|
{ |
|
"_class_name": "UNet2DConditionModel", |
|
"_diffusers_version": "0.15.0.dev0", |
|
"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": [ |
|
"CrossAttnDownBlock2D", |
|
"CrossAttnDownBlock2D", |
|
"CrossAttnDownBlock2D", |
|
"DownBlock2D" |
|
], |
|
"downsample_padding": 1, |
|
"dual_cross_attention": false, |
|
"flip_sin_to_cos": true, |
|
"freq_shift": 0, |
|
"in_channels": 9, |
|
"layers_per_block": 2, |
|
"mid_block_scale_factor": 1, |
|
"mid_block_type": "UNetMidBlock2DCrossAttn", |
|
"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_time_scale_shift": "default", |
|
"sample_size": 64, |
|
"time_cond_proj_dim": null, |
|
"time_embedding_type": "positional", |
|
"timestep_post_act": null, |
|
"up_block_types": [ |
|
"UpBlock2D", |
|
"CrossAttnUpBlock2D", |
|
"CrossAttnUpBlock2D", |
|
"CrossAttnUpBlock2D" |
|
], |
|
"upcast_attention": false, |
|
"use_linear_projection": false |
|
} |
|
|