Luma Ray 3.2
Luma's Ray 3.2 video model. Text to video, and image to video from a first and optional last frame, 5 or 10 seconds from 360p to 1080p. Frames can't be combined with 10-second clips.
Preview
Parameters and limits may change before this model is generally available.
- Model id:
luma/ray-3.2 - Type: Video, from Luma AI
- Modes: Text to video, Image to video
- Prompt: up to 6,000 characters
- Canceling: Only while queued. Generations finish within seconds once submitted.
Parameters
Set these in params. Anything left out takes the default, which is what the price estimate assumes.
| Parameter | Accepted values | Default |
|---|---|---|
duration_seconds | 5, 10 | 5 |
resolution | 720p, 360p, 540p, 1080p | 720p |
aspect_ratio | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 | 16:9 |
num_outputs | 1 only | 1 |
output_format | mp4 | provider's |
References
Pass media in references, each with a role and an upload_id or HTTPS url (Uploads). When mode is left out it is inferred from the roles.
| Role | Used as | At most |
|---|---|---|
first_frame | First frame of the video | 1 |
last_frame | Last frame of the video | 1 |
Pricing
Billed per request, varying by resolution and duration_seconds. The full price list for your account is on the dashboard's billing page and in pricing from GET /v1/models/luma%2Fray-3.2. Each request reserves its maximum price and is charged for what was produced (Pricing and credits).
Examples
Text to video
import { RawFrame } from "@rawframe/sdk";
const rf = new RawFrame();
const generation = await rf.generations.createAndWait({
model: "luma/ray-3.2",
prompt: "A paper boat drifting down a rain-soaked city gutter, macro lens, golden hour",
params: { duration_seconds: 5, aspect_ratio: "16:9", resolution: "720p" },
});
console.log(generation.outputs?.[0]?.url);