Load single-file checkpoints directly without conversion (#6510)

* use model_class.load_singlefile() instead of converting; works, but performance is poor

* adjust the convert api - not right just yet

* working, needs sql migrator update

* rename migration_11 before conflict merge with main

* Update invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py

Co-authored-by: Ryan Dick <[email protected]>

* Update invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py

Co-authored-by: Ryan Dick <[email protected]>

* implement lightweight version-by-version config migration

* simplified config schema migration code

* associate sdxl config with sdxl VAEs

* remove use of original_config_file in load_single_file()

---------

Co-authored-by: Lincoln Stein <[email protected]>
Co-authored-by: Ryan Dick <[email protected]>

Author: 3 people

invokeai/app/api/routers/model_manager.py

@@ -3,9 +3,9 @@
 
 import io
 import pathlib
-import shutil
 import traceback
 from copy import deepcopy
+from tempfile import TemporaryDirectory
 from typing import Any, Dict, List, Optional, Type
 
 from fastapi import Body, Path, Query, Response, UploadFile
@@ -19,7 +19,6 @@
 from invokeai.app.services.model_images.model_images_common import ModelImageFileNotFoundException
 from invokeai.app.services.model_install.model_install_common import ModelInstallJob
 from invokeai.app.services.model_records import (
-    DuplicateModelException,
     InvalidModelException,
     ModelRecordChanges,
     UnknownModelException,
@@ -30,7 +29,6 @@
     MainCheckpointConfig,
     ModelFormat,
     ModelType,
-    SubModelType,
 )
 from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
 from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
@@ -174,18 +172,6 @@ async def get_model_record(
         raise HTTPException(status_code=404, detail=str(e))
 
 
-# @model_manager_router.get("/summary", operation_id="list_model_summary")
-# async def list_model_summary(
-#     page: int = Query(default=0, description="The page to get"),
-#     per_page: int = Query(default=10, description="The number of models per page"),
-#     order_by: ModelRecordOrderBy = Query(default=ModelRecordOrderBy.Default, description="The attribute to order by"),
-# ) -> PaginatedResults[ModelSummary]:
-#     """Gets a page of model summary data."""
-#     record_store = ApiDependencies.invoker.services.model_manager.store
-#     results: PaginatedResults[ModelSummary] = record_store.list_models(page=page, per_page=per_page, order_by=order_by)
-#     return results
-
-
 class FoundModel(BaseModel):
     path: str = Field(description="Path to the model")
     is_installed: bool = Field(description="Whether or not the model is already installed")
@@ -746,39 +732,36 @@ async def convert_model(
         logger.error(f"The model with key {key} is not a main checkpoint model.")
         raise HTTPException(400, f"The model with key {key} is not a main checkpoint model.")
 
-    # loading the model will convert it into a cached diffusers file
-    try:
-        cc_size = loader.convert_cache.max_size
-        if cc_size == 0:  # temporary set the convert cache to a positive number so that cached model is written
-            loader._convert_cache.max_size = 1.0
-        loader.load_model(model_config, submodel_type=SubModelType.Scheduler)
-    finally:
-        loader._convert_cache.max_size = cc_size
-
-    # Get the path of the converted model from the loader
-    cache_path = loader.convert_cache.cache_path(key)
-    assert cache_path.exists()
-
-    # temporarily rename the original safetensors file so that there is no naming conflict
-    original_name = model_config.name
-    model_config.name = f"{original_name}.DELETE"
-    changes = ModelRecordChanges(name=model_config.name)
-    store.update_model(key, changes=changes)
-
-    # install the diffusers
-    try:
-        new_key = installer.install_path(
-            cache_path,
-            config={
-                "name": original_name,
-                "description": model_config.description,
-                "hash": model_config.hash,
-                "source": model_config.source,
-            },
-        )
-    except DuplicateModelException as e:
-        logger.error(str(e))
-        raise HTTPException(status_code=409, detail=str(e))
+    with TemporaryDirectory(dir=ApiDependencies.invoker.services.configuration.models_path) as tmpdir:
+        convert_path = pathlib.Path(tmpdir) / pathlib.Path(model_config.path).stem
+        converted_model = loader.load_model(model_config)
+        # write the converted file to the convert path
+        raw_model = converted_model.model
+        assert hasattr(raw_model, "save_pretrained")
+        raw_model.save_pretrained(convert_path)
+        assert convert_path.exists()
+
+        # temporarily rename the original safetensors file so that there is no naming conflict
+        original_name = model_config.name
+        model_config.name = f"{original_name}.DELETE"
+        changes = ModelRecordChanges(name=model_config.name)
+        store.update_model(key, changes=changes)
+
+        # install the diffusers
+        try:
+            new_key = installer.install_path(
+                convert_path,
+                config={
+                    "name": original_name,
+                    "description": model_config.description,
+                    "hash": model_config.hash,
+                    "source": model_config.source,
+                },
+            )
+        except Exception as e:
+            logger.error(str(e))
+            store.update_model(key, changes=ModelRecordChanges(name=original_name))
+            raise HTTPException(status_code=409, detail=str(e))
 
     # Update the model image if the model had one
     try:
@@ -791,8 +774,8 @@ async def convert_model(
     # delete the original safetensors file
     installer.delete(key)
 
-    # delete the cached version
-    shutil.rmtree(cache_path)
+    # delete the temporary directory
+    # shutil.rmtree(cache_path)
 
     # return the config record for the new diffusers directory
     new_config = store.get_model(new_key)

invokeai/app/services/config/config_default.py

@@ -3,6 +3,7 @@
 
 from __future__ import annotations
 
+import copy
 import locale
 import os
 import re
@@ -25,14 +26,13 @@
 LEGACY_INIT_FILE = Path("invokeai.init")
 DEFAULT_RAM_CACHE = 10.0
 DEFAULT_VRAM_CACHE = 0.25
-DEFAULT_CONVERT_CACHE = 20.0
 DEVICE = Literal["auto", "cpu", "cuda", "cuda:1", "mps"]
 PRECISION = Literal["auto", "float16", "bfloat16", "float32"]
 ATTENTION_TYPE = Literal["auto", "normal", "xformers", "sliced", "torch-sdp"]
 ATTENTION_SLICE_SIZE = Literal["auto", "balanced", "max", 1, 2, 3, 4, 5, 6, 7, 8]
 LOG_FORMAT = Literal["plain", "color", "syslog", "legacy"]
 LOG_LEVEL = Literal["debug", "info", "warning", "error", "critical"]
-CONFIG_SCHEMA_VERSION = "4.0.1"
+CONFIG_SCHEMA_VERSION = "4.0.2"
 
 
 def get_default_ram_cache_size() -> float:
@@ -85,7 +85,7 @@ class InvokeAIAppConfig(BaseSettings):
         log_tokenization: Enable logging of parsed prompt tokens.
         patchmatch: Enable patchmatch inpaint code.
         models_dir: Path to the models directory.
-        convert_cache_dir: Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.
+        convert_cache_dir: Path to the converted models cache directory (DEPRECATED, but do not delete because it is needed for migration from previous versions).
         download_cache_dir: Path to the directory that contains dynamically downloaded models.
         legacy_conf_dir: Path to directory of legacy checkpoint config files.
         db_dir: Path to InvokeAI databases directory.
@@ -102,7 +102,6 @@ class InvokeAIAppConfig(BaseSettings):
         profiles_dir: Path to profiles output directory.
         ram: Maximum memory amount used by memory model cache for rapid switching (GB).
         vram: Amount of VRAM reserved for model storage (GB).
-        convert_cache: Maximum size of on-disk converted models cache (GB).
         lazy_offload: Keep models in VRAM until their space is needed.
         log_memory_usage: If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.
         device: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.<br>Valid values: `auto`, `cpu`, `cuda`, `cuda:1`, `mps`
@@ -148,7 +147,7 @@ class InvokeAIAppConfig(BaseSettings):
 
     # PATHS
     models_dir:                    Path = Field(default=Path("models"),     description="Path to the models directory.")
-    convert_cache_dir:             Path = Field(default=Path("models/.convert_cache"), description="Path to the converted models cache directory. When loading a non-diffusers model, it will be converted and store on disk at this location.")
+    convert_cache_dir:             Path = Field(default=Path("models/.convert_cache"), description="Path to the converted models cache directory (DEPRECATED, but do not delete because it is needed for migration from previous versions).")
     download_cache_dir:            Path = Field(default=Path("models/.download_cache"), description="Path to the directory that contains dynamically downloaded models.")
     legacy_conf_dir:               Path = Field(default=Path("configs"), description="Path to directory of legacy checkpoint config files.")
     db_dir:                        Path = Field(default=Path("databases"),  description="Path to InvokeAI databases directory.")
@@ -170,9 +169,8 @@ class InvokeAIAppConfig(BaseSettings):
     profiles_dir:                  Path = Field(default=Path("profiles"),   description="Path to profiles output directory.")
 
     # CACHE
-    ram:                          float = Field(default_factory=get_default_ram_cache_size, gt=0, description="Maximum memory amount used by memory model cache for rapid switching (GB).")
-    vram:                         float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (GB).")
-    convert_cache:                float = Field(default=DEFAULT_CONVERT_CACHE, ge=0, description="Maximum size of on-disk converted models cache (GB).")
+    ram:                           float = Field(default_factory=get_default_ram_cache_size, gt=0, description="Maximum memory amount used by memory model cache for rapid switching (GB).")
+    vram:                          float = Field(default=DEFAULT_VRAM_CACHE, ge=0, description="Amount of VRAM reserved for model storage (GB).")
     lazy_offload:                  bool = Field(default=True,               description="Keep models in VRAM until their space is needed.")
     log_memory_usage:              bool = Field(default=False,              description="If True, a memory snapshot will be captured before and after every model cache operation, and the result will be logged (at debug level). There is a time cost to capturing the memory snapshots, so it is recommended to only enable this feature if you are actively inspecting the model cache's behaviour.")
 
@@ -357,14 +355,14 @@ def settings_customise_sources(
         return (init_settings,)
 
 
-def migrate_v3_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
-    """Migrate a v3 config dictionary to a current config object.
+def migrate_v3_config_dict(config_dict: dict[str, Any]) -> dict[str, Any]:
+    """Migrate a v3 config dictionary to a v4.0.0.
 
     Args:
         config_dict: A dictionary of settings from a v3 config file.
 
     Returns:
-        An instance of `InvokeAIAppConfig` with the migrated settings.
+        An `InvokeAIAppConfig` config dict.
 
     """
     parsed_config_dict: dict[str, Any] = {}
@@ -398,32 +396,41 @@ def migrate_v3_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
             elif k in InvokeAIAppConfig.model_fields:
                 # skip unknown fields
                 parsed_config_dict[k] = v
-    # When migrating the config file, we should not include currently-set environment variables.
-    config = DefaultInvokeAIAppConfig.model_validate(parsed_config_dict)
-
-    return config
+    parsed_config_dict["schema_version"] = "4.0.0"
+    return parsed_config_dict
 
 
-def migrate_v4_0_0_config_dict(config_dict: dict[str, Any]) -> InvokeAIAppConfig:
-    """Migrate v4.0.0 config dictionary to a current config object.
+def migrate_v4_0_0_to_4_0_1_config_dict(config_dict: dict[str, Any]) -> dict[str, Any]:
+    """Migrate v4.0.0 config dictionary to a v4.0.1 config dictionary
 
     Args:
         config_dict: A dictionary of settings from a v4.0.0 config file.
 
     Returns:
-        An instance of `InvokeAIAppConfig` with the migrated settings.
+        A config dict with the settings migrated to v4.0.1.
     """
-    parsed_config_dict: dict[str, Any] = {}
-    for k, v in config_dict.items():
-        # autocast was removed from precision in v4.0.1
-        if k == "precision" and v == "autocast":
-            parsed_config_dict["precision"] = "auto"
-        else:
-            parsed_config_dict[k] = v
-        if k == "schema_version":
-            parsed_config_dict[k] = CONFIG_SCHEMA_VERSION
-    config = DefaultInvokeAIAppConfig.model_validate(parsed_config_dict)
-    return config
+    parsed_config_dict: dict[str, Any] = copy.deepcopy(config_dict)
+    # precision "autocast" was replaced by "auto" in v4.0.1
+    if parsed_config_dict.get("precision") == "autocast":
+        parsed_config_dict["precision"] = "auto"
+    parsed_config_dict["schema_version"] = "4.0.1"
+    return parsed_config_dict
+
+
+def migrate_v4_0_1_to_4_0_2_config_dict(config_dict: dict[str, Any]) -> dict[str, Any]:
+    """Migrate v4.0.1 config dictionary to a v4.0.2 config dictionary.
+
+    Args:
+        config_dict: A dictionary of settings from a v4.0.1 config file.
+
+    Returns:
+        An config dict with the settings migrated to v4.0.2.
+    """
+    parsed_config_dict: dict[str, Any] = copy.deepcopy(config_dict)
+    # convert_cache was removed in 4.0.2
+    parsed_config_dict.pop("convert_cache", None)
+    parsed_config_dict["schema_version"] = "4.0.2"
+    return parsed_config_dict
 
 
 def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
@@ -437,27 +444,31 @@ def load_and_migrate_config(config_path: Path) -> InvokeAIAppConfig:
     """
     assert config_path.suffix == ".yaml"
     with open(config_path, "rt", encoding=locale.getpreferredencoding()) as file:
-        loaded_config_dict = yaml.safe_load(file)
+        loaded_config_dict: dict[str, Any] = yaml.safe_load(file)
 
     assert isinstance(loaded_config_dict, dict)
 
+    migrated = False
     if "InvokeAI" in loaded_config_dict:
-        # This is a v3 config file, attempt to migrate it
+        migrated = True
+        loaded_config_dict = migrate_v3_config_dict(loaded_config_dict)  # pyright: ignore [reportUnknownArgumentType]
+    if loaded_config_dict["schema_version"] == "4.0.0":
+        migrated = True
+        loaded_config_dict = migrate_v4_0_0_to_4_0_1_config_dict(loaded_config_dict)
+    if loaded_config_dict["schema_version"] == "4.0.1":
+        migrated = True
+        loaded_config_dict = migrate_v4_0_1_to_4_0_2_config_dict(loaded_config_dict)
+
+    if migrated:
         shutil.copy(config_path, config_path.with_suffix(".yaml.bak"))
         try:
-            # loaded_config_dict could be the wrong shape, but we will catch all exceptions below
-            migrated_config = migrate_v3_config_dict(loaded_config_dict)  # pyright: ignore [reportUnknownArgumentType]
+            # load and write without environment variables
+            migrated_config = DefaultInvokeAIAppConfig.model_validate(loaded_config_dict)
+            migrated_config.write_file(config_path)
         except Exception as e:
             shutil.copy(config_path.with_suffix(".yaml.bak"), config_path)
             raise RuntimeError(f"Failed to load and migrate v3 config file {config_path}: {e}") from e
-        migrated_config.write_file(config_path)
-        return migrated_config
-
-    if loaded_config_dict["schema_version"] == "4.0.0":
-        loaded_config_dict = migrate_v4_0_0_config_dict(loaded_config_dict)
-        loaded_config_dict.write_file(config_path)
 
-    # Attempt to load as a v4 config file
     try:
         # Meta is not included in the model fields, so we need to validate it separately
         config = InvokeAIAppConfig.model_validate(loaded_config_dict)

invokeai/app/services/model_load/model_load_base.py

@@ -7,7 +7,6 @@
 
 from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
 from invokeai.backend.model_manager.load import LoadedModel, LoadedModelWithoutConfig
-from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
 from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 
 
@@ -28,11 +27,6 @@ def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubMo
     def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the RAM cache used by this loader."""
 
-    @property
-    @abstractmethod
-    def convert_cache(self) -> ModelConvertCacheBase:
-        """Return the checkpoint convert cache used by this loader."""
-
     @abstractmethod
     def load_model_from_path(
         self, model_path: Path, loader: Optional[Callable[[Path], AnyModel]] = None

invokeai/app/services/model_load/model_load_default.py

@@ -17,7 +17,6 @@
     ModelLoaderRegistry,
     ModelLoaderRegistryBase,
 )
-from invokeai.backend.model_manager.load.convert_cache import ModelConvertCacheBase
 from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import GenericDiffusersLoader
 from invokeai.backend.util.devices import TorchDevice
@@ -33,7 +32,6 @@ def __init__(
         self,
         app_config: InvokeAIAppConfig,
         ram_cache: ModelCacheBase[AnyModel],
-        convert_cache: ModelConvertCacheBase,
         registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
     ):
         """Initialize the model load service."""
@@ -42,7 +40,6 @@ def __init__(
         self._logger = logger
         self._app_config = app_config
         self._ram_cache = ram_cache
-        self._convert_cache = convert_cache
         self._registry = registry
 
     def start(self, invoker: Invoker) -> None:
@@ -53,11 +50,6 @@ def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the RAM cache used by this loader."""
         return self._ram_cache
 
-    @property
-    def convert_cache(self) -> ModelConvertCacheBase:
-        """Return the checkpoint convert cache used by this loader."""
-        return self._convert_cache
-
     def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
         """
         Given a model's configuration, load it and return the LoadedModel object.
@@ -76,7 +68,6 @@ def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubMo
             app_config=self._app_config,
             logger=self._logger,
             ram_cache=self._ram_cache,
-            convert_cache=self._convert_cache,
         ).load_model(model_config, submodel_type)
 
         if hasattr(self, "_invoker"):

invokeai/app/services/model_manager/model_manager_default.py

@@ -7,7 +7,7 @@
 from typing_extensions import Self
 
 from invokeai.app.services.invoker import Invoker
-from invokeai.backend.model_manager.load import ModelCache, ModelConvertCache, ModelLoaderRegistry
+from invokeai.backend.model_manager.load import ModelCache, ModelLoaderRegistry
 from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
 
@@ -86,11 +86,9 @@ def build_model_manager(
             logger=logger,
             execution_device=execution_device or TorchDevice.choose_torch_device(),
         )
-        convert_cache = ModelConvertCache(cache_path=app_config.convert_cache_path, max_size=app_config.convert_cache)
         loader = ModelLoadService(
             app_config=app_config,
             ram_cache=ram_cache,
-            convert_cache=convert_cache,
             registry=ModelLoaderRegistry,
         )
         installer = ModelInstallService(