Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/MotrixLab/ViMoGen
/ functions
Functions
457 in github.com/MotrixLab/ViMoGen
⨍
Functions
457
◇
Types & classes
71
Method
get_fsdp_wrap_module_list
(self, )
models/transformer/wan/modules/tm2m_model.py:647
Function
get_image_size
(resolution, ar_ratio)
datasets/aspect.py:467
Function
get_local_rank
()
parallel/utils.py:35
Function
get_local_world_size
()
parallel/utils.py:39
Method
get_min_snr_weight
the original min snr weighting in paper https://arxiv.org/abs/2303.09556.
trainer/scheduler.py:17
Method
get_min_snr_weight_cogvideo
modified loss weighting, so that the weighting at zero snr is not zero the original min snr weighting in paper https://arxiv.org/abs/2
trainer/scheduler.py:45
Method
get_min_snr_weight_modified
modified loss weighting, so that the weighting at zero snr is not zero the original min snr weighting in paper https://arxiv.org/abs/2
trainer/scheduler.py:29
Function
get_node_rank
()
parallel/utils.py:56
Function
get_num_frames
(num_frames)
datasets/aspect.py:492
Method
get_prob
(self, bucket_id)
datasets/bucket.py:136
Method
get_projection_matrix
(self, width=None, height=None)
mbench/render.py:39
Function
get_prompt_from_filename
Extract prompt from video filename by removing extensions and special characters Args: filename: Video filename Ret
mbench/utils.py:8
Function
get_rank
()
parallel/utils.py:43
Function
get_scheduler
(beta_type: str = None, use_dpm_solver: bool = False)
trainer/scheduler.py:93
Function
get_side_list_64_base
()
datasets/bucket_config.py:76
Function
get_smooth_dynamic_cfg_scale_list
(cfg_scale, num_inference_steps)
trainer/scheduler.py:119
Function
guess_cogvideo_config_from_state_dict
(state_dict: dict)
models/transformer/utils.py:128
Function
guess_cogvideo_config_from_state_dict
(state_dict: dict)
models/transformer/wan/modules/utils.py:128
Function
hash_state_dict_keys
(state_dict, with_shape=True)
models/transformer/utils.py:205
Function
help
(args)
mbench/cli/mbench.py:18
Function
init_weights
(m)
models/transformer/wan/modules/t5.py:27
Function
load_safetensors
(in_path: str)
models/transformer/wan/modules/utils.py:102
Function
load_single_motion
(entry)
scripts/prepare_training_data.py:30
Method
load_state_dict
(self, state_dict: dict)
datasets/sampler.py:56
Method
load_state_dict
(self, state_dict: dict)
datasets/sampler.py:317
Method
load_state_dict
(self, state_dict: dict)
datasets/sampler.py:358
Method
loss_weight
(self, sigmas, weight_type: str = 'SNR')
trainer/sd3_scheduler.py:155
Function
lr_lambda
(current_step)
trainer/base_trainer.py:414
Function
main
()
mbench/cli/mbench.py:7
Method
merge_bucket
(bucket_dict: OrderedDict, min_length: int)
datasets/multi_resolution_sampler.py:41
Function
on_main_process
Decorator to selectively run the decorated function on the main process only based on the `main_process_only` attribute in a class. Checks at
parallel/utils.py:15
Function
prepare_extra_step_kwargs
(scheduler, generator, eta=0.0)
models/transformer/utils.py:73
Function
prepare_extra_step_kwargs
(scheduler, generator, eta=0.0)
models/transformer/wan/modules/utils.py:73
Method
qkv_fn
(x)
models/transformer/wan/modules/tm2m_model.py:288
Method
qkv_fn
(x)
models/transformer/wan/modules/t2m_model.py:287
Function
quaternion_to_rot6d
Convert 4d quaternion to 6d rotation representation. Shape: - Input: :Torch:`(N, 4)` - Output: :Torch:`(N, 6)`
motion_rep/rotation_transform.py:102
Function
randn_tensor
A helper function to create random tensors on the desired `device` with the desired `dtype`. When passing a list of generators, you can seed
models/transformer/wan/modules/utils.py:8
Function
register_subparsers
(subparser)
mbench/cli/evaluate.py:7
Method
reset
(self)
datasets/sampler.py:50
Method
reset
(self)
datasets/sampler.py:352
Method
retrieve_inference_timesteps_and_sigma
( self, num_inference_steps: int, frames: int, height: int, width: int
trainer/sd3_scheduler.py:141
Method
return_to_timestep
(self, timestep, sample, sample_stablized)
trainer/scheduler.py:199
Function
rot6d_to_quaternion
Convert 6d rotation representation to 4d quaternion. Shape: - Input: :Torch:`(N, 4)` - Output: :Torch:`(N, 6)`
motion_rep/rotation_transform.py:112
Method
sample_t
(self, batch_size: int, training_iter: int = None)
trainer/scheduler.py:81
Method
sample_t_and_sigma
( self, batch_size: int, frames: int, height: int, width: int,
trainer/sd3_scheduler.py:30
Function
seed_worker
(worker_id)
datasets/dataloader.py:18
Function
smpl_to_joints_and_verts
Convert SMPL pose parameters to joint positions and vertices. smpl_model: SMPL model object smpl_params: Dictionary of SMPL parameters (e
mbench/pose_quality.py:38
Method
state_dict
(self, step)
datasets/sampler.py:53
Method
state_dict
(self, num_steps: int)
datasets/sampler.py:306
Method
state_dict
(self, step)
datasets/sampler.py:355
Method
state_dict_converter
()
models/transformer/wan/modules/tm2m_model.py:785
Method
state_dict_converter
()
models/transformer/wan/modules/t2m_model.py:705
Method
step
(self, model_output, timestep, sample, to_final=False)
trainer/scheduler.py:186
Function
stringify_cmd
(cmd_ls)
mbench/cli/evaluate.py:48
Method
tracker
(self)
parallel/logging.py:91
Function
validate_video_path
Validate that a video file exists and has a supported extension Args: video_path: Path to video file Returns:
mbench/utils.py:62
Method
warning_once
This method is identical to `logger.warning()`, but will emit the warning with the same message only once. Note: The cache is for the
parallel/logging.py:57
← previous
401–457 of 457, ranked by callers