MCPcopy Create free account

hub / github.com/360CVGroup/FancyVideo / functions

Functions243 in github.com/360CVGroup/FancyVideo

⨍ Functions 243◇ Types & classes 62
Methodforward
( self, x, context=None, mask=None, additional_tokens=None, n_
fancyvideo/models/cv_vae/vae_models.py:111
Methodforward
(self, x)
fancyvideo/models/cv_vae/vae_models.py:220
Methodforward
(self, x)
fancyvideo/models/cv_vae/vae_models.py:257
Methodforward
(self, input: Tensor)
fancyvideo/models/cv_vae/vae_models.py:304
Methodforward
(self, input: Tensor)
fancyvideo/models/cv_vae/vae_models.py:338
Methodforward
(self, x, temb=None)
fancyvideo/models/cv_vae/vae_models.py:396
Methodforward
(self, x)
fancyvideo/models/cv_vae/vae_models.py:425
Methodforward
(self, x, **kwargs)
fancyvideo/models/cv_vae/vae_models.py:469
Methodforward
(self, x, **kwargs)
fancyvideo/models/cv_vae/vae_models.py:548
Methodforward
(self, x, **kwargs)
fancyvideo/models/cv_vae/vae_models.py:660
Methodforward
(self, x, context=None, mask=None, **unused_kwargs)
fancyvideo/models/cv_vae/vae_models.py:674
Methodforward
(self, z, **kwargs)
fancyvideo/models/cv_vae/vae_models.py:1001
Methodforward
r""" Args: sample (`torch.FloatTensor`): Input sample. sample_posterior (`bool`, *optional*, defaults to `False`):
fancyvideo/models/cv_vae/modeling_vae.py:103
Methodforward
(self, hidden_states,encoder_hidden_states=None, attention_mask=None, video_length=16)
fancyvideo/models/ctgm/attention.py:188
Methodforward
(self, hidden_states, encoder_hidden_states=None, timestep=None, return_dict: bool = True)
fancyvideo/models/ctgm/attention.py:517
Methodforward
(self, hidden_states, encoder_hidden_states=None, timestep=None, attention_mask=None, video_length=None)
fancyvideo/models/ctgm/attention.py:727
Methodforward
(self, input_tensor, temb, encoder_hidden_states, attention_mask=None, anchor_frame_idx=None)
fancyvideo/models/ctgm/temporal_cross_module.py:87
Methodforward
(self, hidden_states, encoder_hidden_states=None, attention_mask=None)
fancyvideo/models/ctgm/temporal_cross_module.py:147
Methodforward
(self, hidden_states, encoder_hidden_states=None, attention_mask=None, video_length=None)
fancyvideo/models/ctgm/temporal_cross_module.py:222
Methodforward
(self, hidden_states, encoder_hidden_states=None, attention_mask=None, video_length=None)
fancyvideo/models/ctgm/temporal_cross_module.py:282
Methodforward
(self, x: torch.Tensor)
fancyvideo/models/long_clip/model_longclip.py:42
Methodforward
(self, x)
fancyvideo/models/long_clip/model_longclip.py:68
Methodforward
(self, x)
fancyvideo/models/long_clip/model_longclip.py:138
Methodforward
(self, x: torch.Tensor)
fancyvideo/models/long_clip/model_longclip.py:160
Methodforward
(self, x: torch.Tensor)
fancyvideo/models/long_clip/model_longclip.py:167
Methodforward
(self, x: torch.Tensor)
fancyvideo/models/long_clip/model_longclip.py:189
Methodforward
(self, x: torch.Tensor)
fancyvideo/models/long_clip/model_longclip.py:202
Methodforward
(self, x: torch.Tensor)
fancyvideo/models/long_clip/model_longclip.py:223
Methodget_last_layer
(self, **kwargs)
fancyvideo/models/cv_vae/vae_models.py:998
Functionget_timestep_embedding
This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches
fancyvideo/models/cv_vae/vae_models.py:42
Functioninitialize_weights_to_zero
(m)
fancyvideo/models/unet.py:38
Functionload
Load a long CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model
fancyvideo/models/long_clip/longclip.py:46
Functionload_from_clip
Load from CLIP model for fine-tuning Parameters ---------- name : str A model name listed by `clip.available_models()`, or the p
fancyvideo/models/long_clip/longclip.py:136
Functionload_weights
( animation_pipeline, # motion module motion_module_path = "", motion_module_lora_conf
fancyvideo/utils/util.py:94
Methodmake_lora_conv
(ori_conv, adapter_name, r, inflated=False)
fancyvideo/pipelines/fancyvideo_infer_pipeline.py:270
Functionsave_videos_grid
(videos: torch.Tensor, path: str, rescale=False, n_rows=6, fps=8)
fancyvideo/utils/util.py:21
Methodset_attention_slice
(self, slice_size)
fancyvideo/models/ctgm/attention.py:182
Methodset_use_memory_efficient_attention_xformers
(self, use_memory_efficient_attention_xformers: bool)
fancyvideo/models/ctgm/attention.py:699
Functionstable_unclip_image_encoder
Returns the image processor and clip image encoder for the img2img unclip pipeline. We currently know of two types of stable unclip models w
fancyvideo/utils/convert_from_ckpt.py:866
Functionstable_unclip_image_noising_components
Returns the noising components for the img2img and txt2img unclip pipelines. Converts the stability noise augmentor into 1. a `StableUnC
fancyvideo/utils/convert_from_ckpt.py:899
Methodstem
(x)
fancyvideo/models/long_clip/model_longclip.py:139
Functiontokenize
Returns the tokenized representation of given input string(s) Parameters ---------- texts : Union[str, List[str]] An input s
fancyvideo/models/long_clip/longclip.py:313
Functionzero_rank_print
(s)
fancyvideo/utils/util.py:17
← previous201–243 of 243, ranked by callers