Seedance 2.0 V2V
[Core Function] Seedance 2.0 V2V is ByteDance’s flagship multimodal video-to-video model. [Strengths] It allows powerful editing and stylization of input videos by supporting mixed references (text, images, video, and audio) and producing multi-shot 15s outputs. [Best For] Highly recommended for: complex video-to-video transformations, restyling existing footage, and creating dynamic multi-shot edits. [Limitations] Do NOT use this model for simple still-image generation (use Seedream instead). [Routing] Use this model by default for any video editing or video-to-video generation tasks.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Seedance 2.0 video-to-video request. Official supported combinations are cumulative (not mutually exclusive): video_urls is always required; optionally add prompt, reference_images, and/or audio_urls. First/last frame parameters are not supported on V2V.
Required. One to three reference video URLs.
1 - 3 elementsVideo URL.
1Optional. Video description. Maximum 10000 characters. Use [Image n], [Video n], and [Audio n] placeholders when referencing optional inputs. Recommended prompt length: under 1000 words.
1 - 10000Optional. Up to 9 reference image URLs for style or content guidance. Use [Image n] placeholders in prompt.
1 - 9 elementsImage URL or Base64 data.
1Optional. Up to 3 reference audio URLs. Use [Audio n] placeholders in prompt.
1 - 3 elementsAudio URL.
1Aspect ratio of the generated video.
21:9, 16:9, 4:3, 1:1, 3:4, 9:16 Output resolution of the video.
480p, 720p, 1080p, 4k Video duration in seconds (4-15 seconds).
4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Random seed for reproducible generation. Use -1 for random.
-1 <= x <= 4294967295Whether to keep the camera fixed during generation.
Whether to generate audio.
Task expiration time in seconds.
3600 <= x <= 259200Whether to return the last frame of the generated video.