Hugging Face's logo

Spaces:
LPDoctor
/
AIGC-3D
Running on Zero

App Files Community
SeanYoungxh commited on
Commit
9cef7d5
•
1 Parent(s): 82317e1

Upload folder using huggingface_hub

Browse files
Files changed (32) hide show
  1. mvd_lite/.gitattributes +35 -0
  2. mvd_lite/feature_extractor_clip/preprocessor_config.json +27 -0
  3. mvd_lite/feature_extractor_vae/preprocessor_config.json +19 -0
  4. mvd_lite/model_index.json +120 -0
  5. mvd_lite/scheduler/scheduler_config.json +15 -0
  6. mvd_lite/text_encoder/config.json +25 -0
  7. mvd_lite/text_encoder/model.safetensors +3 -0
  8. mvd_lite/tokenizer/merges.txt +0 -0
  9. mvd_lite/tokenizer/special_tokens_map.json +24 -0
  10. mvd_lite/tokenizer/tokenizer_config.json +38 -0
  11. mvd_lite/tokenizer/vocab.json +0 -0
  12. mvd_lite/unet/config.json +73 -0
  13. mvd_lite/unet/diffusion_pytorch_model.safetensors +3 -0
  14. mvd_lite/vae/config.json +32 -0
  15. mvd_lite/vae/diffusion_pytorch_model.safetensors +3 -0
  16. mvd_lite/vision_encoder/config.json +23 -0
  17. mvd_lite/vision_encoder/model.safetensors +3 -0
  18. mvd_lite/vision_encoder/preprocessor_config.json +27 -0
  19. mvd_std/feature_extractor_vae/preprocessor_config.json +19 -0
  20. mvd_std/model_index.json +116 -0
  21. mvd_std/scheduler/scheduler_config.json +16 -0
  22. mvd_std/uc_text_emb.pt +3 -0
  23. mvd_std/uc_text_emb_2.pt +3 -0
  24. mvd_std/unet/config.json +73 -0
  25. mvd_std/unet/diffusion_pytorch_model.safetensors +3 -0
  26. mvd_std/vae/config.json +38 -0
  27. mvd_std/vae/diffusion_pytorch_model.safetensors +3 -0
  28. mvd_std/vision_encoder/config.json +23 -0
  29. mvd_std/vision_encoder/model.safetensors +3 -0
  30. mvd_std/vision_encoder_2/config.json +23 -0
  31. mvd_std/vision_encoder_2/model.safetensors +3 -0
  32. mvd_std/vision_processor/preprocessor_config.json +27 -0
mvd_lite/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
mvd_lite/feature_extractor_clip/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
mvd_lite/feature_extractor_vae/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 640,
4
+ "width": 640
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": 0.5,
12
+ "image_processor_type": "CLIPImageProcessor",
13
+ "image_std": 0.8,
14
+ "resample": 2,
15
+ "rescale_factor": 0.00392156862745098,
16
+ "size": {
17
+ "shortest_edge": 640
18
+ }
19
+ }
mvd_lite/model_index.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "Zero123PlusPipeline",
3
+ "_diffusers_version": "0.24.0",
4
+ "_name_or_path": "sudo-ai/zero123plus-v1.1",
5
+ "feature_extractor_clip": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "feature_extractor_vae": [
10
+ "transformers",
11
+ "CLIPImageProcessor"
12
+ ],
13
+ "ramping_coefficients": [
14
+ 0.00301829120144248,
15
+ 0.2204633206129074,
16
+ 0.21527841687202454,
17
+ 0.23498539626598358,
18
+ 0.1914631873369217,
19
+ 0.20188239216804504,
20
+ 0.19352824985980988,
21
+ 0.17249998450279236,
22
+ 0.15826298296451569,
23
+ 0.15236389636993408,
24
+ 0.13444548845291138,
25
+ 0.12044154852628708,
26
+ 0.12808501720428467,
27
+ 0.1271015852689743,
28
+ 0.13629068434238434,
29
+ 0.14516159892082214,
30
+ 0.15645112097263336,
31
+ 0.16885493695735931,
32
+ 0.18022602796554565,
33
+ 0.1958882212638855,
34
+ 0.21415705978870392,
35
+ 0.23056700825691223,
36
+ 0.2505834102630615,
37
+ 0.2574525773525238,
38
+ 0.275470107793808,
39
+ 0.2808215022087097,
40
+ 0.29953837394714355,
41
+ 0.2967497408390045,
42
+ 0.2883710563182831,
43
+ 0.3023308515548706,
44
+ 0.3054688572883606,
45
+ 0.32596179842948914,
46
+ 0.3225354254245758,
47
+ 0.3140765428543091,
48
+ 0.3288663625717163,
49
+ 0.3435625731945038,
50
+ 0.3342442810535431,
51
+ 0.32937031984329224,
52
+ 0.35734811425209045,
53
+ 0.3601177930831909,
54
+ 0.3517529368400574,
55
+ 0.3810708224773407,
56
+ 0.40007662773132324,
57
+ 0.4264647364616394,
58
+ 0.3977527916431427,
59
+ 0.4314143657684326,
60
+ 0.49558719992637634,
61
+ 0.4665665030479431,
62
+ 0.48960328102111816,
63
+ 0.5141982436180115,
64
+ 0.5230164527893066,
65
+ 0.5266074538230896,
66
+ 0.5456079840660095,
67
+ 0.5737904906272888,
68
+ 0.5882097482681274,
69
+ 0.6210350394248962,
70
+ 0.6530380845069885,
71
+ 0.6383244395256042,
72
+ 0.6792004704475403,
73
+ 0.6567418575286865,
74
+ 0.7517656683921814,
75
+ 0.736494243144989,
76
+ 0.7586457133293152,
77
+ 0.8130561709403992,
78
+ 0.9578766226768494,
79
+ 1.001284122467041,
80
+ 0.9404520988464355,
81
+ 1.004292368888855,
82
+ 0.9145274758338928,
83
+ 0.9771682620048523,
84
+ 1.0350638628005981,
85
+ 1.0265849828720093,
86
+ 1.0594775676727295,
87
+ 0.980824887752533,
88
+ 1.0715670585632324,
89
+ 1.0140161514282227,
90
+ 1.1983819007873535
91
+ ],
92
+ "safety_checker": [
93
+ null,
94
+ null
95
+ ],
96
+ "scheduler": [
97
+ "diffusers",
98
+ "EulerAncestralDiscreteScheduler"
99
+ ],
100
+ "text_encoder": [
101
+ "transformers",
102
+ "CLIPTextModel"
103
+ ],
104
+ "tokenizer": [
105
+ "transformers",
106
+ "CLIPTokenizer"
107
+ ],
108
+ "unet": [
109
+ "diffusers",
110
+ "UNet2DConditionModel"
111
+ ],
112
+ "vae": [
113
+ "diffusers",
114
+ "AutoencoderKL"
115
+ ],
116
+ "vision_encoder": [
117
+ "transformers",
118
+ "CLIPVisionModelWithProjection"
119
+ ]
120
+ }
mvd_lite/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.24.0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "v_prediction",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "timestep_spacing": "linspace",
14
+ "trained_betas": null
15
+ }
mvd_lite/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "D:\\.cache\\huggingface\\hub\\models--sudo-ai--zero123plus-v1.1\\snapshots\\36df7de980afd15f80b2e1a4e9a920d7020e2654\\text_encoder",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.36.0",
24
+ "vocab_size": 49408
25
+ }
mvd_lite/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1827c465450322616f06dea41596eac7d493f4e95904dcb51f0fc745c4e13f
3
+ size 680820392
mvd_lite/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
mvd_lite/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
mvd_lite/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49406": {
13
+ "content": "<|startoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "49407": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|startoftext|>",
30
+ "clean_up_tokenization_spaces": true,
31
+ "do_lower_case": true,
32
+ "eos_token": "<|endoftext|>",
33
+ "errors": "replace",
34
+ "model_max_length": 77,
35
+ "pad_token": "!",
36
+ "tokenizer_class": "CLIPTokenizer",
37
+ "unk_token": "<|endoftext|>"
38
+ }
mvd_lite/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
mvd_lite/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.24.0",
4
+ "_name_or_path": "D:\\.cache\\huggingface\\hub\\models--stabilityai--stable-diffusion-2\\snapshots\\1e128c8891e52218b74cde8f26dbfc701cb99d79\\unet",
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": 4,
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": 96,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": false,
72
+ "use_linear_projection": true
73
+ }
mvd_lite/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea255fd757cb817544734b1510b4015d6c49bcad55c3895186bede0835ab257e
3
+ size 3463726472
mvd_lite/vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.24.0",
4
+ "_name_or_path": "D:\\.cache\\huggingface\\hub\\models--sudo-ai--zero123plus-v1.1\\snapshots\\36df7de980afd15f80b2e1a4e9a920d7020e2654\\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": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 256,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
mvd_lite/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342
mvd_lite/vision_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "D:\\.cache\\huggingface\\hub\\models--sudo-ai--zero123plus-v1.1\\snapshots\\36df7de980afd15f80b2e1a4e9a920d7020e2654\\vision_encoder",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.36.0"
23
+ }
mvd_lite/vision_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae616c24393dd1854372b0639e5541666f7521cbe219669255e865cb7f89466a
3
+ size 1264217240
mvd_lite/vision_encoder/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
mvd_std/feature_extractor_vae/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 512,
4
+ "width": 512
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": 0.5,
12
+ "image_processor_type": "CLIPImageProcessor",
13
+ "image_std": 0.5,
14
+ "resample": 2,
15
+ "rescale_factor": 0.00392156862745098,
16
+ "size": {
17
+ "shortest_edge": 512
18
+ }
19
+ }
mvd_std/model_index.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "HunYuan3DMVDPipeline",
3
+ "_diffusers_version": "0.20.0",
4
+ "_name_or_path": "./hunyuan3d/v72_s22k",
5
+ "feature_extractor_vae": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "ramping_coefficients": [
10
+ 0.00301829120144248,
11
+ 0.2204633206129074,
12
+ 0.21527841687202454,
13
+ 0.23498539626598358,
14
+ 0.1914631873369217,
15
+ 0.20188239216804504,
16
+ 0.19352824985980988,
17
+ 0.17249998450279236,
18
+ 0.15826298296451569,
19
+ 0.15236389636993408,
20
+ 0.13444548845291138,
21
+ 0.12044154852628708,
22
+ 0.12808501720428467,
23
+ 0.1271015852689743,
24
+ 0.13629068434238434,
25
+ 0.14516159892082214,
26
+ 0.15645112097263336,
27
+ 0.16885493695735931,
28
+ 0.18022602796554565,
29
+ 0.1958882212638855,
30
+ 0.21415705978870392,
31
+ 0.23056700825691223,
32
+ 0.2505834102630615,
33
+ 0.2574525773525238,
34
+ 0.275470107793808,
35
+ 0.2808215022087097,
36
+ 0.29953837394714355,
37
+ 0.2967497408390045,
38
+ 0.2883710563182831,
39
+ 0.3023308515548706,
40
+ 0.3054688572883606,
41
+ 0.32596179842948914,
42
+ 0.3225354254245758,
43
+ 0.3140765428543091,
44
+ 0.3288663625717163,
45
+ 0.3435625731945038,
46
+ 0.3342442810535431,
47
+ 0.32937031984329224,
48
+ 0.35734811425209045,
49
+ 0.3601177930831909,
50
+ 0.3517529368400574,
51
+ 0.3810708224773407,
52
+ 0.40007662773132324,
53
+ 0.4264647364616394,
54
+ 0.3977527916431427,
55
+ 0.4314143657684326,
56
+ 0.49558719992637634,
57
+ 0.4665665030479431,
58
+ 0.48960328102111816,
59
+ 0.5141982436180115,
60
+ 0.5230164527893066,
61
+ 0.5266074538230896,
62
+ 0.5456079840660095,
63
+ 0.5737904906272888,
64
+ 0.5882097482681274,
65
+ 0.6210350394248962,
66
+ 0.6530380845069885,
67
+ 0.6383244395256042,
68
+ 0.6792004704475403,
69
+ 0.6567418575286865,
70
+ 0.7517656683921814,
71
+ 0.736494243144989,
72
+ 0.7586457133293152,
73
+ 0.8130561709403992,
74
+ 0.9578766226768494,
75
+ 1.001284122467041,
76
+ 0.9404520988464355,
77
+ 1.004292368888855,
78
+ 0.9145274758338928,
79
+ 0.9771682620048523,
80
+ 1.0350638628005981,
81
+ 1.0265849828720093,
82
+ 1.0594775676727295,
83
+ 0.980824887752533,
84
+ 1.0715670585632324,
85
+ 1.0140161514282227,
86
+ 1.1983819007873535
87
+ ],
88
+ "safety_checker": [
89
+ null,
90
+ null
91
+ ],
92
+ "scheduler": [
93
+ "diffusers",
94
+ "EulerAncestralDiscreteScheduler"
95
+ ],
96
+ "unet": [
97
+ "diffusers",
98
+ "UNet2DConditionModel"
99
+ ],
100
+ "vae": [
101
+ "diffusers",
102
+ "AutoencoderKL"
103
+ ],
104
+ "vision_encoder": [
105
+ "transformers",
106
+ "CLIPVisionModelWithProjection"
107
+ ],
108
+ "vision_encoder_2": [
109
+ "transformers",
110
+ "CLIPVisionModelWithProjection"
111
+ ],
112
+ "vision_processor": [
113
+ "transformers",
114
+ "CLIPImageProcessor"
115
+ ]
116
+ }
mvd_std/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EulerAncestralDiscreteScheduler",
3
+ "_diffusers_version": "0.20.0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "rescale_betas_zero_snr": false,
11
+ "set_alpha_to_one": false,
12
+ "skip_prk_steps": true,
13
+ "steps_offset": 1,
14
+ "timestep_spacing": "trailing",
15
+ "trained_betas": null
16
+ }
mvd_std/uc_text_emb.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b66304d244a8c1bb2f8e4047710da9fe249d9c4bcacdae909a1b23c084e9a0
3
+ size 631543
mvd_std/uc_text_emb_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86259792b6f0c6efadd1fbebc6b735d93e62b4f4f77555550971e3648a52ebe
3
+ size 5885
mvd_std/unet/config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.20.0",
4
+ "_name_or_path": "./hunyuan3d/v72_s22k/unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": "text_time",
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": 256,
9
+ "attention_head_dim": [
10
+ 5,
11
+ 10,
12
+ 20
13
+ ],
14
+ "attention_type": "default",
15
+ "block_out_channels": [
16
+ 320,
17
+ 640,
18
+ 1280
19
+ ],
20
+ "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
+ "cross_attention_dim": 2048,
26
+ "cross_attention_norm": null,
27
+ "down_block_types": [
28
+ "DownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "CrossAttnDownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "dropout": 0.0,
34
+ "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
+ "flip_sin_to_cos": true,
38
+ "freq_shift": 0,
39
+ "in_channels": 4,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "norm_eps": 1e-05,
45
+ "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
+ "num_class_embeds": null,
48
+ "only_cross_attention": false,
49
+ "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": 2816,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "reverse_transformer_layers_per_block": null,
55
+ "sample_size": 128,
56
+ "time_cond_proj_dim": null,
57
+ "time_embedding_act_fn": null,
58
+ "time_embedding_dim": null,
59
+ "time_embedding_type": "positional",
60
+ "timestep_post_act": null,
61
+ "transformer_layers_per_block": [
62
+ 1,
63
+ 2,
64
+ 10
65
+ ],
66
+ "up_block_types": [
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "UpBlock2D"
70
+ ],
71
+ "upcast_attention": null,
72
+ "use_linear_projection": true
73
+ }
mvd_std/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e687df99afd99a178d3ed8a8935951ae4484d4ac01d355668ddd9657807b02d0
3
+ size 5135149760
mvd_std/vae/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.20.0",
4
+ "_name_or_path": "./hunyuan3d/v72_s22k/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
+ }
mvd_std/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
3
+ size 167335342
mvd_std/vision_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./hunyuan3d/v72_s22k/vision_encoder",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 1024,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 24,
19
+ "patch_size": 14,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.27.2"
23
+ }
mvd_std/vision_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0839dc3a0f2899f9b85df8cd64b8acd1a3303a95f73a895aced7c31aee7d80cf
3
+ size 607982256
mvd_std/vision_encoder_2/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./hunyuan3d/v72_s22k/vision_encoder_2",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1664,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 48,
19
+ "patch_size": 14,
20
+ "projection_dim": 1280,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.27.2"
23
+ }
mvd_std/vision_encoder_2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657723e09f46a7c3957df651601029f66b1748afb12b419816330f16ed45d64d
3
+ size 3689912664
mvd_std/vision_processor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }