Hugging Face's logo

ziyiwhat
/
StableMotion

Diffusers
Safetensors
Model card Files
xet
 Community
ziyiwhat commited on
Commit
ce0bcac
·
verified ·
1 Parent(s): 204cfe7

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. StableMotion_RSC/unet/config.json +76 -0
  2. StableMotion_RSC/unet/diffusion_pytorch_model.safetensors +3 -0
  3. StableMotion_RSC/unet_ema/config.json +83 -0
  4. StableMotion_RSC/unet_ema/diffusion_pytorch_model.safetensors +3 -0
  5. StableMotion_SIR/unet/config.json +76 -0
  6. StableMotion_SIR/unet/diffusion_pytorch_model.safetensors +3 -0
  7. StableMotion_SIR/unet_ema/config.json +83 -0
  8. StableMotion_SIR/unet_ema/diffusion_pytorch_model.safetensors +3 -0
StableMotion_RSC/unet/config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.32.2",
4
+ "_name_or_path": "/vepfs-d-data/q-jigan/hmb/stablerec/SD2/models--stabilityai--stable-diffusion-2",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 8,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": [
59
+ 32,
60
+ 32
61
+ ],
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "use_linear_projection": true
76
+ }
StableMotion_RSC/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c6e2f5c0c818846807b6ded19e1a570b341aef7b2f388b5be5de7ce3c0edfc
3
+ size 3463772592
StableMotion_RSC/unet_ema/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.32.2",
4
+ "_name_or_path": "/vepfs-d-data/q-jigan/hmb/stablerec/SD2/models--stabilityai--stable-diffusion-2",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 8,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 60000,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": [
64
+ 32,
65
+ 32
66
+ ],
67
+ "time_cond_proj_dim": null,
68
+ "time_embedding_act_fn": null,
69
+ "time_embedding_dim": null,
70
+ "time_embedding_type": "positional",
71
+ "timestep_post_act": null,
72
+ "transformer_layers_per_block": 1,
73
+ "up_block_types": [
74
+ "UpBlock2D",
75
+ "CrossAttnUpBlock2D",
76
+ "CrossAttnUpBlock2D",
77
+ "CrossAttnUpBlock2D"
78
+ ],
79
+ "upcast_attention": false,
80
+ "update_after_step": 0,
81
+ "use_ema_warmup": false,
82
+ "use_linear_projection": true
83
+ }
StableMotion_RSC/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2014a15f237bd2073995fb67e17cfd62cac8d966feb80eeb48a32bbbbd5605e7
3
+ size 3463772592
StableMotion_SIR/unet/config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "../phase2/checkpoint-40000",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 12,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": [
59
+ 48,
60
+ 64
61
+ ],
62
+ "time_cond_proj_dim": null,
63
+ "time_embedding_act_fn": null,
64
+ "time_embedding_dim": null,
65
+ "time_embedding_type": "positional",
66
+ "timestep_post_act": null,
67
+ "transformer_layers_per_block": 1,
68
+ "up_block_types": [
69
+ "UpBlock2D",
70
+ "CrossAttnUpBlock2D",
71
+ "CrossAttnUpBlock2D",
72
+ "CrossAttnUpBlock2D"
73
+ ],
74
+ "upcast_attention": false,
75
+ "use_linear_projection": true
76
+ }
StableMotion_SIR/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b678987215f8958c15cdf5a31a87ad0fb239592be9db620bddb1b6751350383
3
+ size 3463818688
StableMotion_SIR/unet_ema/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.31.0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "decay": 0.9999,
30
+ "down_block_types": [
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "CrossAttnDownBlock2D",
34
+ "DownBlock2D"
35
+ ],
36
+ "downsample_padding": 1,
37
+ "dropout": 0.0,
38
+ "dual_cross_attention": false,
39
+ "encoder_hid_dim": null,
40
+ "encoder_hid_dim_type": null,
41
+ "flip_sin_to_cos": true,
42
+ "freq_shift": 0,
43
+ "in_channels": 12,
44
+ "inv_gamma": 1.0,
45
+ "layers_per_block": 2,
46
+ "mid_block_only_cross_attention": null,
47
+ "mid_block_scale_factor": 1,
48
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
49
+ "min_decay": 0.0,
50
+ "norm_eps": 1e-05,
51
+ "norm_num_groups": 32,
52
+ "num_attention_heads": null,
53
+ "num_class_embeds": null,
54
+ "only_cross_attention": false,
55
+ "optimization_step": 30000,
56
+ "out_channels": 4,
57
+ "power": 0.6666666666666666,
58
+ "projection_class_embeddings_input_dim": null,
59
+ "resnet_out_scale_factor": 1.0,
60
+ "resnet_skip_time_act": false,
61
+ "resnet_time_scale_shift": "default",
62
+ "reverse_transformer_layers_per_block": null,
63
+ "sample_size": [
64
+ 48,
65
+ 64
66
+ ],
67
+ "time_cond_proj_dim": null,
68
+ "time_embedding_act_fn": null,
69
+ "time_embedding_dim": null,
70
+ "time_embedding_type": "positional",
71
+ "timestep_post_act": null,
72
+ "transformer_layers_per_block": 1,
73
+ "up_block_types": [
74
+ "UpBlock2D",
75
+ "CrossAttnUpBlock2D",
76
+ "CrossAttnUpBlock2D",
77
+ "CrossAttnUpBlock2D"
78
+ ],
79
+ "upcast_attention": false,
80
+ "update_after_step": 0,
81
+ "use_ema_warmup": false,
82
+ "use_linear_projection": true
83
+ }
StableMotion_SIR/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9a38984146c2442f7b207716a3bceca4eb64215854a72295e6e1a7145b2a7f
3
+ size 3463818688