bi8ddlZddlZddlZddlZddlZddlmZm Z ddl m Z ddl m Z mZddlmZmZeeZej(j+dduZej(j+dduZej(j+d duZer ddlZdd lmZned erdd lmZdd lm Z m!Z!neder ddl"m#Z#ddl$m%Z%nedddZ&ddZ'dZ( ddZ) ddZ*dZ+y)N)ImageImageOps)InterpolationMode) normalizeresize) get_logger load_image insightfaceconsisid_eva_clipfacexlib) FaceAnalysiszPinsightface is not available. Please install it using 'pip install insightface'.)create_model_and_transforms)OPENAI_DATASET_MEANOPENAI_DATASET_STDz\consisid_eva_clip is not available. Please install it using 'pip install consisid_eva_clip'.)init_parsing_model)FaceRestoreHelperzJfacexlib is not available. Please install it using 'pip install facexlib'.c|jdd\}}t|||kr|S|t||z }t||z}t||z}tj|||ftj }|S)a Resize the input image to a specified long edge while maintaining aspect ratio. Args: image (numpy.ndarray): Input image (H x W x C or H x W). resize_long_edge (int): The target size for the long edge of the image. Default is 768. Returns: numpy.ndarray: Resized image with the long edge matching `resize_long_edge`, while maintaining the aspect ratio. N) interpolation)shapemaxintcv2rINTER_LANCZOS4)imageresize_long_edgehwks f/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/pipelines/consisid/consisid_utils.pyresize_numpy_image_longr"'sv ;;r?DAq 1ay$$ 3q!9$A AE A AE A JJuq!fC4F4F GE Lcvd}t|tr|Dcgc] }||||c}S||||Scc}w)aONumpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb. float32 (bool): Whether to change to float32. Returns: list[tensor] | tensor: Tensor images. If returned results only have one element, just return tensor. c&|jddk(rF|rD|jdk(r|jd}tj|tj }t j|jddd}|r|j}|S)Nrrfloat64float32r) rdtypeastypercvtColor COLOR_BGR2RGBtorch from_numpy transposefloat)imgbgr2rgbr's r! _totensorzimg2tensor.._totensorKst 99Q<1 yyI%jj+,,sC$5$56Cs}}Q156 ))+C r#) isinstancelist)imgsr2r'r3r1s r! img2tensorr7>sB$<@AS #w0AA T7G ,,Bs6cd|ddddfzd|ddddfzzd|ddddfzz}|jdddd}|S) a Converts an RGB image to grayscale by applying the standard luminosity formula. Args: img (torch.Tensor): The input image tensor with shape (batch_size, channels, height, width). The image is expected to be in RGB format (3 channels). Returns: torch.Tensor: The grayscale image tensor with shape (batch_size, 3, height, width). The grayscale values are replicated across all three channels. gA`"?Nrr(gbX9?rgv/?r)repeat)r1xs r!to_grayr;Zs_ AqsF ec!QqS&k11EC1Q3K4GGA Aq!A Hr#c P|jtj|tj} |j | } t | dkDrt | dd} | d} | d}nd} d}|j| |jd ||jd}|jt |jdk(r td |jd}| &tjd |j|} t!j"| j%||} | j&d k(r| j)d} | rt+|d j)ddz }|j%|}|j-t/|gdgddj1d dgd}t3fd|Dj5}t!j6|}t!j8||t;|}t!j8|||}nXtj| tj}t+|d j)ddz }|j%|}|x}}t=||j>t@jB}t/|||}||j%|ddd\}}t!jD|dd d}t!jF||}t!jH| |gd}||||fS)a Process face embeddings from an image, extracting relevant features such as face embeddings, landmarks, and parsed face features using a series of face detection and alignment tools. Args: face_helper_1: Face helper object (first helper) for alignment and landmark detection. clip_vision_model: Pre-trained CLIP vision model used for feature extraction. face_helper_2: Face helper object (second helper) for embedding extraction. eva_transform_mean: Mean values for image normalization before passing to EVA model. eva_transform_std: Standard deviation values for image normalization before passing to EVA model. app: Application instance used for face detection. device: Device (CPU or GPU) where the computations will be performed. weight_dtype: Data type of the weights for precision (e.g., `torch.float32`). image: Input image in RGB format with pixel values in the range [0, 255]. original_id_image: (Optional) Original image for feature extraction if `is_align_face` is False. is_align_face: Boolean flag indicating whether face alignment should be performed. Returns: Tuple: - id_cond: Concatenated tensor of Ante face embedding and CLIP vision embedding - id_vit_hidden: Hidden state of the CLIP vision model, a list of tensors. - return_face_features_image_2: Processed face features image after normalization and parsing. - face_kps: Keypoints of the face detected in the image. rcH|dd|ddz |dd|ddz zS)Nbboxrrrr()r:s r!z)process_face_embeddings..s?QvYq\AfIaL5PUVW]U^_`UadefldmnodpUp4qr#)key embeddingkpsNT)only_center_facezfacexlib align face failzMFailed to detect face using insightface. Extracting embedding with align facer()r2go@)g ףp= ?gv/?gCl?)gZd;O?gy&1?g?)dimkeepdim)r c3(K|] }|k( yw)Nr?).0i parsing_outs r! z*process_face_embeddings..s4a!4sF)return_all_features return_hiddenshuffler)rF)% clean_allrr+ COLOR_RGB2BGRgetlensorted read_imageget_face_landmarks_5all_landmarks_5align_warp_face cropped_faces RuntimeErrorloggerwarningget_featr-r.tondim unsqueezer7 face_parserargmaxsumbool ones_likewherer;r image_sizerBICUBICnormdivcat) face_helper_1clip_vision_model face_helper_2eva_transform_meaneva_transform_stdappdevice weight_dtyperoriginal_id_image is_align_face image_bgr face_infoid_ante_embeddingface_kps align_faceinputbg_labelbg white_imagereturn_face_features_imagereturn_face_features_image_2original_image_bgrface_features_image id_cond_vit id_vit_hiddenid_cond_vit_normid_condrRs @r!process_face_embeddingsrks L UC$5$56I "I 9~9*qr  &k2U# Y'&&&= 003!!# = & &'1,566,,Q/J fg)22:>(():;>>v|T"-77::t4>>qAEI #..y@UWl/mnopq !((Q(= / 484 4 9 9 ;ooe, %*[[['%.%Q"',{{2{E'J$ \\*;S=N=NO-t<FFqIEQ DII"%A!"$5$@$@BSB[B[$$79KM^_!2|,%W[ej"Kzz+q!T:))K)9:Kii K(bG $  r#c t|tr/tjt |j d} nJtjt jtj|j d} t| d} | } t||||||||| | | \} } }}|jj}|j}|jddd}|j!dz}|j#tj$}t jtj|} | | | |fS)a Process face embeddings from an input image for inference, including alignment, feature extraction, and embedding concatenation. Args: face_helper_1: Face helper object (first helper) for alignment and landmark detection. clip_vision_model: Pre-trained CLIP vision model used for feature extraction. face_helper_2: Face helper object (second helper) for embedding extraction. eva_transform_mean: Mean values for image normalization before passing to EVA model. eva_transform_std: Standard deviation values for image normalization before passing to EVA model. app: Application instance used for face detection. device: Device (CPU or GPU) where the computations will be performed. weight_dtype: Data type of the weights for precision (e.g., `torch.float32`). img_file_path: Path to the input image file (string) or a numpy array representing an image. is_align_face: Boolean flag indicating whether face alignment should be performed (default: True). Returns: Tuple: - id_cond: Concatenated tensor of Ante face embedding and CLIP vision embedding. - id_vit_hidden: Hidden state of the CLIP vision model, a list of tensors. - image: Processed face image after feature extraction and alignment. - face_kps: Keypoints of the face detected in the image. )rRGBir(rr)r4strnparrayr convertrexif_transposer fromarrayr"rcpudetachsqueezepermutenumpyr*uint8)rsrtrurvrwrxryrz img_file_pathr|rr{rralign_crop_face_imagertensors r!process_face_embeddings_inferrs(J-%-8@@GH001OPXXY^_` $E4 0E?V   ?;G]18# & & ( / / 1F ^^ F ^^Aq! $F \\^c !F ]]288 $F  # #EOOF$; PQ (4- 802Q6 '$ 7.014+)#  Z HUlTmO1z:!!!#f%'vU+ -/K]_p ppr#)i)TT)NT)T),importlib.util importlibrrrrr-PILrrtorchvision.transformsr!torchvision.transforms.functionalrrutilsr r __name__rbutil find_spec_insightface_available_consisid_eva_clip_available_facexlib_availabler insightface.appr ImportErrorr rconsisid_eva_clip.constantsrrfacexlib.parsingr&facexlib.utils.face_restoration_helperrr"r7r;rrrr?r#r!rs  4?+ H "11-@L(~~778KLTXXnn..z:$F, h ii=SS t uu3H b cc.-8 6mtE3PBqr#