mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
expose max_cache_size in config
This commit is contained in:
Eugene Brodsky
parent
66c10cc2f7
commit
7170e82f73
@ -228,10 +228,10 @@ class InvokeAISettings(BaseSettings):
|
||||
upcase_environ = dict()
|
||||
for key,value in os.environ.items():
|
||||
upcase_environ[key.upper()] = value
|
||||
|
||||
|
||||
fields = cls.__fields__
|
||||
cls.argparse_groups = {}
|
||||
|
||||
|
||||
for name, field in fields.items():
|
||||
if name not in cls._excluded():
|
||||
current_default = field.default
|
||||
@ -348,7 +348,7 @@ setting environment variables INVOKEAI_<setting>.
|
||||
'''
|
||||
singleton_config: ClassVar[InvokeAIAppConfig] = None
|
||||
singleton_init: ClassVar[Dict] = None
|
||||
|
||||
|
||||
#fmt: off
|
||||
type: Literal["InvokeAI"] = "InvokeAI"
|
||||
host : str = Field(default="127.0.0.1", description="IP address to bind to", category='Web Server')
|
||||
@ -367,7 +367,8 @@ 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="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='Memory/Performance')
|
||||
max_cache_size : float = Field(default=6.0, gt=0, description="Maximum memory amount used by model cache for rapid switching", category='Memory/Performance')
|
||||
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')
|
||||
@ -385,9 +386,9 @@ setting environment variables INVOKEAI_<setting>.
|
||||
outdir : Path = Field(default='outputs', description='Default folder for output images', category='Paths')
|
||||
from_file : Path = Field(default=None, description='Take command input from the indicated file (command-line client only)', category='Paths')
|
||||
use_memory_db : bool = Field(default=False, description='Use in-memory database for storing image metadata', category='Paths')
|
||||
|
||||
|
||||
model : str = Field(default='stable-diffusion-1.5', description='Initial model name', category='Models')
|
||||
|
||||
|
||||
log_handlers : List[str] = Field(default=["console"], description='Log handler. Valid options are "console", "file=<path>", "syslog=path|address:host:port", "http=<url>"', category="Logging")
|
||||
# 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")
|
||||
@ -396,7 +397,7 @@ setting environment variables INVOKEAI_<setting>.
|
||||
|
||||
def parse_args(self, argv: List[str]=None, conf: DictConfig = None, clobber=False):
|
||||
'''
|
||||
Update settings with contents of init file, environment, and
|
||||
Update settings with contents of init file, environment, and
|
||||
command-line settings.
|
||||
:param conf: alternate Omegaconf dictionary object
|
||||
:param argv: aternate sys.argv list
|
||||
@ -411,7 +412,7 @@ setting environment variables INVOKEAI_<setting>.
|
||||
except:
|
||||
pass
|
||||
InvokeAISettings.initconf = conf
|
||||
|
||||
|
||||
# parse args again in order to pick up settings in configuration file
|
||||
super().parse_args(argv)
|
||||
|
||||
@ -431,7 +432,7 @@ setting environment variables INVOKEAI_<setting>.
|
||||
cls.singleton_config = cls(**kwargs)
|
||||
cls.singleton_init = kwargs
|
||||
return cls.singleton_config
|
||||
|
||||
|
||||
@property
|
||||
def root_path(self)->Path:
|
||||
'''
|
||||
|
||||
@ -33,13 +33,13 @@ class ModelManagerServiceBase(ABC):
|
||||
logger: types.ModuleType,
|
||||
):
|
||||
"""
|
||||
Initialize with the path to the models.yaml config file.
|
||||
Initialize with the path to the models.yaml config file.
|
||||
Optional parameters are the torch device type, precision, max_models,
|
||||
and sequential_offload boolean. Note that the default device
|
||||
type and precision are set up for a CUDA system running at half precision.
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
@abstractmethod
|
||||
def get_model(
|
||||
self,
|
||||
@ -50,8 +50,8 @@ class ModelManagerServiceBase(ABC):
|
||||
node: Optional[BaseInvocation] = None,
|
||||
context: Optional[InvocationContext] = None,
|
||||
) -> ModelInfo:
|
||||
"""Retrieve the indicated model with name and type.
|
||||
submodel can be used to get a part (such as the vae)
|
||||
"""Retrieve the indicated model with name and type.
|
||||
submodel can be used to get a part (such as the vae)
|
||||
of a diffusers pipeline."""
|
||||
pass
|
||||
|
||||
@ -115,8 +115,8 @@ class ModelManagerServiceBase(ABC):
|
||||
"""
|
||||
Update the named model with a dictionary of attributes. Will fail with an
|
||||
assertion error if the name already exists. Pass clobber=True to overwrite.
|
||||
On a successful update, the config will be changed in memory. Will fail
|
||||
with an assertion error if provided attributes are incorrect or
|
||||
On a successful update, the config will be changed in memory. Will fail
|
||||
with an assertion error if provided attributes are incorrect or
|
||||
the model name is missing. Call commit() to write changes to disk.
|
||||
"""
|
||||
pass
|
||||
@ -129,8 +129,8 @@ class ModelManagerServiceBase(ABC):
|
||||
model_type: ModelType,
|
||||
):
|
||||
"""
|
||||
Delete the named model from configuration. If delete_files is true,
|
||||
then the underlying weight file or diffusers directory will be deleted
|
||||
Delete the named model from configuration. If delete_files is true,
|
||||
then the underlying weight file or diffusers directory will be deleted
|
||||
as well. Call commit() to write to disk.
|
||||
"""
|
||||
pass
|
||||
@ -176,7 +176,7 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
logger: types.ModuleType,
|
||||
):
|
||||
"""
|
||||
Initialize with the path to the models.yaml config file.
|
||||
Initialize with the path to the models.yaml config file.
|
||||
Optional parameters are the torch device type, precision, max_models,
|
||||
and sequential_offload boolean. Note that the default device
|
||||
type and precision are set up for a CUDA system running at half precision.
|
||||
@ -206,6 +206,8 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
if hasattr(config,'max_cache_size') \
|
||||
else config.max_loaded_models * 2.5
|
||||
|
||||
logger.debug(f"Maximum RAM cache size: {max_cache_size} GiB")
|
||||
|
||||
sequential_offload = config.sequential_guidance
|
||||
|
||||
self.mgr = ModelManager(
|
||||
@ -261,7 +263,7 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
submodel=submodel,
|
||||
model_info=model_info
|
||||
)
|
||||
|
||||
|
||||
return model_info
|
||||
|
||||
def model_exists(
|
||||
@ -314,8 +316,8 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
"""
|
||||
Update the named model with a dictionary of attributes. Will fail with an
|
||||
assertion error if the name already exists. Pass clobber=True to overwrite.
|
||||
On a successful update, the config will be changed in memory. Will fail
|
||||
with an assertion error if provided attributes are incorrect or
|
||||
On a successful update, the config will be changed in memory. Will fail
|
||||
with an assertion error if provided attributes are incorrect or
|
||||
the model name is missing. Call commit() to write changes to disk.
|
||||
"""
|
||||
return self.mgr.add_model(model_name, base_model, model_type, model_attributes, clobber)
|
||||
@ -328,8 +330,8 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
model_type: ModelType,
|
||||
):
|
||||
"""
|
||||
Delete the named model from configuration. If delete_files is true,
|
||||
then the underlying weight file or diffusers directory will be deleted
|
||||
Delete the named model from configuration. If delete_files is true,
|
||||
then the underlying weight file or diffusers directory will be deleted
|
||||
as well. Call commit() to write to disk.
|
||||
"""
|
||||
self.mgr.del_model(model_name, base_model, model_type)
|
||||
@ -383,7 +385,7 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
@property
|
||||
def logger(self):
|
||||
return self.mgr.logger
|
||||
|
||||
|
||||
def heuristic_import(self,
|
||||
items_to_import: Set[str],
|
||||
prediction_type_helper: Callable[[Path],SchedulerPredictionType]=None,
|
||||
@ -404,4 +406,4 @@ class ModelManagerService(ModelManagerServiceBase):
|
||||
of the set is a dict corresponding to the newly-created OmegaConf stanza for
|
||||
that model.
|
||||
'''
|
||||
return self.mgr.heuristic_import(items_to_import, prediction_type_helper)
|
||||
return self.mgr.heuristic_import(items_to_import, prediction_type_helper)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user