Skip to content

inference.partner.seedance-2.fast.ref2vid.v2

View markdown

The inference.partner.seedance-2.fast.ref2vid.v2 job generates video from reference images, videos, and audio.

{
"type": "inference.partner.seedance-2.fast.ref2vid.v2",
"config": {
"references": [
"reference.mp4"
],
"prompt": "Continue the movement in this reference",
"duration": 8
}
}

Use a references filename array and upload each file with its corresponding image, video, or audio Content-Type. Up to 9 images, 3 videos, and 3 audio clips are accepted, with at most 15 seconds each of reference video and audio. Audio must accompany an image or video.

Use inference.partner.seedance-2.fast.img2vid.v2 for first/last frame inputs. Reference generation supports resolution, aspect ratio, duration (4–15 or -1 for automatic), seed, watermark, audio generation, and returning the last frame.

Set duration to -1 for automatic duration. Automatic duration is determined from the prompt and reference content.

{
"type": "object",
"required": [
"type",
"config"
],
"additionalProperties": false,
"properties": {
"type": {
"type": "string"
},
"config": {
"type": "object",
"required": [
"prompt",
"references"
],
"additionalProperties": false,
"properties": {
"references": {
"description": "Reference filenames: up to 9 images, 3 videos, and 3 audio clips; 15 seconds total each of video and audio. Audio must accompany an image or video.",
"type": "array",
"minItems": 1,
"maxItems": 15,
"uniqueItems": true,
"items": {
"type": "string",
"format": "filename"
}
},
"prompt": {
"description": "Description of desired output.",
"type": "string",
"default": "a flying dragon over mountains",
"minLength": 3,
"maxLength": 4096
},
"resolution": {
"description": "This controls the general quality level of the output. Exact width and height will vary depending on the selected aspect ratio. For a video with approximately 480 or 720 pixel height use a 16:9 aspect ratio.",
"type": "string",
"default": "720p",
"enum": [
"480p",
"720p"
]
},
"aspect_ratio": {
"description": "Controls the approximate aspect ratio of the resulting video. Use \"adaptive\" to let the model pick automatically based on the prompt.",
"type": "string",
"default": "adaptive",
"enum": [
"16:9",
"4:3",
"1:1",
"3:4",
"9:16",
"21:9",
"adaptive"
]
},
"duration": {
"description": "Output duration in seconds: 4–15, or -1 for automatic duration. Automatic duration is determined from the prompt and reference content.",
"type": "integer",
"default": 5,
"maximum": 15,
"anyOf": [
{
"const": -1
},
{
"minimum": 4,
"maximum": 15
}
]
},
"watermark": {
"description": "When set to true a watermark is added indicating the output is AI generated.",
"type": "boolean",
"default": false
},
"generate_audio": {
"description": "When true the output video includes synchronized audio. When false a silent video is produced.",
"type": "boolean",
"default": true
},
"return_last_frame": {
"description": "When true the last frame of the generated video is also returned as a PNG (last_frame.png) alongside the video.",
"type": "boolean",
"default": false
},
"seed": {
"description": "A randomness initializer for image reproducability.",
"type": "integer",
"minimum": -1,
"maximum": 2147483647
}
}
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}