Process multiple frames. Args: video: VideoReader object frame_ids: List of frame indices to process

Center crop and resize image to maintain aspect ratio. Args: image: Input image (PIL Image or numpy array) as

process image pose Args: ref_image (np.ndarray): reference image pixel value Returns: np.ndarray: pose visual image in RGB-m

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

To calculate the affine matrix, three pairs of points are required. This function is used to get the 3rd point, given 2D points a & b. The 3r

blend color according to point conf

vis dwpose outputs Args: pose (List): DWposeDetector outputs in dwpose_detector.py H (int): height W (int): width

Add watermark text to the image. Args: image: Input image as numpy array (H,W,C) Returns:

Reads a video using decord, resizes frames, limits the frame count, and aligns frames. Args: video_path (str): Path to the video

Draws samples from an lognormal distribution.

Appends dimensions to the end of a tensor until it has target_dims dimensions.

Compute padding tuple.

Extend the scale to match the given aspect ratio. Args: scale (np.ndarray): The image scale (w, h) in shape (2, ) aspect_ratio (f

Initialize weights with He. initialization and zero out the biases

Initialize weights with He. initialization and zero out the biases

Rotate a point by an angle. Args: pt (np.ndarray): 2D point coordinates (x, y) in shape (2, ) angle_rad (float): rotation angle i

Aligns the input image using scaling and bias parameters. If the input is in channel-first format (C, H, W), it will be converted to

Aligns all frames of the input video. Args: video (np.ndarray): Video tensor with shape (F, C, H, W). p_scale (tuple): S

Transform the bbox format from (x,y,w,h) into (center, scale) Args: bbox (ndarray): Bounding box(es) in shape (4,) or (n, 4), formatted

Calculate pixel-wise similarity ratio between reference and generated videos. Args: reference_folder: Path to directory containing re

create mimicmotion pipeline and load pretrained weight Args: infer_config (str): device (str or torch.device): "cpu" or "cuda:{d

Modulate simcc distribution with Gaussian. Args: simcc_x (np.ndarray[K, Wx]): model predicted simcc in x. simcc_y (np.ndarray[K,

Get maximum response location and value from simcc representations. Note: instance number: N num_keypoints: K heatmap hei

preprocess ref image pose and video pose Args: video_path (str): video pose path ref_image (np.ndarray): reference image

Calculate the affine transformation matrix that can warp the bbox area in the input image to the output size. Args: center (np.ndarra

Inference RTMPose model. Args: sess (ort.InferenceSession): ONNXRuntime session. img (np.ndarray): Input image in shape. Ret

run human detect

run pose detect Args: session (ort.InferenceSession): ONNXRuntime session. out_bbox (np.ndarray): bbox list oriImg (np.n

Multiclass NMS implemented in Numpy. Class-aware version. Args: boxes (np.ndarray): shape=(N,4); N is number of boxes scores (np.

Single class NMS implemented in Numpy. Args: boxes (np.ndarray): shape=(N,4); N is number of boxes scores (np.ndarray): the score

Patch GEGLU with inplace multiplication to save GPU memory.

Postprocess for RTMPose model output. Args: outputs (np.ndarray): Output of RTMPose model. model_input_size (tuple): RTMPose mode

Preprocess input data for training phase. Args: video_path: Path to the input video pose_path: Path to the pose video

Preprocess the reference image pose and video pose, and extract additional references for object appearance, object trajectory, and hand vide

Do preprocessing for RTMPose model inference. Args: img (np.ndarray): Input image in shape. input_size (tuple): Input image size

Process single frame from video. Args: video: VideoReader object frame_id: Frame index to process

Run the anchor crafter pipeline to synthesize video frames based on multiple inputs. Args: pipeline (AnchorCrafterPipeline): The pipe

Get the bbox image as the model input by affine transform. Args: input_size (dict): The input size of the model. bbox_scale (dict

r""" The call function to the pipeline for generation. Args: image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torc

call to process dwpose-detect Args: oriImg (np.ndarray): detected image

construnct base model components and load pretrained svd model except pose-net Args: base_model_path (str): pretrained svd model p