( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, in_channels: int, out_channels: int, dropout: float = 0.0, num

( self, in_channels: int, out_channels: int, dropout: float = 0.0, num

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, dim: int, num_attention_heads: int, attention_head_dim: int, d

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, text_encoder_2: CLIPT

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, text_encoder_2: CLIPT

( self, vae: AutoencoderKLTemporalDecoder, image_encoder: CLIPVisionModelWithProjectio

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

( self, in_channels: int, out_channels: int, attention_head_dim: int = 512,

( self, in_channels: int, out_channels: int, num_layers: int = 1, add_

( self, in_channels: int, temb_channels: int, num_layers: int = 1, tra

( self, in_channels: int, out_channels: int, temb_channels: int, num_l

( self, in_channels: int, out_channels: int, temb_channels: int, num_l

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, sample_size: Optional[int] = None, in_channels: int = 8, out_channels:

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, tokenizer: CLIPTokeni

( self, sample_size: Optional[int] = None, in_channels: int = 4, out_channels:

(self, in_channels: int, out_channels: int, act_fn: str)

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, dropout: float = 0.0, num

( self, in_channels: int, out_channels: int, dropout: float = 0.0, num

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, cross

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, in_channels: int, out_channels: int, dropout: float = 0.0, num

( self, in_channels: int, out_channels: int, dropout: float = 0.0, num

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, prev_output_channel: int, out_channels: int,

( self, in_channels: int, out_channels: int, prev_output_channel: int,

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

( self, dim: int, num_attention_heads: int, attention_head_dim: int, d

(self, batch_size=2)

( self, vae: AutoencoderKL, text_encoder: CLIPTextModel, tokenizer: CLIPTokeni

(self, pipe=None)

(self, files, transforms=None)

(self, config, root_dir = 'runtime_log', sub_name = None, overwrite = False, append=False)

(self, root_dir = 'runtime_log', sub_name = None, overwrite = False, append=False)

(self, args, config)

(self, args, config)

(self, path, transform, resolution=8)

(self, root, transforms=None, transform=None, target_transform=None)

(self, transform=None, target_transform=None)

(self, x1, x2, y1, y2)

(self, root, transform=None, target_transform=None)

(self, root, split="train", target_type="attr", transform=N

(self, mu=0.999)

(self, in_channels, with_conv)

(self, in_channels, with_conv)

(self, *, in_channels, out_channels=None, conv_shortcut=False, dropout, temb_channels=512)

(self, in_channels)

(self, in_channels, with_conv)

(self, in_channels, with_conv)

(self, *, in_channels, out_channels=None, conv_shortcut=False, dropout, temb_channels=512)

(self, in_channels)

(self, dataset)

(self, batch_size, train=None, validation=None, test=None, predict=None, wrap=False, num_work

(self, resume, now, logdir, ckptdir, cfgdir, config, lightning_config)

(self, database, retriever_version='ViT-L/14')

(self, warm_up_steps, lr_min, lr_max, lr_start, max_decay_steps, verbosity_interval=0)

(self, warm_up_steps, f_min, f_max, f_start, cycle_lengths, verbosity_interval=0)

(self, model, decay=0.9999, use_num_upates=True)

(self, dim, max_seq_len)

(self, dim)

(self, fn)

(self, dim, eps=1e-5)

(self, dim, eps=1e-8)

(self, dim)

(self, dim_in, dim_out)

(self, dim, dim_out=None, mult=4, glu=False, dropout=0.)

( self, dim, dim_head=DEFAULT_DIM_HEAD, heads=8, c

( self, dim, depth, heads=8, causal=False,

(self, **kwargs)