Ray 3.2
Ray 3.2 is the latest video model from Luma Labs, producing cinematic 540p, 720p or 1080p clips of 5 or 10 seconds. It generates from a text prompt or animates between a first and last frame, re-renders existing footage into a new look while keeping its motion, and reframes a clip to a new aspect ratio by outpainting the canvas around the original frames. That range makes it a strong fit for trailers, cutscenes, and adapting game footage across landscape, square, and vertical formats.
See more
Ray 3.2 is the latest video model from Luma Labs, producing cinematic 540p, 720p or 1080p clips of 5 or 10 seconds. It generates from a text prompt or animates between a first and last frame, re-renders existing footage into a new look while keeping its motion, and reframes a clip to a new aspect ratio by outpainting the canvas around the original frames. That range makes it a strong fit for trailers, cutscenes, and adapting game footage across landscape, square, and vertical formats.
Connect Claude, Cursor, VS Code, or Codex to Layer’s MCP server and Ray 3.2 becomes a tool your agent can reach for — it picks the parameters, runs the generation, and shows you the result in the conversation.
https://mcp.app.layer.ai/mcpAsk your agent
“Use Ray 3.2 to animate a torch-lit dungeon corridor with a slow dolly forward.”
execute_forge({
"base_model_id": "ray-3-2",
"prompt": "A torch-lit dungeon corridor, slow dolly forward",
"batch_size": 1,
"duration_seconds": 5
})Authenticate with a personal access token, post the model’s own form, and poll the inference until it completes. Every field below is accepted by this endpoint.
# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/lumalabs-ray-3-2/inferences \
-H "Authorization: Bearer $LAYER_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A torch-lit dungeon corridor, slow dolly forward"
}'
# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
-H "Authorization: Bearer $LAYER_TOKEN"- prompt stringrequired
- Describe what to generate, or the change to make.
- aspect_ratio enumdefault LANDSCAPE_16_9_540p18 options
- The shape and size of the output.
- duration_seconds integerdefault 5
- Length of the generated clip, in seconds.
- guidance_file_first_frame file[]
- The frame the video starts on
- guidance_file_last_frame file[]
- The frame the video ends on
- guidance_file_init_video file[]
- The video to modify
- prompt_language string
- The language the prompt is written in, so it reaches the model as you meant it.
Why use Ray 3.2 for video?
Cinematic video generation
Ray 3.2 creates high-fidelity video content suitable for trailers, gameplay previews, and marketing materials with temporal consistency.
Flexible input modes
Generate from text prompts, reference images, or existing video. Supports various aspect ratios and durations for different content needs.
Production-ready output
Clean motion, stable framing, and coherent transitions make outputs ready for direct use in UA campaigns and social content.
Game trailers and cinematic previews
Create attention-grabbing trailers and gameplay previews that showcase your game at its best. High temporal consistency ensures smooth, professional results.
UA video creative at scale
Generate dozens of video ad variants for A/B testing across platforms. Rapid iteration lets performance teams optimize creative angles quickly.
Character animations and in-game cinematics
Bring characters to life with animated sequences for cutscenes, promotional materials, and social content.
FAQ
How much does Ray 3.2 cost? Is it free?+
How does Layer's pricing work?+
There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.
What Elo score does Ray 3.2 have?+
Other video models on Layer
Ray 2 Flash
Luma AI
High-speed variant of Ray 2, optimized for rapid video creation. Perfect blend of speed and quality.
Ray 2
Luma AI
Large-scale, state-of-the-art video model for stunning realistic and coherent 1080p motion.
LTX Video 2.5 Fast
Lightricks
Speed-optimized LTX 2.5 audio-video model with 720p–4K output and clips up to 20 seconds.
Wan 2.6
Alibaba
State-of-the-art multimodal video generation model from Alibaba, with native audio support
LTX Video 2.5 Fast Audio-to-Video
Lightricks
Speed-optimized LTX 2.5 mode that generates video timed to a supplied audio clip.
Veo 3
Next-gen video model with enhanced control over narrative, tone, and shot composition. Includes audio.