stable_audio

Config for the Stable Audio Open 1.0 DiT.

Note: the SA pipeline bypasses the standard ComposedPipelineBase component loader because the published HF repo ships a single monolithic model.safetensors (no Diffusers-style model_index.json or per-subfolder layout). The arch fields and param_names_mapping here document the architecture and key remap so the same conventions used by the rest of the DiT family apply (FSDP shard conditions, supported attention backends, future loader integrations) — they are not currently consumed by fastvideo/models/loader/fsdp_load.py for SA.

fastvideo.configs.models.dits.stable_audio.DiTArchConfig

DiTArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), _fsdp_shard_conditions: list = list(), _compile_conditions: list = list(), param_names_mapping: dict = dict(), reverse_param_names_mapping: dict = dict(), lora_param_names_mapping: dict = dict(), cast_prompt_embeds_to_dit_dtype: bool = False, _supported_attention_backends: tuple[AttentionBackendEnum, ...] = (AttentionBackendEnum.SAGE_ATTN, AttentionBackendEnum.FLASH_ATTN, AttentionBackendEnum.TORCH_SDPA, AttentionBackendEnum.VIDEO_SPARSE_ATTN, AttentionBackendEnum.VMOBA_ATTN, AttentionBackendEnum.SAGE_ATTN_THREE, AttentionBackendEnum.ATTN_QAT_INFER, AttentionBackendEnum.ATTN_QAT_TRAIN, AttentionBackendEnum.SLA_ATTN, AttentionBackendEnum.SAGE_SLA_ATTN), hidden_size: int = 0, num_attention_heads: int = 0, num_channels_latents: int = 0, in_channels: int = 0, out_channels: int = 0, exclude_lora_layers: list[str] = list(), boundary_ratio: float | None = None)

fastvideo.configs.models.dits.stable_audio.DiTConfig

DiTConfig(arch_config: DiTArchConfig = DiTArchConfig(), prefix: str = '', quant_config: QuantizationConfig | None = None, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

fastvideo.configs.models.dits.stable_audio.DiTConfig.add_cli_args

add_cli_args(parser: Any, prefix: str = 'dit-config') -> Any

Add CLI arguments for DiTConfig fields

fastvideo.configs.models.dits.stable_audio.AttentionBackendEnum

AttentionBackendEnum()

fastvideo.configs.models.dits.stable_audio.StableAudioArchConfig

StableAudioArchConfig(stacked_params_mapping: list[tuple[str, str, str]] = list(), _fsdp_shard_conditions: list = (lambda: [_is_transformer_layer])(), _compile_conditions: list = list(), param_names_mapping: dict = (lambda: {'^model\\.model\\.(.*?)\\.gamma$': '\\1.weight', '^model\\.model\\.(.*?)\\.beta$': '\\1.bias', '^model\\.model\\.(.*)$': '\\1'})(), reverse_param_names_mapping: dict = dict(), lora_param_names_mapping: dict = dict(), cast_prompt_embeds_to_dit_dtype: bool = False, _supported_attention_backends: tuple[AttentionBackendEnum, ...] = (AttentionBackendEnum.FLASH_ATTN, AttentionBackendEnum.TORCH_SDPA), hidden_size: int = 0, num_attention_heads: int = 24, num_channels_latents: int = 0, in_channels: int = 0, out_channels: int = 0, exclude_lora_layers: list[str] = list(), boundary_ratio: float | None = None, io_channels: int = 64, embed_dim: int = 1536, depth: int = 24, cond_token_dim: int = 768, global_cond_dim: int = 1536, project_cond_tokens: bool = False, project_global_cond: bool = True, qk_norm: str | None = None)

@dataclass
class StableAudioArchConfig(DiTArchConfig):
    _fsdp_shard_conditions: list = field(default_factory=lambda: [_is_transformer_layer])
# SA's checkpoint is `stable_audio_tools` raw format (not Diffusers),
# so the only remaps are: strip the `model.model.` host-pipeline
# prefix, and rename `nn.LayerNorm`'s `gamma`/`beta` to torch's
# canonical `weight`/`bias`. Linear / cross-attention naming already
# matches FastVideo's conventions, so no further remap is needed.
param_names_mapping: dict = field(
    default_factory=lambda: {
        r"^model\.model\.(.*?)\.gamma$": r"\1.weight",
        r"^model\.model\.(.*?)\.beta$": r"\1.bias",
        r"^model\.model\.(.*)$": r"\1",
    })

# SA only supports backends compatible with single-GPU LocalAttention.
_supported_attention_backends: tuple[AttentionBackendEnum, ...] = (
    AttentionBackendEnum.FLASH_ATTN,
    AttentionBackendEnum.TORCH_SDPA,
)

# Architecture constants (from the published `model_config.json` for
# `stabilityai/stable-audio-open-1.0`).
io_channels: int = 64
embed_dim: int = 1536
depth: int = 24
num_attention_heads: int = 24
cond_token_dim: int = 768
global_cond_dim: int = 1536
project_cond_tokens: bool = False
project_global_cond: bool = True
# Set to "ln" to wrap attention Q/K in LayerNorm (used by
# `stable-audio-open-small`; absent in the 1.0 base).
qk_norm: str | None = None

def __post_init__(self) -> None:
    super().__post_init__()
    self.hidden_size = self.embed_dim
    self.in_channels = self.io_channels
    self.out_channels = self.io_channels
    self.num_channels_latents = self.io_channels
    self.attention_head_dim = self.embed_dim // self.num_attention_heads</code></pre></details>
fastvideo.configs.models.dits.stable_audio.StableAudioConfig
StableAudioConfig(arch_config: DiTArchConfig = StableAudioArchConfig(), prefix: str = 'StableAudio', quant_config: QuantizationConfig | None = None, *, _resolved_attention_backend: AttentionBackendEnum | None = None)
Source
@dataclass
class StableAudioConfig(DiTConfig):
    arch_config: DiTArchConfig = field(default_factory=StableAudioArchConfig)
prefix: str = &quot;StableAudio&quot;</code></pre></details>