{ "_center_input_sample": false, "_class_name": "UNet3DConditionModel", "_diffusers_version": "0.31.0", "_out_channels": 4, "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "audio_attention_dim": 768, "block_out_channels": [ 320, 640, 1280, 1280 ], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "cross_attention_dim": 768, "down_block_types": [ "CrossAttnDownBlock3D", "CrossAttnDownBlock3D", "CrossAttnDownBlock3D", "DownBlock3D" ], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "emo_drop_rate": 0.05, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock3DCrossAttn", "motion_module_kwargs": { "attention_block_types": [ "Temporal_Self", "Temporal_Self" ], "num_attention_heads": 8, "num_transformer_block": 1, "temporal_attention_dim_div": 1, "temporal_position_encoding": true, "temporal_position_encoding_max_len": 32 }, "motion_module_resolutions": [ 1, 2, 4, 8 ], "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "sample_size": 64, "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "unet_use_cross_frame_attention": false, "unet_use_temporal_attention": false, "up_block_types": [ "UpBlock3D", "CrossAttnUpBlock3D", "CrossAttnUpBlock3D", "CrossAttnUpBlock3D" ], "upcast_attention": false, "use_inflated_groupnorm": true, "use_linear_projection": false }