h0witended commited on
Commit
8c6bf7b
·
verified ·
1 Parent(s): f5c3814

Upload folder using huggingface_hub

Browse files
audio_vae/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTX2Audio",
3
+ "_diffusers_version": "0.38.0",
4
+ "attn_resolutions": null,
5
+ "base_channels": 128,
6
+ "causality_axis": "height",
7
+ "ch_mult": [
8
+ 1
9
+ ],
10
+ "double_z": true,
11
+ "dropout": 0.0,
12
+ "in_channels": 2,
13
+ "is_causal": true,
14
+ "latent_channels": 8,
15
+ "mel_bins": 64,
16
+ "mel_hop_length": 160,
17
+ "mid_block_add_attention": false,
18
+ "norm_type": "pixel",
19
+ "num_res_blocks": 1,
20
+ "output_channels": 2,
21
+ "resolution": 256,
22
+ "sample_rate": 16000
23
+ }
audio_vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ad3cafdaaf21f2e1936c26012b545ed2eccb3befffcbac68bc7d7cc0294bbb
3
+ size 8399728
connectors/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2TextConnectors",
3
+ "_diffusers_version": "0.38.0",
4
+ "audio_connector_attention_head_dim": 8,
5
+ "audio_connector_num_attention_heads": 4,
6
+ "audio_connector_num_layers": 1,
7
+ "audio_connector_num_learnable_registers": 8,
8
+ "caption_channels": 32,
9
+ "causal_temporal_positioning": false,
10
+ "connector_rope_base_seq_len": 4096,
11
+ "rope_double_precision": true,
12
+ "rope_theta": 10000.0,
13
+ "rope_type": "split",
14
+ "text_proj_in_factor": 3,
15
+ "video_connector_attention_head_dim": 8,
16
+ "video_connector_num_attention_heads": 4,
17
+ "video_connector_num_layers": 1,
18
+ "video_connector_num_learnable_registers": 8
19
+ }
connectors/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac319aa7c2711d7cfe3df6bc9e4b1248e2ffbaf5818304f5d846f062a1e1df4a
3
+ size 118992
model_index.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2Pipeline",
3
+ "_diffusers_version": "0.38.0",
4
+ "audio_vae": [
5
+ "diffusers",
6
+ "AutoencoderKLLTX2Audio"
7
+ ],
8
+ "connectors": [
9
+ "ltx2",
10
+ "LTX2TextConnectors"
11
+ ],
12
+ "scheduler": [
13
+ "diffusers",
14
+ "FlowMatchEulerDiscreteScheduler"
15
+ ],
16
+ "text_encoder": [
17
+ "transformers",
18
+ "Gemma3ForConditionalGeneration"
19
+ ],
20
+ "tokenizer": [
21
+ "transformers",
22
+ "GemmaTokenizerFast"
23
+ ],
24
+ "transformer": [
25
+ "diffusers",
26
+ "LTX2VideoTransformer3DModel"
27
+ ],
28
+ "vae": [
29
+ "diffusers",
30
+ "AutoencoderKLLTX2Video"
31
+ ],
32
+ "vocoder": [
33
+ "ltx2",
34
+ "LTX2Vocoder"
35
+ ]
36
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.38.0",
4
+ "base_image_seq_len": 1024,
5
+ "base_shift": 0.95,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 2.05,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": 0.1,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "dtype": "float32",
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": [
9
+ 1,
10
+ 106
11
+ ],
12
+ "image_token_index": 262144,
13
+ "initializer_range": 0.02,
14
+ "mm_tokens_per_image": 256,
15
+ "model_type": "gemma3",
16
+ "text_config": {
17
+ "_sliding_window_pattern": 6,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "bos_token_id": 2,
22
+ "cache_implementation": "hybrid",
23
+ "dtype": "float32",
24
+ "eos_token_id": 1,
25
+ "final_logit_softcapping": null,
26
+ "head_dim": 8,
27
+ "hidden_activation": "gelu_pytorch_tanh",
28
+ "hidden_size": 32,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 64,
31
+ "layer_types": [
32
+ "sliding_attention",
33
+ "full_attention"
34
+ ],
35
+ "max_position_embeddings": 1024,
36
+ "model_type": "gemma3_text",
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 2,
39
+ "num_key_value_heads": 2,
40
+ "pad_token_id": 0,
41
+ "query_pre_attn_scalar": 8,
42
+ "rms_norm_eps": 1e-06,
43
+ "rope_parameters": {
44
+ "full_attention": {
45
+ "factor": 8.0,
46
+ "rope_theta": 1000000,
47
+ "rope_type": "linear"
48
+ },
49
+ "sliding_attention": {
50
+ "rope_theta": 10000,
51
+ "rope_type": "default"
52
+ }
53
+ },
54
+ "sliding_window": 1024,
55
+ "sliding_window_pattern": 6,
56
+ "tie_word_embeddings": true,
57
+ "use_bidirectional_attention": false,
58
+ "use_cache": true,
59
+ "vocab_size": 1024
60
+ },
61
+ "tie_word_embeddings": true,
62
+ "transformers_version": "5.0.0",
63
+ "vision_config": {
64
+ "attention_dropout": 0.0,
65
+ "dtype": "float32",
66
+ "hidden_act": "gelu_pytorch_tanh",
67
+ "hidden_size": 32,
68
+ "image_size": 56,
69
+ "intermediate_size": 64,
70
+ "layer_norm_eps": 1e-06,
71
+ "model_type": "siglip_vision_model",
72
+ "num_attention_heads": 4,
73
+ "num_channels": 3,
74
+ "num_hidden_layers": 1,
75
+ "patch_size": 14,
76
+ "vision_use_head": false
77
+ }
78
+ }
text_encoder/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "output_attentions": false,
10
+ "output_hidden_states": false,
11
+ "pad_token_id": 0,
12
+ "transformers_version": "5.0.0",
13
+ "use_cache": true
14
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fef7f82ffd8bb857df36b43cf3e6d2e00c852913817ff848ff6500d1ffbbdfb
3
+ size 328336
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,1057 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [],
6
+ "normalizer": null,
7
+ "pre_tokenizer": {
8
+ "type": "ByteLevel",
9
+ "add_prefix_space": false,
10
+ "trim_offsets": true,
11
+ "use_regex": true
12
+ },
13
+ "post_processor": null,
14
+ "decoder": {
15
+ "type": "ByteLevel",
16
+ "add_prefix_space": true,
17
+ "trim_offsets": true,
18
+ "use_regex": true
19
+ },
20
+ "model": {
21
+ "type": "BPE",
22
+ "dropout": null,
23
+ "unk_token": null,
24
+ "continuing_subword_prefix": null,
25
+ "end_of_word_suffix": null,
26
+ "fuse_unk": false,
27
+ "byte_fallback": false,
28
+ "ignore_merges": false,
29
+ "vocab": {
30
+ "<pad>": 0,
31
+ "<eos>": 1,
32
+ "<bos>": 2,
33
+ "<unk>": 3,
34
+ "v4": 4,
35
+ "v5": 5,
36
+ "v6": 6,
37
+ "v7": 7,
38
+ "v8": 8,
39
+ "v9": 9,
40
+ "v10": 10,
41
+ "v11": 11,
42
+ "v12": 12,
43
+ "v13": 13,
44
+ "v14": 14,
45
+ "v15": 15,
46
+ "v16": 16,
47
+ "v17": 17,
48
+ "v18": 18,
49
+ "v19": 19,
50
+ "v20": 20,
51
+ "v21": 21,
52
+ "v22": 22,
53
+ "v23": 23,
54
+ "v24": 24,
55
+ "v25": 25,
56
+ "v26": 26,
57
+ "v27": 27,
58
+ "v28": 28,
59
+ "v29": 29,
60
+ "v30": 30,
61
+ "v31": 31,
62
+ "v32": 32,
63
+ "v33": 33,
64
+ "v34": 34,
65
+ "v35": 35,
66
+ "v36": 36,
67
+ "v37": 37,
68
+ "v38": 38,
69
+ "v39": 39,
70
+ "v40": 40,
71
+ "v41": 41,
72
+ "v42": 42,
73
+ "v43": 43,
74
+ "v44": 44,
75
+ "v45": 45,
76
+ "v46": 46,
77
+ "v47": 47,
78
+ "v48": 48,
79
+ "v49": 49,
80
+ "v50": 50,
81
+ "v51": 51,
82
+ "v52": 52,
83
+ "v53": 53,
84
+ "v54": 54,
85
+ "v55": 55,
86
+ "v56": 56,
87
+ "v57": 57,
88
+ "v58": 58,
89
+ "v59": 59,
90
+ "v60": 60,
91
+ "v61": 61,
92
+ "v62": 62,
93
+ "v63": 63,
94
+ "v64": 64,
95
+ "v65": 65,
96
+ "v66": 66,
97
+ "v67": 67,
98
+ "v68": 68,
99
+ "v69": 69,
100
+ "v70": 70,
101
+ "v71": 71,
102
+ "v72": 72,
103
+ "v73": 73,
104
+ "v74": 74,
105
+ "v75": 75,
106
+ "v76": 76,
107
+ "v77": 77,
108
+ "v78": 78,
109
+ "v79": 79,
110
+ "v80": 80,
111
+ "v81": 81,
112
+ "v82": 82,
113
+ "v83": 83,
114
+ "v84": 84,
115
+ "v85": 85,
116
+ "v86": 86,
117
+ "v87": 87,
118
+ "v88": 88,
119
+ "v89": 89,
120
+ "v90": 90,
121
+ "v91": 91,
122
+ "v92": 92,
123
+ "v93": 93,
124
+ "v94": 94,
125
+ "v95": 95,
126
+ "v96": 96,
127
+ "v97": 97,
128
+ "v98": 98,
129
+ "v99": 99,
130
+ "v100": 100,
131
+ "v101": 101,
132
+ "v102": 102,
133
+ "v103": 103,
134
+ "v104": 104,
135
+ "v105": 105,
136
+ "v106": 106,
137
+ "v107": 107,
138
+ "v108": 108,
139
+ "v109": 109,
140
+ "v110": 110,
141
+ "v111": 111,
142
+ "v112": 112,
143
+ "v113": 113,
144
+ "v114": 114,
145
+ "v115": 115,
146
+ "v116": 116,
147
+ "v117": 117,
148
+ "v118": 118,
149
+ "v119": 119,
150
+ "v120": 120,
151
+ "v121": 121,
152
+ "v122": 122,
153
+ "v123": 123,
154
+ "v124": 124,
155
+ "v125": 125,
156
+ "v126": 126,
157
+ "v127": 127,
158
+ "v128": 128,
159
+ "v129": 129,
160
+ "v130": 130,
161
+ "v131": 131,
162
+ "v132": 132,
163
+ "v133": 133,
164
+ "v134": 134,
165
+ "v135": 135,
166
+ "v136": 136,
167
+ "v137": 137,
168
+ "v138": 138,
169
+ "v139": 139,
170
+ "v140": 140,
171
+ "v141": 141,
172
+ "v142": 142,
173
+ "v143": 143,
174
+ "v144": 144,
175
+ "v145": 145,
176
+ "v146": 146,
177
+ "v147": 147,
178
+ "v148": 148,
179
+ "v149": 149,
180
+ "v150": 150,
181
+ "v151": 151,
182
+ "v152": 152,
183
+ "v153": 153,
184
+ "v154": 154,
185
+ "v155": 155,
186
+ "v156": 156,
187
+ "v157": 157,
188
+ "v158": 158,
189
+ "v159": 159,
190
+ "v160": 160,
191
+ "v161": 161,
192
+ "v162": 162,
193
+ "v163": 163,
194
+ "v164": 164,
195
+ "v165": 165,
196
+ "v166": 166,
197
+ "v167": 167,
198
+ "v168": 168,
199
+ "v169": 169,
200
+ "v170": 170,
201
+ "v171": 171,
202
+ "v172": 172,
203
+ "v173": 173,
204
+ "v174": 174,
205
+ "v175": 175,
206
+ "v176": 176,
207
+ "v177": 177,
208
+ "v178": 178,
209
+ "v179": 179,
210
+ "v180": 180,
211
+ "v181": 181,
212
+ "v182": 182,
213
+ "v183": 183,
214
+ "v184": 184,
215
+ "v185": 185,
216
+ "v186": 186,
217
+ "v187": 187,
218
+ "v188": 188,
219
+ "v189": 189,
220
+ "v190": 190,
221
+ "v191": 191,
222
+ "v192": 192,
223
+ "v193": 193,
224
+ "v194": 194,
225
+ "v195": 195,
226
+ "v196": 196,
227
+ "v197": 197,
228
+ "v198": 198,
229
+ "v199": 199,
230
+ "v200": 200,
231
+ "v201": 201,
232
+ "v202": 202,
233
+ "v203": 203,
234
+ "v204": 204,
235
+ "v205": 205,
236
+ "v206": 206,
237
+ "v207": 207,
238
+ "v208": 208,
239
+ "v209": 209,
240
+ "v210": 210,
241
+ "v211": 211,
242
+ "v212": 212,
243
+ "v213": 213,
244
+ "v214": 214,
245
+ "v215": 215,
246
+ "v216": 216,
247
+ "v217": 217,
248
+ "v218": 218,
249
+ "v219": 219,
250
+ "v220": 220,
251
+ "v221": 221,
252
+ "v222": 222,
253
+ "v223": 223,
254
+ "v224": 224,
255
+ "v225": 225,
256
+ "v226": 226,
257
+ "v227": 227,
258
+ "v228": 228,
259
+ "v229": 229,
260
+ "v230": 230,
261
+ "v231": 231,
262
+ "v232": 232,
263
+ "v233": 233,
264
+ "v234": 234,
265
+ "v235": 235,
266
+ "v236": 236,
267
+ "v237": 237,
268
+ "v238": 238,
269
+ "v239": 239,
270
+ "v240": 240,
271
+ "v241": 241,
272
+ "v242": 242,
273
+ "v243": 243,
274
+ "v244": 244,
275
+ "v245": 245,
276
+ "v246": 246,
277
+ "v247": 247,
278
+ "v248": 248,
279
+ "v249": 249,
280
+ "v250": 250,
281
+ "v251": 251,
282
+ "v252": 252,
283
+ "v253": 253,
284
+ "v254": 254,
285
+ "v255": 255,
286
+ "v256": 256,
287
+ "v257": 257,
288
+ "v258": 258,
289
+ "v259": 259,
290
+ "v260": 260,
291
+ "v261": 261,
292
+ "v262": 262,
293
+ "v263": 263,
294
+ "v264": 264,
295
+ "v265": 265,
296
+ "v266": 266,
297
+ "v267": 267,
298
+ "v268": 268,
299
+ "v269": 269,
300
+ "v270": 270,
301
+ "v271": 271,
302
+ "v272": 272,
303
+ "v273": 273,
304
+ "v274": 274,
305
+ "v275": 275,
306
+ "v276": 276,
307
+ "v277": 277,
308
+ "v278": 278,
309
+ "v279": 279,
310
+ "v280": 280,
311
+ "v281": 281,
312
+ "v282": 282,
313
+ "v283": 283,
314
+ "v284": 284,
315
+ "v285": 285,
316
+ "v286": 286,
317
+ "v287": 287,
318
+ "v288": 288,
319
+ "v289": 289,
320
+ "v290": 290,
321
+ "v291": 291,
322
+ "v292": 292,
323
+ "v293": 293,
324
+ "v294": 294,
325
+ "v295": 295,
326
+ "v296": 296,
327
+ "v297": 297,
328
+ "v298": 298,
329
+ "v299": 299,
330
+ "v300": 300,
331
+ "v301": 301,
332
+ "v302": 302,
333
+ "v303": 303,
334
+ "v304": 304,
335
+ "v305": 305,
336
+ "v306": 306,
337
+ "v307": 307,
338
+ "v308": 308,
339
+ "v309": 309,
340
+ "v310": 310,
341
+ "v311": 311,
342
+ "v312": 312,
343
+ "v313": 313,
344
+ "v314": 314,
345
+ "v315": 315,
346
+ "v316": 316,
347
+ "v317": 317,
348
+ "v318": 318,
349
+ "v319": 319,
350
+ "v320": 320,
351
+ "v321": 321,
352
+ "v322": 322,
353
+ "v323": 323,
354
+ "v324": 324,
355
+ "v325": 325,
356
+ "v326": 326,
357
+ "v327": 327,
358
+ "v328": 328,
359
+ "v329": 329,
360
+ "v330": 330,
361
+ "v331": 331,
362
+ "v332": 332,
363
+ "v333": 333,
364
+ "v334": 334,
365
+ "v335": 335,
366
+ "v336": 336,
367
+ "v337": 337,
368
+ "v338": 338,
369
+ "v339": 339,
370
+ "v340": 340,
371
+ "v341": 341,
372
+ "v342": 342,
373
+ "v343": 343,
374
+ "v344": 344,
375
+ "v345": 345,
376
+ "v346": 346,
377
+ "v347": 347,
378
+ "v348": 348,
379
+ "v349": 349,
380
+ "v350": 350,
381
+ "v351": 351,
382
+ "v352": 352,
383
+ "v353": 353,
384
+ "v354": 354,
385
+ "v355": 355,
386
+ "v356": 356,
387
+ "v357": 357,
388
+ "v358": 358,
389
+ "v359": 359,
390
+ "v360": 360,
391
+ "v361": 361,
392
+ "v362": 362,
393
+ "v363": 363,
394
+ "v364": 364,
395
+ "v365": 365,
396
+ "v366": 366,
397
+ "v367": 367,
398
+ "v368": 368,
399
+ "v369": 369,
400
+ "v370": 370,
401
+ "v371": 371,
402
+ "v372": 372,
403
+ "v373": 373,
404
+ "v374": 374,
405
+ "v375": 375,
406
+ "v376": 376,
407
+ "v377": 377,
408
+ "v378": 378,
409
+ "v379": 379,
410
+ "v380": 380,
411
+ "v381": 381,
412
+ "v382": 382,
413
+ "v383": 383,
414
+ "v384": 384,
415
+ "v385": 385,
416
+ "v386": 386,
417
+ "v387": 387,
418
+ "v388": 388,
419
+ "v389": 389,
420
+ "v390": 390,
421
+ "v391": 391,
422
+ "v392": 392,
423
+ "v393": 393,
424
+ "v394": 394,
425
+ "v395": 395,
426
+ "v396": 396,
427
+ "v397": 397,
428
+ "v398": 398,
429
+ "v399": 399,
430
+ "v400": 400,
431
+ "v401": 401,
432
+ "v402": 402,
433
+ "v403": 403,
434
+ "v404": 404,
435
+ "v405": 405,
436
+ "v406": 406,
437
+ "v407": 407,
438
+ "v408": 408,
439
+ "v409": 409,
440
+ "v410": 410,
441
+ "v411": 411,
442
+ "v412": 412,
443
+ "v413": 413,
444
+ "v414": 414,
445
+ "v415": 415,
446
+ "v416": 416,
447
+ "v417": 417,
448
+ "v418": 418,
449
+ "v419": 419,
450
+ "v420": 420,
451
+ "v421": 421,
452
+ "v422": 422,
453
+ "v423": 423,
454
+ "v424": 424,
455
+ "v425": 425,
456
+ "v426": 426,
457
+ "v427": 427,
458
+ "v428": 428,
459
+ "v429": 429,
460
+ "v430": 430,
461
+ "v431": 431,
462
+ "v432": 432,
463
+ "v433": 433,
464
+ "v434": 434,
465
+ "v435": 435,
466
+ "v436": 436,
467
+ "v437": 437,
468
+ "v438": 438,
469
+ "v439": 439,
470
+ "v440": 440,
471
+ "v441": 441,
472
+ "v442": 442,
473
+ "v443": 443,
474
+ "v444": 444,
475
+ "v445": 445,
476
+ "v446": 446,
477
+ "v447": 447,
478
+ "v448": 448,
479
+ "v449": 449,
480
+ "v450": 450,
481
+ "v451": 451,
482
+ "v452": 452,
483
+ "v453": 453,
484
+ "v454": 454,
485
+ "v455": 455,
486
+ "v456": 456,
487
+ "v457": 457,
488
+ "v458": 458,
489
+ "v459": 459,
490
+ "v460": 460,
491
+ "v461": 461,
492
+ "v462": 462,
493
+ "v463": 463,
494
+ "v464": 464,
495
+ "v465": 465,
496
+ "v466": 466,
497
+ "v467": 467,
498
+ "v468": 468,
499
+ "v469": 469,
500
+ "v470": 470,
501
+ "v471": 471,
502
+ "v472": 472,
503
+ "v473": 473,
504
+ "v474": 474,
505
+ "v475": 475,
506
+ "v476": 476,
507
+ "v477": 477,
508
+ "v478": 478,
509
+ "v479": 479,
510
+ "v480": 480,
511
+ "v481": 481,
512
+ "v482": 482,
513
+ "v483": 483,
514
+ "v484": 484,
515
+ "v485": 485,
516
+ "v486": 486,
517
+ "v487": 487,
518
+ "v488": 488,
519
+ "v489": 489,
520
+ "v490": 490,
521
+ "v491": 491,
522
+ "v492": 492,
523
+ "v493": 493,
524
+ "v494": 494,
525
+ "v495": 495,
526
+ "v496": 496,
527
+ "v497": 497,
528
+ "v498": 498,
529
+ "v499": 499,
530
+ "v500": 500,
531
+ "v501": 501,
532
+ "v502": 502,
533
+ "v503": 503,
534
+ "v504": 504,
535
+ "v505": 505,
536
+ "v506": 506,
537
+ "v507": 507,
538
+ "v508": 508,
539
+ "v509": 509,
540
+ "v510": 510,
541
+ "v511": 511,
542
+ "v512": 512,
543
+ "v513": 513,
544
+ "v514": 514,
545
+ "v515": 515,
546
+ "v516": 516,
547
+ "v517": 517,
548
+ "v518": 518,
549
+ "v519": 519,
550
+ "v520": 520,
551
+ "v521": 521,
552
+ "v522": 522,
553
+ "v523": 523,
554
+ "v524": 524,
555
+ "v525": 525,
556
+ "v526": 526,
557
+ "v527": 527,
558
+ "v528": 528,
559
+ "v529": 529,
560
+ "v530": 530,
561
+ "v531": 531,
562
+ "v532": 532,
563
+ "v533": 533,
564
+ "v534": 534,
565
+ "v535": 535,
566
+ "v536": 536,
567
+ "v537": 537,
568
+ "v538": 538,
569
+ "v539": 539,
570
+ "v540": 540,
571
+ "v541": 541,
572
+ "v542": 542,
573
+ "v543": 543,
574
+ "v544": 544,
575
+ "v545": 545,
576
+ "v546": 546,
577
+ "v547": 547,
578
+ "v548": 548,
579
+ "v549": 549,
580
+ "v550": 550,
581
+ "v551": 551,
582
+ "v552": 552,
583
+ "v553": 553,
584
+ "v554": 554,
585
+ "v555": 555,
586
+ "v556": 556,
587
+ "v557": 557,
588
+ "v558": 558,
589
+ "v559": 559,
590
+ "v560": 560,
591
+ "v561": 561,
592
+ "v562": 562,
593
+ "v563": 563,
594
+ "v564": 564,
595
+ "v565": 565,
596
+ "v566": 566,
597
+ "v567": 567,
598
+ "v568": 568,
599
+ "v569": 569,
600
+ "v570": 570,
601
+ "v571": 571,
602
+ "v572": 572,
603
+ "v573": 573,
604
+ "v574": 574,
605
+ "v575": 575,
606
+ "v576": 576,
607
+ "v577": 577,
608
+ "v578": 578,
609
+ "v579": 579,
610
+ "v580": 580,
611
+ "v581": 581,
612
+ "v582": 582,
613
+ "v583": 583,
614
+ "v584": 584,
615
+ "v585": 585,
616
+ "v586": 586,
617
+ "v587": 587,
618
+ "v588": 588,
619
+ "v589": 589,
620
+ "v590": 590,
621
+ "v591": 591,
622
+ "v592": 592,
623
+ "v593": 593,
624
+ "v594": 594,
625
+ "v595": 595,
626
+ "v596": 596,
627
+ "v597": 597,
628
+ "v598": 598,
629
+ "v599": 599,
630
+ "v600": 600,
631
+ "v601": 601,
632
+ "v602": 602,
633
+ "v603": 603,
634
+ "v604": 604,
635
+ "v605": 605,
636
+ "v606": 606,
637
+ "v607": 607,
638
+ "v608": 608,
639
+ "v609": 609,
640
+ "v610": 610,
641
+ "v611": 611,
642
+ "v612": 612,
643
+ "v613": 613,
644
+ "v614": 614,
645
+ "v615": 615,
646
+ "v616": 616,
647
+ "v617": 617,
648
+ "v618": 618,
649
+ "v619": 619,
650
+ "v620": 620,
651
+ "v621": 621,
652
+ "v622": 622,
653
+ "v623": 623,
654
+ "v624": 624,
655
+ "v625": 625,
656
+ "v626": 626,
657
+ "v627": 627,
658
+ "v628": 628,
659
+ "v629": 629,
660
+ "v630": 630,
661
+ "v631": 631,
662
+ "v632": 632,
663
+ "v633": 633,
664
+ "v634": 634,
665
+ "v635": 635,
666
+ "v636": 636,
667
+ "v637": 637,
668
+ "v638": 638,
669
+ "v639": 639,
670
+ "v640": 640,
671
+ "v641": 641,
672
+ "v642": 642,
673
+ "v643": 643,
674
+ "v644": 644,
675
+ "v645": 645,
676
+ "v646": 646,
677
+ "v647": 647,
678
+ "v648": 648,
679
+ "v649": 649,
680
+ "v650": 650,
681
+ "v651": 651,
682
+ "v652": 652,
683
+ "v653": 653,
684
+ "v654": 654,
685
+ "v655": 655,
686
+ "v656": 656,
687
+ "v657": 657,
688
+ "v658": 658,
689
+ "v659": 659,
690
+ "v660": 660,
691
+ "v661": 661,
692
+ "v662": 662,
693
+ "v663": 663,
694
+ "v664": 664,
695
+ "v665": 665,
696
+ "v666": 666,
697
+ "v667": 667,
698
+ "v668": 668,
699
+ "v669": 669,
700
+ "v670": 670,
701
+ "v671": 671,
702
+ "v672": 672,
703
+ "v673": 673,
704
+ "v674": 674,
705
+ "v675": 675,
706
+ "v676": 676,
707
+ "v677": 677,
708
+ "v678": 678,
709
+ "v679": 679,
710
+ "v680": 680,
711
+ "v681": 681,
712
+ "v682": 682,
713
+ "v683": 683,
714
+ "v684": 684,
715
+ "v685": 685,
716
+ "v686": 686,
717
+ "v687": 687,
718
+ "v688": 688,
719
+ "v689": 689,
720
+ "v690": 690,
721
+ "v691": 691,
722
+ "v692": 692,
723
+ "v693": 693,
724
+ "v694": 694,
725
+ "v695": 695,
726
+ "v696": 696,
727
+ "v697": 697,
728
+ "v698": 698,
729
+ "v699": 699,
730
+ "v700": 700,
731
+ "v701": 701,
732
+ "v702": 702,
733
+ "v703": 703,
734
+ "v704": 704,
735
+ "v705": 705,
736
+ "v706": 706,
737
+ "v707": 707,
738
+ "v708": 708,
739
+ "v709": 709,
740
+ "v710": 710,
741
+ "v711": 711,
742
+ "v712": 712,
743
+ "v713": 713,
744
+ "v714": 714,
745
+ "v715": 715,
746
+ "v716": 716,
747
+ "v717": 717,
748
+ "v718": 718,
749
+ "v719": 719,
750
+ "v720": 720,
751
+ "v721": 721,
752
+ "v722": 722,
753
+ "v723": 723,
754
+ "v724": 724,
755
+ "v725": 725,
756
+ "v726": 726,
757
+ "v727": 727,
758
+ "v728": 728,
759
+ "v729": 729,
760
+ "v730": 730,
761
+ "v731": 731,
762
+ "v732": 732,
763
+ "v733": 733,
764
+ "v734": 734,
765
+ "v735": 735,
766
+ "v736": 736,
767
+ "v737": 737,
768
+ "v738": 738,
769
+ "v739": 739,
770
+ "v740": 740,
771
+ "v741": 741,
772
+ "v742": 742,
773
+ "v743": 743,
774
+ "v744": 744,
775
+ "v745": 745,
776
+ "v746": 746,
777
+ "v747": 747,
778
+ "v748": 748,
779
+ "v749": 749,
780
+ "v750": 750,
781
+ "v751": 751,
782
+ "v752": 752,
783
+ "v753": 753,
784
+ "v754": 754,
785
+ "v755": 755,
786
+ "v756": 756,
787
+ "v757": 757,
788
+ "v758": 758,
789
+ "v759": 759,
790
+ "v760": 760,
791
+ "v761": 761,
792
+ "v762": 762,
793
+ "v763": 763,
794
+ "v764": 764,
795
+ "v765": 765,
796
+ "v766": 766,
797
+ "v767": 767,
798
+ "v768": 768,
799
+ "v769": 769,
800
+ "v770": 770,
801
+ "v771": 771,
802
+ "v772": 772,
803
+ "v773": 773,
804
+ "v774": 774,
805
+ "v775": 775,
806
+ "v776": 776,
807
+ "v777": 777,
808
+ "v778": 778,
809
+ "v779": 779,
810
+ "v780": 780,
811
+ "v781": 781,
812
+ "v782": 782,
813
+ "v783": 783,
814
+ "v784": 784,
815
+ "v785": 785,
816
+ "v786": 786,
817
+ "v787": 787,
818
+ "v788": 788,
819
+ "v789": 789,
820
+ "v790": 790,
821
+ "v791": 791,
822
+ "v792": 792,
823
+ "v793": 793,
824
+ "v794": 794,
825
+ "v795": 795,
826
+ "v796": 796,
827
+ "v797": 797,
828
+ "v798": 798,
829
+ "v799": 799,
830
+ "v800": 800,
831
+ "v801": 801,
832
+ "v802": 802,
833
+ "v803": 803,
834
+ "v804": 804,
835
+ "v805": 805,
836
+ "v806": 806,
837
+ "v807": 807,
838
+ "v808": 808,
839
+ "v809": 809,
840
+ "v810": 810,
841
+ "v811": 811,
842
+ "v812": 812,
843
+ "v813": 813,
844
+ "v814": 814,
845
+ "v815": 815,
846
+ "v816": 816,
847
+ "v817": 817,
848
+ "v818": 818,
849
+ "v819": 819,
850
+ "v820": 820,
851
+ "v821": 821,
852
+ "v822": 822,
853
+ "v823": 823,
854
+ "v824": 824,
855
+ "v825": 825,
856
+ "v826": 826,
857
+ "v827": 827,
858
+ "v828": 828,
859
+ "v829": 829,
860
+ "v830": 830,
861
+ "v831": 831,
862
+ "v832": 832,
863
+ "v833": 833,
864
+ "v834": 834,
865
+ "v835": 835,
866
+ "v836": 836,
867
+ "v837": 837,
868
+ "v838": 838,
869
+ "v839": 839,
870
+ "v840": 840,
871
+ "v841": 841,
872
+ "v842": 842,
873
+ "v843": 843,
874
+ "v844": 844,
875
+ "v845": 845,
876
+ "v846": 846,
877
+ "v847": 847,
878
+ "v848": 848,
879
+ "v849": 849,
880
+ "v850": 850,
881
+ "v851": 851,
882
+ "v852": 852,
883
+ "v853": 853,
884
+ "v854": 854,
885
+ "v855": 855,
886
+ "v856": 856,
887
+ "v857": 857,
888
+ "v858": 858,
889
+ "v859": 859,
890
+ "v860": 860,
891
+ "v861": 861,
892
+ "v862": 862,
893
+ "v863": 863,
894
+ "v864": 864,
895
+ "v865": 865,
896
+ "v866": 866,
897
+ "v867": 867,
898
+ "v868": 868,
899
+ "v869": 869,
900
+ "v870": 870,
901
+ "v871": 871,
902
+ "v872": 872,
903
+ "v873": 873,
904
+ "v874": 874,
905
+ "v875": 875,
906
+ "v876": 876,
907
+ "v877": 877,
908
+ "v878": 878,
909
+ "v879": 879,
910
+ "v880": 880,
911
+ "v881": 881,
912
+ "v882": 882,
913
+ "v883": 883,
914
+ "v884": 884,
915
+ "v885": 885,
916
+ "v886": 886,
917
+ "v887": 887,
918
+ "v888": 888,
919
+ "v889": 889,
920
+ "v890": 890,
921
+ "v891": 891,
922
+ "v892": 892,
923
+ "v893": 893,
924
+ "v894": 894,
925
+ "v895": 895,
926
+ "v896": 896,
927
+ "v897": 897,
928
+ "v898": 898,
929
+ "v899": 899,
930
+ "v900": 900,
931
+ "v901": 901,
932
+ "v902": 902,
933
+ "v903": 903,
934
+ "v904": 904,
935
+ "v905": 905,
936
+ "v906": 906,
937
+ "v907": 907,
938
+ "v908": 908,
939
+ "v909": 909,
940
+ "v910": 910,
941
+ "v911": 911,
942
+ "v912": 912,
943
+ "v913": 913,
944
+ "v914": 914,
945
+ "v915": 915,
946
+ "v916": 916,
947
+ "v917": 917,
948
+ "v918": 918,
949
+ "v919": 919,
950
+ "v920": 920,
951
+ "v921": 921,
952
+ "v922": 922,
953
+ "v923": 923,
954
+ "v924": 924,
955
+ "v925": 925,
956
+ "v926": 926,
957
+ "v927": 927,
958
+ "v928": 928,
959
+ "v929": 929,
960
+ "v930": 930,
961
+ "v931": 931,
962
+ "v932": 932,
963
+ "v933": 933,
964
+ "v934": 934,
965
+ "v935": 935,
966
+ "v936": 936,
967
+ "v937": 937,
968
+ "v938": 938,
969
+ "v939": 939,
970
+ "v940": 940,
971
+ "v941": 941,
972
+ "v942": 942,
973
+ "v943": 943,
974
+ "v944": 944,
975
+ "v945": 945,
976
+ "v946": 946,
977
+ "v947": 947,
978
+ "v948": 948,
979
+ "v949": 949,
980
+ "v950": 950,
981
+ "v951": 951,
982
+ "v952": 952,
983
+ "v953": 953,
984
+ "v954": 954,
985
+ "v955": 955,
986
+ "v956": 956,
987
+ "v957": 957,
988
+ "v958": 958,
989
+ "v959": 959,
990
+ "v960": 960,
991
+ "v961": 961,
992
+ "v962": 962,
993
+ "v963": 963,
994
+ "v964": 964,
995
+ "v965": 965,
996
+ "v966": 966,
997
+ "v967": 967,
998
+ "v968": 968,
999
+ "v969": 969,
1000
+ "v970": 970,
1001
+ "v971": 971,
1002
+ "v972": 972,
1003
+ "v973": 973,
1004
+ "v974": 974,
1005
+ "v975": 975,
1006
+ "v976": 976,
1007
+ "v977": 977,
1008
+ "v978": 978,
1009
+ "v979": 979,
1010
+ "v980": 980,
1011
+ "v981": 981,
1012
+ "v982": 982,
1013
+ "v983": 983,
1014
+ "v984": 984,
1015
+ "v985": 985,
1016
+ "v986": 986,
1017
+ "v987": 987,
1018
+ "v988": 988,
1019
+ "v989": 989,
1020
+ "v990": 990,
1021
+ "v991": 991,
1022
+ "v992": 992,
1023
+ "v993": 993,
1024
+ "v994": 994,
1025
+ "v995": 995,
1026
+ "v996": 996,
1027
+ "v997": 997,
1028
+ "v998": 998,
1029
+ "v999": 999,
1030
+ "v1000": 1000,
1031
+ "v1001": 1001,
1032
+ "v1002": 1002,
1033
+ "v1003": 1003,
1034
+ "v1004": 1004,
1035
+ "v1005": 1005,
1036
+ "v1006": 1006,
1037
+ "v1007": 1007,
1038
+ "v1008": 1008,
1039
+ "v1009": 1009,
1040
+ "v1010": 1010,
1041
+ "v1011": 1011,
1042
+ "v1012": 1012,
1043
+ "v1013": 1013,
1044
+ "v1014": 1014,
1045
+ "v1015": 1015,
1046
+ "v1016": 1016,
1047
+ "v1017": 1017,
1048
+ "v1018": 1018,
1049
+ "v1019": 1019,
1050
+ "v1020": 1020,
1051
+ "v1021": 1021,
1052
+ "v1022": 1022,
1053
+ "v1023": 1023
1054
+ },
1055
+ "merges": []
1056
+ }
1057
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": "<bos>",
5
+ "eos_token": "<eos>",
6
+ "pad_token": "<pad>",
7
+ "unk_token": "<unk>",
8
+ "model_max_length": 1024,
9
+ "tokenizer_class": "GemmaTokenizerFast"
10
+ }
transformer/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2VideoTransformer3DModel",
3
+ "_diffusers_version": "0.38.0",
4
+ "activation_fn": "gelu-approximate",
5
+ "attention_bias": true,
6
+ "attention_head_dim": 8,
7
+ "attention_out_bias": true,
8
+ "audio_attention_head_dim": 8,
9
+ "audio_cross_attention_dim": 32,
10
+ "audio_hop_length": 160,
11
+ "audio_in_channels": 128,
12
+ "audio_num_attention_heads": 4,
13
+ "audio_out_channels": 128,
14
+ "audio_patch_size": 1,
15
+ "audio_patch_size_t": 1,
16
+ "audio_pos_embed_max_pos": 20,
17
+ "audio_sampling_rate": 16000,
18
+ "audio_scale_factor": 4,
19
+ "base_height": 2048,
20
+ "base_width": 2048,
21
+ "caption_channels": 32,
22
+ "causal_offset": 1,
23
+ "cross_attention_dim": 32,
24
+ "cross_attn_timestep_scale_multiplier": 1000,
25
+ "in_channels": 8,
26
+ "norm_elementwise_affine": false,
27
+ "norm_eps": 1e-06,
28
+ "num_attention_heads": 4,
29
+ "num_layers": 1,
30
+ "out_channels": 8,
31
+ "patch_size": 1,
32
+ "patch_size_t": 1,
33
+ "pos_embed_max_pos": 20,
34
+ "qk_norm": "rms_norm_across_heads",
35
+ "rope_double_precision": true,
36
+ "rope_theta": 10000.0,
37
+ "rope_type": "split",
38
+ "timestep_scale_multiplier": 1000,
39
+ "vae_scale_factors": [
40
+ 8,
41
+ 32,
42
+ 32
43
+ ]
44
+ }
transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f006daf27380a849221dea0a77759054a92a70e65d9411650406b4a20a2a612b
3
+ size 554912
vae/config.json ADDED
@@ -0,0 +1,361 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTX2Video",
3
+ "_diffusers_version": "0.38.0",
4
+ "block_out_channels": [
5
+ 8,
6
+ 8,
7
+ 8,
8
+ 8
9
+ ],
10
+ "decoder_block_out_channels": [
11
+ 8,
12
+ 16,
13
+ 32
14
+ ],
15
+ "decoder_causal": false,
16
+ "decoder_inject_noise": [
17
+ false,
18
+ false,
19
+ false,
20
+ false
21
+ ],
22
+ "decoder_layers_per_block": [
23
+ 1,
24
+ 1,
25
+ 1,
26
+ 1
27
+ ],
28
+ "decoder_spatial_padding_mode": "zeros",
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": 8,
50
+ "layers_per_block": [
51
+ 1,
52
+ 1,
53
+ 1,
54
+ 1,
55
+ 1
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
+ "latents_mean_data": [
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0,
88
+ 0.0,
89
+ 0.0
90
+ ],
91
+ "latents_std_data": [
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0
100
+ ],
101
+ "audio_latents_mean_data": [
102
+ 0.0,
103
+ 0.0,
104
+ 0.0,
105
+ 0.0,
106
+ 0.0,
107
+ 0.0,
108
+ 0.0,
109
+ 0.0,
110
+ 0.0,
111
+ 0.0,
112
+ 0.0,
113
+ 0.0,
114
+ 0.0,
115
+ 0.0,
116
+ 0.0,
117
+ 0.0,
118
+ 0.0,
119
+ 0.0,
120
+ 0.0,
121
+ 0.0,
122
+ 0.0,
123
+ 0.0,
124
+ 0.0,
125
+ 0.0,
126
+ 0.0,
127
+ 0.0,
128
+ 0.0,
129
+ 0.0,
130
+ 0.0,
131
+ 0.0,
132
+ 0.0,
133
+ 0.0,
134
+ 0.0,
135
+ 0.0,
136
+ 0.0,
137
+ 0.0,
138
+ 0.0,
139
+ 0.0,
140
+ 0.0,
141
+ 0.0,
142
+ 0.0,
143
+ 0.0,
144
+ 0.0,
145
+ 0.0,
146
+ 0.0,
147
+ 0.0,
148
+ 0.0,
149
+ 0.0,
150
+ 0.0,
151
+ 0.0,
152
+ 0.0,
153
+ 0.0,
154
+ 0.0,
155
+ 0.0,
156
+ 0.0,
157
+ 0.0,
158
+ 0.0,
159
+ 0.0,
160
+ 0.0,
161
+ 0.0,
162
+ 0.0,
163
+ 0.0,
164
+ 0.0,
165
+ 0.0,
166
+ 0.0,
167
+ 0.0,
168
+ 0.0,
169
+ 0.0,
170
+ 0.0,
171
+ 0.0,
172
+ 0.0,
173
+ 0.0,
174
+ 0.0,
175
+ 0.0,
176
+ 0.0,
177
+ 0.0,
178
+ 0.0,
179
+ 0.0,
180
+ 0.0,
181
+ 0.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 0.0,
188
+ 0.0,
189
+ 0.0,
190
+ 0.0,
191
+ 0.0,
192
+ 0.0,
193
+ 0.0,
194
+ 0.0,
195
+ 0.0,
196
+ 0.0,
197
+ 0.0,
198
+ 0.0,
199
+ 0.0,
200
+ 0.0,
201
+ 0.0,
202
+ 0.0,
203
+ 0.0,
204
+ 0.0,
205
+ 0.0,
206
+ 0.0,
207
+ 0.0,
208
+ 0.0,
209
+ 0.0,
210
+ 0.0,
211
+ 0.0,
212
+ 0.0,
213
+ 0.0,
214
+ 0.0,
215
+ 0.0,
216
+ 0.0,
217
+ 0.0,
218
+ 0.0,
219
+ 0.0,
220
+ 0.0,
221
+ 0.0,
222
+ 0.0,
223
+ 0.0,
224
+ 0.0,
225
+ 0.0,
226
+ 0.0,
227
+ 0.0,
228
+ 0.0,
229
+ 0.0
230
+ ],
231
+ "audio_latents_std_data": [
232
+ 1.0,
233
+ 1.0,
234
+ 1.0,
235
+ 1.0,
236
+ 1.0,
237
+ 1.0,
238
+ 1.0,
239
+ 1.0,
240
+ 1.0,
241
+ 1.0,
242
+ 1.0,
243
+ 1.0,
244
+ 1.0,
245
+ 1.0,
246
+ 1.0,
247
+ 1.0,
248
+ 1.0,
249
+ 1.0,
250
+ 1.0,
251
+ 1.0,
252
+ 1.0,
253
+ 1.0,
254
+ 1.0,
255
+ 1.0,
256
+ 1.0,
257
+ 1.0,
258
+ 1.0,
259
+ 1.0,
260
+ 1.0,
261
+ 1.0,
262
+ 1.0,
263
+ 1.0,
264
+ 1.0,
265
+ 1.0,
266
+ 1.0,
267
+ 1.0,
268
+ 1.0,
269
+ 1.0,
270
+ 1.0,
271
+ 1.0,
272
+ 1.0,
273
+ 1.0,
274
+ 1.0,
275
+ 1.0,
276
+ 1.0,
277
+ 1.0,
278
+ 1.0,
279
+ 1.0,
280
+ 1.0,
281
+ 1.0,
282
+ 1.0,
283
+ 1.0,
284
+ 1.0,
285
+ 1.0,
286
+ 1.0,
287
+ 1.0,
288
+ 1.0,
289
+ 1.0,
290
+ 1.0,
291
+ 1.0,
292
+ 1.0,
293
+ 1.0,
294
+ 1.0,
295
+ 1.0,
296
+ 1.0,
297
+ 1.0,
298
+ 1.0,
299
+ 1.0,
300
+ 1.0,
301
+ 1.0,
302
+ 1.0,
303
+ 1.0,
304
+ 1.0,
305
+ 1.0,
306
+ 1.0,
307
+ 1.0,
308
+ 1.0,
309
+ 1.0,
310
+ 1.0,
311
+ 1.0,
312
+ 1.0,
313
+ 1.0,
314
+ 1.0,
315
+ 1.0,
316
+ 1.0,
317
+ 1.0,
318
+ 1.0,
319
+ 1.0,
320
+ 1.0,
321
+ 1.0,
322
+ 1.0,
323
+ 1.0,
324
+ 1.0,
325
+ 1.0,
326
+ 1.0,
327
+ 1.0,
328
+ 1.0,
329
+ 1.0,
330
+ 1.0,
331
+ 1.0,
332
+ 1.0,
333
+ 1.0,
334
+ 1.0,
335
+ 1.0,
336
+ 1.0,
337
+ 1.0,
338
+ 1.0,
339
+ 1.0,
340
+ 1.0,
341
+ 1.0,
342
+ 1.0,
343
+ 1.0,
344
+ 1.0,
345
+ 1.0,
346
+ 1.0,
347
+ 1.0,
348
+ 1.0,
349
+ 1.0,
350
+ 1.0,
351
+ 1.0,
352
+ 1.0,
353
+ 1.0,
354
+ 1.0,
355
+ 1.0,
356
+ 1.0,
357
+ 1.0,
358
+ 1.0,
359
+ 1.0
360
+ ]
361
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb5cf80ab79380acfe1ecebe8342da13e32f1a6ab0b52b7741919f6cd0d162a
3
+ size 1056836
vocoder/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTX2Vocoder",
3
+ "_diffusers_version": "0.38.0",
4
+ "hidden_channels": 32,
5
+ "in_channels": 128,
6
+ "leaky_relu_negative_slope": 0.1,
7
+ "out_channels": 2,
8
+ "output_sampling_rate": 24000,
9
+ "resnet_dilations": [
10
+ [
11
+ 1,
12
+ 3,
13
+ 5
14
+ ]
15
+ ],
16
+ "resnet_kernel_sizes": [
17
+ 3
18
+ ],
19
+ "upsample_factors": [
20
+ 6,
21
+ 5,
22
+ 2,
23
+ 2,
24
+ 2
25
+ ],
26
+ "upsample_kernel_sizes": [
27
+ 16,
28
+ 15,
29
+ 8,
30
+ 4,
31
+ 4
32
+ ]
33
+ }
vocoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51bae55a27700223d49e2257d02b4e0df4e2efac4cf42ed0a16319283d499a29
3
+ size 188372