{ "_class_name": "UNet3DConditionXLModel", "_diffusers_version": "0.18.1", "_name_or_path": "./outputs/2023-11-07T13-00-06_txt2vid-diffuser-xl-train-webmix-1-1.2-768-aescond-lat-action-lf16-lr3-A800/checkpoint-0-12000/unet", "act_fn": "silu", "action_prob_fea_guidance": true, "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 256, "aes_condition": true, "attention_head_dim": [ 5, 10, 20 ], "block_out_channels": [ 320, 640, 1280 ], "center_input_sample": false, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 1280, "cross_attention_norm": null, "down_block_types": [ "DownBlock3D", "CrossAttnDownBlock3D", "CrossAttnDownBlock3D" ], "downsample_padding": 1, "dual_cross_attention": false, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "insert_text_adapter": false, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock3DCrossAttn", "midf_clip_pool_fea_guidance": true, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": 2816, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "sample_size": 128, "temporal_res_use_more_conv": false, "temporal_trans_double_equip": false, "temporal_trans_num_align_spatial": true, "temporal_transformer_zero_init": true, "text_embedding_guidance": false, "time_cond_proj_dim": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": [ 1, 2, 10 ], "up_block_types": [ "CrossAttnUpBlock3D", "CrossAttnUpBlock3D", "UpBlock3D" ], "upcast_attention": false, "use_linear_projection": true, "use_transformer_in": true, "warping_concate_in_channel": false }