Hugging Face's logo

kandinskylab
/
Kandinsky-S2V-1.0-Pro-Diffusers

Image-to-Video
Diffusers
Safetensors
speech-to-video
avatar
video-generation
kandinsky
Model card Files
xet
 Community
Kandinsky-S2V-1.0-Pro-Diffusers
File size: 2,521 Bytes
c6df68f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
{
  "_class_name": "KandinskyS2VModularPipeline",
  "_diffusers_version": "0.40.0",
  "_blocks_class_name": "KandinskyS2VAutoBlocks",
  "transformer": [
    "diffusers",
    "KandinskyS2VTransformer3DModel",
    {
      "type_hint": [
        "diffusers",
        "KandinskyS2VTransformer3DModel"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "transformer",
      "variant": null,
      "revision": null
    }
  ],
  "vae": [
    "diffusers",
    "AutoencoderKLHunyuanVideo",
    {
      "type_hint": [
        "diffusers",
        "AutoencoderKLHunyuanVideo"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "vae",
      "variant": null,
      "revision": null
    }
  ],
  "text_encoder": [
    "transformers",
    "Qwen2_5OmniThinkerForConditionalGeneration",
    {
      "type_hint": [
        "transformers",
        "Qwen2_5OmniThinkerForConditionalGeneration"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "text_encoder",
      "variant": null,
      "revision": null
    }
  ],
  "tokenizer": [
    "transformers",
    "Qwen2_5OmniProcessor",
    {
      "type_hint": [
        "transformers",
        "Qwen2_5OmniProcessor"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "tokenizer",
      "variant": null,
      "revision": null
    }
  ],
  "text_encoder_2": [
    "transformers",
    "CLIPTextModel",
    {
      "type_hint": [
        "transformers",
        "CLIPTextModel"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "text_encoder_2",
      "variant": null,
      "revision": null
    }
  ],
  "tokenizer_2": [
    "transformers",
    "CLIPTokenizer",
    {
      "type_hint": [
        "transformers",
        "CLIPTokenizer"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "tokenizer_2",
      "variant": null,
      "revision": null
    }
  ],
  "scheduler": [
    "diffusers",
    "FlowMatchEulerDiscreteScheduler",
    {
      "type_hint": [
        "diffusers",
        "FlowMatchEulerDiscreteScheduler"
      ],
      "pretrained_model_name_or_path": "kandinskylab/Kandinsky-S2V-1.0-Pro-Diffusers",
      "subfolder": "scheduler",
      "variant": null,
      "revision": null
    }
  ]
}