bi! d dl Z d dlZd dlmZ d dlmZ d dlmZmZ d dl Z d dl
m Z d dl m
Z
ddlmZmZ d Z G d
d e Zg d g d
g dg dg ddZe G d de Z G d de Zy) N) dataclass)Enum)OptionalUnion)validate_hf_hub_args)Self )
BaseOutputPushToHubMixinzscheduler_config.jsonc H e Zd ZdZdZdZdZdZdZdZ dZ
d Z d
Z d Z
d Zd
ZdZdZy)KarrasDiffusionSchedulers r
N)__name__
__module__ __qualname__
DDIMScheduler
DDPMScheduler
PNDMSchedulerLMSDiscreteSchedulerEulerDiscreteSchedulerHeunDiscreteScheduler EulerAncestralDiscreteSchedulerDPMSolverMultistepScheduler DPMSolverSinglestepSchedulerKDPM2DiscreteScheduler KDPM2AncestralDiscreteSchedulerDEISMultistepSchedulerUniPCMultistepSchedulerDPMSolverSDESchedulerEDMEulerScheduler `/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/schedulers/scheduling_utils.pyr
r
" sY MMM &'#"# #$ &(# r/ r
)
iR i i i! i iW | ) {G:-@gfffff@gS@g~jt@gV-?gtV?g7A`?gw/?gK7?g~jt? )
r1 iM i iK i i6 t 5 r ) r5 g(\B@g^I +@g r@gFx?g/$?g(\?gR Q?gʡE?g!rh?r6 ) g @g @K@gʡ/@g r @gˡE@g9v?g1 Zd?gn?g/$?g rh?r6 )StableDiffusionTimestepsStableDiffusionSigmasStableDiffusionXLTimestepsStableDiffusionXLSigmasStableDiffusionVideoSigmasc 0 e Zd ZU dZej
ed< y)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/ r0 r@ r@ = s r/ r@ c e Zd ZdZeZg ZdZee d
de
e e e
j f de
e defd Zdde e e
j f d efd
Zed Zed Zy)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).
TN pretrained_model_name_or_path subfolderreturnc b | j d||ddd|\ }}} | j |fd|i|S )a<
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 `hf
auth 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)rH rI return_unused_kwargsreturn_commit_hashrL r. ) load_config from_config)clsrH rI rL kwargsconfig commit_hashs r0 from_pretrainedz SchedulerMixin.from_pretrained_ sV p '6coo '
*G !% # '
'
# sv[r| sx ! " 6 " . 0 & !R i"R k"n
j
w"^ w"r/