Classes¶
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.
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)