Ray Flash 2
Ray Flash 2 is Luma AI's fast video generation model designed for efficient, high-quality text-to-video and image-to-video creation.
Fast text-to-video and image-to-video generation
Ray Flash 2 is a video generation model developed by Luma AI, designed to produce AI-generated videos from text prompts and images. It is the speed-optimized variant within the Ray 2 model family, prioritizing throughput and fast iteration while maintaining visual quality. As part of the broader Ray lineup, it sits alongside Ray 2, Ray 1.6, and Photo Flash 1, giving users options across different speed and quality trade-offs.
Ray Flash 2 is well-suited for workflows that require rapid video generation or high-volume production, such as creative prototyping or iterative content development. It is accessible through multiple platforms, including ComfyUI's Partner Nodes system for visual AI workflows and the Codenteam Intersect platform for developer integrations. The model accepts both text and image inputs, supporting flexible generation modes for a range of creative and technical use cases.
What Ray Flash 2 supports
Text-to-Video
Generates video clips directly from text prompts, allowing creators to describe a scene and receive a rendered video output.
Image-to-Video
Animates one or more input images into video sequences, accepting up to two image URLs as starting frames.
Fast Generation
Optimized for speed as the flash variant of the Ray 2 family, enabling faster turnaround compared to standard Ray 2 for high-volume or iterative workflows.
ComfyUI Integration
Available as a Partner Node within ComfyUI, allowing direct incorporation into node-based visual AI pipelines without custom API setup.
Configurable Parameters
Supports multiple select-type inputs for controlling generation settings such as aspect ratio, resolution, or style options.
Ready to build with Ray Flash 2?
Get Started FreeCommon questions about Ray Flash 2
What is the context window for Ray Flash 2?
Ray Flash 2 has a context window of 1,000 tokens, as specified in the model metadata.
What input types does Ray Flash 2 accept?
Ray Flash 2 accepts multiple select inputs for configuration parameters as well as up to two image URLs, enabling both text-to-video and image-to-video generation.
How does Ray Flash 2 differ from Ray 2?
Ray Flash 2 is the speed-optimized variant within the Ray 2 family. It is designed for faster generation and higher throughput, making it suited for workflows that prioritize iteration speed.
Is there a known training data cutoff for Ray Flash 2?
No training date or knowledge cutoff is listed in the available metadata for Ray Flash 2.
Where can Ray Flash 2 be accessed?
Ray Flash 2 is available on MindStudio, through ComfyUI's Partner Nodes system, and via the Codenteam Intersect platform, among other integrations.
Parameters & options
Image URL to use as a start frame.
Image URL to use as an end frame.
Explore similar models
Luma Labs Ray 2
Luma AI's flagship video generation model that creates strikingly realistic, physically accurate video clips from text or image inputs.
Luma Labs Photon 1 Flash
Photon Flash 1 is a fast, efficient AI model designed for high-speed inference and responsive applications.
Luma Labs Photon 1
Luma Labs' photorealistic AI image generator built on a proprietary Universal Transformer architecture, delivering studio-quality 1080p images with exceptional prompt understanding and character consistency.
Google Veo 3.1 Fast
A fast video generation model from Google designed for quick, high-quality AI video creation via Vertex AI and the Gemini API.
Lightricks LTX-2.3 LoRA
LTX-2.3 LoRA is a fine-tuning extension for Lightricks' LTX-2.3 video generation model, enabling custom character, style, and camera control in AI-generated videos.
Kling Kling 3.0 Motion Control
Kling 3.0 Standard Motion Control transfers motion from reference videos to animate still images.
Start building with Ray Flash 2
No API keys required. Create AI-powered workflows with Ray Flash 2 in minutes — free.