Functions — github.com/JaydenLyh/Reward-Forcing

Methodcritic_loss

Generate image/videos from noise and train the critic with generated samples. The noisy input to the generator is backward simulated.

model/sid.py:188

Methodcritic_loss

Generate image/videos from noise and train the critic with generated samples. The noisy input to the generator is backward simulated.

model/dmd.py:237

Functioncrop_or_pad_yield_mask

(x, length)

demo_utils/utils.py:480

Methodcross_attn_ffn

(x, context, context_lens, e, crossattn_cache=None)

wan/modules/causal_model.py:342

Methodcross_attn_ffn

(x, context, context_lens, e)

wan/modules/model.py:346

Methodcross_attn_ffn

(x, context)

wan/modules/model.py:428

Methodcustom_forward

(*inputs, **kwargs)

wan/modules/causal_model.py:828

Methodcustom_forward

(*inputs, **kwargs)

wan/modules/model.py:724

Functiond_resize

(x, y)

demo_utils/utils.py:36

Functiondim3

(x)

demo_utils/utils.py:476

Functiondim4

(x)

demo_utils/utils.py:472

Functiondim5

(x)

demo_utils/utils.py:468

Functionduplicate_prefix_to_suffix

(x, count, zero_out=False)

demo_utils/utils.py:429

Functionencode

(self, videos: torch.Tensor)

inference.py:116

Methodextend

(self, prompt, system_prompt, seed=-1, *args, **kwargs)

wan/utils/prompt_extend.py:196

Methodextend

(self, prompt, system_prompt, seed=-1, *args, **kwargs)

wan/utils/prompt_extend.py:366

Functionextend_dim

(x, dim, minimal_length, zero_pad=False)

demo_utils/utils.py:495

Methodextend_with_img

(self, prompt, system_prompt, image: U

wan/utils/prompt_extend.py:232

Methodextend_with_img

(self, prompt, system_prompt, image: U

wan/utils/prompt_extend.py:397

Functionfake_diffusers_current_device

(model: torch.nn.Module, target_device: torch.device)

demo_utils/memory.py:61

Methodforward

( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N

videoalign/trainer.py:71

Methodforward

(self, text_prompts: List[str])

utils/wan_wrapper.py:38

Methodforward

( self, noisy_image_or_video: torch.Tensor, conditional_dict: dict, timestep: torch.Te

utils/wan_wrapper.py:220

Methodforward

r""" Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor

wan/modules/causal_model.py:110

Methodforward

r""" Args: x(Tensor): Shape [B, L, C] e(Tensor): Shape [B, F, 6, C] seq_lens(Tensor): Shape [B], length of

wan/modules/causal_model.py:303

Methodforward

r""" Args: x(Tensor): Shape [B, L1, C] e(Tensor): Shape [B, F, 1, C]

wan/modules/causal_model.py:375

Methodforward

( self, *args, **kwargs )

wan/modules/causal_model.py:1021

Methodforward

(self, x)

wan/modules/clip.py:43

Methodforward

(self, x)

wan/modules/clip.py:49

Methodforward

x: [B, L, C].

wan/modules/clip.py:74

Methodforward

(self, x)

wan/modules/clip.py:146

Methodforward

x: [B, L, C].

wan/modules/clip.py:186

Methodforward

(self, x, interpolation=False, use_31_block=False)

wan/modules/clip.py:279

Methodforward

(self, ids)

wan/modules/clip.py:315

Methodforward

imgs: [B, 3, H, W] of torch.float32. - mean: [0.48145466, 0.4578275, 0.40821073] - std: [0.26862954, 0.2613025

wan/modules/clip.py:406

Methodforward

(self, x)

wan/modules/t5.py:48

Methodforward

(self, x)

wan/modules/t5.py:61

Methodforward

x: [B, L1, C]. context: [B, L2, C] or None. mask: [B, L2] or [B, L1, L2] or None.

wan/modules/t5.py:86

Methodforward

(self, x)

wan/modules/t5.py:136

Methodforward

(self, x, mask=None, pos_bias=None)

wan/modules/t5.py:170

Methodforward

(self, x, mask=None, encoder_states=None, enco

wan/modules/t5.py:206

Methodforward

(self, lq, lk)

wan/modules/t5.py:233

Methodforward

(self, ids, mask=None)

wan/modules/t5.py:303

Methodforward

(self, ids, mask=None, encoder_states=None, encoder_mask=None)

wan/modules/t5.py:351

Methodforward

(self, encoder_ids, encoder_mask, decoder_ids, decoder_mask)

wan/modules/t5.py:408

Methodforward

(self, x, cache_x=None)

wan/modules/vae.py:28

Methodforward

(self, x)

wan/modules/vae.py:51

Methodforward

Fix bfloat16 support for nearest neighbor interpolation.

wan/modules/vae.py:59

Methodforward

(self, x, feat_cache=None, feat_idx=[0])

wan/modules/vae.py:101

Methodforward

(self, x, feat_cache=None, feat_idx=[0])

wan/modules/vae.py:202

Methodforward

(self, x)

wan/modules/vae.py:240

Methodforward

(self, x, feat_cache=None, feat_idx=[0])

wan/modules/vae.py:318

Methodforward

(self, x, feat_cache=None, feat_idx=[0])

wan/modules/vae.py:423

Methodforward

x: [B, L, C].

wan/modules/xlm_roberta.py:27

Methodforward

(self, x, mask)

wan/modules/xlm_roberta.py:66

Methodforward

ids: [B, L] of torch.LongTensor.

wan/modules/xlm_roberta.py:118

Methodforward

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

wan/modules/model.py:78

Methodforward

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

wan/modules/model.py:94

Methodforward

r""" Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor

wan/modules/model.py:127

Methodforward

r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]

wan/modules/model.py:161

Methodforward

r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]

wan/modules/model.py:199

Methodforward

r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]

wan/modules/model.py:240

Methodforward

r""" Args: x(Tensor): Shape [B, L, C] e(Tensor): Shape [B, 6, C] seq_lens(Tensor): Shape [B], length of ea

wan/modules/model.py:315

Methodforward

r""" Args: x(Tensor): Shape [B, L, C] e(Tensor): Shape [B, 6, C] seq_lens(Tensor): Shape [B], length of ea

wan/modules/model.py:397

Methodforward

(self, image_embeds)

wan/modules/model.py:479

Methodforward

(self)

wan/modules/model.py:490

Methodforward

( self, *args, **kwargs )

wan/modules/model.py:626

Methodforward

(self, x, feat_cache=None, feat_idx=[0])

demo_utils/vae_block3.py:45

Methodforward

( self, z: torch.Tensor, *feat_cache: List[torch.Tensor] )

demo_utils/vae_block3.py:147

Methodforward

( self, x: torch.Tensor, feat_cache: List[torch.Tensor] )

demo_utils/vae_block3.py:242

Methodforward

(self, x, feat_cache_1, feat_cache_2)

demo_utils/vae.py:29

Methodforward

(self, x, is_first_frame, feat_cache)

demo_utils/vae.py:73

Methodforward

( self, z: torch.Tensor, is_first_frame: torch.Tensor, *feat_c

demo_utils/vae.py:168

Methodforward

( self, x: torch.Tensor, is_first_frame: torch.Tensor, feat_ca

demo_utils/vae.py:254

Methodforward

(self, *test_inputs)

demo_utils/vae.py:381

Methodforward

(self, x)

demo_utils/taehv.py:21

Methodforward

(self, x, past)

demo_utils/taehv.py:33

Methodforward

(self, x)

demo_utils/taehv.py:43

Methodforward

(self, x)

demo_utils/taehv.py:54

Methodforward

(self, x)

demo_utils/taehv.py:236

Functionframe_mark

(x)

demo_utils/utils.py:401

Functionfreeze_module

(m)

demo_utils/utils.py:213

Methodgenerate

r""" Generates video frames from input image and text prompt using diffusion process. Args: input_prompt (`str`):

wan/image2video.py:129

Functiongenerate_random_prompt_from_tags

(tags_str, min_length=3, max_length=32)

demo_utils/utils.py:232

Functiongenerate_timestamp

()

demo_utils/utils.py:587

Methodgenerate_video

(self, pipeline, prompts, image=None)

trainer/distillation.py:294

Methodgenerate_video

(self, pipeline, prompts, image=None)

trainer/diffusion.py:235

Methodgenerate_video

(self, pipeline, prompts, image=None)

trainer/gan.py:324

Methodgenerate_video

(self, pipeline, prompts, image=None)

trainer/rewarded_distillation.py:298

Methodgenerator_loss