fal Adds Luma Ray 3.2 for Cinematic Video with Multi-Keyframe Control

falfal

fal has made LumaLabsAI's Ray 3.2 video generation model available on its platform, featuring multi-keyframe control, expressive facial performance, HDR + EXR outputs, and reframing + motion transfer. The update provides full API access to Ray 3.2's control surface, enabling developers to integrate advanced video creation capabilities.

fal now hosts Luma Ray 3.2, a video generation model from LumaLabsAI, on its serverless platform. This update introduces multi-keyframe control, expressive facial performance, HDR + EXR outputs, and reframing with motion transfer. For the first time, the full control surface for Ray 3.2 is accessible via API.
Model
Luma Ray 3.2
Capabilities
Multi-keyframe control, expressive facial performance, HDR + EXR outputs, reframing + motion transfer
Access
Full control surface via API
Video Tasks
Text-to-video, image-to-video
5s Video Pricing (540p)
$0.50
5s Video Pricing (1080p)
$2.00

The availability of Ray 3.2 on fal, alongside LumaLabsAI's UNI-1 multimodal reasoning image model, provides developers with tools for professional-grade generative media. Features like HDR + EXR outputs align with industry moves toward higher fidelity AI video, as seen with HeyGen's HyperFrames and fal's own LTX 2.3 Quality model. This expands options for precise video creation and editing, similar to Runway's Aleph 2.0 API for multi-shot video.

Luma Ray 3.2 is available on fal for text-to-video and image-to-video tasks, with pricing for 5-second videos at $0.50 for 540p, $1 for 720p, and $2 for 1080p. UNI-1 is also accessible for text-to-image generation and image editing. Both models can be tried on fal's platform, offering programmatic access for integration into custom applications.

View the full update on fal.ai
fal
fal
@fal
X

Ray3.2 from @LumaLabsAI is live on fal, day 0. - Multi-keyframe control - Expressive facial performance - HDR + EXR outputs - Reframing + motion transfer And for the first time, the full Ray control surface is available via API. https://t.co/tinyGQ7I2i

20retweets140likes
View on X

Still wondering? A few quick answers below.

Luma Ray 3.2 is a video generation model from LumaLabsAI that creates cinematic video from text prompts or reference images. It offers control over resolution, duration, and looping, along with new features for multi-keyframe control and expressive facial performance.

Ray 3.2 introduces multi-keyframe control for directing video changes, expressive facial performance, and support for HDR (High Dynamic Range) and EXR (OpenEXR) outputs. It also includes capabilities for reframing and motion transfer.

Developers can access Luma Ray 3.2 through fal's platform, where the model's full control surface is available via API. This allows for programmatic integration into custom applications for video generation and editing.

Luma UNI-1 is a multimodal reasoning model that can generate pixels with visual intelligence, strong taste, and reference following. It is also available on fal for tasks such as text-to-image generation and image editing.

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Share this update