Back to Nodes
FLUX.3 Text to Video

FLUX.3 Text to Video

Official

Generate a 5–20 second FLUX.3 video from text with optional native audio. Choose this mode for prompt-first shots that need strong composition, motion

Nodespell AI
AI / Video / Black Forest Labs

Generate a 5–20 second FLUX.3 video from text with optional native audio. Choose this mode for prompt-first shots that need strong composition, motion, and typography without source media. It supports 720p or 1080p output and landscape, square, portrait, or automatic framing.

Inputs (1)

Prompt

String

Text prompt describing the scene, motion, camera direction, and audio intent.

RequiredMulti InputMin: 0Max: 100
Parameters (6)

Prompt

String

Text prompt describing the scene, motion, camera direction, and audio intent.

Required
Default:

Duration

String

Generated video duration from 5 to 20 seconds, or auto for model-selected length.

Default: auto

Resolution

String

Output resolution. 1080p preserves more detail and takes more credits.

Default: 720p

Aspect Ratio

String

Output framing, or auto to infer it from the prompt and source media.

Default: auto

Generate Audio

Boolean

Generate synchronized audio with the video.

Default: true

Safety Tolerance

Number

Content safety tolerance from 0 (strictest) to 4 (most permissive).

Default: 2
Outputs (1)

Output

Inferred

Generated video output.

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Black Forest Labs

Input

Text

Output

Video

Keywords (7)

Video GenerationPrompt ConditioningAspect ControlResolution ControlLength ControlNative Audio
Use in Workflow