Ray 2
Ray 2 is a video generation model from Luma Labs that creates videos from text prompts and reference images.
Luma LabsText and image-driven video generation
Ray 2 is a video generation model developed by Luma Labs and released in January 2025. It accepts text prompts alongside optional start and end frame images to guide video output, giving users control over how a generated clip begins and ends. The model supports configurable duration, resolution, aspect ratio, and looping, making it adaptable to a range of output formats.
Ray 2 is suited for workflows that require structured video generation with defined visual anchors, such as animating a still image or producing a looping clip from a described scene. Its input design — particularly the start and end frame controls — allows creators to constrain the motion and composition of generated video rather than relying solely on open-ended generation. The model is available through MindStudio without requiring separate API key setup.
What Ray 2 supports
Text-to-Video Generation
Generates video clips from natural language prompts using a 1000-token context window to interpret scene descriptions.
Start Frame Control
Accepts an image URL as the first frame of the generated video, anchoring the visual starting point of the clip.
End Frame Control
Accepts a second image URL to define the final frame, allowing the model to interpolate motion between two visual states.
Aspect Ratio Selection
Supports selectable aspect ratios so output video dimensions can be matched to specific platform or display requirements.
Resolution Control
Offers selectable resolution settings, letting users balance output quality against generation constraints.
Loop Mode
Includes a looping option that produces seamlessly repeating video clips, useful for animated backgrounds or GIF-style content.
Duration Selection
Allows users to specify clip length via a select input, giving control over how long the generated video runs.
Ready to build with Ray 2?
Get Started FreeCommon questions about Ray 2
What is the context window for Ray 2?
Ray 2 has a context window of 1000 tokens, which applies to the text prompt used to describe the video scene.
Who makes Ray 2?
Ray 2 is developed and published by Luma Labs. It is provided as a first-party model on MindStudio.
When was Ray 2 released?
Ray 2 was released in January 2025.
Can I use images as inputs when generating video with Ray 2?
Yes. Ray 2 accepts image URLs for both a start frame and an end frame, allowing you to anchor the beginning and end of the generated clip to specific images.
What output formats and settings can I configure?
You can configure duration, resolution, aspect ratio, and whether the video loops. These are all selectable inputs available when using the model.
Is pricing information available for Ray 2?
Published pricing details for Ray 2 are not listed in the current metadata. Check MindStudio's pricing page or the Luma Labs website for the latest cost information.
Documentation & links
Parameters & options
Image URL to use as a start frame.
Image URL to use as an end frame.
Explore similar models
Luma LabsRay 3.2
Luma LabsRay Flash 2
Ray Flash 2 is a video generation model from Luma Labs designed for fast video creation with configurable resolution, aspect ratio, and keyframe inputs.
Luma LabsUNI 1.1 Max
UNI 1.1 Max is an image generation model from Luma Labs supporting reference images, style selection, and web search.
ByteDanceSeedance 2.5 Turbo
Seedance 2.5 Turbo is a video generation model from ByteDance that supports text-to-video, image-to-video, and video editing modes.
Black Forest LabsFLUX 3 Video
FLUX 3 Video is a video generation model from Black Forest Labs that supports audio, keyframes, and video continuation.
X.aiGrok Imagine 1.5
Grok Imagine 1.5 is a video generation model from X.ai that accepts text, image, and video inputs to produce generated video output.
Start building with Ray 2
No API keys required. Create AI-powered workflows with Ray 2 in minutes — free.