ByteDance/seedance2-0-r2v
Seedance 2.0 R2V is ByteDance's latest reference-media-to-video AI model, designed to generate videos from reference images, videos, or audio with prompt guidance and up to 4k output.
Output: $0.08 / use or 12 uses / $1
Input
prompt * string
Text prompt for video generation
reference_images list
reference_images for image-to-image generation. Up to five images
Click to add more images
reference_audios list
reference_audios for image-to-image generation. Up to five images
Click to add more images
reference_videos list
reference_videos for image-to-image generation. Up to five images
Click to add more images
duration int
Video duration in seconds
resolution enum
Video resolution
aspect_ratio enum
Video aspect ratio for text-to-video generation.
audio boolean
audio
Reset
Output
{
  "task_id": "d9zzvghifs95q8fkfd",
  "user_id": 1,
  "version": "c06a3d987be881bfe7a5972672bef244b74123de30a4604333128a68f6c1ccf3",
  "error": null,
  "total_time": 87.9,
  "predict_time": 87.9,
  "logs": null,
  "output": [
    "https://vmodel.ai/data/dev/model/bytedance/seedance2-0-r2v/iw0YzjRmpo_0.mp4"
  ],
  "status": "succeeded",
  "create_at": 1746492954,
  "completed_at": 1746493015,
  "input": {
    "resolution": "480p",
    "aspect_ratio": "auto",
    "prompt": "Extend Video 1 by 11 seconds; a car drives smoothly toward a desert oasis, the cattle and horses from the photo appear ahead, and the background music comes from Audio 1.",
    "duration": 11,
    "audio": true,
    "byteplus_fallback": false,
    "reference_images": [
      "https://vmodel.ai/data/dev/model/bytedance/seedance2-0-r2v/v2-ac0db0a7e87773160ebef79d97fb8871_r.jpg"
    ],
    "reference_audios": [
      "https://vmodel.ai/data/dev/model/bytedance/seedance2-0-r2v/audio.mp3"
    ],
    "reference_videos": [
      "https://vmodel.ai/data/dev/model/bytedance/seedance2-0-r2v/origin.mp4"
    ]
  }
}
Generated in: 87.9 seconds
Download
Examples
Pricing
Model pricing for bytedance/seedance2-0-r2v. Looking for volume pricing? Get in touch.
When
⚙ using this model
$0.0800
per use
or 12 uses for $1
Readme

Loading...