Branch for invokeai 3.0-beta bugfixes (#3683)

Model installer and documentation fixes for the beta branch.

installer/templates/invoke.bat.in

@@ -20,7 +20,7 @@ echo 9. Update InvokeAI
 echo 10. Command-line help
 echo Q - Quit
 set /P choice="Please enter 1-10, Q: [2] "
-if not defined choice set choice=2
+if not defined choice set choice=1
 IF /I "%choice%" == "1" (
     echo Starting the InvokeAI browser-based UI..
     python .venv\Scripts\invokeai-web.exe %*
@@ -56,7 +56,7 @@ IF /I "%choice%" == "1" (
     call cmd /k
 ) ELSE IF /I "%choice%" == "9" (
    echo Running invokeai-update...
-   python .venv\Scripts\invokeai-update.exe %*
+   python -m invokeai.frontend.install.invokeai_update
 ) ELSE IF /I "%choice%" == "10" (
     echo Displaying command line help...
     python .venv\Scripts\invokeai.exe --help %*

installer/templates/invoke.sh.in

@@ -93,7 +93,7 @@ do_choice() {
     9)
         clear
         printf "Update InvokeAI\n"
-        invokeai-update
+        python -m invokeai.frontend.install.invokeai_update
         ;;
     10)
         clear

invokeai/app/api/dependencies.py

@@ -17,6 +17,7 @@ from invokeai.app.services.metadata import CoreMetadataService
 from invokeai.app.services.resource_name import SimpleNameService
 from invokeai.app.services.urls import LocalUrlService
 from invokeai.backend.util.logging import InvokeAILogger
+from invokeai.version.invokeai_version import __version__
 
 from ..services.default_graphs import create_system_graphs
 from ..services.latent_storage import DiskLatentsStorage, ForwardCacheLatentsStorage
@@ -58,7 +59,8 @@ class ApiDependencies:
 
     @staticmethod
     def initialize(config, event_handler_id: int, logger: Logger = logger):
-        logger.info(f"Internet connectivity is {config.internet_available}")
+        logger.debug(f'InvokeAI version {__version__}')
+        logger.debug(f"Internet connectivity is {config.internet_available}")
 
         events = FastAPIEventService(event_handler_id)
 

invokeai/app/api_app.py

@@ -1,5 +1,6 @@
-# Copyright (c) 2022 Kyle Schouviller (https://github.com/kyle0654)
+# Copyright (c) 2022-2023 Kyle Schouviller (https://github.com/kyle0654) and the InvokeAI Team
 import asyncio
+import sys
 from inspect import signature
 
 import uvicorn
@@ -20,6 +21,13 @@ from ..backend.util.logging import InvokeAILogger
 app_config = InvokeAIAppConfig.get_config()
 app_config.parse_args()
 logger = InvokeAILogger.getLogger(config=app_config)
+from invokeai.version.invokeai_version import __version__
+
+# we call this early so that the message appears before
+# other invokeai initialization messages
+if app_config.version:
+    print(f'InvokeAI version {__version__}')
+    sys.exit(0)
 
 import invokeai.frontend.web as web_dir
 import mimetypes
@@ -28,6 +36,7 @@ from .api.dependencies import ApiDependencies
 from .api.routers import sessions, models, images, boards, board_images, app_info
 from .api.sockets import SocketIO
 from .invocations.baseinvocation import BaseInvocation
+    
 
 import torch
 if torch.backends.mps.is_available():

invokeai/app/cli_app.py

@@ -16,6 +16,12 @@ from invokeai.backend.util.logging import InvokeAILogger
 config = InvokeAIAppConfig.get_config()
 config.parse_args()
 logger = InvokeAILogger().getLogger(config=config)
+from invokeai.version.invokeai_version import __version__
+
+# we call this early so that the message appears before other invokeai initialization messages
+if config.version:
+    print(f'InvokeAI version {__version__}')
+    sys.exit(0)
 
 from invokeai.app.services.board_image_record_storage import (
     SqliteBoardImageRecordStorage,
@@ -208,6 +214,7 @@ def invoke_all(context: CliContext):
         raise SessionError()
 
 def invoke_cli():
+    logger.info(f'InvokeAI version {__version__}')
     # get the optional list of invocations to execute on the command line
     parser = config.get_parser()
     parser.add_argument('commands',nargs='*')

invokeai/app/services/config.py

@@ -23,7 +23,8 @@ InvokeAI:
     xformers_enabled: false
     sequential_guidance: false
     precision: float16
-    max_loaded_models: 4
+    max_cache_size: 6
+    max_vram_cache_size: 2.7
     always_use_cpu: false
     free_gpu_mem: false
   Features:
@@ -168,7 +169,7 @@ from argparse import ArgumentParser
 from omegaconf import OmegaConf, DictConfig
 from pathlib import Path
 from pydantic import BaseSettings, Field, parse_obj_as
-from typing import ClassVar, Dict, List, Literal, Union, get_origin, get_type_hints, get_args
+from typing import ClassVar, Dict, List, Set, Literal, Union, get_origin, get_type_hints, get_args
 
 INIT_FILE = Path('invokeai.yaml')
 MODEL_CORE = Path('models/core')
@@ -270,7 +271,8 @@ class InvokeAISettings(BaseSettings):
 
     @classmethod
     def _excluded(self)->List[str]:
-        return ['type','initconf']
+        # combination of deprecated parameters and internal ones
+        return ['type','initconf', 'gpu_mem_reserved', 'max_loaded_models', 'version']
 
     class Config:
         env_file_encoding = 'utf-8'
@@ -363,8 +365,10 @@ setting environment variables INVOKEAI_<setting>.
 
     always_use_cpu      : bool = Field(default=False, description="If true, use the CPU for rendering even if a GPU is available.", category='Memory/Performance')
     free_gpu_mem        : bool = Field(default=False, description="If true, purge model from GPU after each generation.", category='Memory/Performance')
-    max_loaded_models   : int = Field(default=3, gt=0, description="(DEPRECATED: use max_cache_size) Maximum number of models to keep in memory for rapid switching", category='Memory/Performance')
+    max_loaded_models   : int = Field(default=3, gt=0, description="(DEPRECATED: use max_cache_size) Maximum number of models to keep in memory for rapid switching", category='DEPRECATED')
     max_cache_size      : float = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
+    max_vram_cache_size : float = Field(default=2.75, ge=0, description="Amount of VRAM reserved for model storage", category='Memory/Performance')
+    gpu_mem_reserved    : float = Field(default=2.75, ge=0, description="DEPRECATED: use max_vram_cache_size. Amount of VRAM reserved for model storage", category='DEPRECATED')
     precision           : Literal[tuple(['auto','float16','float32','autocast'])] = Field(default='float16',description='Floating point precision', category='Memory/Performance')
     sequential_guidance : bool = Field(default=False, description="Whether to calculate guidance in serial instead of in parallel, lowering memory requirements", category='Memory/Performance')
     xformers_enabled    : bool = Field(default=True, description="Enable/disable memory-efficient attention", category='Memory/Performance')
@@ -389,6 +393,8 @@ setting environment variables INVOKEAI_<setting>.
     # note - would be better to read the log_format values from logging.py, but this creates circular dependencies issues
     log_format          : Literal[tuple(['plain','color','syslog','legacy'])] = Field(default="color", description='Log format. Use "plain" for text-only, "color" for colorized output, "legacy" for 2.3-style logging and "syslog" for syslog-style', category="Logging")
     log_level           : Literal[tuple(["debug","info","warning","error","critical"])] = Field(default="debug", description="Emit logging messages at this level or  higher", category="Logging")
+
+    version             : bool = Field(default=False, description="Show InvokeAI version and exit", category="Other")
     #fmt: on
 
     def parse_args(self, argv: List[str]=None, conf: DictConfig = None, clobber=False):

invokeai/app/services/model_manager_service.py

@@ -258,9 +258,7 @@ class ModelManagerService(ModelManagerServiceBase):
             config_file = config.model_conf_path
         else:
             config_file = config.root_dir / "configs/models.yaml"
-        if not config_file.exists():
-            raise IOError(f"The file {config_file} could not be found.")
-
+            
         logger.debug(f'config file={config_file}')
 
         device = torch.device(choose_torch_device())

invokeai/app/services/processor.py

@@ -104,6 +104,7 @@ class DefaultInvocationProcessor(InvocationProcessorABC):
 
                 except Exception as e:
                     error = traceback.format_exc()
+                    logger.error(error)
 
                     # Save error
                     graph_execution_state.set_node_error(invocation.id, error)

invokeai/backend/model_management/model_cache.py

@@ -36,6 +36,9 @@ from .models import BaseModelType, ModelType, SubModelType, ModelBase
 # Default is roughly enough to hold three fp16 diffusers models in RAM simultaneously
 DEFAULT_MAX_CACHE_SIZE = 6.0
 
+# amount of GPU memory to hold in reserve for use by generations (GB)
+DEFAULT_MAX_VRAM_CACHE_SIZE= 2.75
+
 # actual size of a gig
 GIG = 1073741824
 
@@ -82,6 +85,7 @@ class ModelCache(object):
     def __init__(
         self,
         max_cache_size: float=DEFAULT_MAX_CACHE_SIZE,
+        max_vram_cache_size: float=DEFAULT_MAX_VRAM_CACHE_SIZE,
         execution_device: torch.device=torch.device('cuda'),
         storage_device: torch.device=torch.device('cpu'),
         precision: torch.dtype=torch.float16,
@@ -99,12 +103,11 @@ class ModelCache(object):
         :param sequential_offload: Conserve VRAM by loading and unloading each stage of the pipeline sequentially
         :param sha_chunksize: Chunksize to use when calculating sha256 model hash
         '''
-        #max_cache_size = 9999
         self.model_infos: Dict[str, ModelBase] = dict()
         self.lazy_offloading = lazy_offloading
-        #self.sequential_offload: bool=sequential_offload
         self.precision: torch.dtype=precision
-        self.max_cache_size: int=max_cache_size
+        self.max_cache_size: float=max_cache_size
+        self.max_vram_cache_size: float=max_vram_cache_size
         self.execution_device: torch.device=execution_device
         self.storage_device: torch.device=storage_device
         self.sha_chunksize=sha_chunksize
@@ -201,14 +204,22 @@ class ModelCache(object):
             self._cache_stack.remove(key)
         self._cache_stack.append(key)
 
-        return self.ModelLocker(self, key, cache_entry.model, gpu_load)
+        return self.ModelLocker(self, key, cache_entry.model, gpu_load, cache_entry.size)
 
     class ModelLocker(object):
-        def __init__(self, cache, key, model, gpu_load):
+        def __init__(self, cache, key, model, gpu_load, size_needed):
+            '''
+            :param cache: The model_cache object
+            :param key: The key of the model to lock in GPU
+            :param model: The model to lock
+            :param gpu_load: True if load into gpu
+            :param size_needed: Size of the model to load
+            '''
             self.gpu_load = gpu_load
             self.cache = cache
             self.key = key
             self.model = model
+            self.size_needed = size_needed
             self.cache_entry = self.cache._cached_models[self.key]
 
         def __enter__(self) -> Any:
@@ -222,7 +233,7 @@ class ModelCache(object):
 
                 try:
                     if self.cache.lazy_offloading:
-                       self.cache._offload_unlocked_models()
+                       self.cache._offload_unlocked_models(self.size_needed)
                        
                     if self.model.device != self.cache.execution_device:
                         self.cache.logger.debug(f'Moving {self.key} into {self.cache.execution_device}')
@@ -337,14 +348,20 @@ class ModelCache(object):
 
         self.logger.debug(f"After unloading: cached_models={len(self._cached_models)}")
 
-
-    def _offload_unlocked_models(self):
-        for model_key, cache_entry in self._cached_models.items():
+    def _offload_unlocked_models(self, size_needed: int=0):
+        reserved = self.max_vram_cache_size * GIG
+        vram_in_use = torch.cuda.memory_allocated()
+        self.logger.debug(f'{(vram_in_use/GIG):.2f}GB VRAM used for models; max allowed={(reserved/GIG):.2f}GB')
+        for model_key, cache_entry in sorted(self._cached_models.items(), key=lambda x:x[1].size):
+            if vram_in_use <= reserved:
+                break
             if not cache_entry.locked and cache_entry.loaded:
                 self.logger.debug(f'Offloading {model_key} from {self.execution_device} into {self.storage_device}')
                 with VRAMUsage() as mem:
                     cache_entry.model.to(self.storage_device)
                 self.logger.debug(f'GPU VRAM freed: {(mem.vram_used/GIG):.2f} GB')
+                vram_in_use += mem.vram_used  # note vram_used is negative
+                self.logger.debug(f'{(vram_in_use/GIG):.2f}GB VRAM used for models; max allowed={(reserved/GIG):.2f}GB')
         
     def _local_model_hash(self, model_path: Union[str, Path]) -> str:
         sha = hashlib.sha256()

invokeai/backend/model_management/model_manager.py

@@ -231,6 +231,7 @@ from __future__ import annotations
 import os
 import hashlib
 import textwrap
+import yaml
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Optional, List, Tuple, Union, Dict, Set, Callable, types
@@ -314,6 +315,9 @@ class ModelManager(object):
         self.config_path = None
         if isinstance(config, (str, Path)):
             self.config_path = Path(config)
+            if not self.config_path.exists():
+                logger.warning(f'The file {self.config_path} was not found. Initializing a new file')
+                self.initialize_model_config(self.config_path)
             config = OmegaConf.load(self.config_path)
 
         elif not isinstance(config, DictConfig):
@@ -336,6 +340,7 @@ class ModelManager(object):
         self.logger = logger
         self.cache = ModelCache(
             max_cache_size=max_cache_size,
+            max_vram_cache_size = self.app_config.max_vram_cache_size,
             execution_device = device_type,
             precision = precision,
             sequential_offload = sequential_offload,
@@ -386,6 +391,16 @@ class ModelManager(object):
     def _get_model_cache_path(self, model_path):
         return self.app_config.models_path / ".cache" / hashlib.md5(str(model_path).encode()).hexdigest()
 
+    @classmethod
+    def initialize_model_config(cls, config_path: Path):
+        """Create empty config file"""
+        with open(config_path,'w') as yaml_file:
+            yaml_file.write(yaml.dump({'__metadata__':
+                                       {'version':'3.0.0'}
+                                       }
+                                      )
+                            )
+
     def get_model(
         self,
         model_name: str,
@@ -853,16 +868,22 @@ class ModelManager(object):
                         scanned_dirs.add(path)
                         continue
                     if any([(path/x).exists() for x in {'config.json','model_index.json','learned_embeds.bin','pytorch_lora_weights.bin'}]):
-                        new_models_found.update(installer.heuristic_import(path))
-                        scanned_dirs.add(path)
+                        try:
+                            new_models_found.update(installer.heuristic_import(path))
+                            scanned_dirs.add(path)
+                        except ValueError as e:
+                            self.logger.warning(str(e))
 
                 for f in files:
                     path = Path(root) / f
                     if path in known_paths or path.parent in scanned_dirs:
                         continue
                     if path.suffix in {'.ckpt','.bin','.pth','.safetensors','.pt'}:
-                        import_result = installer.heuristic_import(path)
-                        new_models_found.update(import_result)
+                        try:
+                            import_result = installer.heuristic_import(path)
+                            new_models_found.update(import_result)
+                        except ValueError as e:
+                            self.logger.warning(str(e))
 
             self.logger.info(f'Scanned {items_scanned} files and directories, imported {len(new_models_found)} models')
             installed.update(new_models_found)

invokeai/backend/model_management/model_probe.py

@@ -59,7 +59,7 @@ class ModelProbe(object):
         elif isinstance(model,(dict,ModelMixin,ConfigMixin)):
             return cls.probe(model_path=None, model=model, prediction_type_helper=prediction_type_helper)
         else:
-            raise Exception("model parameter {model} is neither a Path, nor a model")
+            raise ValueError("model parameter {model} is neither a Path, nor a model")
 
     @classmethod
     def probe(cls,
@@ -237,7 +237,7 @@ class CheckpointProbeBase(ProbeBase):
         elif in_channels == 4:
             return ModelVariantType.Normal
         else:
-            raise Exception("Cannot determine variant type")
+            raise ValueError(f"Cannot determine variant type (in_channels={in_channels}) at {self.checkpoint_path}")
 
 class PipelineCheckpointProbe(CheckpointProbeBase):
     def get_base_type(self)->BaseModelType:
@@ -248,7 +248,7 @@ class PipelineCheckpointProbe(CheckpointProbeBase):
             return BaseModelType.StableDiffusion1
         if key_name in state_dict and state_dict[key_name].shape[-1] == 1024:
             return BaseModelType.StableDiffusion2
-        raise Exception("Cannot determine base type")
+        raise ValueError("Cannot determine base type")
 
     def get_scheduler_prediction_type(self)->SchedulerPredictionType:
         type = self.get_base_type()
@@ -329,7 +329,7 @@ class ControlNetCheckpointProbe(CheckpointProbeBase):
                 return BaseModelType.StableDiffusion2
             elif self.checkpoint_path and self.helper:
                 return self.helper(self.checkpoint_path)
-        raise Exception("Unable to determine base type for {self.checkpoint_path}")
+        raise ValueError("Unable to determine base type for {self.checkpoint_path}")
 
 ########################################################
 # classes for probing folders
@@ -418,7 +418,7 @@ class ControlNetFolderProbe(FolderProbeBase):
     def get_base_type(self)->BaseModelType:
         config_file = self.folder_path / 'config.json'
         if not config_file.exists():
-            raise Exception(f"Cannot determine base type for {self.folder_path}")
+            raise ValueError(f"Cannot determine base type for {self.folder_path}")
         with open(config_file,'r') as file:
             config = json.load(file)
         # no obvious way to distinguish between sd2-base and sd2-768
@@ -435,7 +435,7 @@ class LoRAFolderProbe(FolderProbeBase):
                 model_file = base_file
                 break
         if not model_file:
-            raise Exception('Unknown LoRA format encountered')
+            raise ValueError('Unknown LoRA format encountered')
         return LoRACheckpointProbe(model_file,None).get_base_type()
 
 ############## register probe classes ######

invokeai/frontend/install/model_install.py

@@ -773,7 +773,7 @@ def main():
     config.parse_args(invoke_args)
     logger = InvokeAILogger().getLogger(config=config)
 
-    if not (config.root_dir / config.conf_path.parent).exists():
+    if not (config.conf_path / 'models.yaml').exists():
         logger.info(
             "Your InvokeAI root directory is not set up. Calling invokeai-configure."
         )

invokeai/frontend/web/dist/index.html

@@ -12,7 +12,7 @@
         margin: 0;
       }
     </style>
-    <script type="module" crossorigin src="./assets/index-581af3d4.js"></script>
+    <script type="module" crossorigin src="./assets/index-078526aa.js"></script>
   </head>
 
   <body dir="ltr">

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

@@ -53,7 +53,7 @@
         "linear": "Linear",
         "nodes": "Node Editor",
         "batch": "Batch Manager",
-        "modelmanager": "Model Manager",
+        "modelManager": "Model Manager",
         "postprocessing": "Post Processing",
         "nodesDesc": "A node based system for the generation of images is under development currently. Stay tuned for updates about this amazing feature.",
         "postProcessing": "Post Processing",
@@ -527,7 +527,9 @@
         "showOptionsPanel": "Show Options Panel",
         "hidePreview": "Hide Preview",
         "showPreview": "Show Preview",
-        "controlNetControlMode": "Control Mode"
+        "controlNetControlMode": "Control Mode",
+        "clipSkip": "Clip Skip",
+        "aspectRatio": "Ratio"
     },
     "settings": {
         "models": "Models",
@@ -551,7 +553,8 @@
         "generation": "Generation",
         "ui": "User Interface",
         "favoriteSchedulers": "Favorite Schedulers",
-        "favoriteSchedulersPlaceholder": "No schedulers favorited"
+        "favoriteSchedulersPlaceholder": "No schedulers favorited",
+        "showAdvancedOptions": "Show Advanced Options"
     },
     "toast": {
         "serverError": "Server Error",
@@ -669,6 +672,7 @@
     },
     "ui": {
         "showProgressImages": "Show Progress Images",
-        "hideProgressImages": "Hide Progress Images"
+        "hideProgressImages": "Hide Progress Images",
+        "swapSizes": "Swap Sizes"
     }
 }

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

@@ -53,7 +53,7 @@
         "linear": "Linear",
         "nodes": "Node Editor",
         "batch": "Batch Manager",
-        "modelmanager": "Model Manager",
+        "modelManager": "Model Manager",
         "postprocessing": "Post Processing",
         "nodesDesc": "A node based system for the generation of images is under development currently. Stay tuned for updates about this amazing feature.",
         "postProcessing": "Post Processing",

invokeai/version/invokeai_version.py

@@ -1 +1 @@
-__version__ = "3.0.0+b1"
+__version__ = "3.0.0+b5"