Hugging Face's logo

jdopensource
/
JoyAI-Echo

Image-to-Video
Diffusers
Safetensors
video-generation
audio-video-generation
reference-to-video
long-video
multi-shot
dmd
Model card Files
xet
 Community
10
GelerCAT commited on
Commit
0985d43
·
1 Parent(s): 9ec5d87

Add Diffusers modular pipeline weights

Browse files
Files changed (21) hide show
  1. audio_vae/config.json +25 -0
  2. audio_vae/diffusion_pytorch_model.safetensors +3 -0
  3. connectors/config.json +25 -0
  4. connectors/diffusion_pytorch_model-00001-of-00002.safetensors +3 -0
  5. connectors/diffusion_pytorch_model-00002-of-00002.safetensors +3 -0
  6. connectors/diffusion_pytorch_model.safetensors.index.json +269 -0
  7. modular_model_index.json +103 -0
  8. transformer/config.json +54 -0
  9. transformer/diffusion_pytorch_model-00001-of-00008.safetensors +3 -0
  10. transformer/diffusion_pytorch_model-00002-of-00008.safetensors +3 -0
  11. transformer/diffusion_pytorch_model-00003-of-00008.safetensors +3 -0
  12. transformer/diffusion_pytorch_model-00004-of-00008.safetensors +3 -0
  13. transformer/diffusion_pytorch_model-00005-of-00008.safetensors +3 -0
  14. transformer/diffusion_pytorch_model-00006-of-00008.safetensors +3 -0
  15. transformer/diffusion_pytorch_model-00007-of-00008.safetensors +3 -0
  16. transformer/diffusion_pytorch_model-00008-of-00008.safetensors +3 -0
  17. transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
  18. vae/config.json +93 -0
  19. vae/diffusion_pytorch_model.safetensors +3 -0
  20. vocoder/config.json +104 -0
  21. vocoder/diffusion_pytorch_model.safetensors +3 -0
audio_vae/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTX2Audio",
3
+ "_diffusers_version": "0.41.0.dev0",
4
+ "attn_resolutions": null,
5
+ "base_channels": 128,
6
+ "causality_axis": "height",
7
+ "ch_mult": [
8
+ 1,
9
+ 2,
10
+ 4
11
+ ],
12
+ "double_z": true,
13
+ "dropout": 0.0,
14
+ "in_channels": 2,
15
+ "is_causal": true,
16
+ "latent_channels": 8,
17
+ "mel_bins": 64,
18
+ "mel_hop_length": 160,
19
+ "mid_block_add_attention": false,
20
+ "norm_type": "pixel",
21
+ "num_res_blocks": 2,
22
+ "output_channels": 2,
23
+ "resolution": 256,
24
+ "sample_rate": 16000
25
+ }
audio_vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45dcb1c3cffc8c8b7710a04dd19500e481daff31f5ea8e8529f2cf697c439d12
3
+ size 106507972
connectors/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2TextConnectors",
3
+ "_diffusers_version": "0.41.0.dev0",
4
+ "audio_connector_attention_head_dim": 64,
5
+ "audio_connector_num_attention_heads": 32,
6
+ "audio_connector_num_layers": 8,
7
+ "audio_connector_num_learnable_registers": 128,
8
+ "audio_gated_attn": true,
9
+ "audio_hidden_dim": 2048,
10
+ "caption_channels": 3840,
11
+ "causal_temporal_positioning": false,
12
+ "connector_rope_base_seq_len": 4096,
13
+ "per_modality_projections": true,
14
+ "proj_bias": true,
15
+ "rope_double_precision": true,
16
+ "rope_theta": 10000.0,
17
+ "rope_type": "split",
18
+ "text_proj_in_factor": 49,
19
+ "video_connector_attention_head_dim": 128,
20
+ "video_connector_num_attention_heads": 32,
21
+ "video_connector_num_layers": 8,
22
+ "video_connector_num_learnable_registers": 128,
23
+ "video_gated_attn": true,
24
+ "video_hidden_dim": 4096
25
+ }
connectors/diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b767a411e336d692306d7d34fa85627db1d17809a4690f45dd96a4b3807d248c
3
+ size 4999998520
connectors/diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe33521b2bbd12604abe2d63b5cf02cf55f2fdf10226ff5aae00e437678ebc8
3
+ size 1344490576
connectors/diffusion_pytorch_model.safetensors.index.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6344455168
4
+ },
5
+ "weight_map": {
6
+ "audio_connector.learnable_registers": "diffusion_pytorch_model-00002-of-00002.safetensors",
7
+ "audio_connector.transformer_blocks.0.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
8
+ "audio_connector.transformer_blocks.0.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
9
+ "audio_connector.transformer_blocks.0.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
10
+ "audio_connector.transformer_blocks.0.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
11
+ "audio_connector.transformer_blocks.0.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
12
+ "audio_connector.transformer_blocks.0.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
13
+ "audio_connector.transformer_blocks.0.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
14
+ "audio_connector.transformer_blocks.0.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
15
+ "audio_connector.transformer_blocks.0.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
16
+ "audio_connector.transformer_blocks.0.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
17
+ "audio_connector.transformer_blocks.0.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
18
+ "audio_connector.transformer_blocks.0.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
19
+ "audio_connector.transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
20
+ "audio_connector.transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
21
+ "audio_connector.transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
22
+ "audio_connector.transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
23
+ "audio_connector.transformer_blocks.1.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
24
+ "audio_connector.transformer_blocks.1.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
25
+ "audio_connector.transformer_blocks.1.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
26
+ "audio_connector.transformer_blocks.1.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
27
+ "audio_connector.transformer_blocks.1.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
28
+ "audio_connector.transformer_blocks.1.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
29
+ "audio_connector.transformer_blocks.1.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
30
+ "audio_connector.transformer_blocks.1.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
31
+ "audio_connector.transformer_blocks.1.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
32
+ "audio_connector.transformer_blocks.1.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
33
+ "audio_connector.transformer_blocks.1.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
34
+ "audio_connector.transformer_blocks.1.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
35
+ "audio_connector.transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
36
+ "audio_connector.transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
37
+ "audio_connector.transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
38
+ "audio_connector.transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
39
+ "audio_connector.transformer_blocks.2.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
40
+ "audio_connector.transformer_blocks.2.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
41
+ "audio_connector.transformer_blocks.2.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
42
+ "audio_connector.transformer_blocks.2.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
43
+ "audio_connector.transformer_blocks.2.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
44
+ "audio_connector.transformer_blocks.2.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
45
+ "audio_connector.transformer_blocks.2.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
46
+ "audio_connector.transformer_blocks.2.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
47
+ "audio_connector.transformer_blocks.2.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
48
+ "audio_connector.transformer_blocks.2.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
49
+ "audio_connector.transformer_blocks.2.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
50
+ "audio_connector.transformer_blocks.2.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
51
+ "audio_connector.transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
52
+ "audio_connector.transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
53
+ "audio_connector.transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
54
+ "audio_connector.transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
55
+ "audio_connector.transformer_blocks.3.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
56
+ "audio_connector.transformer_blocks.3.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
57
+ "audio_connector.transformer_blocks.3.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
58
+ "audio_connector.transformer_blocks.3.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
59
+ "audio_connector.transformer_blocks.3.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
60
+ "audio_connector.transformer_blocks.3.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
61
+ "audio_connector.transformer_blocks.3.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
62
+ "audio_connector.transformer_blocks.3.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
63
+ "audio_connector.transformer_blocks.3.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
64
+ "audio_connector.transformer_blocks.3.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
65
+ "audio_connector.transformer_blocks.3.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
66
+ "audio_connector.transformer_blocks.3.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
67
+ "audio_connector.transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
68
+ "audio_connector.transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
69
+ "audio_connector.transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
70
+ "audio_connector.transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
71
+ "audio_connector.transformer_blocks.4.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
72
+ "audio_connector.transformer_blocks.4.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
73
+ "audio_connector.transformer_blocks.4.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
74
+ "audio_connector.transformer_blocks.4.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
75
+ "audio_connector.transformer_blocks.4.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
76
+ "audio_connector.transformer_blocks.4.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
77
+ "audio_connector.transformer_blocks.4.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
78
+ "audio_connector.transformer_blocks.4.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
79
+ "audio_connector.transformer_blocks.4.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
80
+ "audio_connector.transformer_blocks.4.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
81
+ "audio_connector.transformer_blocks.4.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
82
+ "audio_connector.transformer_blocks.4.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
83
+ "audio_connector.transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
84
+ "audio_connector.transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
85
+ "audio_connector.transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
86
+ "audio_connector.transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
87
+ "audio_connector.transformer_blocks.5.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
88
+ "audio_connector.transformer_blocks.5.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
89
+ "audio_connector.transformer_blocks.5.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
90
+ "audio_connector.transformer_blocks.5.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
91
+ "audio_connector.transformer_blocks.5.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
92
+ "audio_connector.transformer_blocks.5.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
93
+ "audio_connector.transformer_blocks.5.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
94
+ "audio_connector.transformer_blocks.5.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
95
+ "audio_connector.transformer_blocks.5.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
96
+ "audio_connector.transformer_blocks.5.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
97
+ "audio_connector.transformer_blocks.5.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
98
+ "audio_connector.transformer_blocks.5.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
99
+ "audio_connector.transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
100
+ "audio_connector.transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
101
+ "audio_connector.transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
102
+ "audio_connector.transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
103
+ "audio_connector.transformer_blocks.6.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
104
+ "audio_connector.transformer_blocks.6.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
105
+ "audio_connector.transformer_blocks.6.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
106
+ "audio_connector.transformer_blocks.6.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
107
+ "audio_connector.transformer_blocks.6.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
108
+ "audio_connector.transformer_blocks.6.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
109
+ "audio_connector.transformer_blocks.6.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
110
+ "audio_connector.transformer_blocks.6.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
111
+ "audio_connector.transformer_blocks.6.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
112
+ "audio_connector.transformer_blocks.6.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
113
+ "audio_connector.transformer_blocks.6.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
114
+ "audio_connector.transformer_blocks.6.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
115
+ "audio_connector.transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
116
+ "audio_connector.transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
117
+ "audio_connector.transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
118
+ "audio_connector.transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
119
+ "audio_connector.transformer_blocks.7.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
120
+ "audio_connector.transformer_blocks.7.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
121
+ "audio_connector.transformer_blocks.7.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
122
+ "audio_connector.transformer_blocks.7.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
123
+ "audio_connector.transformer_blocks.7.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
124
+ "audio_connector.transformer_blocks.7.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
125
+ "audio_connector.transformer_blocks.7.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
126
+ "audio_connector.transformer_blocks.7.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
127
+ "audio_connector.transformer_blocks.7.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
128
+ "audio_connector.transformer_blocks.7.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
129
+ "audio_connector.transformer_blocks.7.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
130
+ "audio_connector.transformer_blocks.7.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
131
+ "audio_connector.transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
132
+ "audio_connector.transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
133
+ "audio_connector.transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
134
+ "audio_connector.transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
135
+ "audio_text_proj_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
136
+ "audio_text_proj_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
137
+ "video_connector.learnable_registers": "diffusion_pytorch_model-00001-of-00002.safetensors",
138
+ "video_connector.transformer_blocks.0.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
139
+ "video_connector.transformer_blocks.0.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
140
+ "video_connector.transformer_blocks.0.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
141
+ "video_connector.transformer_blocks.0.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
142
+ "video_connector.transformer_blocks.0.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
143
+ "video_connector.transformer_blocks.0.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
144
+ "video_connector.transformer_blocks.0.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
145
+ "video_connector.transformer_blocks.0.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
146
+ "video_connector.transformer_blocks.0.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
147
+ "video_connector.transformer_blocks.0.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
148
+ "video_connector.transformer_blocks.0.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
149
+ "video_connector.transformer_blocks.0.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
150
+ "video_connector.transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
151
+ "video_connector.transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
152
+ "video_connector.transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
153
+ "video_connector.transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
154
+ "video_connector.transformer_blocks.1.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
155
+ "video_connector.transformer_blocks.1.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
156
+ "video_connector.transformer_blocks.1.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
157
+ "video_connector.transformer_blocks.1.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
158
+ "video_connector.transformer_blocks.1.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
159
+ "video_connector.transformer_blocks.1.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
160
+ "video_connector.transformer_blocks.1.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
161
+ "video_connector.transformer_blocks.1.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
162
+ "video_connector.transformer_blocks.1.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
163
+ "video_connector.transformer_blocks.1.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
164
+ "video_connector.transformer_blocks.1.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
165
+ "video_connector.transformer_blocks.1.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
166
+ "video_connector.transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
167
+ "video_connector.transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
168
+ "video_connector.transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
169
+ "video_connector.transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
170
+ "video_connector.transformer_blocks.2.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
171
+ "video_connector.transformer_blocks.2.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
172
+ "video_connector.transformer_blocks.2.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
173
+ "video_connector.transformer_blocks.2.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
174
+ "video_connector.transformer_blocks.2.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
175
+ "video_connector.transformer_blocks.2.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
176
+ "video_connector.transformer_blocks.2.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
177
+ "video_connector.transformer_blocks.2.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
178
+ "video_connector.transformer_blocks.2.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
179
+ "video_connector.transformer_blocks.2.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
180
+ "video_connector.transformer_blocks.2.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
181
+ "video_connector.transformer_blocks.2.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
182
+ "video_connector.transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
183
+ "video_connector.transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
184
+ "video_connector.transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
185
+ "video_connector.transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
186
+ "video_connector.transformer_blocks.3.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
187
+ "video_connector.transformer_blocks.3.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
188
+ "video_connector.transformer_blocks.3.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
189
+ "video_connector.transformer_blocks.3.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
190
+ "video_connector.transformer_blocks.3.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
191
+ "video_connector.transformer_blocks.3.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
192
+ "video_connector.transformer_blocks.3.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
193
+ "video_connector.transformer_blocks.3.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
194
+ "video_connector.transformer_blocks.3.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
195
+ "video_connector.transformer_blocks.3.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
196
+ "video_connector.transformer_blocks.3.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
197
+ "video_connector.transformer_blocks.3.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
198
+ "video_connector.transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
199
+ "video_connector.transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
200
+ "video_connector.transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
201
+ "video_connector.transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
202
+ "video_connector.transformer_blocks.4.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
203
+ "video_connector.transformer_blocks.4.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
204
+ "video_connector.transformer_blocks.4.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
205
+ "video_connector.transformer_blocks.4.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
206
+ "video_connector.transformer_blocks.4.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
207
+ "video_connector.transformer_blocks.4.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
208
+ "video_connector.transformer_blocks.4.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
209
+ "video_connector.transformer_blocks.4.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
210
+ "video_connector.transformer_blocks.4.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
211
+ "video_connector.transformer_blocks.4.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
212
+ "video_connector.transformer_blocks.4.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
213
+ "video_connector.transformer_blocks.4.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
214
+ "video_connector.transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
215
+ "video_connector.transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
216
+ "video_connector.transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
217
+ "video_connector.transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
218
+ "video_connector.transformer_blocks.5.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
219
+ "video_connector.transformer_blocks.5.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
220
+ "video_connector.transformer_blocks.5.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
221
+ "video_connector.transformer_blocks.5.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
222
+ "video_connector.transformer_blocks.5.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
223
+ "video_connector.transformer_blocks.5.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
224
+ "video_connector.transformer_blocks.5.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
225
+ "video_connector.transformer_blocks.5.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
226
+ "video_connector.transformer_blocks.5.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
227
+ "video_connector.transformer_blocks.5.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
228
+ "video_connector.transformer_blocks.5.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
229
+ "video_connector.transformer_blocks.5.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
230
+ "video_connector.transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
231
+ "video_connector.transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
232
+ "video_connector.transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
233
+ "video_connector.transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
234
+ "video_connector.transformer_blocks.6.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
235
+ "video_connector.transformer_blocks.6.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
236
+ "video_connector.transformer_blocks.6.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
237
+ "video_connector.transformer_blocks.6.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
238
+ "video_connector.transformer_blocks.6.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
239
+ "video_connector.transformer_blocks.6.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
240
+ "video_connector.transformer_blocks.6.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
241
+ "video_connector.transformer_blocks.6.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
242
+ "video_connector.transformer_blocks.6.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
243
+ "video_connector.transformer_blocks.6.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
244
+ "video_connector.transformer_blocks.6.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
245
+ "video_connector.transformer_blocks.6.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
246
+ "video_connector.transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
247
+ "video_connector.transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
248
+ "video_connector.transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
249
+ "video_connector.transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
250
+ "video_connector.transformer_blocks.7.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
251
+ "video_connector.transformer_blocks.7.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
252
+ "video_connector.transformer_blocks.7.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
253
+ "video_connector.transformer_blocks.7.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
254
+ "video_connector.transformer_blocks.7.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
255
+ "video_connector.transformer_blocks.7.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
256
+ "video_connector.transformer_blocks.7.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
257
+ "video_connector.transformer_blocks.7.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
258
+ "video_connector.transformer_blocks.7.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
259
+ "video_connector.transformer_blocks.7.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
260
+ "video_connector.transformer_blocks.7.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
261
+ "video_connector.transformer_blocks.7.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
262
+ "video_connector.transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
263
+ "video_connector.transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
264
+ "video_connector.transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
265
+ "video_connector.transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
266
+ "video_text_proj_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
267
+ "video_text_proj_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
268
+ }
269
+ }
modular_model_index.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "EchoLTXModularPipeline",
3
+ "_diffusers_version": "0.41.0.dev0",
4
+ "_blocks_class_name": "EchoLTXBlocks",
5
+ "text_encoder": [
6
+ null,
7
+ null,
8
+ {
9
+ "type_hint": [
10
+ "transformers",
11
+ "Gemma3ForConditionalGeneration"
12
+ ],
13
+ "pretrained_model_name_or_path": "google/gemma-3-12b-it",
14
+ "subfolder": null,
15
+ "variant": null,
16
+ "revision": null
17
+ }
18
+ ],
19
+ "tokenizer": [
20
+ null,
21
+ null,
22
+ {
23
+ "type_hint": [
24
+ "transformers",
25
+ "GemmaTokenizerFast"
26
+ ],
27
+ "pretrained_model_name_or_path": "google/gemma-3-12b-it",
28
+ "subfolder": null,
29
+ "variant": null,
30
+ "revision": null
31
+ }
32
+ ],
33
+ "connectors": [
34
+ null,
35
+ null,
36
+ {
37
+ "type_hint": [
38
+ "ltx2",
39
+ "LTX2TextConnectors"
40
+ ],
41
+ "pretrained_model_name_or_path": "jdopensource/JoyAI-Echo",
42
+ "subfolder": "connectors",
43
+ "variant": null,
44
+ "revision": null
45
+ }
46
+ ],
47
+ "vae": [
48
+ null,
49
+ null,
50
+ {
51
+ "type_hint": [
52
+ "diffusers",
53
+ "AutoencoderKLLTX2Video"
54
+ ],
55
+ "pretrained_model_name_or_path": "jdopensource/JoyAI-Echo",
56
+ "subfolder": "vae",
57
+ "variant": null,
58
+ "revision": null
59
+ }
60
+ ],
61
+ "audio_vae": [
62
+ null,
63
+ null,
64
+ {
65
+ "type_hint": [
66
+ "diffusers",
67
+ "AutoencoderKLLTX2Audio"
68
+ ],
69
+ "pretrained_model_name_or_path": "jdopensource/JoyAI-Echo",
70
+ "subfolder": "audio_vae",
71
+ "variant": null,
72
+ "revision": null
73
+ }
74
+ ],
75
+ "transformer": [
76
+ null,
77
+ null,
78
+ {
79
+ "type_hint": [
80
+ "diffusers",
81
+ "LTX2VideoTransformer3DModel"
82
+ ],
83
+ "pretrained_model_name_or_path": "jdopensource/JoyAI-Echo",
84
+ "subfolder": "transformer",
85
+ "variant": null,
86
+ "revision": null
87
+ }
88
+ ],
89
+ "vocoder": [
90
+ null,
91
+ null,
92
+ {
93
+ "type_hint": [
94
+ "ltx2",
95
+ "LTX2VocoderWithBWE"
96
+ ],
97
+ "pretrained_model_name_or_path": "jdopensource/JoyAI-Echo",
98
+ "subfolder": "vocoder",
99
+ "variant": null,
100
+ "revision": null
101
+ }
102
+ ]
103
+ }
transformer/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2VideoTransformer3DModel",
3
+ "_diffusers_version": "0.41.0.dev0",
4
+ "activation_fn": "gelu-approximate",
5
+ "attention_bias": true,
6
+ "attention_head_dim": 128,
7
+ "attention_out_bias": true,
8
+ "audio_attention_head_dim": 64,
9
+ "audio_cross_attention_dim": 2048,
10
+ "audio_cross_attn_mod": true,
11
+ "audio_ff_bias": true,
12
+ "audio_gated_attn": true,
13
+ "audio_hop_length": 160,
14
+ "audio_in_channels": 128,
15
+ "audio_num_attention_heads": 32,
16
+ "audio_out_channels": 128,
17
+ "audio_patch_size": 1,
18
+ "audio_patch_size_t": 1,
19
+ "audio_pos_embed_max_pos": 20,
20
+ "audio_sampling_rate": 16000,
21
+ "audio_scale_factor": 4,
22
+ "base_height": 2048,
23
+ "base_width": 2048,
24
+ "caption_channels": 3840,
25
+ "causal_offset": 1,
26
+ "cross_attention_dim": 4096,
27
+ "cross_attn_mod": true,
28
+ "cross_attn_timestep_scale_multiplier": 1000,
29
+ "ff_bias": true,
30
+ "gated_attn": true,
31
+ "in_channels": 128,
32
+ "norm_elementwise_affine": false,
33
+ "norm_eps": 1e-06,
34
+ "num_attention_heads": 32,
35
+ "num_layers": 48,
36
+ "out_channels": 128,
37
+ "patch_size": 1,
38
+ "patch_size_t": 1,
39
+ "perturbed_attn": true,
40
+ "pos_embed_max_pos": 20,
41
+ "qk_norm": "rms_norm_across_heads",
42
+ "rope_double_precision": true,
43
+ "rope_theta": 10000.0,
44
+ "rope_type": "split",
45
+ "timestep_scale_multiplier": 1000,
46
+ "use_keyframes_abs_pos_embedding": false,
47
+ "use_prompt_adaln_single": true,
48
+ "use_prompt_embeddings": false,
49
+ "vae_scale_factors": [
50
+ 8,
51
+ 32,
52
+ 32
53
+ ]
54
+ }
transformer/diffusion_pytorch_model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85c6e60119acfcd98c255cc4b9740c2c75ef188bce2d05d3907173f592fa20f
3
+ size 4989505528
transformer/diffusion_pytorch_model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0968f9399b8c9b8c605f7204a2586121d43abb0b815742438c6fcf59cdbd2898
3
+ size 4943307864
transformer/diffusion_pytorch_model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0112a201af7f5448f7fd80746d2f31b4eaf55f6faf65d9b149ca7d4ef4d7e6
3
+ size 4993285768
transformer/diffusion_pytorch_model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae6919de66256867d6f6d468eec2f0ce1ff327f26c4cc8e81bae736f330a919
3
+ size 4926679968
transformer/diffusion_pytorch_model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:137773acc4c22d141583d58f3f1d6c491e6e3030b7a65dc9d6eacdd0561b62bc
3
+ size 4976228344
transformer/diffusion_pytorch_model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8654f3741adb5f7a13e8fbf510e3da362c30a767c6befa67ce2bf3d7345c36c
3
+ size 4993665208
transformer/diffusion_pytorch_model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba1bfe185c474e0e2fc3941f7741f897f6a06fc147b1e528774c8db9a4c0349
3
+ size 4993207488
transformer/diffusion_pytorch_model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bc84cab5390207e4f0e57b58e484ef288b11ffb625f121154528887fcc730c
3
+ size 3162308536
transformer/diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
vae/config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTX2Video",
3
+ "_diffusers_version": "0.41.0.dev0",
4
+ "block_out_channels": [
5
+ 256,
6
+ 512,
7
+ 1024,
8
+ 1024
9
+ ],
10
+ "decoder_block_out_channels": [
11
+ 256,
12
+ 512,
13
+ 512,
14
+ 1024
15
+ ],
16
+ "decoder_causal": false,
17
+ "decoder_inject_noise": [
18
+ false,
19
+ false,
20
+ false,
21
+ false,
22
+ false
23
+ ],
24
+ "decoder_layers_per_block": [
25
+ 4,
26
+ 6,
27
+ 4,
28
+ 2,
29
+ 2
30
+ ],
31
+ "decoder_spatial_padding_mode": "zeros",
32
+ "decoder_spatio_temporal_scaling": [
33
+ true,
34
+ true,
35
+ true,
36
+ true
37
+ ],
38
+ "down_block_types": [
39
+ "LTX2VideoDownBlock3D",
40
+ "LTX2VideoDownBlock3D",
41
+ "LTX2VideoDownBlock3D",
42
+ "LTX2VideoDownBlock3D"
43
+ ],
44
+ "downsample_type": [
45
+ "spatial",
46
+ "temporal",
47
+ "spatiotemporal",
48
+ "spatiotemporal"
49
+ ],
50
+ "encoder_causal": true,
51
+ "encoder_spatial_padding_mode": "zeros",
52
+ "in_channels": 3,
53
+ "latent_channels": 128,
54
+ "layers_per_block": [
55
+ 4,
56
+ 6,
57
+ 4,
58
+ 2,
59
+ 2
60
+ ],
61
+ "out_channels": 3,
62
+ "patch_size": 4,
63
+ "patch_size_t": 1,
64
+ "resnet_norm_eps": 1e-06,
65
+ "scaling_factor": 1.0,
66
+ "spatial_compression_ratio": 32,
67
+ "spatio_temporal_scaling": [
68
+ true,
69
+ true,
70
+ true,
71
+ true
72
+ ],
73
+ "temporal_compression_ratio": 8,
74
+ "timestep_conditioning": false,
75
+ "upsample_factor": [
76
+ 2,
77
+ 2,
78
+ 1,
79
+ 2
80
+ ],
81
+ "upsample_residual": [
82
+ false,
83
+ false,
84
+ false,
85
+ false
86
+ ],
87
+ "upsample_type": [
88
+ "spatiotemporal",
89
+ "spatiotemporal",
90
+ "temporal",
91
+ "spatial"
92
+ ]
93
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425f0dfa227dee5d0ff3d9720563370810409a439c302ca74f0f944057ce55c5
3
+ size 1452233194
vocoder/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2VocoderWithBWE",
3
+ "_diffusers_version": "0.41.0.dev0",
4
+ "act_fn": "snakebeta",
5
+ "antialias": true,
6
+ "antialias_kernel_size": 12,
7
+ "antialias_ratio": 2,
8
+ "bwe_act_fn": "snakebeta",
9
+ "bwe_antialias": true,
10
+ "bwe_antialias_kernel_size": 12,
11
+ "bwe_antialias_ratio": 2,
12
+ "bwe_final_act_fn": null,
13
+ "bwe_final_bias": false,
14
+ "bwe_hidden_channels": 512,
15
+ "bwe_in_channels": 128,
16
+ "bwe_leaky_relu_negative_slope": 0.1,
17
+ "bwe_out_channels": 2,
18
+ "bwe_resnet_dilations": [
19
+ [
20
+ 1,
21
+ 3,
22
+ 5
23
+ ],
24
+ [
25
+ 1,
26
+ 3,
27
+ 5
28
+ ],
29
+ [
30
+ 1,
31
+ 3,
32
+ 5
33
+ ]
34
+ ],
35
+ "bwe_resnet_kernel_sizes": [
36
+ 3,
37
+ 7,
38
+ 11
39
+ ],
40
+ "bwe_upsample_factors": [
41
+ 6,
42
+ 5,
43
+ 2,
44
+ 2,
45
+ 2
46
+ ],
47
+ "bwe_upsample_kernel_sizes": [
48
+ 12,
49
+ 11,
50
+ 4,
51
+ 4,
52
+ 4
53
+ ],
54
+ "filter_length": 512,
55
+ "final_act_fn": null,
56
+ "final_bias": false,
57
+ "hidden_channels": 1536,
58
+ "hop_length": 80,
59
+ "in_channels": 128,
60
+ "input_sampling_rate": 16000,
61
+ "leaky_relu_negative_slope": 0.1,
62
+ "num_mel_channels": 64,
63
+ "out_channels": 2,
64
+ "output_sampling_rate": 48000,
65
+ "resnet_dilations": [
66
+ [
67
+ 1,
68
+ 3,
69
+ 5
70
+ ],
71
+ [
72
+ 1,
73
+ 3,
74
+ 5
75
+ ],
76
+ [
77
+ 1,
78
+ 3,
79
+ 5
80
+ ]
81
+ ],
82
+ "resnet_kernel_sizes": [
83
+ 3,
84
+ 7,
85
+ 11
86
+ ],
87
+ "upsample_factors": [
88
+ 5,
89
+ 2,
90
+ 2,
91
+ 2,
92
+ 2,
93
+ 2
94
+ ],
95
+ "upsample_kernel_sizes": [
96
+ 11,
97
+ 4,
98
+ 4,
99
+ 4,
100
+ 4,
101
+ 4
102
+ ],
103
+ "window_length": 512
104
+ }
vocoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99dde145a982974bc4c39608b3b929f232f0126a55d8326a47ad54f486ae23c
3
+ size 258305056