Seedance 2.0 Reference To Video

Name: Seedance 2.0 Reference To Video
Author: Nodespell Team

Official

Seedance 2.0 video generation guided by images, video clips, or audio.

Nodespell AI

AI / Video / Bytedance

Seedance 2.0 video generation guided by images, video clips, or audio.

This is the most flexible Seedance 2.0 variant in the batch. Use it when external media should shape the result, and name each reference in the prompt with @Image, @Video, or @Audio so the model has a clear role for each asset.

Keep the reference set intentional. Too many loosely related references can weaken direction; a small set with explicit roles usually gives a clearer shot. Duration, aspect ratio, 1080p-capable output, generated audio, and seed remain available.

Inputs (4)

Prompt

String

Text prompt describing the generated video and how to use references.

RequiredMulti InputMin: 0Max: 100

Reference Images

String

Reference images for subject, style, or scene guidance. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.

Multi InputMin: 0Max: 100

Reference Videos

String

Reference videos for motion, style, or scene guidance. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Resolution must be between ~480p and ~720p. Total files across all modalities must not exceed 12.

Multi InputMin: 0Max: 100

Reference Audio

String

Reference audio for audio-guided video generation. Supported formats: MP3, WAV. Up to 3 files, combined duration must not exceed 15 seconds. Max 15 MB per file. At least one reference image or video is required when audio is provided. Total files across all modalities must not exceed 12.

Multi InputMin: 0Max: 100

Parameters (6)

Prompt

String

Text prompt describing the generated video and how to use references.

Required

Default:

Duration

String

Video duration in seconds, or auto to let the model decide.

Default: auto

Resolution

String

Video resolution. 480p is cheaper; 720p balances cost and detail; 1080p is highest quality.

Default: 720p

Aspect Ratio

String

Aspect ratio of the generated video.

Default: auto

Generate Audio

Boolean

Generate synchronized audio for the video.

Default: true

Seed

Number

Random seed. Leave at -1 for a random result.

Outputs (1)

Output

Inferred

Generated video output.

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Keywords (7)

Video GenerationMultimodal GenerationConditional GenerationPrompt ConditioningAspect ControlResolution Control

Use in Workflow