← All models
Luma Ray 3.2 re-renders an existing video into new cinematic motion guided by a text prompt, preserving the source's look and movement while controlling resolution, duration, and HDR.
Example
Details
- Accepts
- text + image + video
Pricing
- Price
- 3.75 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| hdr | boolean | Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with loop. |
| loop | boolean | Generate a seamless loop. Only valid for standard-dynamic-range generations without an end frame or keyframes. |
| promptrequired | string | Text prompt describing the motion/scene to generate. |
| duration | stringenum: 5s, 10s | Duration of the generated video. 10s requires multi-keyframe input (keyframes / keyframe_indexes); it is not supported with a single image_url / end_image_url anchor. |
| image_url | — | URL of the image used as the first frame of the video. Provide either image_url (optionally with end_image_url) or keyframes — the two anchoring modes are mutually exclusive. |
| keyframes | — | |
| exr_export | boolean | Also export an EXR file alongside the MP4. Requires hdr=true and HDR access. |
| resolution | stringenum: 540p, 720p, 1080p | Resolution of the generated video. Higher resolutions cost more. |
| aspect_ratio | stringenum: 3:4, 4:3, 1:1, 9:16, 16:9, 21:9 | Aspect ratio of the generated video. |
| end_image_url | — | Optional URL of an image used as the last frame. When set, the model interpolates between image_url and end_image_url. Cannot be combined with keyframes. |
| keyframe_indexes | — | Output-frame positions (duration x 24fps: 5s -> 0-120, 10s -> 0-240) where each keyframes[i] is anchored. Non-negative, unique, and the same length as keyframes. |
| user | — | |
| controls | — | Per-signal conditioning controls (pose, depth, normals, trajectory, face) for finer control than edit_strength. Cannot be combined with auto_controls. |
| video_url | string | URL of the source video to edit. |
| auto_controls | boolean | Let the model derive the edit conditioning schedule from the source video. Cannot be combined with edit_strength. |
| edit_strength | — | How closely the edit preserves the source video. 'adhere_*' stays closest to the source, 'flex_*' is balanced, and 'reimagine_*' diverges most. Leave unset to use Luma's default. Cannot be combined with auto_controls. |
| start_image_url | — | Optional URL of an image to use as the edited video's first frame — e.g. a restyled version of the source's opening frame to steer the look of the edit. Leave unset to let the model derive the first frame from the source video. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The generated video. |
| exr_file | — | The generated EXR sidecar when exr_export is true. This may be a single EXR file or a ZIP package depending on Luma's export shape. |