MCPcopy Create free account

hub / github.com/NJU-PCALab/STAR / functions

Functions1,973 in github.com/NJU-PCALab/STAR

⨍ Functions 1,973◇ Types & classes 452↳ Endpoints 3
↓ 1 callersFunctiongenerate_video
Generates a video based on the given prompt and saves it to the specified path. Parameters: - prompt (str): The description of the video
cogvideox-based/inference/cli_demo.py:40
↓ 1 callersFunctiongenerate_video
Generate a video based on the provided prompt and model path. Args: - pipe (CogVideoXPipeline): The pipeline for generating videos.
cogvideox-based/inference/streamlit_web_demo.py:48
↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid
(embed_dim, grid)
utils_data/opensora/models/layers/blocks.py:1186
↓ 1 callersFunctionget_3d_sincos_pos_embed
grid_size: int of the grid height and width t_size: int of the temporal size return: pos_embed: [t_size*grid_size*grid_size, embed_di
cogvideox-based/sat/dit_video_concat.py:85
↓ 1 callersMethodget_alpha
(self, image_only_indicator: torch.Tensor)
cogvideox-based/sat/sgm/modules/diffusionmodules/util.py:303
↓ 1 callersMethodget_alpha
(self, bs)
cogvideox-based/sat/sgm/modules/autoencoding/temporal_ae.py:54
↓ 1 callersMethodget_alpha
( self, )
cogvideox-based/sat/sgm/modules/autoencoding/temporal_ae.py:163
↓ 1 callersMethodget_alpha
( self, )
cogvideox-based/sat/sgm/modules/autoencoding/temporal_ae.py:229
↓ 1 callersFunctionget_args
()
cogvideox-based/tools/convert_weight_sat2hf.py:205
↓ 1 callersFunctionget_args
Parse all the args.
cogvideox-based/sat/arguments.py:54
↓ 1 callersFunctionget_batch
(keys, value_dict, N: Union[List, ListConfig], T=None, device="cuda")
cogvideox-based/sat/sample_sr.py:52
↓ 1 callersFunctionget_beta_schedule
This is the deprecated API for creating beta schedules. See get_named_beta_schedule() for the new library of schedules.
utils_data/opensora/schedulers/iddpm/gaussian_diffusion.py:71
↓ 1 callersFunctionget_beta_schedule
This is the deprecated API for creating beta schedules. See get_named_beta_schedule() for the new library of schedules.
utils_data/opensora/schedulers/dpms/dpm_solver.py:37
↓ 1 callersMethodget_discriminator_params
(self)
cogvideox-based/sat/sgm/models/autoencoder.py:192
↓ 1 callersMethodget_discriminator_params
(self)
cogvideox-based/sat/vae_modules/autoencoder.py:208
↓ 1 callersFunctionget_gaussian_kernel
(kernel_size, sigma)
utils_data/opensora/models/vsr/fdie_arch.py:41
↓ 1 callersMethodget_loss
(self, model_output, target, w)
cogvideox-based/sat/sgm/modules/diffusionmodules/loss.py:63
↓ 1 callersMethodget_loss
(self, model_output, target, w)
cogvideox-based/sat/sgm/modules/diffusionmodules/loss.py:117
↓ 1 callersFunctionget_model_numel
(model: torch.nn.Module)
video_super_resolution/scripts/train_sr.py:40
↓ 1 callersMethodget_mult
(self, h, s, t, t_next)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:267
↓ 1 callersMethodget_mult
(self, h, r, t, t_next, previous_sigma)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:310
↓ 1 callersMethodget_mult
(self, h, r, t, t_next, previous_sigma)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:381
↓ 1 callersMethodget_mult
(self, h, r, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:591
↓ 1 callersMethodget_mult
(self, h, r, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:705
↓ 1 callersFunctionget_named_beta_schedule
Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the limi
utils_data/opensora/schedulers/dpms/dpm_solver.py:68
↓ 1 callersMethodget_nll_loss
( self, rec_loss: torch.Tensor, weights: Optional[Union[float, torch.Tensor]] = None,
cogvideox-based/sat/sgm/modules/autoencoding/losses/discriminator_loss.py:289
↓ 1 callersMethodget_orders_and_timesteps_for_singlestep_solver
Get the order of each step for sampling by the singlestep DPM-Solver. We combine both DPM-Solver-1,2,3 to use all the function evalu
utils_data/opensora/schedulers/dpms/dpm_solver.py:605
↓ 1 callersMethodget_params
(self, clip)
utils_data/opensora/datasets/video_transforms.py:234
↓ 1 callersMethodget_spatial_pos_embed
(self, grid_size=None)
utils_data/opensora/models/stdit/stdit_qknorm_rope.py:348
↓ 1 callersMethodget_spatial_pos_embed
(self, grid_size=None)
utils_data/opensora/models/stdit/stdit_freq.py:333
↓ 1 callersMethodget_spatial_pos_embed
(self, grid_size=None)
utils_data/opensora/models/stdit/stdit_mmdit_qk.py:388
↓ 1 callersMethodget_spatial_pos_embed
(self, grid_size=None)
utils_data/opensora/models/stdit/stdit.py:318
↓ 1 callersMethodget_spatial_pos_embed
(self, grid_size=None)
utils_data/opensora/models/stdit/stdit_mmdit.py:390
↓ 1 callersMethodget_spatial_pos_embed
(self)
utils_data/opensora/models/dit/dit.py:158
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/pixart/pixart.py:263
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/vsr/fdie_arch.py:163
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/stdit/stdit_qknorm_rope.py:359
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/stdit/stdit_freq.py:349
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/stdit/stdit_mmdit_qk.py:399
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/stdit/stdit.py:329
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/stdit/stdit_mmdit.py:401
↓ 1 callersMethodget_temporal_pos_embed
(self)
utils_data/opensora/models/dit/dit.py:166
↓ 1 callersMethodget_text_embeddings
(self, texts)
utils_data/opensora/models/text_encoder/t5.py:113
↓ 1 callersMethodget_text_embeddings
(self, texts)
video_to_video/modules/t5.py:113
↓ 1 callersFunctionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
cogvideox-based/sat/sgm/modules/diffusionmodules/model.py:23
↓ 1 callersMethodget_trainable_params
(self)
cogvideox-based/sat/sgm/modules/autoencoding/losses/video_loss.py:549
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_panda50m.py:24
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_path2text.py:21
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_ours1m.py:20
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_celebv.py:21
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_ours1m1080p.py:21
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_panda50m_dense.py:23
↓ 1 callersFunctionget_transforms_video
(resolution=256)
utils_data/opensora/datasets/datasets_webvid10m.py:20
↓ 1 callersFunctionget_unique_embedder_keys_from_conditioner
(conditioner)
cogvideox-based/sat/sample_sr.py:48
↓ 1 callersMethodget_variables
(self, sigma, sigma_down)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:261
↓ 1 callersMethodget_variables
(self, sigma, next_sigma, previous_sigma=None)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:299
↓ 1 callersMethodget_variables
(self, sigma, next_sigma, previous_sigma=None)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:370
↓ 1 callersMethodget_variables
(self, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt=None)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:575
↓ 1 callersMethodget_variables
(self, alpha_cumprod_sqrt, next_alpha_cumprod_sqrt, previous_alpha_cumprod_sqrt=None)
cogvideox-based/sat/sgm/modules/diffusionmodules/sampling.py:689
↓ 1 callersMethodget_velocity
(self, x0, xt, t)
video_to_video/diffusion/diffusion_sdedit.py:32
↓ 1 callersMethodget_x0
(self, v, xt, t)
video_to_video/diffusion/diffusion_sdedit.py:38
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_panda50m.py:89
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_path2text.py:83
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_ours1m.py:127
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_webvid.py:83
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets.py:64
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_celebv.py:85
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_ours1m1080p.py:83
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_panda50m_dense.py:99
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_old.py:74
↓ 1 callersMethodgetitem
(self, index)
utils_data/opensora/datasets/datasets_webvid10m.py:82
↓ 1 callersFunctiongradient_penalty
(images, output)
cogvideox-based/sat/sgm/modules/autoencoding/magvit2_pytorch.py:119
↓ 1 callersFunctiongradient_penalty
(images, output)
cogvideox-based/sat/sgm/modules/autoencoding/losses/video_loss.py:61
↓ 1 callersFunctionhflip
Args: clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W) Returns: flipped clip (torch.tensor): Size is (T
utils_data/opensora/datasets/video_transforms.py:204
↓ 1 callersFunctionhigh_pass_filter
对输入张量进行高通滤波，提取高频和低频部分。 参数: x (torch.Tensor): 形状为 [B, C, T, H, W] 的输入张量，值范围在 [-1, 1]。 kernel_size (int): 高斯核的大小。 返回:
utils_data/opensora/models/vsr/fdie_arch.py:18
↓ 1 callersFunctionhinge_discr_loss
(fake, real)
cogvideox-based/sat/sgm/modules/autoencoding/losses/video_loss.py:37
↓ 1 callersFunctionhinge_gen_loss
(fake)
cogvideox-based/sat/sgm/modules/autoencoding/losses/video_loss.py:41
↓ 1 callersMethodidx_to_sigma
(self, idx)
cogvideox-based/sat/sgm/modules/diffusionmodules/sigma_sampling.py:71
↓ 1 callersMethodidx_to_sigma
(self, idx)
cogvideox-based/sat/sgm/modules/diffusionmodules/denoiser.py:68
↓ 1 callersMethodindices_to_codes
(self, indices, project_out=True)
cogvideox-based/sat/sgm/modules/autoencoding/regularizers/lookup_free_quantization.py:145
↓ 1 callersMethodindices_to_codes
Inverse of `codes_to_indices`.
cogvideox-based/sat/sgm/modules/autoencoding/regularizers/finite_scalar_quantization.py:118
↓ 1 callersFunctioninfer
( prompt: str, num_inference_steps: int, guidance_scale: float, progress=gr.Pr
cogvideox-based/inference/gradio_web_demo.py:91
↓ 1 callersMethodinit_conv_
(self, conv)
cogvideox-based/sat/sgm/modules/autoencoding/magvit2_pytorch.py:749
↓ 1 callersMethodinit_conv_
(self, conv)
cogvideox-based/sat/sgm/modules/autoencoding/magvit2_pytorch.py:779
↓ 1 callersMethodinit_decoder
(self, config)
cogvideox-based/sat/sgm/modules/autoencoding/losses/lpips.py:27
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
cogvideox-based/sat/vae_modules/autoencoder.py:75
↓ 1 callersFunctioninitialize_distributed
Initialize torch.distributed.
cogvideox-based/sat/arguments.py:179
↓ 1 callersMethodinitialize_temporal
(self)
utils_data/opensora/models/stdit/stdit_qknorm_rope.py:378
↓ 1 callersMethodinitialize_temporal
(self)
utils_data/opensora/models/stdit/stdit_freq.py:368
↓ 1 callersMethodinitialize_temporal
(self)
utils_data/opensora/models/stdit/stdit_mmdit_qk.py:418
↓ 1 callersMethodinitialize_temporal
(self)
utils_data/opensora/models/stdit/stdit.py:348
↓ 1 callersMethodinitialize_temporal
(self)
utils_data/opensora/models/stdit/stdit_mmdit.py:427
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/pixart/pixart.py:277
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/stdit/stdit_qknorm_rope.py:383
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/stdit/stdit_freq.py:375
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/stdit/stdit_mmdit_qk.py:423
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/stdit/stdit.py:353
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/stdit/stdit_mmdit.py:432
↓ 1 callersMethodinitialize_weights
(self)
utils_data/opensora/models/dit/dit.py:226
↓ 1 callersFunctioninject_trainable_lora_extended
( model: nn.Module, target_replace_module: Set[str] = None, rank: int = 4, scale: float = 1.0,
cogvideox-based/sat/sgm/modules/diffusionmodules/lora.py:286
← previousnext →501–600 of 1,973, ranked by callers