{
  "schema_version": 1,
  "id": "wan22-s2v",
  "name": "Wan 2.2 S2V 14B",
  "description": "Supply a start image and reference audio through Video Generation.",
  "model_url": "https://huggingface.co/Wan-AI/Wan2.2-S2V-14B",
  "slots": [
    {
      "id": "diffusion_model",
      "required": true
    },
    {
      "id": "t5xxl",
      "required": true,
      "label": "UMT5-XXL"
    },
    {
      "id": "audio_encoder",
      "required": true,
      "label": "Wav2Vec2 Large English"
    },
    {
      "id": "vae",
      "required": false,
      "label": "Wan 2.1 VAE"
    },
    {
      "id": "tae",
      "required": false
    }
  ],
  "required_any": [
    [
      "vae",
      "tae"
    ]
  ],
  "defaults": {
    "sampling_method": "euler",
    "flow_shift": 3,
    "video_frames": 33,
    "cfg_scale": 4.5,
    "steps": 20
  },
  "features": [
    "flow_shift",
    "init_image",
    "ref_audios"
  ],
  "disabled_features": [
    "img2img",
    "mask_image"
  ]
}