Hugging Face's logo

CalamitousFelicitousness
/
LTX-2.3-dev-Diffusers

Image-to-Video
Diffusers
Safetensors
English
LTX2Pipeline
text-to-video
ltx-2
ltx-2-3
ltx-video
lightricks
Model card Files
xet
Community
CalamitousFelicitousness commited on
Commit
a482fd3
·
verified ·
1 Parent(s): 64e2174

Replace text_encoder with google/gemma-3-12b-it (bf16, 24GB vs 49GB float32)

Browse files
Files changed (16) hide show
  1. text_encoder/config.json +3 -77
  2. text_encoder/diffusion_pytorch_model-00005-of-00012.safetensors +0 -3
  3. text_encoder/diffusion_pytorch_model-00006-of-00012.safetensors +0 -3
  4. text_encoder/diffusion_pytorch_model-00007-of-00012.safetensors +0 -3
  5. text_encoder/diffusion_pytorch_model-00008-of-00012.safetensors +0 -3
  6. text_encoder/diffusion_pytorch_model-00009-of-00012.safetensors +0 -3
  7. text_encoder/diffusion_pytorch_model-00010-of-00012.safetensors +0 -3
  8. text_encoder/diffusion_pytorch_model-00011-of-00012.safetensors +0 -3
  9. text_encoder/diffusion_pytorch_model-00012-of-00012.safetensors +0 -3
  10. text_encoder/generation_config.json +3 -1
  11. text_encoder/{diffusion_pytorch_model-00001-of-00012.safetensors → model-00001-of-00005.safetensors} +2 -2
  12. text_encoder/{diffusion_pytorch_model-00002-of-00012.safetensors → model-00002-of-00005.safetensors} +2 -2
  13. text_encoder/{diffusion_pytorch_model-00003-of-00012.safetensors → model-00003-of-00005.safetensors} +2 -2
  14. text_encoder/{diffusion_pytorch_model-00004-of-00012.safetensors → model-00004-of-00005.safetensors} +2 -2
  15. text_encoder/model-00005-of-00005.safetensors +3 -0
  16. text_encoder/model.safetensors.index.json +0 -0
text_encoder/config.json CHANGED
@@ -3,7 +3,6 @@
3
  "Gemma3ForConditionalGeneration"
4
  ],
5
  "boi_token_index": 255999,
6
- "dtype": "float32",
7
  "eoi_token_index": 256000,
8
  "eos_token_id": [
9
  1,
@@ -14,99 +13,26 @@
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
- "cache_implementation": "hybrid",
22
- "dtype": "float32",
23
- "final_logit_softcapping": null,
24
- "head_dim": 256,
25
- "hidden_activation": "gelu_pytorch_tanh",
26
  "hidden_size": 3840,
27
- "initializer_range": 0.02,
28
  "intermediate_size": 15360,
29
- "layer_types": [
30
- "sliding_attention",
31
- "sliding_attention",
32
- "sliding_attention",
33
- "sliding_attention",
34
- "sliding_attention",
35
- "full_attention",
36
- "sliding_attention",
37
- "sliding_attention",
38
- "sliding_attention",
39
- "sliding_attention",
40
- "sliding_attention",
41
- "full_attention",
42
- "sliding_attention",
43
- "sliding_attention",
44
- "sliding_attention",
45
- "sliding_attention",
46
- "sliding_attention",
47
- "full_attention",
48
- "sliding_attention",
49
- "sliding_attention",
50
- "sliding_attention",
51
- "sliding_attention",
52
- "sliding_attention",
53
- "full_attention",
54
- "sliding_attention",
55
- "sliding_attention",
56
- "sliding_attention",
57
- "sliding_attention",
58
- "sliding_attention",
59
- "full_attention",
60
- "sliding_attention",
61
- "sliding_attention",
62
- "sliding_attention",
63
- "sliding_attention",
64
- "sliding_attention",
65
- "full_attention",
66
- "sliding_attention",
67
- "sliding_attention",
68
- "sliding_attention",
69
- "sliding_attention",
70
- "sliding_attention",
71
- "full_attention",
72
- "sliding_attention",
73
- "sliding_attention",
74
- "sliding_attention",
75
- "sliding_attention",
76
- "sliding_attention",
77
- "full_attention"
78
- ],
79
- "max_position_embeddings": 131072,
80
  "model_type": "gemma3_text",
81
  "num_attention_heads": 16,
82
  "num_hidden_layers": 48,
83
  "num_key_value_heads": 8,
84
- "query_pre_attn_scalar": 256,
85
- "rms_norm_eps": 1e-06,
86
- "rope_local_base_freq": 10000,
87
  "rope_scaling": {
88
  "factor": 8.0,
89
  "rope_type": "linear"
90
  },
91
- "rope_theta": 1000000,
92
- "sliding_window": 1024,
93
- "sliding_window_pattern": 6,
94
- "use_bidirectional_attention": false,
95
- "use_cache": true,
96
- "vocab_size": 262208
97
  },
98
- "transformers_version": "4.57.3",
 
99
  "vision_config": {
100
- "attention_dropout": 0.0,
101
- "dtype": "float32",
102
- "hidden_act": "gelu_pytorch_tanh",
103
  "hidden_size": 1152,
104
  "image_size": 896,
105
  "intermediate_size": 4304,
106
- "layer_norm_eps": 1e-06,
107
  "model_type": "siglip_vision_model",
108
  "num_attention_heads": 16,
109
- "num_channels": 3,
110
  "num_hidden_layers": 27,
111
  "patch_size": 14,
112
  "vision_use_head": false
 
3
  "Gemma3ForConditionalGeneration"
4
  ],
5
  "boi_token_index": 255999,
 
6
  "eoi_token_index": 256000,
7
  "eos_token_id": [
8
  1,
 
13
  "mm_tokens_per_image": 256,
14
  "model_type": "gemma3",
15
  "text_config": {
 
 
 
 
 
 
 
 
 
16
  "hidden_size": 3840,
 
17
  "intermediate_size": 15360,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  "model_type": "gemma3_text",
19
  "num_attention_heads": 16,
20
  "num_hidden_layers": 48,
21
  "num_key_value_heads": 8,
 
 
 
22
  "rope_scaling": {
23
  "factor": 8.0,
24
  "rope_type": "linear"
25
  },
26
+ "sliding_window": 1024
 
 
 
 
 
27
  },
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.50.0.dev0",
30
  "vision_config": {
 
 
 
31
  "hidden_size": 1152,
32
  "image_size": 896,
33
  "intermediate_size": 4304,
 
34
  "model_type": "siglip_vision_model",
35
  "num_attention_heads": 16,
 
36
  "num_hidden_layers": 27,
37
  "patch_size": 14,
38
  "vision_use_head": false
text_encoder/diffusion_pytorch_model-00005-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9424d48871c4a1dbd3015739b575827c98bdf265477181613380b3a8a2c9c9b0
3
- size 2453837880
 
 
 
 
text_encoder/diffusion_pytorch_model-00006-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e09a56a7a942f813ae20d89486e00578ff5e258a3a3240a677dee4e379428056
3
- size 2477460416
 
 
 
 
text_encoder/diffusion_pytorch_model-00007-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5026393f63e560c1109b704ff5e7ec31707b3c32a205e0afa86557b5289d80
3
- size 2453837880
 
 
 
 
text_encoder/diffusion_pytorch_model-00008-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ce05cf1062842c14d5a436f9b6ba76c05e1d0b7eafacffcdd3b0effa9fd56a1
3
- size 2477460416
 
 
 
 
text_encoder/diffusion_pytorch_model-00009-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:97f81169d8eeb712c9aadc5ec86bb45e1d80002ce9c4014355d6d5b43b5b6eb0
3
- size 2453837880
 
 
 
 
text_encoder/diffusion_pytorch_model-00010-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5ac39c5bc6ee9082ca49d1cfeea68ecd1cf927cc6a9b059466d17a5f31fe239
3
- size 2477460416
 
 
 
 
text_encoder/diffusion_pytorch_model-00011-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f12f0a6ca282a039cd02b807e7a8152272c3b4ebedbc034fae461c10474a26b
3
- size 3617916064
 
 
 
 
text_encoder/diffusion_pytorch_model-00012-of-00012.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:80edbf223b284a9e0681a23e62084d0379a5b6d5ad8d3326b36da709800532e4
3
- size 589949192
 
 
 
 
text_encoder/generation_config.json CHANGED
@@ -1,11 +1,13 @@
1
  {
 
2
  "cache_implementation": "hybrid",
3
  "do_sample": true,
4
  "eos_token_id": [
5
  1,
6
  106
7
  ],
 
8
  "top_k": 64,
9
  "top_p": 0.95,
10
- "transformers_version": "4.57.3"
11
  }
 
1
  {
2
+ "bos_token_id": 2,
3
  "cache_implementation": "hybrid",
4
  "do_sample": true,
5
  "eos_token_id": [
6
  1,
7
  106
8
  ],
9
+ "pad_token_id": 0,
10
  "top_k": 64,
11
  "top_p": 0.95,
12
+ "transformers_version": "4.50.0.dev0"
13
  }
text_encoder/{diffusion_pytorch_model-00001-of-00012.safetensors → model-00001-of-00005.safetensors} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eee7f7f9592994fe2d3d326ecea737e305f73b8c133f9eb76e47e4cb71b14143
3
- size 842649288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4847447e92599833e8dbaa3067cd201c3bb5c052efa91f11ba891e43234f7832
3
+ size 4979902192
text_encoder/{diffusion_pytorch_model-00002-of-00012.safetensors → model-00002-of-00005.safetensors} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5209062512f28285489e7b733b737cfc6e2287375a1d9e6e97f94b2906c90a07
3
- size 2493514840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891bd54eed03cba9ee1e705533a02a8217fcc29f356e4a1f53e5fd0d178883ad
3
+ size 4931296592
text_encoder/{diffusion_pytorch_model-00003-of-00012.safetensors → model-00003-of-00005.safetensors} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adc81519d4cb524eec107e0ec50f1210d992004537965e6c0fdb8d0c1be6bc97
3
- size 2422380384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cee411d9d57324e50ce064a192cc5a858276d508611b12fc599e0c9767112e0
3
+ size 4931296656
text_encoder/{diffusion_pytorch_model-00004-of-00012.safetensors → model-00004-of-00005.safetensors} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b23642feb7d72c7228205ebbefd3f6882b115e750bd9c41b0e2f680db5969ac
3
- size 2477460360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc75a29a730c9e743cad013feda3b0991a913fafe787c58a1c6e20afad97723
3
+ size 4931296656
text_encoder/model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed14bd4908c98fed9f61e8cd410167e0846de9abd78e0452ab092072e5d9252d
3
+ size 4601000928
text_encoder/model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff