o
pi! @ s d dl Z d dlZd dlmZ d dlmZ d dlmZmZ d dl Z d dl
m Z ddl m
Z
mZ dZG d d
d
eZg d g d g d
g dg ddZeG dd de
ZG dd deZdS ) N) dataclass)Enum)OptionalUnion)validate_hf_hub_args )
BaseOutputPushToHubMixinzscheduler_config.jsonc @ sH e Zd ZdZdZdZdZdZdZdZ dZ
d Z d
Z d Z
d Zd
ZdZdZdS )KarrasDiffusionSchedulers r
N)__name__
__module__ __qualname__
DDIMScheduler
DDPMScheduler
PNDMSchedulerLMSDiscreteSchedulerEulerDiscreteSchedulerHeunDiscreteScheduler EulerAncestralDiscreteSchedulerDPMSolverMultistepScheduler DPMSolverSinglestepSchedulerKDPM2DiscreteScheduler KDPM2AncestralDiscreteSchedulerDEISMultistepSchedulerUniPCMultistepSchedulerDPMSolverSDESchedulerEDMEulerScheduler r+ r+ c/home/ubuntu/SoloSpeech/.venv/lib/python3.10/site-packages/diffusers/schedulers/scheduling_utils.pyr
! s r
)
iR i i i! i iW | ) {G:-@gfffff@gS@g~jt@gV-?gtV?g7A`?gw/?gK7?g~jt? )
r- iM i iK i i6 t 5 r ) r1 g(\B@g^I +@g r@gFx?g/$?g(\?gR Q?gʡE?g!rh?r2 ) g @g @K@gʡ/@g r @gˡE@g9v?g1 Zd?gn?g/$?g rh?r2 )StableDiffusionTimestepsStableDiffusionSigmasStableDiffusionXLTimestepsStableDiffusionXLSigmasStableDiffusionVideoSigmasc @ s e Zd ZU dZejed< dS )SchedulerOutputaH
Base class for the output of a scheduler's `step` function.
Args:
prev_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
denoising loop.
prev_sampleN)r r r __doc__torchTensor__annotations__r+ r+ r+ r, r; < s
r; c @ s e Zd ZdZeZg ZdZee dde
e e e
jf de
e fddZdd e e e
jf d
efd d Zed
d Zedd ZdS )SchedulerMixina
Base class for all schedulers.
[`SchedulerMixin`] contains common functions shared by all schedulers such as general loading and saving
functionalities.
[`ConfigMixin`] takes care of storing the configuration attributes (like `num_train_timesteps`) that are passed to
the scheduler's `__init__` function, and the attributes can be accessed by `scheduler.config.num_train_timesteps`.
Class attributes:
- **_compatibles** (`List[str]`) -- A list of scheduler classes that are compatible with the parent scheduler
class. Use [`~ConfigMixin.from_config`] to load a different compatible scheduler class (should be overridden
by parent class).
TNF pretrained_model_name_or_path subfolderc K s6 | j d||ddd|\}}}| j|fd|i|S )aD
Instantiate a scheduler from a pre-defined JSON configuration file in a local directory or Hub repository.
Parameters:
pretrained_model_name_or_path (`str` or `os.PathLike`, *optional*):
Can be either:
- A string, the *model id* (for example `google/ddpm-celebahq-256`) of a pretrained model hosted on
the Hub.
- A path to a *directory* (for example `./my_model_directory`) containing the scheduler
configuration saved with [`~SchedulerMixin.save_pretrained`].
subfolder (`str`, *optional*):
The subfolder location of a model file within a larger model repository on the Hub or locally.
return_unused_kwargs (`bool`, *optional*, defaults to `False`):
Whether kwargs that are not consumed by the Python class should be returned or not.
cache_dir (`Union[str, os.PathLike]`, *optional*):
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.
force_download (`bool`, *optional*, defaults to `False`):
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.
proxies (`Dict[str, str]`, *optional*):
A dictionary of proxy servers to use by protocol or endpoint, for example, `{'http': 'foo.bar:3128',
'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
output_loading_info(`bool`, *optional*, defaults to `False`):
Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.
local_files_only(`bool`, *optional*, defaults to `False`):
Whether to only load local model weights and configuration files or not. If set to `True`, the model
won't be downloaded from the Hub.
token (`str` or *bool*, *optional*):
The token to use as HTTP bearer authorization for remote files. If `True`, the token generated from
`diffusers-cli login` (stored in `~/.huggingface`) is used.
revision (`str`, *optional*, defaults to `"main"`):
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.
To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with
`huggingface-cli login`. You can also activate the special
["offline-mode"](https://huggingface.co/diffusers/installation.html#offline-mode) to use this method in a
firewalled environment.
T)rB rC return_unused_kwargsreturn_commit_hashrD Nr+ ) load_config from_config)clsrB rC rD kwargsconfig commit_hashr+ r+ r, from_pretrained^ s 8 z SchedulerMixin.from_pretrainedsave_directory push_to_hubc K s | j d||d| dS )a?
Save a scheduler configuration object to a directory so that it can be reloaded using the
[`~SchedulerMixin.from_pretrained`] class method.
Args:
save_directory (`str` or `os.PathLike`):
Directory where the configuration JSON file will be saved (will be created if it does not exist).
push_to_hub (`bool`, *optional*, defaults to `False`):
Whether or not to push your model to the Hugging Face Hub after saving it. You can specify the
repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
namespace).
kwargs (`Dict[str, Any]`, *optional*):
Additional keyword arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
)rM rN Nr+ ) save_config)selfrM rN rI r+ r+ r, save_pretrained s z SchedulerMixin.save_pretrainedc C s | S )z
Returns all schedulers that are compatible with this scheduler
Returns:
`List[SchedulerMixin]`: List of compatible schedulers
)_get_compatibles)rP r+ r+ r, compatibles s zSchedulerMixin.compatiblesc s@ t t| jg| j }ttdd fdd|D }|S )N.r c s g | ] }t |rt |qS r+ )hasattrgetattr).0cdiffusers_libraryr+ r,
s
z3SchedulerMixin._get_compatibles..)listsetr _compatibles importlib
import_modulesplit)rH compatible_classes_strcompatible_classesr+ rY r, rR s
z SchedulerMixin._get_compatibles)NNF)F)r r r r= SCHEDULER_CONFIG_NAME config_namer^ has_compatibles classmethodr r r strosPathLikerL boolrQ propertyrS rR r+ r+ r+ r, rA J s( ?
rA )r_ ri dataclassesr enumr typingr r r> huggingface_hub.utilsr utilsr r rd r
AysSchedulesr; rA r+ r+ r+ r, s&