Skip to content

vaes

Classes

fastvideo.configs.models.vaes.Cosmos25VAEConfig dataclass 

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)

Bases: VAEConfig

Cosmos2.5 VAE config.

fastvideo.configs.models.vaes.Flux2VAEConfig dataclass 

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)

Bases: VAEConfig

Configuration for Flux2 VAE model.

fastvideo.configs.models.vaes.GameCraftVAEConfig dataclass 

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)

Bases: VAEConfig

Full config for GameCraft VAE.

fastvideo.configs.models.vaes.Gen3CVAEConfig dataclass 

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)

Bases: CosmosVAEConfig

GEN3C VAE config placeholder.

GEN3C uses tokenizer-backed VAE loading logic at runtime, but we keep a model-specific config class so pipeline/model configs stay model-scoped.

fastvideo.configs.models.vaes.OobleckVAEArchConfig dataclass 

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)

Bases: VAEArchConfig

Stable Audio Open 1.0 VAE architecture constants.

fastvideo.configs.models.vaes.OobleckVAEConfig dataclass 

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')

Bases: VAEConfig

FastVideo VAE config wrapping the Oobleck arch.

Audio VAEs don't use the temporal/spatial tiling defaults that the base VAEConfig is shaped for (those exist for video VAEs); they are retained but irrelevant for audio.

Modules

fastvideo.configs.models.vaes.base

Classes

fastvideo.configs.models.vaes.base.VAEConfig dataclass 
VAEConfig(arch_config: VAEArchConfig = VAEArchConfig(), 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)

Bases: ModelConfig

Methods:
fastvideo.configs.models.vaes.base.VAEConfig.add_cli_args staticmethod 
add_cli_args(parser: Any, prefix: str = 'vae-config') -> Any

Add CLI arguments for VAEConfig fields

Source code in fastvideo/configs/models/vaes/base.py 
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
@staticmethod
def add_cli_args(parser: Any, prefix: str = "vae-config") -> Any:
    """Add CLI arguments for VAEConfig fields"""
    parser.add_argument(
        f"--{prefix}.load-encoder",
        action=StoreBoolean,
        dest=f"{prefix.replace('-', '_')}.load_encoder",
        default=VAEConfig.load_encoder,
        help="Whether to load the VAE encoder",
    )
    parser.add_argument(
        f"--{prefix}.load-decoder",
        action=StoreBoolean,
        dest=f"{prefix.replace('-', '_')}.load_decoder",
        default=VAEConfig.load_decoder,
        help="Whether to load the VAE decoder",
    )
    parser.add_argument(
        f"--{prefix}.tile-sample-min-height",
        type=int,
        dest=f"{prefix.replace('-', '_')}.tile_sample_min_height",
        default=VAEConfig.tile_sample_min_height,
        help="Minimum height for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.tile-sample-min-width",
        type=int,
        dest=f"{prefix.replace('-', '_')}.tile_sample_min_width",
        default=VAEConfig.tile_sample_min_width,
        help="Minimum width for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.tile-sample-min-num-frames",
        type=int,
        dest=f"{prefix.replace('-', '_')}.tile_sample_min_num_frames",
        default=VAEConfig.tile_sample_min_num_frames,
        help="Minimum number of frames for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.tile-sample-stride-height",
        type=int,
        dest=f"{prefix.replace('-', '_')}.tile_sample_stride_height",
        default=VAEConfig.tile_sample_stride_height,
        help="Stride height for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.tile-sample-stride-width",
        type=int,
        dest=f"{prefix.replace('-', '_')}.tile_sample_stride_width",
        default=VAEConfig.tile_sample_stride_width,
        help="Stride width for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.tile-sample-stride-num-frames",
        type=int,
        dest=f"{prefix.replace('-', '_')}.tile_sample_stride_num_frames",
        default=VAEConfig.tile_sample_stride_num_frames,
        help="Stride number of frames for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.blend-num-frames",
        type=int,
        dest=f"{prefix.replace('-', '_')}.blend_num_frames",
        default=VAEConfig.blend_num_frames,
        help="Number of frames to blend for VAE tile sampling",
    )
    parser.add_argument(
        f"--{prefix}.use-tiling",
        action=StoreBoolean,
        dest=f"{prefix.replace('-', '_')}.use_tiling",
        default=VAEConfig.use_tiling,
        help="Whether to use tiling for VAE",
    )
    parser.add_argument(
        f"--{prefix}.use-temporal-tiling",
        action=StoreBoolean,
        dest=f"{prefix.replace('-', '_')}.use_temporal_tiling",
        default=VAEConfig.use_temporal_tiling,
        help="Whether to use temporal tiling for VAE",
    )
    parser.add_argument(
        f"--{prefix}.use-parallel-tiling",
        action=StoreBoolean,
        dest=f"{prefix.replace('-', '_')}.use_parallel_tiling",
        default=VAEConfig.use_parallel_tiling,
        help="Whether to use parallel tiling for VAE",
    )

    return parser

fastvideo.configs.models.vaes.cosmos2_5vae

Cosmos 2.5 (Wan2.1-style) VAE config and checkpoint-key mapping.

Classes

fastvideo.configs.models.vaes.cosmos2_5vae.Cosmos25VAEArchConfig dataclass 
Cosmos25VAEArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), scaling_factor: float | Tensor = 0, temporal_compression_ratio: int = 4, spatial_compression_ratio: int = 8, _name_or_path: str = '', base_dim: int = 96, decoder_base_dim: int | None = None, z_dim: int = 16, dim_mult: tuple[int, ...] = (1, 2, 4, 4), num_res_blocks: int = 2, attn_scales: tuple[float, ...] = (), temperal_downsample: tuple[bool, ...] = (False, True, True), dropout: float = 0.0, is_residual: bool = False, in_channels: int = 3, out_channels: int = 3, patch_size: int | None = None, scale_factor_temporal: int = 4, scale_factor_spatial: int = 8, clip_output: bool = True, latents_mean: tuple[float, ...] = (-0.7571, -0.7089, -0.9113, 0.1075, -0.1745, 0.9653, -0.1517, 1.5508, 0.4134, -0.0715, 0.5517, -0.3632, -0.1922, -0.9497, 0.2503, -0.2921), latents_std: tuple[float, ...] = (2.8184, 1.4541, 2.3275, 2.6558, 1.2196, 1.7708, 2.6052, 2.0743, 3.2687, 2.1526, 2.8652, 1.5579, 1.6382, 1.1253, 2.8251, 1.916), param_names_mapping: dict[str, str] = (lambda: {'^conv1\\.(.*)$': 'quant_conv.\\1', '^conv2\\.(.*)$': 'post_quant_conv.\\1', '^encoder\\.conv1\\.(.*)$': 'encoder.conv_in.\\1', '^decoder\\.conv1\\.(.*)$': 'decoder.conv_in.\\1', '^encoder\\.head\\.0\\.gamma$': 'encoder.norm_out.gamma', '^encoder\\.head\\.2\\.(.*)$': 'encoder.conv_out.\\1', '^decoder\\.head\\.0\\.gamma$': 'decoder.norm_out.gamma', '^decoder\\.head\\.2\\.(.*)$': 'decoder.conv_out.\\1'})())

Bases: VAEArchConfig

Methods:
fastvideo.configs.models.vaes.cosmos2_5vae.Cosmos25VAEArchConfig.map_official_key staticmethod 
map_official_key(key: str) -> str | None

Map a single official checkpoint key into FastVideo key space.

Source code in fastvideo/configs/models/vaes/cosmos2_5vae.py 
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
@staticmethod
def map_official_key(key: str) -> str | None:
    """Map a single official checkpoint key into FastVideo key space."""

    def map_residual_subkey(prefix: str, sub: str) -> str | None:
        if re.match(r"^residual\.0\.gamma$", sub):
            return f"{prefix}.norm1.gamma"
        m = re.match(r"^residual\.2\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.conv1.{m.group(1)}"
        if re.match(r"^residual\.3\.gamma$", sub):
            return f"{prefix}.norm2.gamma"
        m = re.match(r"^residual\.6\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.conv2.{m.group(1)}"
        m = re.match(r"^shortcut\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.conv_shortcut.{m.group(1)}"
        return None

    def map_attn_subkey(prefix: str, sub: str) -> str | None:
        if re.match(r"^norm\.gamma$", sub):
            return f"{prefix}.norm.gamma"
        m = re.match(r"^to_qkv\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.to_qkv.{m.group(1)}"
        m = re.match(r"^proj\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.proj.{m.group(1)}"
        return None

    def map_resample_subkey(prefix: str, sub: str) -> str | None:
        m = re.match(r"^resample\.1\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.resample.1.{m.group(1)}"
        m = re.match(r"^time_conv\.(weight|bias)$", sub)
        if m:
            return f"{prefix}.time_conv.{m.group(1)}"
        return None

    m = re.match(r"^conv1\.(weight|bias)$", key)
    if m:
        return f"quant_conv.{m.group(1)}"
    m = re.match(r"^conv2\.(weight|bias)$", key)
    if m:
        return f"post_quant_conv.{m.group(1)}"
    m = re.match(r"^(encoder|decoder)\.conv1\.(weight|bias)$", key)
    if m:
        return f"{m.group(1)}.conv_in.{m.group(2)}"
    m = re.match(r"^(encoder|decoder)\.head\.0\.gamma$", key)
    if m:
        return f"{m.group(1)}.norm_out.gamma"
    m = re.match(r"^(encoder|decoder)\.head\.2\.(weight|bias)$", key)
    if m:
        return f"{m.group(1)}.conv_out.{m.group(2)}"

    m = re.match(r"^(encoder|decoder)\.middle\.0\.(.*)$", key)
    if m:
        return map_residual_subkey(f"{m.group(1)}.mid_block.resnets.0", m.group(2))
    m = re.match(r"^(encoder|decoder)\.middle\.1\.(.*)$", key)
    if m:
        return map_attn_subkey(f"{m.group(1)}.mid_block.attentions.0", m.group(2))
    m = re.match(r"^(encoder|decoder)\.middle\.2\.(.*)$", key)
    if m:
        return map_residual_subkey(f"{m.group(1)}.mid_block.resnets.1", m.group(2))

    m = re.match(r"^encoder\.downsamples\.(\d+)\.(.*)$", key)
    if m:
        idx = int(m.group(1))
        sub = m.group(2)
        if sub.startswith("residual.") or sub.startswith("shortcut."):
            return map_residual_subkey(f"encoder.down_blocks.{idx}", sub)
        if sub.startswith("resample.") or sub.startswith("time_conv."):
            return map_resample_subkey(f"encoder.down_blocks.{idx}", sub)
        return None

    m = re.match(r"^decoder\.upsamples\.(\d+)\.(.*)$", key)
    if m:
        uidx = int(m.group(1))
        sub = m.group(2)

        if uidx in (0, 1, 2):
            block_i, res_i = 0, uidx
        elif uidx == 3:
            block_i, res_i = 0, None
        elif uidx in (4, 5, 6):
            block_i, res_i = 1, uidx - 4
        elif uidx == 7:
            block_i, res_i = 1, None
        elif uidx in (8, 9, 10):
            block_i, res_i = 2, uidx - 8
        elif uidx == 11:
            block_i, res_i = 2, None
        elif uidx in (12, 13, 14):
            block_i, res_i = 3, uidx - 12
        else:
            return None

        if res_i is None:
            return map_resample_subkey(
                f"decoder.up_blocks.{block_i}.upsamplers.0",
                sub,
            )

        return map_residual_subkey(
            f"decoder.up_blocks.{block_i}.resnets.{res_i}",
            sub,
        )

    return None
fastvideo.configs.models.vaes.cosmos2_5vae.Cosmos25VAEConfig dataclass 
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)

Bases: VAEConfig

Cosmos2.5 VAE config.

fastvideo.configs.models.vaes.flux2vae

Classes

fastvideo.configs.models.vaes.flux2vae.Flux2VAEArchConfig dataclass 
Flux2VAEArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), scaling_factor: float = 0.13025, temporal_compression_ratio: int = 1, spatial_compression_ratio: int = 8, in_channels: int = 3, out_channels: int = 3, down_block_types: tuple[str, ...] = ('DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'AttnDownEncoderBlock2D'), up_block_types: tuple[str, ...] = ('AttnUpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D'), block_out_channels: tuple[int, ...] = (128, 256, 512, 512), layers_per_block: int = 2, act_fn: str = 'silu', latent_channels: int = 16, norm_num_groups: int = 32, sample_size: int = 512, force_upcast: bool = False, use_quant_conv: bool = True, use_post_quant_conv: bool = True, mid_block_add_attention: bool = True, batch_norm_eps: float = 1e-05, batch_norm_momentum: float = 0.1, patch_size: tuple[int, int] = (1, 1))

Bases: VAEArchConfig

Architecture configuration for Flux2 VAE model.

fastvideo.configs.models.vaes.flux2vae.Flux2VAEConfig dataclass 
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)

Bases: VAEConfig

Configuration for Flux2 VAE model.

fastvideo.configs.models.vaes.gamecraftvae

GameCraft VAE config - matches official config.json from Hunyuan-GameCraft-1.0.

Classes

fastvideo.configs.models.vaes.gamecraftvae.GameCraftVAEArchConfig dataclass 
GameCraftVAEArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), scaling_factor: float = 0.476986, temporal_compression_ratio: int = 4, spatial_compression_ratio: int = 8, in_channels: int = 3, out_channels: int = 3, latent_channels: int = 16, down_block_types: tuple[str, ...] = ('DownEncoderBlockCausal3D', 'DownEncoderBlockCausal3D', 'DownEncoderBlockCausal3D', 'DownEncoderBlockCausal3D'), up_block_types: tuple[str, ...] = ('UpDecoderBlockCausal3D', 'UpDecoderBlockCausal3D', 'UpDecoderBlockCausal3D', 'UpDecoderBlockCausal3D'), block_out_channels: tuple[int, ...] = (128, 256, 512, 512), layers_per_block: int = 2, act_fn: str = 'silu', norm_num_groups: int = 32, time_compression_ratio: int = 4, mid_block_add_attention: bool = True, mid_block_causal_attn: bool = True, sample_size: int = 256, sample_tsize: int = 64)

Bases: VAEArchConfig

Architecture config matching official AutoencoderKLCausal3D config.json.

fastvideo.configs.models.vaes.gamecraftvae.GameCraftVAEConfig dataclass 
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)

Bases: VAEConfig

Full config for GameCraft VAE.

fastvideo.configs.models.vaes.gen3cvae

Classes

fastvideo.configs.models.vaes.gen3cvae.Gen3CVAEConfig dataclass 
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)

Bases: CosmosVAEConfig

GEN3C VAE config placeholder.

GEN3C uses tokenizer-backed VAE loading logic at runtime, but we keep a model-specific config class so pipeline/model configs stay model-scoped.

fastvideo.configs.models.vaes.ltx2vae

LTX-2 VAE configuration.

Classes

fastvideo.configs.models.vaes.oobleck

Config for the Stable Audio Open 1.0 "Oobleck" VAE.

Mirrors the per-channel vae/config.json shipped in stabilityai/stable-audio-open-1.0 1:1 (see fastvideo/models/vaes/oobleck.py::OobleckVAE.from_pretrained, which constructs the VAE from these fields). Inherits the FastVideo VAEConfig base so the standard load_encoder / load_decoder flags + tiling knobs apply.

Naming: the VAE architecture is officially "Oobleck" (per Stability AI's stable-audio-tools) — the surrounding model family is "Stable Audio Open 1.0". This config is named after the architecture (OobleckVAEConfig) since the same VAE is shared across Stable Audio checkpoints; downstream pipelines reference it by its arch name, not by a host-pipeline name.

Classes

fastvideo.configs.models.vaes.oobleck.OobleckVAEArchConfig dataclass 
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)

Bases: VAEArchConfig

Stable Audio Open 1.0 VAE architecture constants.

fastvideo.configs.models.vaes.oobleck.OobleckVAEConfig dataclass 
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')

Bases: VAEConfig

FastVideo VAE config wrapping the Oobleck arch.

Audio VAEs don't use the temporal/spatial tiling defaults that the base VAEConfig is shaped for (those exist for video VAEs); they are retained but irrelevant for audio.