Cosmos25Config(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 0.0, flow_shift: float = 5.0, disable_autocast: bool = False, is_causal: bool = False, dit_config: DiTConfig = (lambda: Cosmos25VideoConfig(arch_config=Cosmos25ArchConfig(num_attention_heads=16, attention_head_dim=128, in_channels=16, out_channels=16, num_layers=28, patch_size=[1, 2, 2], max_size=[128, 240, 240], rope_scale=[1.0, 3.0, 3.0], text_embed_dim=1024, mlp_ratio=4.0, adaln_lora_dim=256, use_adaln_lora=True, concat_padding_mask=True, extra_pos_embed_type=None, use_crossattn_projection=True, rope_enable_fps_modulation=False, qk_norm='rms_norm')))(), dit_precision: str = 'bf16', vae_config: VAEConfig = Cosmos25VAEConfig(), vae_precision: str = 'bf16', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = EncoderConfig(), image_encoder_precision: str = 'fp32', text_encoder_configs: tuple[EncoderConfig, ...] = (lambda: (Reason1Config(arch_config=Reason1ArchConfig(embedding_concat_strategy='full_concat')),))(), text_encoder_precisions: tuple[str, ...] = (lambda: ('bf16',))(), preprocess_text_funcs: tuple[Callable[[str], str], ...] = (lambda: (_identity_preprocess_text,))(), postprocess_text_funcs: tuple[Callable[[BaseEncoderOutput], Tensor], ...] = (lambda: (reason1_postprocess_text,))(), pos_magic: str | None = None, neg_magic: str | None = None, timesteps_scale: bool | None = None, mask_strategy_file_path: str | None = None, STA_mode: STA_Mode = NONE, skip_time_steps: int = 0, dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, boundary_ratio: float | None = None)
Bases: PipelineConfig
Configuration for Cosmos 2.5 (Predict2.5) video generation pipeline.