{ | |
"_class_name": "UNet2DConditionModel", | |
"_diffusers_version": "0.12.0.dev0", | |
"_name_or_path": "stabilityai/stable-diffusion-2-1-base", | |
"act_fn": "silu", | |
"attention_head_dim": [ | |
5, | |
10, | |
20, | |
20 | |
], | |
"block_out_channels": [ | |
320, | |
640, | |
1280, | |
1280 | |
], | |
"center_input_sample": false, | |
"class_embed_type": null, | |
"cross_attention_dim": 1024, | |
"down_block_types": [ | |
"CrossAttnDownBlock2D", | |
"CrossAttnDownBlock2D", | |
"CrossAttnDownBlock2D", | |
"DownBlock2D" | |
], | |
"downsample_padding": 1, | |
"dual_cross_attention": false, | |
"flip_sin_to_cos": true, | |
"freq_shift": 0, | |
"in_channels": 4, | |
"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, | |
"resnet_time_scale_shift": "default", | |
"sample_size": 64, | |
"up_block_types": [ | |
"UpBlock2D", | |
"CrossAttnUpBlock2D", | |
"CrossAttnUpBlock2D", | |
"CrossAttnUpBlock2D" | |
], | |
"upcast_attention": false, | |
"use_linear_projection": true | |
} | |