{
  "_class_name": "UNet3DConditionModel",
  "_diffusers_version": "0.21.0.dev0",
  "_name_or_path": "/cfs-datasets/users/anchorxia/experiments/musev/outputs/20231018_AnivV0_tfm=TT_2SelfAttn_reference-only_noise=vf/checkpoints/checkpoint-16400/",
  "act_fn": "silu",
  "attention_head_dim": 8,
  "block_out_channels": [
    320,
    640,
    1280,
    1280
  ],
  "center_input_sample": false,
  "class_embed_type": null,
  "class_embeddings_concat": false,
  "conv_in_kernel": 3,
  "conv_out_kernel": 3,
  "cross_attention_dim": 768,
  "down_block_types": [
    "CrossAttnDownBlock3D",
    "CrossAttnDownBlock3D",
    "CrossAttnDownBlock3D",
    "DownBlock3D"
  ],
  "downsample_padding": 1,
  "dual_cross_attention": false,
  "flip_sin_to_cos": true,
  "freq_shift": 0,
  "in_channels": 4,
  "keep_vision_condtion": false,
  "layers_per_block": 2,
  "mid_block_scale_factor": 1,
  "mid_block_type": "UNetMidBlock3DCrossAttn",
  "need_adain_temporal_cond": true,
  "need_spatial_position_emb": false,
  "need_t2i_ip_adapter": true,
  "need_transformer_in": true,
  "need_zero_vis_cond_temb": true,
  "norm_eps": 1e-05,
  "norm_num_groups": 32,
  "num_class_embeds": null,
  "only_cross_attention": false,
  "out_channels": 4,
  "projection_class_embeddings_input_dim": null,
  "resnet_2d_skip_time_act": false,
  "resnet_time_scale_shift": "default",
  "sample_size": 64,
  "t2i_ip_adapter_attn_processor": "NonParamReferenceIPXFormersAttnProcessor",
  "temporal_conv_block": "TemporalConvLayer",
  "temporal_transformer": "TransformerTemporalModel",
  "time_cond_proj_dim": null,
  "time_embedding_type": "positional",
  "timestep_post_act": null,
  "up_block_types": [
    "UpBlock3D",
    "CrossAttnUpBlock3D",
    "CrossAttnUpBlock3D",
    "CrossAttnUpBlock3D"
  ],
  "upcast_attention": false,
  "use_anivv1_cfg": false,
  "use_linear_projection": false
}