upload models
Browse files- model_ckpts/insightface_models/models/buffalo_l/1k3d68.onnx +3 -0
- model_ckpts/insightface_models/models/buffalo_l/2d106det.onnx +3 -0
- model_ckpts/insightface_models/models/buffalo_l/det_10g.onnx +3 -0
- model_ckpts/insightface_models/models/buffalo_l/genderage.onnx +3 -0
- model_ckpts/insightface_models/models/buffalo_l/w600k_r50.onnx +3 -0
- model_ckpts/sd-vae-ft-mse/config.json +29 -0
- model_ckpts/sd-vae-ft-mse/diffusion_pytorch_model.bin +3 -0
- model_ckpts/stable-diffusion-v1-5/unet/config.json +36 -0
- model_ckpts/v-express/audio_projection.pth +3 -0
- model_ckpts/v-express/denoising_unet.pth +3 -0
- model_ckpts/v-express/motion_module.pth +3 -0
- model_ckpts/v-express/reference_net.pth +3 -0
- model_ckpts/v-express/v_kps_guider.pth +3 -0
- model_ckpts/wav2vec2-base-960h/config.json +77 -0
- model_ckpts/wav2vec2-base-960h/feature_extractor_config.json +8 -0
- model_ckpts/wav2vec2-base-960h/preprocessor_config.json +8 -0
- model_ckpts/wav2vec2-base-960h/pytorch_model.bin +3 -0
- model_ckpts/wav2vec2-base-960h/special_tokens_map.json +1 -0
- model_ckpts/wav2vec2-base-960h/tokenizer_config.json +1 -0
- model_ckpts/wav2vec2-base-960h/vocab.json +1 -0
model_ckpts/insightface_models/models/buffalo_l/1k3d68.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
|
3 |
+
size 143607619
|
model_ckpts/insightface_models/models/buffalo_l/2d106det.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
|
3 |
+
size 5030888
|
model_ckpts/insightface_models/models/buffalo_l/det_10g.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
|
3 |
+
size 16923827
|
model_ckpts/insightface_models/models/buffalo_l/genderage.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
|
3 |
+
size 1322532
|
model_ckpts/insightface_models/models/buffalo_l/w600k_r50.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43
|
3 |
+
size 174383860
|
model_ckpts/sd-vae-ft-mse/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.4.2",
|
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 |
+
"in_channels": 3,
|
18 |
+
"latent_channels": 4,
|
19 |
+
"layers_per_block": 2,
|
20 |
+
"norm_num_groups": 32,
|
21 |
+
"out_channels": 3,
|
22 |
+
"sample_size": 256,
|
23 |
+
"up_block_types": [
|
24 |
+
"UpDecoderBlock2D",
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D"
|
28 |
+
]
|
29 |
+
}
|
model_ckpts/sd-vae-ft-mse/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
|
3 |
+
size 334707217
|
model_ckpts/stable-diffusion-v1-5/unet/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.6.0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": 8,
|
6 |
+
"block_out_channels": [
|
7 |
+
320,
|
8 |
+
640,
|
9 |
+
1280,
|
10 |
+
1280
|
11 |
+
],
|
12 |
+
"center_input_sample": false,
|
13 |
+
"cross_attention_dim": 768,
|
14 |
+
"down_block_types": [
|
15 |
+
"CrossAttnDownBlock2D",
|
16 |
+
"CrossAttnDownBlock2D",
|
17 |
+
"CrossAttnDownBlock2D",
|
18 |
+
"DownBlock2D"
|
19 |
+
],
|
20 |
+
"downsample_padding": 1,
|
21 |
+
"flip_sin_to_cos": true,
|
22 |
+
"freq_shift": 0,
|
23 |
+
"in_channels": 4,
|
24 |
+
"layers_per_block": 2,
|
25 |
+
"mid_block_scale_factor": 1,
|
26 |
+
"norm_eps": 1e-05,
|
27 |
+
"norm_num_groups": 32,
|
28 |
+
"out_channels": 4,
|
29 |
+
"sample_size": 64,
|
30 |
+
"up_block_types": [
|
31 |
+
"UpBlock2D",
|
32 |
+
"CrossAttnUpBlock2D",
|
33 |
+
"CrossAttnUpBlock2D",
|
34 |
+
"CrossAttnUpBlock2D"
|
35 |
+
]
|
36 |
+
}
|
model_ckpts/v-express/audio_projection.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2d042fcfd8826f3357d920b9f30a655b6e1814cf62f31b4430b0e14f126bc77
|
3 |
+
size 59064859
|
model_ckpts/v-express/denoising_unet.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcbbf05afa1510bf18283dd2dd61c17cc93b9b1b5814a41b8a43b8e5ea7c3ed1
|
3 |
+
size 2727592663
|
model_ckpts/v-express/motion_module.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d587d3b55908d5c4076bdd4ccd4d1317bd31db364ddb5551ac0fa86f4b099495
|
3 |
+
size 909066207
|
model_ckpts/v-express/reference_net.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea1ffee93375a6c78b7e6dc556d83b1fd86085448de8acfb601da28f731ef70b
|
3 |
+
size 1719283117
|
model_ckpts/v-express/v_kps_guider.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:330871104597d4a2713736b4ff550187c5ac120f8402cbf26a65572f70993d80
|
3 |
+
size 2178043
|
model_ckpts/wav2vec2-base-960h/config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"codevector_dim": 256,
|
11 |
+
"contrastive_logits_temperature": 0.1,
|
12 |
+
"conv_bias": false,
|
13 |
+
"conv_dim": [
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"conv_kernel": [
|
23 |
+
10,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
2,
|
29 |
+
2
|
30 |
+
],
|
31 |
+
"conv_stride": [
|
32 |
+
5,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2
|
39 |
+
],
|
40 |
+
"ctc_loss_reduction": "sum",
|
41 |
+
"ctc_zero_infinity": false,
|
42 |
+
"diversity_loss_weight": 0.1,
|
43 |
+
"do_stable_layer_norm": false,
|
44 |
+
"eos_token_id": 2,
|
45 |
+
"feat_extract_activation": "gelu",
|
46 |
+
"feat_extract_dropout": 0.0,
|
47 |
+
"feat_extract_norm": "group",
|
48 |
+
"feat_proj_dropout": 0.1,
|
49 |
+
"feat_quantizer_dropout": 0.0,
|
50 |
+
"final_dropout": 0.1,
|
51 |
+
"gradient_checkpointing": false,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.1,
|
54 |
+
"hidden_dropout_prob": 0.1,
|
55 |
+
"hidden_size": 768,
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.1,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_prob": 0.0,
|
62 |
+
"mask_time_length": 10,
|
63 |
+
"mask_time_prob": 0.05,
|
64 |
+
"model_type": "wav2vec2",
|
65 |
+
"num_attention_heads": 12,
|
66 |
+
"num_codevector_groups": 2,
|
67 |
+
"num_codevectors_per_group": 320,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 12,
|
72 |
+
"num_negatives": 100,
|
73 |
+
"pad_token_id": 0,
|
74 |
+
"proj_codevector_dim": 256,
|
75 |
+
"transformers_version": "4.7.0.dev0",
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
model_ckpts/wav2vec2-base-960h/feature_extractor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_dim": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": false,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
model_ckpts/wav2vec2-base-960h/preprocessor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": false,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
model_ckpts/wav2vec2-base-960h/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c34f9827b034a1b9141dbf6f652f8a60eda61cdf5771c9e05bfa99033c92cd96
|
3 |
+
size 377667514
|
model_ckpts/wav2vec2-base-960h/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
model_ckpts/wav2vec2-base-960h/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "return_attention_mask": false, "do_normalize": true}
|
model_ckpts/wav2vec2-base-960h/vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}
|