Hugging Face's logo

deathlegionteam
/
LEGION-Video-Gen

Diffusers
Safetensors
hunyuan_video
Model card Files
xet
 Community
LEGION-Video-Gen
File size: 2,116 Bytes
98e8a90
 
 
 
 
 
 
 
 
 
 
b565446
98e8a90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
{
  "_class_name": "HunyuanVideo15Pipeline",
  "_diffusers_version": "0.36.0.dev0",
  "_name_or_path": "deathlegionteam/LEGION-Video-Gen",
  "architectures": [
    "HunyuanVideo15ForConditionalGeneration"
  ],
  "model_type": "hunyuan_video",
  "license": "apache-2.0",
  "library_name": "diffusers",
  "pipeline_tag": "text-to-video",
  "base_model": "deathlegionteam/LEGION-Video-Gen",
  "guider": [
    "diffusers",
    "ClassifierFreeGuidance"
  ],
  "scheduler": [
    "diffusers",
    "FlowMatchEulerDiscreteScheduler"
  ],
  "text_encoder": [
    "transformers",
    "Qwen2_5_VLTextModel"
  ],
  "text_encoder_2": [
    "transformers",
    "T5EncoderModel"
  ],
  "tokenizer": [
    "transformers",
    "Qwen2TokenizerFast"
  ],
  "tokenizer_2": [
    "transformers",
    "ByT5Tokenizer"
  ],
  "transformer": [
    "diffusers",
    "HunyuanVideo15Transformer3DModel"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKLHunyuanVideo15"
  ],
  "transformer_config": {
    "_class_name": "HunyuanVideo15Transformer3DModel",
    "attention_head_dim": 128,
    "image_embed_dim": 1152,
    "in_channels": 65,
    "mlp_ratio": 4.0,
    "num_attention_heads": 16,
    "num_layers": 54,
    "num_refiner_layers": 2,
    "out_channels": 32,
    "patch_size": 1,
    "patch_size_t": 1,
    "qk_norm": "rms_norm",
    "rope_axes_dim": [16, 56, 56],
    "rope_theta": 256.0,
    "target_size": 640,
    "task_type": "t2v",
    "text_embed_2_dim": 1472,
    "text_embed_dim": 3584,
    "use_meanflow": false
  },
  "vae_config": {
    "_class_name": "AutoencoderKLHunyuanVideo15",
    "in_channels": 3,
    "out_channels": 3,
    "latent_channels": 32,
    "block_out_channels": [128, 256, 512, 512],
    "layers_per_block": 2,
    "norm_num_groups": 32,
    "scaling_factor": 0.476986,
    "force_upcast": true,
    "use_quant_conv": false
  },
  "scheduler_config": {
    "_class_name": "FlowMatchEulerDiscreteScheduler",
    "num_train_timesteps": 1000,
    "shift": 7.0,
    "use_dynamic_shifting": false,
    "base_shift": 0.5,
    "max_shift": 1.15,
    "base_image_seq_len": 256,
    "max_image_seq_len": 4096
  }
}