Hugging Face's logo

AiArtLab
/
simplevae

Diffusers
Safetensors
Model card Files
xet
Community
recoilme commited on
Commit
8308d70
·
1 Parent(s): d2849c3

simplevae

Browse files
Files changed (21) hide show
  1. config.json +0 -38
  2. create.ipynb +0 -0
  3. diffusion_pytorch_model.safetensors +0 -3
  4. final_vae/config.json +0 -38
  5. final_vae/diffusion_pytorch_model.safetensors +0 -3
  6. sdxl_vae/config.json +0 -38
  7. sdxl_vae/diffusion_pytorch_model.safetensors +0 -3
  8. sdxs_vae/.ipynb_checkpoints/config-checkpoint.json +0 -48
  9. sdxs_vae/config.json +0 -48
  10. sdxs_vae/diffusion_pytorch_model.safetensors +0 -3
  11. simple_vae_nightly/config.json +0 -38
  12. simple_vae_nightly/diffusion_pytorch_model.safetensors +0 -3
  13. simple_vae_nightly2/config.json +0 -38
  14. simple_vae_nightly2/diffusion_pytorch_model.safetensors +0 -3
  15. test.ipynb +0 -95
  16. vae/config.json +2 -2
  17. vae/diffusion_pytorch_model.safetensors +2 -2
  18. wan16x_vae_nightly/config.json +0 -129
  19. wan16x_vae_nightly/diffusion_pytorch_model.safetensors +0 -3
  20. wan16x_vae_nightly2/config.json +0 -129
  21. wan16x_vae_nightly2/diffusion_pytorch_model.safetensors +0 -3
config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.35.0.dev0",
4
- "_name_or_path": "simple_vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": false,
19
- "in_channels": 3,
20
- "latent_channels": 16,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "sample_size": 1024,
28
- "scaling_factor": 1.0,
29
- "shift_factor": 0,
30
- "up_block_types": [
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D",
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D"
35
- ],
36
- "use_post_quant_conv": true,
37
- "use_quant_conv": true
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
create.ipynb DELETED
The diff for this file is too large to render. See raw diff
 
diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5f0a20e403669e880b510514ee575a2a9cb74a1b36ab0e31fc68ef66c2173d7
3
- size 335311892
 
 
 
 
final_vae/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.34.0",
4
- "_name_or_path": "sdxl_vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": false,
19
- "in_channels": 3,
20
- "latent_channels": 4,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "sample_size": 512,
28
- "scaling_factor": 0.13025,
29
- "shift_factor": null,
30
- "up_block_types": [
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D",
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D"
35
- ],
36
- "use_post_quant_conv": true,
37
- "use_quant_conv": true
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
final_vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:00ba31cad0e49ebd19a8c62c72eef3d8e51271675f2cde0ec079aef89e44463d
3
- size 334643268
 
 
 
 
sdxl_vae/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.34.0",
4
- "_name_or_path": "sdxl_vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": false,
19
- "in_channels": 3,
20
- "latent_channels": 4,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "sample_size": 512,
28
- "scaling_factor": 0.13025,
29
- "shift_factor": null,
30
- "up_block_types": [
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D",
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D"
35
- ],
36
- "use_post_quant_conv": true,
37
- "use_quant_conv": true
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
sdxl_vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fd955b1cc451f2cafb58a29e1e0a07589e34d364ddf3d93ccd21a16ff8d3e5c
3
- size 334643268
 
 
 
 
sdxs_vae/.ipynb_checkpoints/config-checkpoint.json DELETED
@@ -1,48 +0,0 @@
1
- {
2
- "_class_name": "AsymmetricAutoencoderKL",
3
- "_diffusers_version": "0.34.0",
4
- "_name_or_path": "vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 768,
11
- 768
12
- ],
13
- "down_block_out_channels": [
14
- 128,
15
- 256,
16
- 512,
17
- 512
18
- ],
19
- "down_block_types": [
20
- "DownEncoderBlock2D",
21
- "DownEncoderBlock2D",
22
- "DownEncoderBlock2D",
23
- "DownEncoderBlock2D"
24
- ],
25
- "force_upcast": false,
26
- "in_channels": 3,
27
- "latent_channels": 16,
28
- "layers_per_down_block": 2,
29
- "layers_per_up_block": 2,
30
- "norm_num_groups": 32,
31
- "out_channels": 3,
32
- "sample_size": 1024,
33
- "scaling_factor": 1,
34
- "up_block_out_channels": [
35
- 128,
36
- 256,
37
- 512,
38
- 768,
39
- 768
40
- ],
41
- "up_block_types": [
42
- "UpDecoderBlock2D",
43
- "UpDecoderBlock2D",
44
- "UpDecoderBlock2D",
45
- "UpDecoderBlock2D",
46
- "UpDecoderBlock2D"
47
- ]
48
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
sdxs_vae/config.json DELETED
@@ -1,48 +0,0 @@
1
- {
2
- "_class_name": "AsymmetricAutoencoderKL",
3
- "_diffusers_version": "0.34.0",
4
- "_name_or_path": "vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 768,
11
- 768
12
- ],
13
- "down_block_out_channels": [
14
- 128,
15
- 256,
16
- 512,
17
- 512
18
- ],
19
- "down_block_types": [
20
- "DownEncoderBlock2D",
21
- "DownEncoderBlock2D",
22
- "DownEncoderBlock2D",
23
- "DownEncoderBlock2D"
24
- ],
25
- "force_upcast": false,
26
- "in_channels": 3,
27
- "latent_channels": 16,
28
- "layers_per_down_block": 2,
29
- "layers_per_up_block": 2,
30
- "norm_num_groups": 32,
31
- "out_channels": 3,
32
- "sample_size": 1024,
33
- "scaling_factor": 1,
34
- "up_block_out_channels": [
35
- 128,
36
- 256,
37
- 512,
38
- 768,
39
- 768
40
- ],
41
- "up_block_types": [
42
- "UpDecoderBlock2D",
43
- "UpDecoderBlock2D",
44
- "UpDecoderBlock2D",
45
- "UpDecoderBlock2D",
46
- "UpDecoderBlock2D"
47
- ]
48
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
sdxs_vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c42f2525cd74fedf496b0d3bf2c1c2ec6eee59250d934c4d74a0b449ad2b627
3
- size 698002772
 
 
 
 
simple_vae_nightly/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.35.0.dev0",
4
- "_name_or_path": "simple_vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": false,
19
- "in_channels": 3,
20
- "latent_channels": 16,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "sample_size": 1024,
28
- "scaling_factor": 1.0,
29
- "shift_factor": 0,
30
- "up_block_types": [
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D",
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D"
35
- ],
36
- "use_post_quant_conv": true,
37
- "use_quant_conv": true
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
simple_vae_nightly/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b39620d0953839362425f03674e6c3e37f03d20be3fbd7f281baea4dfc336a40
3
- size 335311892
 
 
 
 
simple_vae_nightly2/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.35.0.dev0",
4
- "_name_or_path": "simple_vae",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": false,
19
- "in_channels": 3,
20
- "latent_channels": 16,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "sample_size": 1024,
28
- "scaling_factor": 1.0,
29
- "shift_factor": 0,
30
- "up_block_types": [
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D",
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D"
35
- ],
36
- "use_post_quant_conv": true,
37
- "use_quant_conv": true
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
simple_vae_nightly2/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:edf84f6e6e4499cdf73c63d2442a923ee46bfea7b24e4bf04910cf9dd8c1f652
3
- size 335311892
 
 
 
 
test.ipynb DELETED
@@ -1,95 +0,0 @@
1
- {
2
- "cells": [
3
- {
4
- "cell_type": "code",
5
- "execution_count": 1,
6
- "id": "4f62bfd9-5396-48e2-aac7-bdf639cab345",
7
- "metadata": {},
8
- "outputs": [
9
- {
10
- "name": "stderr",
11
- "output_type": "stream",
12
- "text": [
13
- "The config attributes {'block_out_channels': [128, 256, 512, 768, 768], 'force_upcast': False} were passed to AsymmetricAutoencoderKL, but are not expected and will be ignored. Please verify your config.json configuration file.\n"
14
- ]
15
- },
16
- {
17
- "name": "stdout",
18
- "output_type": "stream",
19
- "text": [
20
- "ok\n"
21
- ]
22
- }
23
- ],
24
- "source": [
25
- "import torch\n",
26
- "\n",
27
- "from torchvision import transforms, utils\n",
28
- "\n",
29
- "import diffusers\n",
30
- "from diffusers import AsymmetricAutoencoderKL\n",
31
- "\n",
32
- "from diffusers.utils import load_image\n",
33
- "\n",
34
- "def crop_image_to_nearest_divisible_by_8(img):\n",
35
- " # Check if the image height and width are divisible by 8\n",
36
- " if img.shape[1] % 8 == 0 and img.shape[2] % 8 == 0:\n",
37
- " return img\n",
38
- " else:\n",
39
- " # Calculate the closest lower resolution divisible by 8\n",
40
- " new_height = img.shape[1] - (img.shape[1] % 8)\n",
41
- " new_width = img.shape[2] - (img.shape[2] % 8)\n",
42
- " \n",
43
- " # Use CenterCrop to crop the image\n",
44
- " transform = transforms.CenterCrop((new_height, new_width), interpolation=transforms.InterpolationMode.BILINEAR)\n",
45
- " img = transform(img).to(torch.float32).clamp(-1, 1)\n",
46
- " \n",
47
- " return img\n",
48
- " \n",
49
- "to_tensor = transforms.ToTensor()\n",
50
- "\n",
51
- "device = \"cuda\"\n",
52
- "dtype=torch.float16\n",
53
- "vae = AsymmetricAutoencoderKL.from_pretrained(\"vae\",torch_dtype=dtype).to(device).eval()\n",
54
- "\n",
55
- "image = load_image(\"generated.png\")\n",
56
- "\n",
57
- "image = crop_image_to_nearest_divisible_by_8(to_tensor(image)).unsqueeze(0).to(device,dtype=dtype)\n",
58
- "\n",
59
- "upscaled_image = vae(image).sample\n",
60
- "# Save the reconstructed image\n",
61
- "utils.save_image(upscaled_image, \"test.png\")\n",
62
- "print('ok')"
63
- ]
64
- },
65
- {
66
- "cell_type": "code",
67
- "execution_count": null,
68
- "id": "7e3ad326-c410-44b6-a738-15b7f7e15075",
69
- "metadata": {},
70
- "outputs": [],
71
- "source": []
72
- }
73
- ],
74
- "metadata": {
75
- "kernelspec": {
76
- "display_name": "Python 3 (ipykernel)",
77
- "language": "python",
78
- "name": "python3"
79
- },
80
- "language_info": {
81
- "codemirror_mode": {
82
- "name": "ipython",
83
- "version": 3
84
- },
85
- "file_extension": ".py",
86
- "mimetype": "text/x-python",
87
- "name": "python",
88
- "nbconvert_exporter": "python",
89
- "pygments_lexer": "ipython3",
90
- "version": "3.11.6"
91
- }
92
- },
93
- "nbformat": 4,
94
- "nbformat_minor": 5
95
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.35.0.dev0",
4
- "_name_or_path": "simple_vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.35.1",
4
+ "_name_or_path": "AiArtLab/simplevae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:744c01d5b33fcca51ca9839bb0afb14cce48a13e922d27d8b73ed92c5733dd0c
3
- size 335311892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff1aa1cce9dcf003c7eb23548fdb62101fe9bdeedf30aa4a897b91a6ef13f93
3
+ size 167669678
wan16x_vae_nightly/config.json DELETED
@@ -1,129 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKLWan",
3
- "_diffusers_version": "0.35.1",
4
- "_name_or_path": "wan16x_vae",
5
- "attn_scales": [],
6
- "base_dim": 160,
7
- "clip_output": false,
8
- "decoder_base_dim": 256,
9
- "dim_mult": [
10
- 1,
11
- 2,
12
- 4,
13
- 4
14
- ],
15
- "dropout": 0.0,
16
- "in_channels": 12,
17
- "is_residual": true,
18
- "latents_mean": [
19
- -0.2289,
20
- -0.0052,
21
- -0.1323,
22
- -0.2339,
23
- -0.2799,
24
- 0.0174,
25
- 0.1838,
26
- 0.1557,
27
- -0.1382,
28
- 0.0542,
29
- 0.2813,
30
- 0.0891,
31
- 0.157,
32
- -0.0098,
33
- 0.0375,
34
- -0.1825,
35
- -0.2246,
36
- -0.1207,
37
- -0.0698,
38
- 0.5109,
39
- 0.2665,
40
- -0.2108,
41
- -0.2158,
42
- 0.2502,
43
- -0.2055,
44
- -0.0322,
45
- 0.1109,
46
- 0.1567,
47
- -0.0729,
48
- 0.0899,
49
- -0.2799,
50
- -0.123,
51
- -0.0313,
52
- -0.1649,
53
- 0.0117,
54
- 0.0723,
55
- -0.2839,
56
- -0.2083,
57
- -0.052,
58
- 0.3748,
59
- 0.0152,
60
- 0.1957,
61
- 0.1433,
62
- -0.2944,
63
- 0.3573,
64
- -0.0548,
65
- -0.1681,
66
- -0.0667
67
- ],
68
- "latents_std": [
69
- 0.4765,
70
- 1.0364,
71
- 0.4514,
72
- 1.1677,
73
- 0.5313,
74
- 0.499,
75
- 0.4818,
76
- 0.5013,
77
- 0.8158,
78
- 1.0344,
79
- 0.5894,
80
- 1.0901,
81
- 0.6885,
82
- 0.6165,
83
- 0.8454,
84
- 0.4978,
85
- 0.5759,
86
- 0.3523,
87
- 0.7135,
88
- 0.6804,
89
- 0.5833,
90
- 1.4146,
91
- 0.8986,
92
- 0.5659,
93
- 0.7069,
94
- 0.5338,
95
- 0.4889,
96
- 0.4917,
97
- 0.4069,
98
- 0.4999,
99
- 0.6866,
100
- 0.4093,
101
- 0.5709,
102
- 0.6065,
103
- 0.6415,
104
- 0.4944,
105
- 0.5726,
106
- 1.2042,
107
- 0.5458,
108
- 1.6887,
109
- 0.3971,
110
- 1.06,
111
- 0.3943,
112
- 0.5537,
113
- 0.5444,
114
- 0.4089,
115
- 0.7468,
116
- 0.7744
117
- ],
118
- "num_res_blocks": 2,
119
- "out_channels": 12,
120
- "patch_size": 2,
121
- "scale_factor_spatial": 16,
122
- "scale_factor_temporal": 4,
123
- "temperal_downsample": [
124
- false,
125
- true,
126
- true
127
- ],
128
- "z_dim": 48
129
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wan16x_vae_nightly/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ba8f8440d69d3369abd2a6e7e76aea92a8c4014bf718bb23bb86223a157ca46
3
- size 2818777808
 
 
 
 
wan16x_vae_nightly2/config.json DELETED
@@ -1,129 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKLWan",
3
- "_diffusers_version": "0.35.1",
4
- "_name_or_path": "wan16x_vae",
5
- "attn_scales": [],
6
- "base_dim": 160,
7
- "clip_output": false,
8
- "decoder_base_dim": 256,
9
- "dim_mult": [
10
- 1,
11
- 2,
12
- 4,
13
- 4
14
- ],
15
- "dropout": 0.0,
16
- "in_channels": 12,
17
- "is_residual": true,
18
- "latents_mean": [
19
- -0.2289,
20
- -0.0052,
21
- -0.1323,
22
- -0.2339,
23
- -0.2799,
24
- 0.0174,
25
- 0.1838,
26
- 0.1557,
27
- -0.1382,
28
- 0.0542,
29
- 0.2813,
30
- 0.0891,
31
- 0.157,
32
- -0.0098,
33
- 0.0375,
34
- -0.1825,
35
- -0.2246,
36
- -0.1207,
37
- -0.0698,
38
- 0.5109,
39
- 0.2665,
40
- -0.2108,
41
- -0.2158,
42
- 0.2502,
43
- -0.2055,
44
- -0.0322,
45
- 0.1109,
46
- 0.1567,
47
- -0.0729,
48
- 0.0899,
49
- -0.2799,
50
- -0.123,
51
- -0.0313,
52
- -0.1649,
53
- 0.0117,
54
- 0.0723,
55
- -0.2839,
56
- -0.2083,
57
- -0.052,
58
- 0.3748,
59
- 0.0152,
60
- 0.1957,
61
- 0.1433,
62
- -0.2944,
63
- 0.3573,
64
- -0.0548,
65
- -0.1681,
66
- -0.0667
67
- ],
68
- "latents_std": [
69
- 0.4765,
70
- 1.0364,
71
- 0.4514,
72
- 1.1677,
73
- 0.5313,
74
- 0.499,
75
- 0.4818,
76
- 0.5013,
77
- 0.8158,
78
- 1.0344,
79
- 0.5894,
80
- 1.0901,
81
- 0.6885,
82
- 0.6165,
83
- 0.8454,
84
- 0.4978,
85
- 0.5759,
86
- 0.3523,
87
- 0.7135,
88
- 0.6804,
89
- 0.5833,
90
- 1.4146,
91
- 0.8986,
92
- 0.5659,
93
- 0.7069,
94
- 0.5338,
95
- 0.4889,
96
- 0.4917,
97
- 0.4069,
98
- 0.4999,
99
- 0.6866,
100
- 0.4093,
101
- 0.5709,
102
- 0.6065,
103
- 0.6415,
104
- 0.4944,
105
- 0.5726,
106
- 1.2042,
107
- 0.5458,
108
- 1.6887,
109
- 0.3971,
110
- 1.06,
111
- 0.3943,
112
- 0.5537,
113
- 0.5444,
114
- 0.4089,
115
- 0.7468,
116
- 0.7744
117
- ],
118
- "num_res_blocks": 2,
119
- "out_channels": 12,
120
- "patch_size": 2,
121
- "scale_factor_spatial": 16,
122
- "scale_factor_temporal": 4,
123
- "temperal_downsample": [
124
- false,
125
- true,
126
- true
127
- ],
128
- "z_dim": 48
129
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
wan16x_vae_nightly2/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a97241a505fc54a972fef91bb8006dee59116fa64de7c81f6f54a86ec9a04718
3
- size 2818777808