Hugging Face's logo

TensorStack
/
AutoEncoder

Diffusers
Safetensors
Model card Files
xet
Community
saddam213 commited on
Commit
c280c06
·
verified ·
1 Parent(s): c86f025

Upload 22 files

Browse files
Files changed (22) hide show
  1. CogVideoX/config.json +40 -0
  2. CogVideoX/diffusion_pytorch_model.safetensors +3 -0
  3. Flux1/config.json +38 -0
  4. Flux1/diffusion_pytorch_model.safetensors +3 -0
  5. Flux2/config.json +39 -0
  6. Flux2/diffusion_pytorch_model.safetensors +3 -0
  7. Kandinsky5Image/config.json +38 -0
  8. Kandinsky5Image/diffusion_pytorch_model.safetensors +3 -0
  9. Kandinsky5Video/config.json +32 -0
  10. Kandinsky5Video/diffusion_pytorch_model.safetensors +3 -0
  11. LTX/config.json +32 -0
  12. LTX/diffusion_pytorch_model.safetensors +3 -0
  13. LTX2/config.json +81 -0
  14. LTX2/diffusion_pytorch_model.safetensors +3 -0
  15. QwenImage/config.json +56 -0
  16. QwenImage/diffusion_pytorch_model.safetensors +3 -0
  17. StableDiffusion3/config.json +38 -0
  18. StableDiffusion3/diffusion_pytorch_model.safetensors +3 -0
  19. StableDiffusionXL/config.json +31 -0
  20. StableDiffusionXL/diffusion_pytorch_model.safetensors +3 -0
  21. Wan21/config.json +56 -0
  22. Wan21/diffusion_pytorch_model.safetensors +3 -0
CogVideoX/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLCogVideoX",
3
+ "_diffusers_version": "0.32.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 256,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "CogVideoXDownBlock3D",
13
+ "CogVideoXDownBlock3D",
14
+ "CogVideoXDownBlock3D",
15
+ "CogVideoXDownBlock3D"
16
+ ],
17
+ "force_upcast": true,
18
+ "in_channels": 3,
19
+ "latent_channels": 16,
20
+ "latents_mean": null,
21
+ "latents_std": null,
22
+ "layers_per_block": 3,
23
+ "norm_eps": 1e-06,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_height": 480,
27
+ "sample_width": 720,
28
+ "scaling_factor": 1.15258426,
29
+ "shift_factor": null,
30
+ "temporal_compression_ratio": 4,
31
+ "up_block_types": [
32
+ "CogVideoXUpBlock3D",
33
+ "CogVideoXUpBlock3D",
34
+ "CogVideoXUpBlock3D",
35
+ "CogVideoXUpBlock3D"
36
+ ],
37
+ "use_post_quant_conv": false,
38
+ "use_quant_conv": false,
39
+ "invert_scale_latents": false
40
+ }
CogVideoX/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e
3
+ size 862388596
Flux1/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "_name_or_path": "flux-dev",
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": true,
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": 0.3611,
29
+ "shift_factor": 0.1159,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": false,
37
+ "use_quant_conv": false
38
+ }
Flux1/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3
3
+ size 167666902
Flux2/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLFlux2",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "act_fn": "silu",
5
+ "batch_norm_eps": 0.0001,
6
+ "batch_norm_momentum": 0.1,
7
+ "block_out_channels": [
8
+ 128,
9
+ 256,
10
+ 512,
11
+ 512
12
+ ],
13
+ "down_block_types": [
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D",
17
+ "DownEncoderBlock2D"
18
+ ],
19
+ "force_upcast": true,
20
+ "in_channels": 3,
21
+ "latent_channels": 32,
22
+ "layers_per_block": 2,
23
+ "mid_block_add_attention": true,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "patch_size": [
27
+ 2,
28
+ 2
29
+ ],
30
+ "sample_size": 1024,
31
+ "up_block_types": [
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D",
35
+ "UpDecoderBlock2D"
36
+ ],
37
+ "use_post_quant_conv": true,
38
+ "use_quant_conv": true
39
+ }
Flux2/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64f3a68e1cc4f9f4e29b6e0da38a0204fe9a49f2d4053f0ec1fa1ca02f9c4b5
3
+ size 336213556
Kandinsky5Image/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.32.2",
4
+ "_name_or_path": "black-forest-labs/FLUX.1-dev",
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": true,
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": 0.3611,
29
+ "shift_factor": 0.1159,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": false,
37
+ "use_quant_conv": false
38
+ }
Kandinsky5Image/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58ad0fbb7e0621871b778bf36a6faeb2c46a79adb32b898b60acd1f9560f890
3
+ size 167666654
Kandinsky5Video/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLHunyuanVideo",
3
+ "_diffusers_version": "0.32.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "HunyuanVideoDownBlock3D",
13
+ "HunyuanVideoDownBlock3D",
14
+ "HunyuanVideoDownBlock3D",
15
+ "HunyuanVideoDownBlock3D"
16
+ ],
17
+ "in_channels": 3,
18
+ "latent_channels": 16,
19
+ "layers_per_block": 2,
20
+ "mid_block_add_attention": true,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "scaling_factor": 0.476986,
24
+ "spatial_compression_ratio": 8,
25
+ "temporal_compression_ratio": 4,
26
+ "up_block_types": [
27
+ "HunyuanVideoUpBlock3D",
28
+ "HunyuanVideoUpBlock3D",
29
+ "HunyuanVideoUpBlock3D",
30
+ "HunyuanVideoUpBlock3D"
31
+ ]
32
+ }
Kandinsky5Video/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883
3
+ size 985943868
LTX/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTXVideo",
3
+ "_diffusers_version": "0.32.0.dev0",
4
+ "block_out_channels": [
5
+ 128,
6
+ 256,
7
+ 512,
8
+ 512
9
+ ],
10
+ "decoder_causal": false,
11
+ "encoder_causal": true,
12
+ "in_channels": 3,
13
+ "latent_channels": 128,
14
+ "layers_per_block": [
15
+ 4,
16
+ 3,
17
+ 3,
18
+ 3,
19
+ 4
20
+ ],
21
+ "out_channels": 3,
22
+ "patch_size": 4,
23
+ "patch_size_t": 1,
24
+ "resnet_norm_eps": 1e-06,
25
+ "scaling_factor": 1.0,
26
+ "spatio_temporal_scaling": [
27
+ true,
28
+ true,
29
+ true,
30
+ false
31
+ ]
32
+ }
LTX/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265ca87cb5dff5e37f924286e957324e282fe7710a952a7dafc0df43883e2010
3
+ size 1676798532
LTX2/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTX2Video",
3
+ "_diffusers_version": "0.37.0.dev0",
4
+ "block_out_channels": [
5
+ 256,
6
+ 512,
7
+ 1024,
8
+ 2048
9
+ ],
10
+ "decoder_block_out_channels": [
11
+ 256,
12
+ 512,
13
+ 1024
14
+ ],
15
+ "decoder_causal": false,
16
+ "decoder_inject_noise": [
17
+ false,
18
+ false,
19
+ false,
20
+ false
21
+ ],
22
+ "decoder_layers_per_block": [
23
+ 5,
24
+ 5,
25
+ 5,
26
+ 5
27
+ ],
28
+ "decoder_spatial_padding_mode": "reflect",
29
+ "decoder_spatio_temporal_scaling": [
30
+ true,
31
+ true,
32
+ true
33
+ ],
34
+ "down_block_types": [
35
+ "LTX2VideoDownBlock3D",
36
+ "LTX2VideoDownBlock3D",
37
+ "LTX2VideoDownBlock3D",
38
+ "LTX2VideoDownBlock3D"
39
+ ],
40
+ "downsample_type": [
41
+ "spatial",
42
+ "temporal",
43
+ "spatiotemporal",
44
+ "spatiotemporal"
45
+ ],
46
+ "encoder_causal": true,
47
+ "encoder_spatial_padding_mode": "zeros",
48
+ "in_channels": 3,
49
+ "latent_channels": 128,
50
+ "layers_per_block": [
51
+ 4,
52
+ 6,
53
+ 6,
54
+ 2,
55
+ 2
56
+ ],
57
+ "out_channels": 3,
58
+ "patch_size": 4,
59
+ "patch_size_t": 1,
60
+ "resnet_norm_eps": 1e-06,
61
+ "scaling_factor": 1.0,
62
+ "spatial_compression_ratio": 32,
63
+ "spatio_temporal_scaling": [
64
+ true,
65
+ true,
66
+ true,
67
+ true
68
+ ],
69
+ "temporal_compression_ratio": 8,
70
+ "timestep_conditioning": false,
71
+ "upsample_factor": [
72
+ 2,
73
+ 2,
74
+ 2
75
+ ],
76
+ "upsample_residual": [
77
+ true,
78
+ true,
79
+ true
80
+ ]
81
+ }
LTX2/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:107cc359e3c4bce18c53d98686f4b3fe10c4207b6665d89b38b0741270514bfb
3
+ size 2444982370
QwenImage/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLQwenImage",
3
+ "_diffusers_version": "0.35.0.dev0",
4
+ "attn_scales": [],
5
+ "base_dim": 96,
6
+ "dim_mult": [
7
+ 1,
8
+ 2,
9
+ 4,
10
+ 4
11
+ ],
12
+ "dropout": 0.0,
13
+ "latents_mean": [
14
+ -0.7571,
15
+ -0.7089,
16
+ -0.9113,
17
+ 0.1075,
18
+ -0.1745,
19
+ 0.9653,
20
+ -0.1517,
21
+ 1.5508,
22
+ 0.4134,
23
+ -0.0715,
24
+ 0.5517,
25
+ -0.3632,
26
+ -0.1922,
27
+ -0.9497,
28
+ 0.2503,
29
+ -0.2921
30
+ ],
31
+ "latents_std": [
32
+ 2.8184,
33
+ 1.4541,
34
+ 2.3275,
35
+ 2.6558,
36
+ 1.2196,
37
+ 1.7708,
38
+ 2.6052,
39
+ 2.0743,
40
+ 3.2687,
41
+ 2.1526,
42
+ 2.8652,
43
+ 1.5579,
44
+ 1.6382,
45
+ 1.1253,
46
+ 2.8251,
47
+ 1.916
48
+ ],
49
+ "num_res_blocks": 2,
50
+ "temperal_downsample": [
51
+ false,
52
+ true,
53
+ true
54
+ ],
55
+ "z_dim": 16
56
+ }
QwenImage/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344
3
+ size 253806966
StableDiffusion3/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.31.0.dev0",
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": true,
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": 1.5305,
29
+ "shift_factor": 0.0609,
30
+ "up_block_types": [
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D",
33
+ "UpDecoderBlock2D",
34
+ "UpDecoderBlock2D"
35
+ ],
36
+ "use_post_quant_conv": false,
37
+ "use_quant_conv": false
38
+ }
StableDiffusion3/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f53304a79335b55e13ec50f63e5157fee4deb2f30d5fae0654e2b2653c109dc
3
+ size 167666902
StableDiffusionXL/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.19.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D"
16
+ ],
17
+ "force_upcast": true,
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 1024,
24
+ "scaling_factor": 0.13025,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
StableDiffusionXL/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ed3b02e09638568e99d4398c67bc654dde04e6c0db61fb2d21dba630e7058a
3
+ size 334643268
Wan21/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLWan",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "attn_scales": [],
5
+ "base_dim": 96,
6
+ "dim_mult": [
7
+ 1,
8
+ 2,
9
+ 4,
10
+ 4
11
+ ],
12
+ "dropout": 0.0,
13
+ "latents_mean": [
14
+ -0.7571,
15
+ -0.7089,
16
+ -0.9113,
17
+ 0.1075,
18
+ -0.1745,
19
+ 0.9653,
20
+ -0.1517,
21
+ 1.5508,
22
+ 0.4134,
23
+ -0.0715,
24
+ 0.5517,
25
+ -0.3632,
26
+ -0.1922,
27
+ -0.9497,
28
+ 0.2503,
29
+ -0.2921
30
+ ],
31
+ "latents_std": [
32
+ 2.8184,
33
+ 1.4541,
34
+ 2.3275,
35
+ 2.6558,
36
+ 1.2196,
37
+ 1.7708,
38
+ 2.6052,
39
+ 2.0743,
40
+ 3.2687,
41
+ 2.1526,
42
+ 2.8652,
43
+ 1.5579,
44
+ 1.6382,
45
+ 1.1253,
46
+ 2.8251,
47
+ 1.916
48
+ ],
49
+ "num_res_blocks": 2,
50
+ "temperal_downsample": [
51
+ false,
52
+ true,
53
+ true
54
+ ],
55
+ "z_dim": 16
56
+ }
Wan21/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e524b3fffede1787a74e81b30976dce5400c4439ba64222168e607ed19e793
3
+ size 507591892