`fastvideo.configs.models.dits.flux.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.flux.DiTConfig`

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

`fastvideo.configs.models.dits.flux.DiTConfig.add_cli_args`

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

Add CLI arguments for DiTConfig fields

`fastvideo.configs.models.dits.flux.FluxTransformer2DArchConfig`

FluxTransformer2DArchConfig(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 = 24, num_channels_latents: int = 0, in_channels: int = 64, out_channels: int | None = None, exclude_lora_layers: list[str] = list(), boundary_ratio: float | None = None, patch_size: int = 1, num_layers: int = 19, num_single_layers: int = 38, attention_head_dim: int = 128, joint_attention_dim: int = 4096, pooled_projection_dim: int = 768, guidance_embeds: bool = True, axes_dims_rope: tuple[int, int, int] = (16, 56, 56))

Source

@dataclass
class FluxTransformer2DArchConfig(DiTArchConfig):

    patch_size: int = 1
    in_channels: int = 64
    out_channels: int | None = None
    num_layers: int = 19
    num_single_layers: int = 38
    attention_head_dim: int = 128
    num_attention_heads: int = 24
    joint_attention_dim: int = 4096
    pooled_projection_dim: int = 768
    guidance_embeds: bool = True
    axes_dims_rope: tuple[int, int, int] = (16, 56, 56)

`fastvideo.configs.models.dits.flux.FluxDiTConfig`

FluxDiTConfig(arch_config: DiTArchConfig = FluxTransformer2DArchConfig(), prefix: str = 'flux', quant_config: QuantizationConfig | None = None, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

Source

@dataclass
class FluxDiTConfig(DiTConfig):
    arch_config: DiTArchConfig = field(default_factory=FluxTransformer2DArchConfig)
    prefix: str = "flux"