|
{ |
|
"_class_name": "UNet2DConditionModel", |
|
"_diffusers_version": "0.26.0", |
|
"act_fn": "silu", |
|
"attention_head_dim": 64, |
|
"block_out_channels": [320, 640, 1280, 1280], |
|
"center_input_sample": false, |
|
"class_embed_type": null, |
|
"conv_in_kernel": 3, |
|
"conv_out_kernel": 3, |
|
"cross_attention_dim": 2048, |
|
"down_block_types": [ |
|
"CrossAttnDownBlock2D", |
|
"CrossAttnDownBlock2D", |
|
"CrossAttnDownBlock2D", |
|
"DownBlock2D" |
|
], |
|
"dropout": 0.0, |
|
"flip_sin_to_cos": true, |
|
"freq_shift": 0, |
|
"in_channels": 4, |
|
"layers_per_block": 2, |
|
"mid_block_scale_factor": 1, |
|
"model_type": "UNet2DConditionModel", |
|
"norm_eps": 1e-05, |
|
"norm_num_groups": 32, |
|
"out_channels": 4, |
|
"sample_size": 64, |
|
"up_block_types": [ |
|
"UpBlock2D", |
|
"CrossAttnUpBlock2D", |
|
"CrossAttnUpBlock2D", |
|
"CrossAttnUpBlock2D" |
|
], |
|
"use_linear_projection": true, |
|
"use_memory_efficient_attention": false |
|
} |