Functions — github.com/Doubiiu/ToonCrafter

hub / github.com/Doubiiu/ToonCrafter / functions

Functions475 in github.com/Doubiiu/ToonCrafter

⨍ Functions 475◇ Types & classes 111

Methodforward

(self, input, timesteps, skip_video=False)

lvdm/models/autoencoder_dualref.py:929

Methodforward

(self, x, timesteps, skip_video=False)

lvdm/models/autoencoder_dualref.py:970

Methodforward

(self, x, timesteps, skip_time_block=False)

lvdm/models/autoencoder_dualref.py:1040

Methodforward

(self, input: torch.Tensor, **kwargs)

lvdm/models/autoencoder_dualref.py:1117

Functionframes_to_mp4

(frame_dir,output_path,fps)

utils/save_video.py:14

Functiongather_data

gather data from multiple processes to one list

lvdm/common.py:8

Functionget_dirlist

(path)

scripts/evaluation/funcs.py:101

Functionget_filelist

(data_dir, ext='*')

scripts/evaluation/funcs.py:96

Methodget_last_layer

(self)

lvdm/modules/networks/ae_modules.py:362

Methodget_last_layer

(self, **kwargs)

lvdm/models/autoencoder_dualref.py:486

Methodget_last_layer

(self)

lvdm/models/autoencoder_dualref.py:832

Methodget_last_layer

(self, skip_time_mix=False, **kwargs)

lvdm/models/autoencoder_dualref.py:1142

Functionget_latent_z

(model, videos)

scripts/evaluation/inference.py:157

Methodget_unconditional_conditioning

(self, bs, device="cuda")

lvdm/modules/encoders/condition.py:44

Functiongroup_by_key_prefix

(prefix, d)

lvdm/modules/x_transformer.py:105

lvdm/modules/attention_svd.py:79

Functioninner

(*args, **kwargs)

lvdm/modules/x_transformer.py:64

lvdm/distributions.py:42

Functionload_image_batch

(filepath_list, image_size=(256,256))

scripts/evaluation/funcs.py:195

Functionload_npz_from_dir

(data_dir)

utils/utils.py:45

Functionload_npz_from_paths

scripts/evaluation/funcs.py:145

Functionload_video_batch

Notice about some special cases: 1. video_frames=-1 means to take all the frames (with fs=1) 2. when the total video frames is less th

scripts/evaluation/funcs.py:156

Methodlog_images

(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs)

lvdm/models/ddpm3d.py:420

Methodlog_images

log images for LatentDiffusion

lvdm/models/ddpm3d.py:837

Methodlog_images

log images for LatentVisualDiffusion

lvdm/models/ddpm3d.py:1137

Methodlog_images

(self, batch, only_inputs=False, **kwargs)

lvdm/models/autoencoder.py:194

Functionmake_attn

(in_channels, attn_type="vanilla", attn_kwargs=None)

lvdm/models/autoencoder_dualref.py:218

Functionmake_time_attn

( in_channels, attn_type="vanilla", attn_kwargs=None, alpha: float = 0, merge_strateg

lvdm/models/autoencoder_dualref.py:1078

Functionmax_neg_value

(t)

lvdm/common.py:67

Functionmax_neg_value

(t)

lvdm/modules/attention_svd.py:75

Functionmean_flat

Take the mean over all non-batch dimensions.

lvdm/distributions.py:9

Methodmode

(self)

lvdm/distributions.py:64

Methodnll

(self, sample, dims=[1,2,3])

lvdm/distributions.py:56

source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12 Compute the K

lvdm/distributions.py:68

Functionnpz_to_video_grid

(data_path, out_path, num_frames, fps, num_videos=None, nrow=None, verbose=True)

utils/save_video.py:163

Methodon_train_batch_end

(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx=None)

main/callbacks.py:90

Methodon_train_batch_end

(self, *args, **kwargs)

lvdm/models/ddpm3d.py:408

Methodon_train_batch_start

(self, batch, batch_idx, dataloader_idx=None)

lvdm/models/ddpm3d.py:556

Methodon_train_epoch_end

(self, trainer, pl_module)

main/callbacks.py:117

Methodon_train_epoch_start

(self, trainer, pl_module)

main/callbacks.py:106

Methodon_validation_batch_end

(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx=None)

main/callbacks.py:94

Functionpick_and_pop

(keys, d)

lvdm/modules/x_transformer.py:87

Methodprepare_data

(self)

main/utils_data.py:72

Methodq_mean_variance

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff

lvdm/models/ddpm3d.py:222

Methodregister_schedule

(self, given_betas=None, beta_schedule="linear", timesteps=1000, linear_start=1e-4,

lvdm/models/ddpm3d.py:573

Functionresize_numpy_image

(image, max_resolution=512 * 512, resize_short_edge=None)

utils/utils.py:57

Methodsample

(self)

lvdm/distributions.py:6

Methodsample

(self)

lvdm/distributions.py:17

Methodsample

(self, noise=None)

lvdm/distributions.py:35

Methodsample

(self, S, batch_size, shape, conditioning=None

lvdm/models/samplers/ddim_multiplecond.py:60

Functionsave_results

(prompt, samples, filename, fakedir, fps=8, loop=False)

scripts/evaluation/inference.py:109

Functionscale_module

Scale the parameters of a module and return it.

(self, batch, random_uncond, **kwargs)

lvdm/models/ddpm3d.py:1064

Methodstochastic_encode

(self, x0, t, use_original_steps=False, noise=None)

lvdm/models/samplers/ddim_multiplecond.py:310

Methodstochastic_encode

(self, x0, t, use_original_steps=False, noise=None)

lvdm/models/samplers/ddim.py:304

Functionstring_begins_with

(prefix, str)

lvdm/modules/x_transformer.py:101

Functiontensor2videogrids

(video, root, filename, fps, rescale=True, clamp=True)

utils/save_video.py:44

Methodtraining_step

(self, batch, batch_idx)

lvdm/models/ddpm3d.py:384

Methodtraining_step

(self, batch, batch_idx)

lvdm/models/ddpm3d.py:798

Methodtraining_step

(self, batch, batch_idx, optimizer_idx)

lvdm/models/autoencoder.py:144

lvdm/modules/attention_svd.py:65

Methodvalidation_step

(self, batch, batch_idx)

lvdm/models/ddpm3d.py:400

Methodvalidation_step

(self, batch, batch_idx)

lvdm/models/autoencoder.py:165

Functionworker_init_fn

(_)

main/utils_data.py:15

← previous401–475 of 475, ranked by callers