Back to Nodes
Seedance 2.0 Text To Video

Seedance 2.0 Text To Video

Official

Seedance 2.0 text-to-video for scene ideas without reference media.

Nodespell AI
AI / Video / Bytedance

Seedance 2.0 text-to-video for scene ideas without reference media.

Use this variant when the written prompt is the main creative source. It is a direct way to test motion, pacing, and camera direction from text alone, with settings for resolution, duration, aspect ratio, optional generated audio, and seed.

Choose it over the fast variant when 1080p detail matters. Add references only when the shot depends on a source image, video, or audio cue; that is what the reference-to-video variants are for.

Model Examples (5)

Example Index01 / 05
Example 01

Example 1

Short dramatic monologue aimed at film and TV creators, framed as a broader statement about human indifference.

Source Inputs01
Prompt

Single continuous cinematic shot, intimate medium close-up of a middle-aged man in a dim emergency shelter corridor lit by practical fluorescent lights, quiet background haze, realistic skin texture, shallow depth of field, documentary-drama realism, restrained camera movement. He faces camera with exhausted intensity and delivers one short emotional monologue in clear sync sound: "The danger was never the fire. It was how quickly we learned to look away from each other." His voice is controlled but shaken, with a slight break on "look away," then a hard, steady finish. Small movements only: subtle swallow, one blink, shoulders held still, no exaggerated gestures, no crowd crossing frame, no subtitles, no text on screen, no jump cuts.

Parameters05
Prompt
Single continuous cinematic shot, intimate medium close-up of a middle-aged man in a dim emergency shelter corridor lit by practical fluorescent lights, quiet background haze, realistic skin texture, shallow depth of field, documentary-drama realism, restrained camera movement. He faces camera with exhausted intensity and delivers one short emotional monologue in clear sync sound: "The danger was never the fire. It was how quickly we learned to look away from each other." His voice is controlled but shaken, with a slight break on "look away," then a hard, steady finish. Small movements only: subtle swallow, one blink, shoulders held still, no exaggerated gestures, no crowd crossing frame, no subtitles, no text on screen, no jump cuts.
Duration
8
Resolution
480p
Aspect Ratio
16:9
Generate Audio
true
text-to-videodialoguemonologuedrama
Response
Inputs (1)

Prompt

String

Text prompt describing the scene, style, camera, and motion.

RequiredMulti InputMin: 0Max: 100
Parameters (6)

Prompt

String

Text prompt describing the scene, style, camera, and motion.

Required
Default:

Duration

String

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

Default: auto

Resolution

String

Video resolution. 480p is faster and 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

Category

AI / Video / Bytedance

Input

Text

Output

Video

Keywords

Video GenerationPrompt ConditioningAspect ControlResolution ControlLength Control
Use in Workflow