Hugging Face's logo

isfs
/
ltxv-2B-0.9.8-f16-Colab-Optimized

Diffusers
Safetensors
Model card Files
xet
 Community
isfs commited on
Commit
20e72c9
·
verified ·
1 Parent(s): d85544e

Upload all models and configs for LTX video

Browse files
Files changed (9) hide show
  1. scheduler/scheduler_config.json +18 -0
  2. text_encoders/config.json +34 -0
  3. text_encoders/model.safetensors +3 -0
  4. text_encoders/tokenizer.json +0 -0
  5. text_encoders/tokenizer_config.json +113 -0
  6. transformer/config.json +19 -0
  7. transformer/diffusion_pytorch_model.safetensors +3 -0
  8. vae/config.json +80 -0
  9. vae/diffusion_pytorch_model.safetensors +3 -0
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 4096,
8
+ "max_shift": 1.15,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": null,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": false,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
text_encoders/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5EncoderModel"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 10240,
7
+ "d_kv": 64,
8
+ "d_model": 4096,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float16",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_decoder": false,
17
+ "is_encoder_decoder": false,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 24,
22
+ "num_heads": 64,
23
+ "num_layers": 24,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "scale_decoder_outputs": true,
29
+ "tie_word_embeddings": true,
30
+ "transformers_version": "5.0.0",
31
+ "use_cache": false,
32
+ "vocab_size": 32128,
33
+ "torch_dtype": "float16"
34
+ }
text_encoders/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f247511d8203727e31b69752ebe91de49e89ee9635d5d29c35de23ad18be2751
3
+ size 11537914408
text_encoders/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
text_encoders/tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 100,
6
+ "extra_special_tokens": [
7
+ "<extra_id_0>",
8
+ "<extra_id_1>",
9
+ "<extra_id_2>",
10
+ "<extra_id_3>",
11
+ "<extra_id_4>",
12
+ "<extra_id_5>",
13
+ "<extra_id_6>",
14
+ "<extra_id_7>",
15
+ "<extra_id_8>",
16
+ "<extra_id_9>",
17
+ "<extra_id_10>",
18
+ "<extra_id_11>",
19
+ "<extra_id_12>",
20
+ "<extra_id_13>",
21
+ "<extra_id_14>",
22
+ "<extra_id_15>",
23
+ "<extra_id_16>",
24
+ "<extra_id_17>",
25
+ "<extra_id_18>",
26
+ "<extra_id_19>",
27
+ "<extra_id_20>",
28
+ "<extra_id_21>",
29
+ "<extra_id_22>",
30
+ "<extra_id_23>",
31
+ "<extra_id_24>",
32
+ "<extra_id_25>",
33
+ "<extra_id_26>",
34
+ "<extra_id_27>",
35
+ "<extra_id_28>",
36
+ "<extra_id_29>",
37
+ "<extra_id_30>",
38
+ "<extra_id_31>",
39
+ "<extra_id_32>",
40
+ "<extra_id_33>",
41
+ "<extra_id_34>",
42
+ "<extra_id_35>",
43
+ "<extra_id_36>",
44
+ "<extra_id_37>",
45
+ "<extra_id_38>",
46
+ "<extra_id_39>",
47
+ "<extra_id_40>",
48
+ "<extra_id_41>",
49
+ "<extra_id_42>",
50
+ "<extra_id_43>",
51
+ "<extra_id_44>",
52
+ "<extra_id_45>",
53
+ "<extra_id_46>",
54
+ "<extra_id_47>",
55
+ "<extra_id_48>",
56
+ "<extra_id_49>",
57
+ "<extra_id_50>",
58
+ "<extra_id_51>",
59
+ "<extra_id_52>",
60
+ "<extra_id_53>",
61
+ "<extra_id_54>",
62
+ "<extra_id_55>",
63
+ "<extra_id_56>",
64
+ "<extra_id_57>",
65
+ "<extra_id_58>",
66
+ "<extra_id_59>",
67
+ "<extra_id_60>",
68
+ "<extra_id_61>",
69
+ "<extra_id_62>",
70
+ "<extra_id_63>",
71
+ "<extra_id_64>",
72
+ "<extra_id_65>",
73
+ "<extra_id_66>",
74
+ "<extra_id_67>",
75
+ "<extra_id_68>",
76
+ "<extra_id_69>",
77
+ "<extra_id_70>",
78
+ "<extra_id_71>",
79
+ "<extra_id_72>",
80
+ "<extra_id_73>",
81
+ "<extra_id_74>",
82
+ "<extra_id_75>",
83
+ "<extra_id_76>",
84
+ "<extra_id_77>",
85
+ "<extra_id_78>",
86
+ "<extra_id_79>",
87
+ "<extra_id_80>",
88
+ "<extra_id_81>",
89
+ "<extra_id_82>",
90
+ "<extra_id_83>",
91
+ "<extra_id_84>",
92
+ "<extra_id_85>",
93
+ "<extra_id_86>",
94
+ "<extra_id_87>",
95
+ "<extra_id_88>",
96
+ "<extra_id_89>",
97
+ "<extra_id_90>",
98
+ "<extra_id_91>",
99
+ "<extra_id_92>",
100
+ "<extra_id_93>",
101
+ "<extra_id_94>",
102
+ "<extra_id_95>",
103
+ "<extra_id_96>",
104
+ "<extra_id_97>",
105
+ "<extra_id_98>",
106
+ "<extra_id_99>"
107
+ ],
108
+ "is_local": false,
109
+ "model_max_length": 512,
110
+ "pad_token": "<pad>",
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
transformer/config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "LTXVideoTransformer3DModel",
3
+ "_diffusers_version": "0.35.0.dev0",
4
+ "activation_fn": "gelu-approximate",
5
+ "attention_bias": true,
6
+ "attention_head_dim": 128,
7
+ "attention_out_bias": true,
8
+ "caption_channels": 4096,
9
+ "cross_attention_dim": 4096,
10
+ "in_channels": 128,
11
+ "norm_elementwise_affine": false,
12
+ "norm_eps": 1e-06,
13
+ "num_attention_heads": 32,
14
+ "num_layers": 48,
15
+ "out_channels": 128,
16
+ "patch_size": 1,
17
+ "patch_size_t": 1,
18
+ "qk_norm": "rms_norm_across_heads"
19
+ }
transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76aa8c4786af752fa6f951947129d5290c3c6c0b2fadcadea6b5e114ae2cad8f
3
+ size 6340744492
vae/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKLLTXVideo",
3
+ "_diffusers_version": "0.34.0.dev0",
4
+ "block_out_channels": [
5
+ 128,
6
+ 256,
7
+ 512,
8
+ 1024,
9
+ 2048
10
+ ],
11
+ "decoder_block_out_channels": [
12
+ 256,
13
+ 512,
14
+ 1024
15
+ ],
16
+ "decoder_causal": false,
17
+ "decoder_inject_noise": [
18
+ false,
19
+ false,
20
+ false,
21
+ false
22
+ ],
23
+ "decoder_layers_per_block": [
24
+ 5,
25
+ 5,
26
+ 5,
27
+ 5
28
+ ],
29
+ "decoder_spatio_temporal_scaling": [
30
+ true,
31
+ true,
32
+ true
33
+ ],
34
+ "down_block_types": [
35
+ "LTXVideo095DownBlock3D",
36
+ "LTXVideo095DownBlock3D",
37
+ "LTXVideo095DownBlock3D",
38
+ "LTXVideo095DownBlock3D"
39
+ ],
40
+ "downsample_type": [
41
+ "spatial",
42
+ "temporal",
43
+ "spatiotemporal",
44
+ "spatiotemporal"
45
+ ],
46
+ "encoder_causal": true,
47
+ "in_channels": 3,
48
+ "latent_channels": 128,
49
+ "layers_per_block": [
50
+ 4,
51
+ 6,
52
+ 6,
53
+ 2,
54
+ 2
55
+ ],
56
+ "out_channels": 3,
57
+ "patch_size": 4,
58
+ "patch_size_t": 1,
59
+ "resnet_norm_eps": 1e-06,
60
+ "scaling_factor": 1.0,
61
+ "spatial_compression_ratio": 32,
62
+ "spatio_temporal_scaling": [
63
+ true,
64
+ true,
65
+ true,
66
+ true
67
+ ],
68
+ "temporal_compression_ratio": 8,
69
+ "timestep_conditioning": true,
70
+ "upsample_factor": [
71
+ 2,
72
+ 2,
73
+ 2
74
+ ],
75
+ "upsample_residual": [
76
+ true,
77
+ true,
78
+ true
79
+ ]
80
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265ca87cb5dff5e37f924286e957324e282fe7710a952a7dafc0df43883e2010
3
+ size 1676798532