( self, num_train_timesteps: int = 1000, beta_start: float = 0.00085, beta_end

( self, num_timesteps=1000, num_sampling_steps=10, use_discrete_timesteps=Fals

( self, num_sampling_steps=10, num_timesteps=1000, cfg_scale=4.0, use_

( self, num_train_timesteps: int = 1000, beta_start: float = 0.00085, beta_end

( self, in_channels: int, out_channels: int, kernel_size: int = 3, str

( self, in_channels: int, out_channels: int, kernel_size: int = 3, str

(self, d_model, num_heads, attn_drop=0.0, proj_drop=0.0, enable_flash_attn=False)

( self, query_dim: int, cross_attention_dim: Optional[int] = None, heads: int

(self)

( self, patch_size: int = 2, in_channels: int = 16, embed_dim: int = 1920,

( self, patch_size=(2, 4, 4), in_chans=3, embed_dim=96, norm_layer=Non

(self, hidden_size, frequency_embedding_size=256)

( self, in_channels, hidden_size, uncond_prob, act_layer=nn.GELU(appro

(self, dim: int)

( self, conditioning_dim: int, embedding_dim: int, elementwise_affine: bool =

( self, embedding_dim: int, num_embeddings: Optional[int] = None, output_dim:

( self, f_channels: int, zq_channels: int, )

( self, )

( self, num_frames=1, height=224, width=224, patch_size_t=1, p

( self, num_frames=1, height=224, width=224, patch_size_t=1, p

( self, num_frames=1, height=224, width=224, patch_size_t=1, p

(self, downsampler, attention_mode, use_rope, interpolation_scale_thw, **kwags)

(self, attention_mode="xformers", use_rope=False, interpolation_scale_thw=(1, 1, 1))

(self, downsampler, dim, hidden_features, bias=True)

(self, downsampler, dim, hidden_features, bias=True)

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

( self, num_attention_heads: int = 16, attention_head_dim: int = 88, in_channe

(self, dim, num_attention_heads, attention_head_dim, context_pre_only=False)

( self, sample_size: int = 128, patch_size: int = 2, in_channels: int = 16,

(self)

( self, num_attention_heads: int = 30, attention_head_dim: int = 64, in_channe

(self, query_dim: int, context_dim: int, n_heads: int, d_head: int)

( self, dim: int, dim_out: Optional[int] = None, mult: int = 4, dropou

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

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

(self, embedding_dim: int, use_additional_conditions: bool = False)

(self, freq=10000.0, F0=1.0, scaling_factor=1.0)

(self)

(self)

(self, embedding_dim, size_emb_dim, use_additional_conditions: bool = False)

(self, in_features, hidden_size, num_tokens=120)

( self, height=224, width=224, patch_size=16, in_channels=3, e

( self, query_dim: int, cross_attention_dim: Optional[int] = None, heads: int

(self, dim=1152, attention_mode="xformers", use_rope=False, rope_scaling=None, compress_kv_factor=None)

(self, query_dim: int, context_dim: int, n_heads: int, d_head: int)

( self, dim: int, dim_out: Optional[int] = None, mult: int = 4, dropou

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

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

(self, embedding_dim: int, use_additional_conditions: bool = False)

( self, num_attention_heads: int = 16, patch_size_t: int = 1, attention_head_d

(self, freq=10000.0, F0=1.0, scaling_factor=1.0)

(self)

(self)

(self, embedding_dim, size_emb_dim, use_additional_conditions: bool = False)

(self, in_features, hidden_size, num_tokens=120)

( self, height=224, width=224, patch_size=16, in_channels=3, e

( self, query_dim: int, cross_attention_dim: Optional[int] = None, heads: int

(self, dim=1152, attention_mode="xformers", use_rope=False, rope_scaling=None, compress_kv_factor=None)

(self, query_dim: int, context_dim: int, n_heads: int, d_head: int)

( self, dim: int, dim_out: Optional[int] = None, mult: int = 4, dropou

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

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

(self, embedding_dim: int, use_additional_conditions: bool = False)

( self, num_attention_heads: int = 16, patch_size_t: int = 1, attention_head_d

(self, hidden_size, num_patch, out_channels, d_t=None, d_s=None)

( self, hidden_size, num_heads, mlp_ratio=4.0, drop_path=0.0,

( self, input_size=(None, None, None), input_sq_size=512, in_channels=4,

(self, parameters, deterministic=False)

(self, *args, **kwargs)

( self, z_channels: int, hidden_size: int, hidden_size_mult: Tuple[int] = (1,

( self, z_channels: int, hidden_size: int, hidden_size_mult: Tuple[int] = (1,

( self, lr: float = 1e-5, hidden_size: int = 128, z_channels: int = 4,

(self, model_path, subfolder=None, cache_dir=None, **kwargs)

(self, dim, heads=4, dim_head=32)

(self, in_channels)

(self, in_channels)

(self, in_channels)

(self, in_channels)

(self, in_channels)

( self, in_channels: int, out_channels: int, kernel_size: Union[int, Tuple[int

( self, chan_in, chan_out, kernel_size: Union[int, Tuple[int, int, int]], init_method="random", **kwar

(self, num_channels, num_groups=32, eps=1e-6, *args, **kwargs)

(self, num_features, logdet=False, affine=True, allow_reverse_init=False)

(self, n_codes, embedding_dim)

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

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

(self, in_channels, out_channels)

(self, in_channels, out_channels)

( self, chan_in, chan_out, kernel_size: Union[int, Tuple[int]] = (3, 3),

( self, chan_in, chan_out, kernel_size: Union[int, Tuple[int]] = (3, 3),

(self, chan_in, chan_out, kernel_size: int = 3)

(self, chan_in, chan_out)

( self, in_channels, out_channels, kernel_size: int = 3, mix_factor: f

( self, in_channels, out_channels, kernel_size: int = 3, mix_factor: f

( self, in_channels, out_channels, kernel_size: int = 3, mix_factor: f

( self, in_channels, out_channels, kernel_size: int = 3, mix_factor: f

( self, chan_in, chan_out, kernel_size: Union[int, Tuple[int, int, int]], init_method="random", **kwar

( self, in_channels: int, out_channels: int, kernel_size: Union[int, Tuple[int