bi2:ddlZddlmZmZmZmZmZmZmZddl Z ddl m Z ddl m Z ddlmZddlmZmZerddlmZd ZeeZGd d eeZd d Zy)N) TYPE_CHECKINGAnyDictListOptionalTupleUnion)validate_hf_hub_args)Self) ConfigMixin)PushToHubMixin get_logger BlockStatezguider_config.jsonc LeZdZdZeZdZdZd%dedefdZ dZ dZ d e d e d e jd dfd Zdeeeeeeefffd dfdZde j*j,d dfdZde j*j,d dfdZddd edfdZdedd efdZd efdZed efdZ ed efdZ!ed e fdZ"e#deeeeeeefffddde ded df dZ$e#e% d&de&eee'jPfd e&ed e)fd!Z*d'd"eee'jPfd#efd$Z+y)( BaseGuidancezGBase class providing the skeleton for implementing guidance techniques.N__guidance_identifier__startstopcL||_||_d|_d|_d|_d|_d|_d|_d|cxkrdksntd|d||cxkrdksntd|d|d|jt|jts td y) NrT?z4Expected `start` to be between 0.0 and 1.0, but got .zExpected `stop` to be between z and 1.0, but got z\`_input_predictions` must be a list of required prediction names for the guidance technique.) _start_stop_step_num_inference_steps _timestep_count_prepared _input_fields_enabled ValueError_input_predictions isinstancelist)selfrrs Y/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/guiders/guider_utils.py__init__zBaseGuidance.__init__+s   )-!+/ EI u"s"STYSZZ[\] ]$$=eWDVW[V\\]^_ _  " " **T=T=TVZ2[n 3\cd|_y)NFr"r's r(disablezBaseGuidance.disable?s  r*cd|_y)NTr,r-s r(enablezBaseGuidance.enableBs  r*stepnum_inference_stepstimestepreturnc<||_||_||_d|_y)Nr)rrrr )r'r1r2r3s r( set_statezBaseGuidance.set_stateEs  $7!! r*kwargsc |jD]i\}}t|t}t|txr"t |dk(xrt d|D}|rM|rPt dt|d|d||_y)a Set the input fields for the guidance technique. The input fields are used to specify the names of the returned attributes containing the prepared data after `prepare_inputs` is called. The prepared data is obtained from the values of the provided keyword arguments to this method. Args: **kwargs (`Dict[str, Union[str, Tuple[str, str]]]`): A dictionary where the keys are the names of the fields that will be used to store the data once it is prepared with `prepare_inputs`. The values can be either a string or a tuple of length 2, which is used to look up the required data provided for preparation. If a string is provided, it will be used as the conditional data (or unconditional if used with a guidance method that requires it). If a tuple of length 2 is provided, the first element must be the conditional data identifier and the second element must be the unconditional data identifier or None. Example: ``` data = {"prompt_embeds": , "negative_prompt_embeds": , "latents": } BaseGuidance.set_input_fields( latents="latents", prompt_embeds=("prompt_embeds", "negative_prompt_embeds"), ) ``` r c3<K|]}t|tywN)r%str).0vs r( z0BaseGuidance.set_input_fields..hsDg\]ZPQSVEWDgszcExpected `set_input_fields` to be called with a string or a tuple of string with length 2, but got z for key rN) itemsr%r;tuplelenallr#typer!)r'r7keyvalue is_stringis_tuple_of_str_with_len_2s r(set_input_fieldszBaseGuidance.set_input_fieldsKs4!,,. JC"5#.I5%(gSZ1_gDgafDgAg '!; yz~@E{FzGGPQTPUUVW  $r*denoiserc.|xjdz c_y)z Prepares the models for the guidance technique on a given batch of data. This method should be overridden in subclasses to implement specific model preparation logic. N)r r'rIs r(prepare_modelszBaseGuidance.prepare_modelsps !r*cy)a* Cleans up the models for the guidance technique after a given batch of data. This method should be overridden in subclasses to implement specific model cleanup logic. It is useful for removing any hooks or other stateful modifications made during `prepare_models`. NrLs r(cleanup_modelszBaseGuidance.cleanup_modelsws r*datarctd)Nz?BaseGuidance::prepare_inputs must be implemented in subclasses.NotImplementedError)r'rQs r(prepare_inputszBaseGuidance.prepare_inputss!"cddr*c@td|Ds tdt||jk7r%td|jdt|d|Dcic]#}t ||j |j %}}|jdi|Scc}w)Nc34K|]}t|dyw) noise_predN)hasattr)r<ds r(r>z(BaseGuidance.__call__..s:71l+:sz1Expected all data to have `noise_pred` attribute.z Expected z data items, but got z. Please check the input data.rO)rBr#rAnum_conditionsgetattr_identifier_keyrXforward)r'rQrZforward_inputss r(__call__zBaseGuidance.__call__s:T::PQ Q t9++ +D//00Ec$i[Pno SWWQ'!T%9%9:ALLHWWt||-n--Xs(Bctd)Nz8BaseGuidance::forward must be implemented in subclasses.rS)r'argsr7s r(r^zBaseGuidance.forwards!"\]]r*ctd)Nz?BaseGuidance::is_conditional must be implemented in subclasses.rSr-s r(is_conditionalzBaseGuidance.is_conditional!"cddr*c|j Sr:)rdr-s r(is_unconditionalzBaseGuidance.is_unconditionals&&&&r*ctd)Nz?BaseGuidance::num_conditions must be implemented in subclasses.rSr-s r(r[zBaseGuidance.num_conditionsrer* input_fields tuple_index identifiercdddlm}| tdi}|jD]J\}} t |t rt ||||<n$t |trt |||||<n L|||j<|di|S#t$rtjd|dYwxYw)a Prepares a batch of data for the guidance technique. This method is used in the `prepare_inputs` method of the `BaseGuidance` class. It prepares the batch based on the provided tuple index. Args: input_fields (`Dict[str, Union[str, Tuple[str, str]]]`): A dictionary where the keys are the names of the fields that will be used to store the data once it is prepared with `prepare_inputs`. The values can be either a string or a tuple of length 2, which is used to look up the required data provided for preparation. If a string is provided, it will be used as the conditional data (or unconditional if used with a guidance method that requires it). If a tuple of length 2 is provided, the first element must be the conditional data identifier and the second element must be the unconditional data identifier or None. data (`BlockState`): The input data to be prepared. tuple_index (`int`): The index to use when accessing input fields that are tuples. Returns: `BlockState`: The prepared batch of data. r rzInput fields cannot be None. Please pass `input_fields` to `prepare_inputs` or call `set_input_fields` before preparing inputs.z"`data` does not have attribute(s) z , skipping.rO) "modular_pipelines.modular_pipelinerr#r?r%r;r\r@AttributeErrorloggerdebugr]) clsrirQrjrkr data_batchrDrEs r(_prepare_batchzBaseGuidance._prepare_batchs8 D  R  &,,. VJC VeS)&-dE&:JsOu-&-dE+4F&GJsO V+5 3&&''J''" V A% TU VsAB  "B/.B/pretrained_model_name_or_path subfolderc b|jd||ddd|\}}}|j|fd|i|S)a4 Instantiate a guider 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 guider configuration saved with [`~BaseGuidance.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)rtrureturn_unused_kwargsreturn_commit_hashrwrO) load_config from_config)rqrtrurwr7config commit_hashs r(from_pretrainedzBaseGuidance.from_pretrainedsVp'6coo' *G!%# '  ' # sv[mMG#x''9: #66!>N:NR[9[[I r*)r)rtypingrrrrrrr rhuggingface_hub.utilsr typing_extensionsr configuration_utilsr utilsrrrmrrrrorrrOr*r(rsV III 6"-.?* H x[;x[vr*