update
Browse files- decoder/config.json +83 -0
- decoder_lite/config.json +83 -0
- prior/config.json +64 -0
- prior_lite/config.json +64 -0
decoder/config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableCascadeUNet",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"block_out_channels": [
|
| 5 |
+
320,
|
| 6 |
+
640,
|
| 7 |
+
1280,
|
| 8 |
+
1280
|
| 9 |
+
],
|
| 10 |
+
"block_types_per_layer": [
|
| 11 |
+
[
|
| 12 |
+
"SDCascadeResBlock",
|
| 13 |
+
"SDCascadeTimestepBlock"
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
"SDCascadeResBlock",
|
| 17 |
+
"SDCascadeTimestepBlock"
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
"SDCascadeResBlock",
|
| 21 |
+
"SDCascadeTimestepBlock",
|
| 22 |
+
"SDCascadeAttnBlock"
|
| 23 |
+
],
|
| 24 |
+
[
|
| 25 |
+
"SDCascadeResBlock",
|
| 26 |
+
"SDCascadeTimestepBlock",
|
| 27 |
+
"SDCascadeAttnBlock"
|
| 28 |
+
]
|
| 29 |
+
],
|
| 30 |
+
"clip_image_in_channels": null,
|
| 31 |
+
"clip_seq": 4,
|
| 32 |
+
"clip_text_in_channels": null,
|
| 33 |
+
"clip_text_pooled_in_channels": 1280,
|
| 34 |
+
"conditioning_dim": 1280,
|
| 35 |
+
"down_blocks_repeat_mappers": [
|
| 36 |
+
1,
|
| 37 |
+
1,
|
| 38 |
+
1,
|
| 39 |
+
1
|
| 40 |
+
],
|
| 41 |
+
"down_num_layers_per_block": [
|
| 42 |
+
2,
|
| 43 |
+
6,
|
| 44 |
+
28,
|
| 45 |
+
6
|
| 46 |
+
],
|
| 47 |
+
"dropout": [
|
| 48 |
+
0,
|
| 49 |
+
0,
|
| 50 |
+
0.1,
|
| 51 |
+
0.1
|
| 52 |
+
],
|
| 53 |
+
"effnet_in_channels": 16,
|
| 54 |
+
"in_channels": 4,
|
| 55 |
+
"kernel_size": 3,
|
| 56 |
+
"num_attention_heads": [
|
| 57 |
+
0,
|
| 58 |
+
0,
|
| 59 |
+
20,
|
| 60 |
+
20
|
| 61 |
+
],
|
| 62 |
+
"out_channels": 4,
|
| 63 |
+
"patch_size": 2,
|
| 64 |
+
"pixel_mapper_in_channels": 3,
|
| 65 |
+
"self_attn": true,
|
| 66 |
+
"switch_level": null,
|
| 67 |
+
"timestep_conditioning_type": [
|
| 68 |
+
"sca"
|
| 69 |
+
],
|
| 70 |
+
"timestep_ratio_embedding_dim": 64,
|
| 71 |
+
"up_blocks_repeat_mappers": [
|
| 72 |
+
3,
|
| 73 |
+
3,
|
| 74 |
+
2,
|
| 75 |
+
2
|
| 76 |
+
],
|
| 77 |
+
"up_num_layers_per_block": [
|
| 78 |
+
6,
|
| 79 |
+
28,
|
| 80 |
+
6,
|
| 81 |
+
2
|
| 82 |
+
]
|
| 83 |
+
}
|
decoder_lite/config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableCascadeUNet",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"block_out_channels": [
|
| 5 |
+
320,
|
| 6 |
+
576,
|
| 7 |
+
1152,
|
| 8 |
+
1152
|
| 9 |
+
],
|
| 10 |
+
"block_types_per_layer": [
|
| 11 |
+
[
|
| 12 |
+
"SDCascadeResBlock",
|
| 13 |
+
"SDCascadeTimestepBlock"
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
"SDCascadeResBlock",
|
| 17 |
+
"SDCascadeTimestepBlock"
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
"SDCascadeResBlock",
|
| 21 |
+
"SDCascadeTimestepBlock",
|
| 22 |
+
"SDCascadeAttnBlock"
|
| 23 |
+
],
|
| 24 |
+
[
|
| 25 |
+
"SDCascadeResBlock",
|
| 26 |
+
"SDCascadeTimestepBlock",
|
| 27 |
+
"SDCascadeAttnBlock"
|
| 28 |
+
]
|
| 29 |
+
],
|
| 30 |
+
"clip_image_in_channels": null,
|
| 31 |
+
"clip_seq": 4,
|
| 32 |
+
"clip_text_in_channels": null,
|
| 33 |
+
"clip_text_pooled_in_channels": 1280,
|
| 34 |
+
"conditioning_dim": 1280,
|
| 35 |
+
"down_blocks_repeat_mappers": [
|
| 36 |
+
1,
|
| 37 |
+
1,
|
| 38 |
+
1,
|
| 39 |
+
1
|
| 40 |
+
],
|
| 41 |
+
"down_num_layers_per_block": [
|
| 42 |
+
2,
|
| 43 |
+
4,
|
| 44 |
+
14,
|
| 45 |
+
4
|
| 46 |
+
],
|
| 47 |
+
"dropout": [
|
| 48 |
+
0,
|
| 49 |
+
0,
|
| 50 |
+
0.1,
|
| 51 |
+
0.1
|
| 52 |
+
],
|
| 53 |
+
"effnet_in_channels": 16,
|
| 54 |
+
"in_channels": 4,
|
| 55 |
+
"kernel_size": 3,
|
| 56 |
+
"num_attention_heads": [
|
| 57 |
+
0,
|
| 58 |
+
9,
|
| 59 |
+
18,
|
| 60 |
+
18
|
| 61 |
+
],
|
| 62 |
+
"out_channels": 4,
|
| 63 |
+
"patch_size": 2,
|
| 64 |
+
"pixel_mapper_in_channels": 3,
|
| 65 |
+
"self_attn": true,
|
| 66 |
+
"switch_level": null,
|
| 67 |
+
"timestep_conditioning_type": [
|
| 68 |
+
"sca"
|
| 69 |
+
],
|
| 70 |
+
"timestep_ratio_embedding_dim": 64,
|
| 71 |
+
"up_blocks_repeat_mappers": [
|
| 72 |
+
2,
|
| 73 |
+
2,
|
| 74 |
+
2,
|
| 75 |
+
2
|
| 76 |
+
],
|
| 77 |
+
"up_num_layers_per_block": [
|
| 78 |
+
4,
|
| 79 |
+
14,
|
| 80 |
+
4,
|
| 81 |
+
2
|
| 82 |
+
]
|
| 83 |
+
}
|
prior/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableCascadeUNet",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"block_out_channels": [
|
| 5 |
+
2048,
|
| 6 |
+
2048
|
| 7 |
+
],
|
| 8 |
+
"block_types_per_layer": [
|
| 9 |
+
[
|
| 10 |
+
"SDCascadeResBlock",
|
| 11 |
+
"SDCascadeTimestepBlock",
|
| 12 |
+
"SDCascadeAttnBlock"
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
"SDCascadeResBlock",
|
| 16 |
+
"SDCascadeTimestepBlock",
|
| 17 |
+
"SDCascadeAttnBlock"
|
| 18 |
+
]
|
| 19 |
+
],
|
| 20 |
+
"clip_image_in_channels": 768,
|
| 21 |
+
"clip_seq": 4,
|
| 22 |
+
"clip_text_in_channels": 1280,
|
| 23 |
+
"clip_text_pooled_in_channels": 1280,
|
| 24 |
+
"conditioning_dim": 2048,
|
| 25 |
+
"down_blocks_repeat_mappers": [
|
| 26 |
+
1,
|
| 27 |
+
1
|
| 28 |
+
],
|
| 29 |
+
"down_num_layers_per_block": [
|
| 30 |
+
8,
|
| 31 |
+
24
|
| 32 |
+
],
|
| 33 |
+
"dropout": [
|
| 34 |
+
0.1,
|
| 35 |
+
0.1
|
| 36 |
+
],
|
| 37 |
+
"effnet_in_channels": null,
|
| 38 |
+
"in_channels": 16,
|
| 39 |
+
"kernel_size": 3,
|
| 40 |
+
"num_attention_heads": [
|
| 41 |
+
32,
|
| 42 |
+
32
|
| 43 |
+
],
|
| 44 |
+
"out_channels": 16,
|
| 45 |
+
"patch_size": 1,
|
| 46 |
+
"pixel_mapper_in_channels": null,
|
| 47 |
+
"self_attn": true,
|
| 48 |
+
"switch_level": [
|
| 49 |
+
false
|
| 50 |
+
],
|
| 51 |
+
"timestep_conditioning_type": [
|
| 52 |
+
"sca",
|
| 53 |
+
"crp"
|
| 54 |
+
],
|
| 55 |
+
"timestep_ratio_embedding_dim": 64,
|
| 56 |
+
"up_blocks_repeat_mappers": [
|
| 57 |
+
1,
|
| 58 |
+
1
|
| 59 |
+
],
|
| 60 |
+
"up_num_layers_per_block": [
|
| 61 |
+
24,
|
| 62 |
+
8
|
| 63 |
+
]
|
| 64 |
+
}
|
prior_lite/config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableCascadeUNet",
|
| 3 |
+
"_diffusers_version": "0.27.0.dev0",
|
| 4 |
+
"block_out_channels": [
|
| 5 |
+
1536,
|
| 6 |
+
1536
|
| 7 |
+
],
|
| 8 |
+
"block_types_per_layer": [
|
| 9 |
+
[
|
| 10 |
+
"SDCascadeResBlock",
|
| 11 |
+
"SDCascadeTimestepBlock",
|
| 12 |
+
"SDCascadeAttnBlock"
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
"SDCascadeResBlock",
|
| 16 |
+
"SDCascadeTimestepBlock",
|
| 17 |
+
"SDCascadeAttnBlock"
|
| 18 |
+
]
|
| 19 |
+
],
|
| 20 |
+
"clip_image_in_channels": 768,
|
| 21 |
+
"clip_seq": 4,
|
| 22 |
+
"clip_text_in_channels": 1280,
|
| 23 |
+
"clip_text_pooled_in_channels": 1280,
|
| 24 |
+
"conditioning_dim": 1536,
|
| 25 |
+
"down_blocks_repeat_mappers": [
|
| 26 |
+
1,
|
| 27 |
+
1
|
| 28 |
+
],
|
| 29 |
+
"down_num_layers_per_block": [
|
| 30 |
+
4,
|
| 31 |
+
12
|
| 32 |
+
],
|
| 33 |
+
"dropout": [
|
| 34 |
+
0.1,
|
| 35 |
+
0.1
|
| 36 |
+
],
|
| 37 |
+
"effnet_in_channels": null,
|
| 38 |
+
"in_channels": 16,
|
| 39 |
+
"kernel_size": 3,
|
| 40 |
+
"num_attention_heads": [
|
| 41 |
+
24,
|
| 42 |
+
24
|
| 43 |
+
],
|
| 44 |
+
"out_channels": 16,
|
| 45 |
+
"patch_size": 1,
|
| 46 |
+
"pixel_mapper_in_channels": null,
|
| 47 |
+
"self_attn": true,
|
| 48 |
+
"switch_level": [
|
| 49 |
+
false
|
| 50 |
+
],
|
| 51 |
+
"timestep_conditioning_type": [
|
| 52 |
+
"sca",
|
| 53 |
+
"crp"
|
| 54 |
+
],
|
| 55 |
+
"timestep_ratio_embedding_dim": 64,
|
| 56 |
+
"up_blocks_repeat_mappers": [
|
| 57 |
+
1,
|
| 58 |
+
1
|
| 59 |
+
],
|
| 60 |
+
"up_num_layers_per_block": [
|
| 61 |
+
12,
|
| 62 |
+
4
|
| 63 |
+
]
|
| 64 |
+
}
|