|
{ |
|
"_class_name": "AutoencoderKL", |
|
"_diffusers_version": "0.22.0.dev0", |
|
"act_fn": "silu", |
|
"block_out_channels": [ |
|
128, |
|
256, |
|
512, |
|
512 |
|
], |
|
"down_block_types": [ |
|
"SpatialDownBlock3D", |
|
"SpatialTemporalDownBlock3D", |
|
"SpatialTemporalDownBlock3D", |
|
"SpatialTemporalDownBlock3D" |
|
], |
|
"force_upcast": true, |
|
"in_channels": 3, |
|
"latent_channels": 4, |
|
"layers_per_block": 2, |
|
"norm_num_groups": 32, |
|
"out_channels": 3, |
|
"sample_size": 256, |
|
"scaling_factor": 0.18215, |
|
"slice_compression_vae": false, |
|
"mid_block_attention_type": "3d", |
|
"mini_batch_encoder": 9, |
|
"mini_batch_decoder": 3, |
|
"up_block_types": [ |
|
"SpatialUpBlock3D", |
|
"SpatialTemporalUpBlock3D", |
|
"SpatialTemporalUpBlock3D", |
|
"SpatialTemporalUpBlock3D" |
|
] |
|
} |
|
|