange, config }: Props) => {
 
   const options: { label: string; value: DepthAnythingModelSize }[] = useMemo(
     () => [
-      { label: t('controlnet.depthAnythingSmallV2'), value: 'small_v2' },
       { label: t('controlnet.small'), value: 'small' },
       { label: t('controlnet.base'), value: 'base' },
       { label: t('controlnet.large'), value: 'large' },

invokeai/frontend/web/src/features/controlLayers/util/controlAdapters.ts

@@ -36,7 +36,7 @@ const zContentShuffleProcessorConfig = z.object({
 });
 export type ContentShuffleProcessorConfig = z.infer<typeof zContentShuffleProcessorConfig>;
 
-const zDepthAnythingModelSize = z.enum(['large', 'base', 'small', 'small_v2']);
+const zDepthAnythingModelSize = z.enum(['large', 'base', 'small']);
 export type DepthAnythingModelSize = z.infer<typeof zDepthAnythingModelSize>;
 export const isDepthAnythingModelSize = (v: unknown): v is DepthAnythingModelSize =>
   zDepthAnythingModelSize.safeParse(v).success;
@@ -298,7 +298,7 @@ export const CA_PROCESSOR_DATA: CAProcessorsData = {
     buildDefaults: () => ({
       id: 'depth_anything_image_processor',
       type: 'depth_anything_image_processor',
-      model_size: 'small_v2',
+      model_size: 'small',
     }),
     buildNode: (image, config) => ({
       ...config,

invokeai/frontend/web/src/features/settingsAccordions/components/UpscaleSettingsAccordion/UpscaleWarning.tsx

@@ -57,11 +57,7 @@ export const UpscaleWarning = () => {
     $installModelsTab.set(3);
   }, [dispatch]);
 
-  if (modelWarnings.length && !shouldShowButton) {
-    return null;
-  }
-
-  if ((!modelWarnings.length && !otherWarnings.length) || isLoading) {
+  if ((!modelWarnings.length && !otherWarnings.length) || isLoading || !shouldShowButton) {
     return null;
   }
 

pyproject.toml

@@ -33,31 +33,35 @@ classifiers = [
 ]
 dependencies = [
   # Core generation dependencies, pinned for reproducible builds.
-  "accelerate==0.30.1",
+  "accelerate==0.33.0",
   "clip_anytorch==2.6.0",       # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
   "compel==2.0.2",
   "controlnet-aux==0.0.7",
-  "diffusers[torch]==0.27.2",
+  # TODO(ryand): Bump this once the next diffusers release is ready.
+  "diffusers[torch] @ git+https://github.com/huggingface/diffusers.git@4c6152c2fb0ade468aadb417102605a07a8635d3",
   "invisible-watermark==0.2.0", # needed to install SDXL base and refiner using their repo_ids
   "mediapipe==0.10.7",          # needed for "mediapipeface" controlnet model
   "numpy==1.26.4",              # >1.24.0 is needed to use the 'strict' argument to np.testing.assert_array_equal()
   "onnx==1.15.0",
   "onnxruntime==1.16.3",
   "opencv-python==4.9.0.80",
+  "optimum-quanto==0.2.4",
   "pytorch-lightning==2.1.3",
   "safetensors==0.4.3",
+  # sentencepiece is required to load T5TokenizerFast (used by FLUX).
+  "sentencepiece==0.2.0",
   "spandrel==0.3.4",
   "timm==0.6.13",               # needed to override timm latest in controlnet_aux, see  https://github.com/isl-org/ZoeDepth/issues/26
-  "torch==2.2.2",
+  "torch==2.4.0",
   "torchmetrics==0.11.4",
   "torchsde==0.2.6",
-  "torchvision==0.17.2",
+  "torchvision==0.19.0",
   "transformers==4.41.1",
 
   # Core application dependencies, pinned for reproducible builds.
   "fastapi-events==0.11.1",
   "fastapi==0.111.0",
-  "huggingface-hub==0.23.1",
+  "huggingface-hub==0.24.5",
   "pydantic-settings==2.2.1",
   "pydantic==2.7.2",
   "python-socketio==5.11.1",

tests/backend/model_manager/util/test_hf_model_select.py

@@ -326,3 +326,80 @@ def test_select_multiple_weights(
 ) -> None:
     filtered_files = filter_files(sd15_test_files, variant)
     assert set(filtered_files) == {Path(f) for f in expected_files}
+
+
+@pytest.fixture
+def flux_schnell_test_files() -> list[Path]:
+    return [
+        Path(f)
+        for f in [
+            "FLUX.1-schnell/.gitattributes",
+            "FLUX.1-schnell/README.md",
+            "FLUX.1-schnell/ae.safetensors",
+            "FLUX.1-schnell/flux1-schnell.safetensors",
+            "FLUX.1-schnell/model_index.json",
+            "FLUX.1-schnell/scheduler/scheduler_config.json",
+            "FLUX.1-schnell/schnell_grid.jpeg",
+            "FLUX.1-schnell/text_encoder/config.json",
+            "FLUX.1-schnell/text_encoder/model.safetensors",
+            "FLUX.1-schnell/text_encoder_2/config.json",
+            "FLUX.1-schnell/text_encoder_2/model-00001-of-00002.safetensors",
+            "FLUX.1-schnell/text_encoder_2/model-00002-of-00002.safetensors",
+            "FLUX.1-schnell/text_encoder_2/model.safetensors.index.json",
+            "FLUX.1-schnell/tokenizer/merges.txt",
+            "FLUX.1-schnell/tokenizer/special_tokens_map.json",
+            "FLUX.1-schnell/tokenizer/tokenizer_config.json",
+            "FLUX.1-schnell/tokenizer/vocab.json",
+            "FLUX.1-schnell/tokenizer_2/special_tokens_map.json",
+            "FLUX.1-schnell/tokenizer_2/spiece.model",
+            "FLUX.1-schnell/tokenizer_2/tokenizer.json",
+            "FLUX.1-schnell/tokenizer_2/tokenizer_config.json",
+            "FLUX.1-schnell/transformer/config.json",
+            "FLUX.1-schnell/transformer/diffusion_pytorch_model-00001-of-00003.safetensors",
+            "FLUX.1-schnell/transformer/diffusion_pytorch_model-00002-of-00003.safetensors",
+            "FLUX.1-schnell/transformer/diffusion_pytorch_model-00003-of-00003.safetensors",
+            "FLUX.1-schnell/transformer/diffusion_pytorch_model.safetensors.index.json",
+            "FLUX.1-schnell/vae/config.json",
+            "FLUX.1-schnell/vae/diffusion_pytorch_model.safetensors",
+        ]
+    ]
+
+
+@pytest.mark.parametrize(
+    ["variant", "expected_files"],
+    [
+        (
+            ModelRepoVariant.Default,
+            [
+                "FLUX.1-schnell/model_index.json",
+                "FLUX.1-schnell/scheduler/scheduler_config.json",
+                "FLUX.1-schnell/text_encoder/config.json",
+                "FLUX.1-schnell/text_encoder/model.safetensors",
+                "FLUX.1-schnell/text_encoder_2/config.json",
+                "FLUX.1-schnell/text_encoder_2/model-00001-of-00002.safetensors",
+                "FLUX.1-schnell/text_encoder_2/model-00002-of-00002.safetensors",
+                "FLUX.1-schnell/text_encoder_2/model.safetensors.index.json",
+                "FLUX.1-schnell/tokenizer/merges.txt",
+                "FLUX.1-schnell/tokenizer/special_tokens_map.json",
+                "FLUX.1-schnell/tokenizer/tokenizer_config.json",
+                "FLUX.1-schnell/tokenizer/vocab.json",
+                "FLUX.1-schnell/tokenizer_2/special_tokens_map.json",
+                "FLUX.1-schnell/tokenizer_2/spiece.model",
+                "FLUX.1-schnell/tokenizer_2/tokenizer.json",
+                "FLUX.1-schnell/tokenizer_2/tokenizer_config.json",
+                "FLUX.1-schnell/transformer/config.json",
+                "FLUX.1-schnell/transformer/diffusion_pytorch_model-00001-of-00003.safetensors",
+                "FLUX.1-schnell/transformer/diffusion_pytorch_model-00002-of-00003.safetensors",
+                "FLUX.1-schnell/transformer/diffusion_pytorch_model-00003-of-00003.safetensors",
+                "FLUX.1-schnell/transformer/diffusion_pytorch_model.safetensors.index.json",
+                "FLUX.1-schnell/vae/config.json",
+                "FLUX.1-schnell/vae/diffusion_pytorch_model.safetensors",
+            ],
+        ),
+    ],
+)
+def test_select_flux_schnell_files(
+    flux_schnell_test_files: list[Path], variant: ModelRepoVariant, expected_files: list[str]
+) -> None:
+    filtered_files = filter_files(flux_schnell_test_files, variant)
+    assert set(filtered_files) == {Path(f) for f in expected_files}