3jiSSKrSSKJr SSKJr SSKrSSKJr SSK r SSK J r J r SSKJrJr SSKJrJr SSKJrJr SSKJrJrJrJrJr S S KJrJr S S K J!r!J"r"J#r#J$r$J%r%J&r& S S K'J(r( \&RR"\*5r+"SS\%5r,g)N)UnpicklingError)Any) FrozenDictunfreeze) from_bytesto_bytes) flatten_dictunflatten_dict) create_repohf_hub_download)EntryNotFoundErrorHfHubHTTPErrorRepositoryNotFoundErrorRevisionNotFoundErrorvalidate_hf_hub_args) __version__is_torch_available) CONFIG_NAMEFLAX_WEIGHTS_NAMEHUGGINGFACE_CO_RESOLVE_ENDPOINT WEIGHTS_NAMEPushToHubMixinlogging)"convert_pytorch_state_dict_to_flaxc \rSrSrSr\r/SQr/SQr\ S5r SS\ \ -S\ RS \S \4S jjrSS\ \ -S \4S jjrSS\ \ -S \4S jjrSS\ \ -S \4SjjrS\R*S \ 4Sjr\ \\ R04S\\R6-S\ R4Sjj55rSS\\R6-S\ \ -S\S\4SjjrSrg)FlaxModelMixin2a Base class for all Flax models. [`FlaxModelMixin`] takes care of storing the model configuration and provides methods for loading, downloading and saving models. - **config_name** ([`str`]) -- Filename to save a model to when calling [`~FlaxModelMixin.save_pretrained`]. )_diffusers_version _class_name _name_or_path)nameparentdtypec U"U40UD6$)zJ All context managers that the model should be initialized under go here. )clsconfigkwargss ^/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/models/modeling_flax_utils.py _from_configFlaxModelMixin._from_config@s 6$V$$Nparamsr%maskreturnc^U4SjnUc[R"XA5$[U5n[R"U5upg[ XeR 55HupU(dMXYn U"U 5XY'M [ U5$)z[ Helper method to cast floating-point values of given parameter `PyTree` to given `dtype`. c>[U[R5(aE[R"UR[R 5(aUR T5nU$N) isinstancejnpndarray issubdtyper%floatingastype)paramr%s r+conditional_cast:FlaxModelMixin._cast_floating_to..conditional_castMs?%--#..cll2[2[ U+Lr.)jaxtree_mapr tree_flattenzipkeysr ) selfr/r%r0r< flat_params flat_mask_maskedkeyr;s ` r+_cast_floating_to FlaxModelMixin._cast_floating_toGs|   <<< 09 9"6* ''- y*:*:*<=KFv#(#3E#:  > k**r.cDURU[RU5$)a Cast the floating-point `params` to `jax.numpy.bfloat16`. This returns a new `params` tree and does not cast the `params` in place. This method can be used on a TPU to explicitly convert the model parameters to bfloat16 precision to do full half-precision training or to save weights in bfloat16 for inference in order to save memory and improve speed. Arguments: params (`dict | FrozenDict`): A `PyTree` of model parameters. mask (`dict | FrozenDict`): A `PyTree` with same structure as the `params` tree. The leaves should be booleans. It should be `True` for params you want to cast, and `False` for those you want to skip. Examples: ```python >>> from diffusers import FlaxUNet2DConditionModel >>> # load model >>> model, params = FlaxUNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") >>> # By default, the model parameters will be in fp32 precision, to cast these to bfloat16 precision >>> params = model.to_bf16(params) >>> # If you don't want to cast certain parameters (for example layer norm bias and scale) >>> # then pass the mask as follows >>> from flax import traverse_util >>> model, params = FlaxUNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") >>> flat_params = traverse_util.flatten_dict(params) >>> mask = { ... path: (path[-2] != ("LayerNorm", "bias") and path[-2:] != ("LayerNorm", "scale")) ... for path in flat_params ... } >>> mask = traverse_util.unflatten_dict(mask) >>> params = model.to_bf16(params, mask) ```)rIr6bfloat16rCr/r0s r+to_bf16FlaxModelMixin.to_bf16_sJ%%fcllDAAr.cDURU[RU5$)a Cast the floating-point `params` to `jax.numpy.float32`. This method can be used to explicitly convert the model parameters to fp32 precision. This returns a new `params` tree and does not cast the `params` in place. Arguments: params (`dict | FrozenDict`): A `PyTree` of model parameters. mask (`dict | FrozenDict`): A `PyTree` with same structure as the `params` tree. The leaves should be booleans. It should be `True` for params you want to cast, and `False` for those you want to skip. Examples: ```python >>> from diffusers import FlaxUNet2DConditionModel >>> # Download model and configuration from huggingface.co >>> model, params = FlaxUNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") >>> # By default, the model params will be in fp32, to illustrate the use of this method, >>> # we'll first cast to fp16 and back to fp32 >>> params = model.to_f16(params) >>> # now cast back to fp32 >>> params = model.to_fp32(params) ```)rIr6float32rMs r+to_fp32FlaxModelMixin.to_fp32s2%%fckk4@@r.cDURU[RU5$)a Cast the floating-point `params` to `jax.numpy.float16`. This returns a new `params` tree and does not cast the `params` in place. This method can be used on a GPU to explicitly convert the model parameters to float16 precision to do full half-precision training or to save weights in float16 for inference in order to save memory and improve speed. Arguments: params (`dict | FrozenDict`): A `PyTree` of model parameters. mask (`dict | FrozenDict`): A `PyTree` with same structure as the `params` tree. The leaves should be booleans. It should be `True` for params you want to cast, and `False` for those you want to skip. Examples: ```python >>> from diffusers import FlaxUNet2DConditionModel >>> # load model >>> model, params = FlaxUNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") >>> # By default, the model params will be in fp32, to cast these to float16 >>> params = model.to_fp16(params) >>> # If you want don't want to cast certain parameters (for example layer norm bias and scale) >>> # then pass the mask as follows >>> from flax import traverse_util >>> model, params = FlaxUNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") >>> flat_params = traverse_util.flatten_dict(params) >>> mask = { ... path: (path[-2] != ("LayerNorm", "bias") and path[-2:] != ("LayerNorm", "scale")) ... for path in flat_params ... } >>> mask = traverse_util.unflatten_dict(mask) >>> params = model.to_fp16(params, mask) ```)rIr6float16rMs r+to_fp16FlaxModelMixin.to_fp16sJ%%fckk4@@r.rngc[SU35e)Nz.init_weights method has to be implemented for )NotImplementedError)rCrXs r+ init_weightsFlaxModelMixin.init_weightss!$RSWRX"YZZr.pretrained_model_name_or_pathc [RS5 URSS5nURSS5nURSS5nURSS5nURSS5n URS S5n URS S5n URS S5n URS S5n [S SS.nUcUR"U4USUU U U U U S.UD6up_UR "U4USS.WD6unnU cUO[ RRX5n[ RRU5(GalU(a[ RR[ RRU[55(d[S[SUS35e[ RRU[5nGO[ RR[ RRU[55(a%[ RRU[5nO[ RR[ RRU[55(a[[SUS35e[S[S[SUS35e[UU(d[O[UUU U U UU U S9 nU(a6[+5(aS(S)KJn O [S*5eU"U5n[1UU5nO0[3US+5n[5UUR755nSSS5 [FRHRKS0W5n[MU5n[FRN"URP[FRRRUS15S29n[M[YU55R[55n[M[YU55nU[WUR[55- n[WUR[55U- nU(a#[RS3US4US535 UUl.UR[5HZn U U;dM UU R^UU R^:wdM-['S6U S7UU R^S8UU R^S935e UHn!UU! M [aU5S1:aK[RS:US;URbRdS3 5 O-[RgS?URbRdS@35 [aU5S1:a4[RSAURbRdSBUSCUSD35 OG[RgSEURbRdSFUSGURbRdSH35 U[iU54$![a [US35e[ a [U SUS35e["a [US[S35e[$an[SUS U35eSnAf[&a% [S![(S"US#[S[S$3 5e[a! [S%US&US'[S[S3 5ef=f!,(df  GNx=f![8[:R<R>4an[3U5nUR75RAS,5(a [CS-5e[&Ue!,(df  SnAGN=f![D[&4a [S.US/35ef=fSnAff=f)Ia Instantiate a pretrained Flax model from a pretrained model configuration. Parameters: pretrained_model_name_or_path (`str` or `os.PathLike`): Can be either: - A string, the *model id* (for example `stable-diffusion-v1-5/stable-diffusion-v1-5`) of a pretrained model hosted on the Hub. - A path to a *directory* (for example `./my_model_directory`) containing the model weights saved using [`~FlaxModelMixin.save_pretrained`]. dtype (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`): The data type of the computation. Can be one of `jax.numpy.float32`, `jax.numpy.float16` (on GPUs) and `jax.numpy.bfloat16` (on TPUs). This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified, all the computation will be performed with the given `dtype`. > [!TIP] > This only specifies the dtype of the *computation* and does not influence the dtype of model > parameters. > > If you wish to change the dtype of the model parameters, see [`~FlaxModelMixin.to_fp16`] and > [`~FlaxModelMixin.to_bf16`]. model_args (sequence of positional arguments, *optional*): All remaining positional arguments are passed to the underlying model's `__init__` method. cache_dir (`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. 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. 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. from_pt (`bool`, *optional*, defaults to `False`): Load the model weights from a PyTorch checkpoint save file. kwargs (remaining dictionary of keyword arguments, *optional*): Can be used to update the configuration object (after it is loaded) and initiate the model (for example, `output_attentions=True`). Behaves differently depending on whether a `config` is provided or automatically loaded: - If a configuration is provided with `config`, `kwargs` are directly passed to the underlying model's `__init__` method (we assume all relevant updates to the configuration have already been done). - If a configuration is not provided, `kwargs` are first passed to the configuration class initialization function [`~ConfigMixin.from_config`]. Each key of the `kwargs` that corresponds to a configuration attribute is used to override said attribute with the supplied `kwargs` value. Remaining keys that do not correspond to any configuration attribute are passed to the underlying model's `__init__` function. Examples: ```python >>> from diffusers import FlaxUNet2DConditionModel >>> # Download model and configuration from huggingface.co and cache. >>> model, params = FlaxUNet2DConditionModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5") >>> # Model was saved using *save_pretrained('./test/saved_model/')* (for example purposes, not runnable). >>> model, params = FlaxUNet2DConditionModel.from_pretrained("./test/saved_model/") ``` If you get the error message below, you need to finetune the weights for your downstream task: ```bash Some weights of UNet2DConditionModel were not initialized from the model checkpoint at stable-diffusion-v1-5/stable-diffusion-v1-5 and are newly initialized because the shapes did not match: - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. ``` zFlax classes are deprecated and will be removed in Diffusers v1.0.0. We recommend migrating to PyTorch classes or pinning your version of Diffusers.r)N cache_dirforce_downloadFfrom_ptproxieslocal_files_onlytokenrevision subfoldermodelflax) diffusers file_type frameworkT)r_return_unused_kwargsr`rbrcrdrerf)r%rlzError no file named z found in directory  z file found in directory z-. Please load the model using `from_pt=True`.z or .) filenamer_r`rbrcrd user_agentrfrez is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' If this is a private repository, make sure to pass a token having permission to this repo with `token` or log in with `hf auth login`.z is not a valid git identifier (branch name, tag name or commit id) that exists for this model name. Check the model page at 'https://huggingface.co/z' for available revisions.z& does not appear to have a file named z:There was a specific connection error when trying to load z: zWe couldn't connect to 'zM' to load this model, couldn't find it in the cached files and it looks like z8 is not the path to a directory containing a file named z. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.zCan't load the model for 'z'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'z=' is the correct path to a directory containing a file named r)load_state_dictz|Can't load the model in PyTorch format because PyTorch is not installed. Please, install PyTorch or use native Flax weights.rbversionzYou seem to have cloned a repository without having git-lfs installed. Please install git-lfs and run `git lfs install` followed by `git lfs pull` in the folder you cloned.zUnable to convert z to Flax deserializable object. cZ[R"U[R"SS9S5$)Ncpu)backendr)r> device_put local_devices)xs r+0FlaxModelMixin.from_pretrained..s!3CTCT]bCcdeCf1gr.r)rXzThe checkpoint z is missing required keys: zI. Make sure to call model.init_weights to initialize the missing weights.z)Trying to load the pretrained weight for z failed: checkpoint has shape z, which is incompatible with the model shape z. z(Some weights of the model checkpoint at z! were not used when initializing z: z, - This IS expected if you are initializing zU from the checkpoint of a model trained on another task or with another architecture.z9All model checkpoint weights were used when initializing z. zSome weights of z3 were not initialized from the model checkpoint at z and are newly initialized: zo You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.zAll the weights of z/ were initialized from the model checkpoint at zf. If your task is similar to the task the model of the checkpoint was trained on, you can already use z* for predictions without further training.)5loggerwarningpopr load_config from_configospathjoinisdirisfilerEnvironmentErrorrr rrr r ValueErrorrrmodeling_utilsrqropenrreadrmsgpack exceptions ExtraData startswithOSErrorUnicodeDecodeErrorr> tree_utilr?r eval_shaper[randomPRNGKeysetrrB _missing_keysshapelen __class____name__infor )"r(r]r% model_argsr*r)r_r`rarbrcrdrerfrp unused_kwargsrg model_kwargspretrained_path_with_subfolder model_fileerrrqpytorch_model_filestatestate_fefparams_shape_treerequired_params shape_state missing_keysunexpected_keysrHunexpected_keys" r+from_pretrainedFlaxModelMixin.from_pretrainedsh  [ Hd+JJ{D1 $4e<**Y.**Y-!::&8%@ 7D)::j$/JJ{D1 %   >$'OO- %#%)-!1!# % % !F"oofnEX\n`mn|   *;G ' 77==7 8 8ww~~bggll3QS_&`aa*.|n\=]^-- '*+<*=T,Oc56a9 1 ,16=.<'#1#%5)'%  d !##;&J "1!< 77I5QE n*d+w&sGLLN;E,$ &&'ginoU#NN5+=+=3::CUCUVWCXYl84E+FGLLNO"8,=#>? &UZZ\):: ejjl+o=  NN!"?!@@[\h[ijZZ !-C ::&>%?@12388=8P8P7QR nU+++}+ &456hh ) &j!//L.MMgi & &455[\m[nnop" &PQnPoore &./N.OP>>[=\]::K9LDQ]P^_]]$ &01N0OP--J,KL//@.Al^STV 0,+#W%7%7%A%AB n nj)Q668..y99")!6# #-!3*))+J7n*-? |Kk+lmmn nst2#W# Z=Z+:Z=#AZ(<Y  AZ(+ Z:5Z=:Z==$]"" \:-7\$$ \7 .\:7\:: ]]]"save_directoryis_main_process push_to_hubc P[RRU5(a[R SUS35 g[R "USS9 U(aUR SS5nUR SS5nUR SS 5nUR S S5n UR S UR[RR5S 5n [U SXyS 9Rn Un U(aU RU5 [RRU[5n [U S5n [U5nU R!U5 SSS5 [R#SU 35 U(aUR%UW W WWS9 gg!,(df  NB=f)az Save a model and its configuration file to a directory so that it can be reloaded using the [`~FlaxModelMixin.from_pretrained`] class method. Arguments: save_directory (`str` or `os.PathLike`): Directory to save a model and its configuration file to. Will be created if it doesn't exist. params (`dict | FrozenDict`): A `PyTree` of model parameters. is_main_process (`bool`, *optional*, defaults to `True`): Whether the process calling this is the main process or not. Useful during distributed training and you need to call this function on all processes. In this case, set `is_main_process=True` only on the main process to avoid race conditions. push_to_hub (`bool`, *optional*, defaults to `False`): Whether or not to push your model to the Hugging Face model 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 key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method. zProvided path (z#) should be a directory, not a fileNT)exist_okcommit_messageprivate create_prFrdrepo_id)rrrdwbzModel weights saved in )rdrr)rrrr|errormakedirsr~splitsepr r save_configrrrrwriter_upload_folder)rCrr/rrr*rrrrdr model_to_saveoutput_model_filer model_bytess r+save_pretrainedFlaxModelMixin.save_pretrainedsb8 77>>. ) ) LL?>*::]^ _  NT2 #ZZ(8$?NjjD1G ;6IJJw-EjjN,@,@,Mb,QRG!'D'W__G    % %n 5GGLL9JK #T *a"6*K GGK +  -.?-@AB    -#    + *s >F F%r'r4)TF) r __module__ __qualname____firstlineno____doc__r config_name_automatically_saved_args_flax_internal_args classmethodr,dictrr6r%rrIrNrRrVr>Arrayr[rrQstrrPathLikerboolr__static_attributes__r'r.r+rr2sZK V5%% +z(9+#))+SV+be+0%BdZ/%Bs%BNAdZ/AsA6%AdZ/%As%AN[ [d[;;_,'*R[['8_,yy_,_,J !%! @bkk)@z!@ @  @@r.r)-rpicklertypingrr> jax.numpynumpyr6msgpack.exceptionsrflax.core.frozen_dictrrflax.serializationrrflax.traverse_utilr r huggingface_hubr r huggingface_hub.utilsr rrrrrrutilsrrrrrrmodeling_flax_pytorch_utilsr get_loggerrr|rr'r.r+rsd  " 63;8/L   H %|^|r.