ComfyUI-Lightx2vWrapper/example_workflows/lightx2v_seko_talk_static.json at main · ModelTC/ComfyUI-Lightx2vWrapper · GitHub

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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
{
  "11": {
    "inputs": {
      "audio": "audio_full_female_10s.wav",
      "start_time": 0,
      "duration": 0
    },
    "class_type": "VHS_LoadAudioUpload",
    "_meta": {
      "title": "Load Audio (Upload)🎥🅥🅗🅢"
    }
  },
  "13": {
    "inputs": {
      "prompt": "A person speaks naturally to the camera, with clear lip movement and subtle facial expressions.",
      "negative_prompt": "",
      "inference_config": [
        "14",
        0
      ],
      "image": [
        "20",
        0
      ],
      "audio": [
        "11",
        0
      ],
      "memory_config": [
        "16",
        0
      ],
      "quantization_config": [
        "17",
        0
      ]
    },
    "class_type": "LightX2VConfigCombinerV2",
    "_meta": {
      "title": "LightX2V Config Combiner V2"
    }
  },
  "14": {
    "inputs": {
      "model_cls": "seko_talk",
      "model_name": "Wan2.1-R2V0909-Audio-14B-720P-fp8",
      "task": "s2v",
      "infer_steps": 4,
      "seed": 4221706066,
      "cfg_scale": 1,
      "cfg_scale2": 1,
      "sample_shift": 5,
      "height": 1280,
      "width": 720,
      "duration": 5,
      "attention_type": "sage_attn2",
      "denoising_steps": "",
      "resize_mode": "adaptive",
      "fixed_area": "720p",
      "segment_length": 81,
      "prev_frame_length": 5,
      "use_tiny_vae": false
    },
    "class_type": "LightX2VInferenceConfig",
    "_meta": {
      "title": "LightX2V Inference Config"
    }
  },
  "15": {
    "inputs": {
      "prepared_config": [
        "13",
        0
      ]
    },
    "class_type": "LightX2VModularInferenceV2",
    "_meta": {
      "title": "LightX2V Modular Inference V2"
    }
  },
  "16": {
    "inputs": {
      "enable_rotary_chunk": false,
      "rotary_chunk_size": 100,
      "clean_cuda_cache": true,
      "cpu_offload": true,
      "offload_granularity": "block",
      "offload_ratio": 1.0,
      "t5_cpu_offload": true,
      "t5_offload_granularity": "model",
      "audio_encoder_cpu_offload": true,
      "audio_adapter_cpu_offload": true,
      "vae_cpu_offload": true,
      "use_tiling_vae": true,
      "lazy_load": false,
      "unload_after_inference": false
    },
    "class_type": "LightX2VMemoryOptimization",
    "_meta": {
      "title": "LightX2V Memory Optimization"
    }
  },
  "17": {
    "inputs": {
      "dit_quant_scheme": "fp8-sgl",
      "t5_quant_scheme": "fp8-sgl",
      "clip_quant_scheme": "fp8-sgl",
      "adapter_quant_scheme": "fp8-sgl"
    },
    "class_type": "LightX2VQuantization",
    "_meta": {
      "title": "LightX2V Quantization"
    }
  },
  "18": {
    "inputs": {
      "frame_rate": 16,
      "loop_count": 0,
      "filename_prefix": "lightx2v_sekotalk/static",
      "format": "video/h264-mp4",
      "pix_fmt": "yuv420p",
      "crf": 19,
      "save_metadata": false,
      "trim_to_audio": false,
      "pingpong": false,
      "save_output": true,
      "images": [
        "15",
        0
      ],
      "audio": [
        "15",
        1
      ]
    },
    "class_type": "VHS_VideoCombine",
    "_meta": {
      "title": "Video Combine 🎥🅥🅗🅢"
    }
  },
  "20": {
    "inputs": {
      "image": "codex_image_20260922_135831_1323a530_B.jpg"
    },
    "class_type": "LoadImage",
    "_meta": {
      "title": "Load Image"
    }
  }
}