简化版视频处理：根据FPS抽帧 + Resize

x: [B, L, N, C]. grid_sizes: [B, 3]. freqs: [M, C // 2].

Version-agnostic workspace limit.

calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the configuration of video.

calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the configuration of video.

Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the multistep DPMSolver.

Store rows of multiple numpy arrays in a single LMDB. Each row is stored separately with a naming convention.

r""" Reconstruct video tensors from patch embeddings. Args: x (List[Tensor]): List of patchified features

Compute the KL grad (eq 7 in https://arxiv.org/abs/2311.18828). Input: - noisy_image_or_video: a tensor with shape [B, F,

Compute the KL grad (eq 7 in https://arxiv.org/abs/2311.18828). Input: - noisy_image_or_video: a tensor with shape [B, F,

Compute the KL grad (eq 7 in https://arxiv.org/abs/2311.18828). Input: - noisy_image_or_video: a tensor with shape [B, F,

Simulate the generator's input from noise to avoid training/inference mismatch. See Sec 4.5 of the DMD2 paper (https://arxiv.org/abs/

Simulate the generator's input from noise to avoid training/inference mismatch. See Sec 4.5 of the DMD2 paper (https://arxiv.org/abs/

Inputs: rewards_A: [B, N] rewards_B: [B, N] scores_A: [B, N] scores_B: [B, N] chosen_label: [B, N] Ou

Convert flow matching's prediction to x0 prediction. flow_pred: the prediction with shape [B, C, H, W] xt: the input noisy da

r""" Forward pass through the diffusion model Args: x (List[Tensor]): List of input video tensors, each w

r""" Run the diffusion model with kv caching. See Algorithm 2 of CausVid paper https://arxiv.org/abs/2412.07772 for details. T

r""" Forward pass through the diffusion model Args: x (List[Tensor]): List of input video tensors, each w

Initialize the step_index counter for the scheduler.

Initialize the step_index counter for the scheduler.

Initialize a Per-GPU cross-attention cache for the Wan model.

Initialize a Per-GPU cross-attention cache for the Wan model.

Initialize a Per-GPU cross-attention cache for the Wan model.

Initialize a Per-GPU cross-attention cache for the Wan model.

Lazy initialize the inference pipeline during the first backward simulation run. Here we encapsulate the inference code with a model-

Lazy initialize the inference pipeline during the first backward simulation run. Here we encapsulate the inference code with a model-

Initialize a Per-GPU KV cache for the Wan model.

Initialize a Per-GPU KV cache for the Wan model.

Initialize a Per-GPU KV cache for the Wan model.

Initialize a Per-GPU KV cache for the Wan model.

Utility function to remap the state_dict keys to fit the PEFT model by inserting the adapter name.

we will divide the token sequence into the following format [1 latent frame] [1 latent frame] ... [1 latent frame] We use fle

we will divide the token sequence into the following format [1 latent frame] [N latent frame] ... [N latent frame] The first

Given a tensor containing the whole ODE sampling trajectories, randomly choose an intermediate timestep and return the latent as well

Prepare `inputs` before feeding them to the model, converting them to tensors if they are not already and handling potential state.

Prepare `inputs` before feeding them to the model, converting them to tensors if they are not already and handling potential state.

we will divide the token sequence into the following format [1 latent frame] [1 latent frame] ... [1 latent frame] We use fle

Compute the DMD loss (eq 7 in https://arxiv.org/abs/2311.18828). Input: - image_or_video: a tensor with shape [B, F, C, H

Compute the DMD loss (eq 7 in https://arxiv.org/abs/2311.18828). Input: - image_or_video: a tensor with shape [B, F, C, H

Compute the DMD loss (eq 7 in https://arxiv.org/abs/2311.18828). Input: - image_or_video: a tensor with shape [B, F, C, H

Compute the DMD loss (eq 7 in https://arxiv.org/abs/2311.18828). Input: - image_or_video: a tensor with shape [B, F, C, H

Convert Good/Same/Bad csv data to reward data. Args: example (dict): A dataframe containing the GSB csv data. data_dir (str)

Convert the model output to the corresponding type the DPMSolver/DPMSolver++ algorithm needs. DPM-Solver is designed to discretize an

r""" Convert the model output to the corresponding type the UniPC algorithm needs. Args: model_output (`torch.Tensor`):

One step for the first-order DPMSolver (equivalent to DDIM). Args: model_output (`torch.Tensor`): The dir

Find the target linear modules for LoRA.

r""" Args: x(Tensor): Shape [B, L1, C] e(Tensor): Shape [B, C]

Args: new_k: [B, sink_size, num_heads, head_dim] new_v: [B, sink_size, num_heads, head_dim] current_sink

r""" Initialize model parameters using Xavier initialization.

r""" Initialize model parameters using Xavier initialization.