Back to Nodes
Luma Ray 2

Luma Ray 2

Official

Generate high-quality 5s and 9s videos at 720p resolution, faster and more affordably than Ray 2.

Nodespell AI
AI / Video / Luma

Generate high-quality 5s and 9s videos at 720p resolution, faster and more affordably than Ray 2.

Model Overview

Ray Flash 2 is a sophisticated text-to-video generation model designed for creatives. It leverages Luma's advanced multi-modal architecture to produce realistic videos with coherent motion and detailed visuals based on your text prompts. 🎬

Best At

This model excels at generating dynamic and visually rich video clips. It's particularly strong in creating cinematic scenes, natural motion sequences, physics-based simulations, and detailed close-ups. If you need high-fidelity video content that brings your descriptions to life, Ray Flash 2 is an excellent choice.

Limitations / Not Good At

While powerful, Ray Flash 2 is currently focused on text-to-video generation. Features like image-to-video, video-to-video transformation, and advanced video editing capabilities are planned for future releases.

Ideal Use Cases

  • Creating animated illustrations for blog posts or articles.
  • Generating short, engaging social media video content.
  • Visualizing concepts for presentations or storyboards.
  • Producing atmospheric B-roll footage for videos.
  • Experimenting with surreal or abstract visual ideas.

Input & Output Format

  • Input: Text prompt (string), optional start/end images (string/URL), duration (integer), aspect ratio (string), loop (boolean), camera concepts (array).
  • Output: Video file (URI).

Performance Notes

Ray Flash 2 is optimized for speed and cost-effectiveness compared to its predecessor, Ray 2, while maintaining high video quality.

Inputs (3)

Prompt

String

Text prompt for video generation

Multi InputMin: 0Max: 100

Start Image

String

An optional first frame of the video to use as the starting frame.

Min: 0Max: 100

End Image

String

An optional last frame of the video to use as the ending frame.

Min: 0Max: 100
Parameters (11)

Loop

Boolean

Whether the video should loop, with the last frame matching the first frame for smooth, continuous playback.

Default: false

Prompt

String

Text prompt for video generation

Default:

Duration

Number

Duration of the video in seconds

Default: 5

Aspect Ratio

String

Aspect ratio of the generated video

Default: 16:9

Concepts

String

List of camera concepts to apply to the video generation, separate with comma

Default:

advanced

Inferred

videoSettings

Inferred

availableConcepts

String

List of camera concepts to apply to the video generation

Default: truck_left, pan_right, pedestal_down, low_angle, pedestal_up, selfie, pan_left, roll_right, zoom_in, over_the_shoulder, orbit_right, orbit_left, static, tiny_planet, high_angle, bolt_cam, dolly_zoom, overhead, zoom_out, handheld, roll_left, pov, aerial_drone, push_in, crane_down, truck_right, tilt_down, elevator_doors, tilt_up, ground_level, pull_out, aerial, crane_up, eye_level

The concepts must be in the list below

String
Default:

model

String
Default: ray-flash-2

resolution

String
Default: 540p
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

📍 London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Luma

Input

TextImage

Output

Video

Keywords

Video GenerationText To SpeechAspect ControlResolution ControlLength Control
Use in Workflow