vaes ¶

Cosmos25VAEConfig(arch_config: Cosmos25VAEArchConfig = Cosmos25VAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = False, use_temporal_tiling: bool = False, use_parallel_tiling: bool = False, use_temporal_scaling_frames: bool = True, use_feature_cache: bool = True, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

Flux2VAEConfig(arch_config: Flux2VAEArchConfig = Flux2VAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = False, use_temporal_tiling: bool = False, use_parallel_tiling: bool = False, use_temporal_scaling_frames: bool = True, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

GameCraftVAEConfig(arch_config: VAEArchConfig = GameCraftVAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = True, use_temporal_tiling: bool = True, use_parallel_tiling: bool = True, use_temporal_scaling_frames: bool = True, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

Gen3CVAEConfig(arch_config: CosmosVAEArchConfig = CosmosVAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = False, use_temporal_tiling: bool = False, use_parallel_tiling: bool = False, use_temporal_scaling_frames: bool = True, use_feature_cache: bool = True, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

MiniMaxH3AudioVAEArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), scaling_factor: float = 1.0, temporal_compression_ratio: int = 1, spatial_compression_ratio: int = 1, _class_name: str = 'AutoencoderKLMiniMaxH3Audio', architectures: list[str] = (lambda: ['AutoencoderKLMiniMaxH3Audio'])(), encoder_dim: int = 64, encoder_rates: tuple[int, ...] | list[int] = (2, 4, 4, 5, 5), latent_dim: int = 2048, latent_channels: int = 32, num_attention_heads: int = 8, decoder_dim: int = 1024, decoder_rates: tuple[int, ...] | list[int] = (5, 5, 2, 2, 2, 2, 2), decoder_kernel_sizes: tuple[int, ...] | list[int] = (9, 9, 4, 4, 4, 4, 4), resblock_kernel_sizes: tuple[int, ...] | list[int] = (3, 7, 11), resblock_dilation_sizes: tuple[tuple[int, ...], ...] | list[list[int]] = ((1, 3, 5), (1, 3, 5), (1, 3, 5)), sampling_rate: int = 32000, latents_mean: tuple[float, ...] | list[float] | None = None, latents_std: tuple[float, ...] | list[float] | None = None)

MiniMaxH3AudioVAEConfig(arch_config: MiniMaxH3AudioVAEArchConfig = MiniMaxH3AudioVAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = False, use_temporal_tiling: bool = False, use_parallel_tiling: bool = False, use_temporal_scaling_frames: bool = True, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

MiniMaxH3VideoVAEArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), scaling_factor: float = 1.0, temporal_compression_ratio: int = 4, spatial_compression_ratio: int = 16, _class_name: str = 'AutoencoderKLMiniMaxH3', in_channels: int = 3, out_channels: int = 3, latent_channels: int = 24, block_out_channels: tuple[int, ...] = (128, 256, 256, 512, 512, 1024), layers_per_block: int = 2, spatial_downsample_factors: tuple[int, ...] = (2, 2, 2, 2, 1, 1), temporal_downsample_factors: tuple[int, ...] = (1, 2, 2, 1, 1, 1), norm_num_groups: int = 32, norm_eps: float = 1e-06, spatial_padding_mode: str = 'reflect', decoder_num_layers: int = 36, decoder_num_attention_heads: int = 32, decoder_attention_head_dim: int = 64, decoder_num_register_tokens: int = 4, decoder_ffn_mult: int = 4, decoder_rope_theta: float = 100.0, decoder_rope_dim_ratio: float = 0.75, decoder_norm_eps: float = 1e-05, clip_length: int = 17, token_drop: int = 3, latents_mean: tuple[float, ...] = (0.0,) * 24, latents_std: tuple[float, ...] = (1.0,) * 24)

MiniMaxH3VideoVAEConfig(arch_config: MiniMaxH3VideoVAEArchConfig = MiniMaxH3VideoVAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = True, use_temporal_tiling: bool = True, use_parallel_tiling: bool = True, use_temporal_scaling_frames: bool = True, tile_sample_min_overlap_height: int = 64, tile_sample_min_overlap_width: int = 64, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

OobleckVAEArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), scaling_factor: float | Tensor = 0, temporal_compression_ratio: int = 4, spatial_compression_ratio: int = 8, architectures: list[str] = (lambda: ['AutoencoderOobleck'])(), encoder_hidden_size: int = 128, downsampling_ratios: list[int] = (lambda: [2, 4, 4, 8, 8])(), channel_multiples: list[int] = (lambda: [1, 2, 4, 8, 16])(), decoder_channels: int = 128, decoder_input_channels: int = 64, audio_channels: int = 2, sampling_rate: int = 44100)

OobleckVAEConfig(arch_config: VAEArchConfig = OobleckVAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = False, use_temporal_tiling: bool = False, use_parallel_tiling: bool = False, use_temporal_scaling_frames: bool = True, pretrained_path: str = 'stabilityai/stable-audio-open-1.0', pretrained_subfolder: str = 'vae', pretrained_dtype: str = 'float16', *, _resolved_attention_backend: AttentionBackendEnum | None = None)