unet/config.json

1.7 KB · 66 lines · json Raw

1	`{`
2	`"_class_name": "UNet2DConditionModel",`
3	`"_diffusers_version": "0.16.1",`
4	`"_name_or_path": "segmind/BKSDM-Base-45K",`
5	`"act_fn": "silu",`
6	`"addition_embed_type": null,`
7	`"addition_embed_type_num_heads": 64,`
8	`"addition_time_embed_dim": null,`
9	`"attention_head_dim": 8,`
10	`"block_out_channels": [`
11	`320,`
12	`640,`
13	`1280,`
14	`1280`
15	`],`
16	`"center_input_sample": false,`
17	`"class_embed_type": null,`
18	`"class_embeddings_concat": false,`
19	`"conv_in_kernel": 3,`
20	`"conv_out_kernel": 3,`
21	`"cross_attention_dim": 768,`
22	`"cross_attention_norm": null,`
23	`"down_block_types": [`
24	`"CrossAttnDownBlock2D",`
25	`"CrossAttnDownBlock2D",`
26	`"CrossAttnDownBlock2D",`
27	`"DownBlock2D"`
28	`],`
29	`"downsample_padding": 1,`
30	`"dual_cross_attention": false,`
31	`"encoder_hid_dim": null,`
32	`"encoder_hid_dim_type": null,`
33	`"flip_sin_to_cos": true,`
34	`"freq_shift": 0,`
35	`"in_channels": 4,`
36	`"layers_per_block": 1,`
37	`"mid_block_only_cross_attention": null,`
38	`"mid_block_scale_factor": 1,`
39	`"mid_block_type": "UNetMidBlock2DCrossAttn",`
40	`"norm_eps": 1e-05,`
41	`"norm_num_groups": 32,`
42	`"num_attention_heads": null,`
43	`"num_class_embeds": null,`
44	`"only_cross_attention": false,`
45	`"out_channels": 4,`
46	`"projection_class_embeddings_input_dim": null,`
47	`"resnet_out_scale_factor": 1.0,`
48	`"resnet_skip_time_act": false,`
49	`"resnet_time_scale_shift": "default",`
50	`"sample_size": 64,`
51	`"time_cond_proj_dim": null,`
52	`"time_embedding_act_fn": null,`
53	`"time_embedding_dim": null,`
54	`"time_embedding_type": "positional",`
55	`"timestep_post_act": null,`
56	`"transformer_layers_per_block": 1,`
57	`"up_block_types": [`
58	`"UpBlock2D",`
59	`"CrossAttnUpBlock2D",`
60	`"CrossAttnUpBlock2D",`
61	`"CrossAttnUpBlock2D"`
62	`],`
63	`"upcast_attention": false,`
64	`"use_linear_projection": false`
65	`}`
66