Seedance 2.0 Pro: Cinematic Text-to-Video with 2K Lip-Sync on playground and API | RunComfy

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/bytedance/seedance-2.0/pro \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Golden hour on a quiet cafe terrace: a barista wipes the counter, then looks up and explains today's special in a friendly tone, natural lip-sync. Medium close-up, slow push-in; warm side light, soft bokeh through glass, gentle cafe ambience and subtle film grain."
  }'

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

{
  "type": "object",
  "title": "modelApiDoc_navInputSchema",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "title": "Prompt",
      "description": "Text prompt for the video (Chinese ~≤500 characters, English ~≤1000 words recommended). ",
      "type": "string",
      "default": "Golden hour on a quiet cafe terrace: a barista wipes the counter, then looks up and explains today's special in a friendly tone, natural lip-sync. Medium close-up, slow push-in; warm side light, soft bokeh through glass, gentle cafe ambience and subtle film grain."
    },
    "images": {
      "title": "Images",
      "description": "Reference images for multimodal reference mode (0–9). Support jpeg、png、webp、bmp、tiff、gif.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "image_uri"
      },
      "maxItems": 9
    },
    "videos": {
      "title": "Videos",
      "description": "Reference videos for multimodal reference mode (0–3). Support mp4、mov. Video duration must be between 2 and 15 seconds.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "video_uri"
      },
      "maxItems": 3
    },
    "audios": {
      "title": "Audio URLs",
      "description": "Reference audio for multimodal reference mode (0–3). Support wav、mp3. Audio duration must be between 2 and 15 seconds. Size should be less than 15MB.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "audio_uri"
      },
      "maxItems": 3
    },
    "aspect_ratio": {
      "title": "Aspect Ratio (W:H)",
      "description": "Seedance 2.0 Pro default is adaptive (model picks closest ratio; actual ratio is returned on task query).",
      "type": "string",
      "enum": [
        "adaptive",
        "16:9",
        "9:16",
        "4:3",
        "3:4",
        "1:1",
        "21:9"
      ],
      "default": "adaptive"
    },
    "duration": {
      "title": "Duration (seconds)",
      "description": "Integer seconds in [4, 15].",
      "type": "integer",
      "minimum": 4,
      "maximum": 15,
      "default": 5
    },
    "resolution": {
      "title": "Resolution",
      "description": "",
      "type": "string",
      "enum": [
        "480p",
        "720p"
      ],
      "default": "720p"
    },
    "generate_audio": {
      "title": "Generate audio",
      "description": "When true, the model outputs video with synchronized audio (speech, SFX, music). ",
      "type": "boolean",
      "default": true
    },
    "seed": {
      "title": "Seed",
      "description": "Random seed for the video generation. ",
      "type": "integer"
    },
    "tools": {
      "title": "Web Search",
      "description": " When `web_search` is included, the model may run an online search depending on the prompt (e.g. specific products, current weather), which can improve factual freshness but increases latency. ",
      "type": "boolean",
      "default": false
    }
  }
}