
    +hfA                        S r SSKJrJrJrJr  SSKrSSKrSSK	J
r
JrJr  SSKJrJrJr  SSKJrJrJrJrJrJrJrJrJrJr  SSKJrJrJr  SSK J!r!  \" 5       (       a  SSK"r#\RH                  " \%5      r& " S	 S
\
5      r'g)zImage processor class for BLIP.    )DictListOptionalUnionN)BaseImageProcessorBatchFeatureget_size_dict)convert_to_rgbresizeto_channel_dimension_format)
OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension
ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_arrayvalid_images)
TensorTypeis_vision_availablelogging)numpy_to_pilc                      ^  \ rS rSrSrS/rSS\R                  SSSSSSS4
S\S\	\
\4   S	\S
\S\\\4   S\S\\\\\   4      S\\\\\   4      S\S\SS4U 4S jjjr\R                  SS4S\R$                  S\	\
\4   S	\S\\\
\4      S\\\
\4      S\R$                  4S jjrSSSSSSSSSSS\R*                  S4S\S\\   S\\	\
\4      S	\S
\\   S\\   S\\   S\\   S\\\\\   4      S\\\\\   4      S\\\
\4      S\S\S\\\
\4      S\R2                  R2                  4S jjrSS\R8                  S\
4S jjrSrU =r$ )BlipImageProcessor1   ad	  
Constructs a BLIP image processor.

Args:
    do_resize (`bool`, *optional*, defaults to `True`):
        Whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by the
        `do_resize` parameter in the `preprocess` method.
    size (`dict`, *optional*, defaults to `{"height": 384, "width": 384}`):
        Size of the output image after resizing. Can be overridden by the `size` parameter in the `preprocess`
        method.
    resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
        Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`. Can be
        overridden by the `resample` parameter in the `preprocess` method.
    do_rescale (`bool`, *optional*, defaults to `True`):
        Wwhether to rescale the image by the specified scale `rescale_factor`. Can be overridden by the
        `do_rescale` parameter in the `preprocess` method.
    rescale_factor (`int` or `float`, *optional*, defaults to `1/255`):
        Scale factor to use if rescaling the image. Only has an effect if `do_rescale` is set to `True`. Can be
        overridden by the `rescale_factor` parameter in the `preprocess` method.
    do_normalize (`bool`, *optional*, defaults to `True`):
        Whether to normalize the image. Can be overridden by the `do_normalize` parameter in the `preprocess`
        method. Can be overridden by the `do_normalize` parameter in the `preprocess` method.
    image_mean (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_MEAN`):
        Mean to use if normalizing the image. This is a float or list of floats the length of the number of
        channels in the image. Can be overridden by the `image_mean` parameter in the `preprocess` method. Can be
        overridden by the `image_mean` parameter in the `preprocess` method.
    image_std (`float` or `List[float]`, *optional*, defaults to `IMAGENET_STANDARD_STD`):
        Standard deviation to use if normalizing the image. This is a float or list of floats the length of the
        number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method.
        Can be overridden by the `image_std` parameter in the `preprocess` method.
    do_convert_rgb (`bool`, *optional*, defaults to `True`):
        Whether to convert the image to RGB.
pixel_valuesTNgp?	do_resizesizeresample
do_rescalerescale_factordo_normalize
image_mean	image_stddo_convert_rgbdo_center_cropreturnc                    > [         TU ]  " S0 UD6  Ub  UOSSS.n[        USS9nXl        X l        X0l        X@l        XPl        X`l        Ub  UO[        U l
        Ub  UO[        U l        Xl        Xl        g )N   )heightwidthTdefault_to_square )super__init__r	   r   r    r!   r"   r#   r$   r   r%   r   r&   r'   r(   )selfr   r    r!   r"   r#   r$   r%   r&   r'   r(   kwargs	__class__s               r/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/blip_diffusion/blip_image_processing.pyr2   BlipImageProcessor.__init__V   s{     	"6"'tc-JTT:"	 $,((2(>*DT&/&;,,    imagedata_formatinput_data_formatc                     [        U5      nSU;  d  SU;  a  [        SUR                  5        35      eUS   US   4n[        U4UUUUS.UD6$ )a  
Resize an image to `(size["height"], size["width"])`.

Args:
    image (`np.ndarray`):
        Image to resize.
    size (`Dict[str, int]`):
        Dictionary in the format `{"height": int, "width": int}` specifying the size of the output image.
    resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`):
        `PILImageResampling` filter to use when resizing the image e.g. `PILImageResampling.BICUBIC`.
    data_format (`ChannelDimension` or `str`, *optional*):
        The channel dimension format for the output image. If unset, the channel dimension format of the input
        image is used. Can be one of:
        - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
        - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
        - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
    input_data_format (`ChannelDimension` or `str`, *optional*):
        The channel dimension format for the input image. If unset, the channel dimension format is inferred
        from the input image. Can be one of:
        - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
        - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
        - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.

Returns:
    `np.ndarray`: The resized image.
r,   r-   zFThe `size` dictionary must contain the keys `height` and `width`. Got )r    r!   r:   r;   )r	   
ValueErrorkeysr   )r3   r9   r    r!   r:   r;   r4   output_sizes           r6   r   BlipImageProcessor.resizet   sy    F T"47$#6efjfofofqersttH~tG}5
#/
 
 	
r8   imagesreturn_tensorsc           
         Ub  UOU R                   nUb  UOU R                  nUb  UOU R                  nUb  UOU R                  nUb  UOU R                  nU	b  U	OU R
                  n	U
b  U
OU R                  n
Ub  UOU R                  nUb  UOU R                  nUb  UOU R                  n[        USS9n[        U5      n[        U5      (       d  [        S5      eU(       a  Ub  Uc  [        S5      eU(       a  Uc  [        S5      eU(       a  U	b  U
c  [        S5      eU(       a  U Vs/ s H  n[        U5      PM     nnU Vs/ s H  n[        U5      PM     nn[!        US   5      (       a  U(       a  ["        R%                  S5        Uc  ['        US   5      nU(       a!  U Vs/ s H  nU R)                  UX4US	9PM     nnU(       a   U Vs/ s H  nU R+                  UX~S
9PM     nnU(       a!  U Vs/ s H  nU R-                  UXUS9PM     nnU(       a   U Vs/ s H  nU R/                  UX>S9PM     nnU Vs/ s H  n[1        UXS9PM     nn[3        SU0US9nU$ s  snf s  snf s  snf s  snf s  snf s  snf s  snf )a  
Preprocess an image or batch of images.

Args:
    images (`ImageInput`):
        Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If
        passing in images with pixel values between 0 and 1, set `do_rescale=False`.
    do_resize (`bool`, *optional*, defaults to `self.do_resize`):
        Whether to resize the image.
    size (`Dict[str, int]`, *optional*, defaults to `self.size`):
        Controls the size of the image after `resize`. The shortest edge of the image is resized to
        `size["shortest_edge"]` whilst preserving the aspect ratio. If the longest edge of this resized image
        is > `int(size["shortest_edge"] * (1333 / 800))`, then the image is resized again to make the longest
        edge equal to `int(size["shortest_edge"] * (1333 / 800))`.
    resample (`PILImageResampling`, *optional*, defaults to `self.resample`):
        Resampling filter to use if resizing the image. Only has an effect if `do_resize` is set to `True`.
    do_rescale (`bool`, *optional*, defaults to `self.do_rescale`):
        Whether to rescale the image values between [0 - 1].
    rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`):
        Rescale factor to rescale the image by if `do_rescale` is set to `True`.
    do_normalize (`bool`, *optional*, defaults to `self.do_normalize`):
        Whether to normalize the image.
    image_mean (`float` or `List[float]`, *optional*, defaults to `self.image_mean`):
        Image mean to normalize the image by if `do_normalize` is set to `True`.
    image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
        Image standard deviation to normalize the image by if `do_normalize` is set to `True`.
    do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
        Whether to convert the image to RGB.
    return_tensors (`str` or `TensorType`, *optional*):
        The type of tensors to return. Can be one of:
            - Unset: Return a list of `np.ndarray`.
            - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`.
            - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`.
            - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`.
            - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`.
    data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`):
        The channel dimension format for the output image. Can be one of:
        - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
        - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
        - Unset: Use the channel dimension format of the input image.
    input_data_format (`ChannelDimension` or `str`, *optional*):
        The channel dimension format for the input image. If unset, the channel dimension format is inferred
        from the input image. Can be one of:
        - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format.
        - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format.
        - `"none"` or `ChannelDimension.NONE`: image in (height, width) format.
Fr.   zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.z9Size and resample must be specified if do_resize is True.z7Rescale factor must be specified if do_rescale is True.z=Image mean and std must be specified if do_normalize is True.r   zIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)r9   r    r!   r;   )r9   scaler;   )r9   meanstdr;   )r;   )input_channel_dimr   )datatensor_type)r   r!   r"   r#   r$   r%   r&   r'   r(   r    r	   r   r   r=   r
   r   r   loggerwarning_oncer   r   rescale	normalizecenter_cropr   r   )r3   rA   r   r    r!   r"   r(   r#   r$   r%   r&   rB   r'   r:   r;   r4   r9   encoded_outputss                     r6   
preprocessBlipImageProcessor.preprocess   s   B "+!6IDNN	'38#-#9Zt
+9+E4K^K^'3'?|TEVEV#-#9Zt
!*!6IDNN	+9+E4K^K^+9+E4K^K^'tTYYTU;$V,F##: 
 )9XYY.0VWWZ/93D\]] 9?@nU+F@ 6<<VE.'V<6!9%%*s $ >vay I $#E %dYjk#  
  $#E 5d#    $#E U^op#   flmfl]bd&&ud&XflFm ou
ntej'{`nt 	 
 '^V,DR`aM A =

 n
s*   +I#I((I-I27I7I<?Jsampleoutput_typec                     US;  a  [        SU S35      eUS-  S-   R                  SS5      nUS:X  a  U$ UR                  5       R                  SSS	S5      R	                  5       nUS
:X  a  U$ [        U5      nU$ )N)ptnppilzoutput_type=zD is not supported. Make sure to choose one of ['pt', 'np', or 'pil']   g      ?r      rU      rV   )r=   clampcpupermutenumpyr   )r3   rR   rS   s      r6   postprocessBlipImageProcessor.postprocess-  s    11{m+op 
 1*s"))!Q/$M %%aAq1779$Mf%r8   )
r(   r'   r$   r"   r   r%   r&   r!   r#   r    )rW   ) __name__
__module____qualname____firstlineno____doc__model_input_namesr   BICUBICboolr   strintr   floatr   r   r2   rV   ndarrayr   r   FIRSTr   r   PILImagerP   torchTensorr_   __static_attributes____classcell__)r5   s   @r6   r   r   1   s    D (( #'9'A'A,3!:>9=##-- 38n- %	-
 - c5j)- - U5$u+#567- E%e"456- - - 
- -D (:'A'A>BDH.
zz.
 38n.
 %	.

 eC)9$9:;.
 $E#/?*?$@A.
 
.
f %))-'+%))-*.'+:>9=;?#(8(>(>DHFF D>F tCH~&	F
 %F TNF !F !F tnF U5$u+#567F E%e"456F !sJ!78F F &F $E#/?*?$@AF" 
#FR%,, S  r8   r   )(re   typingr   r   r   r   r^   rV   rp   #transformers.image_processing_utilsr   r   r	   transformers.image_transformsr
   r   r   transformers.image_utilsr   r   r   r   r   r   r   r   r   r   transformers.utilsr   r   r   diffusers.utilsr   	PIL.Imagern   
get_loggerra   rJ   r   r0   r8   r6   <module>r|      sl    & . .   _ _ ] ]   H G (  
		H	%
M+ Mr8   