Video
Luma Ray 3.2
Generate a shot from text with Luma Ray 3.2.
- Text to video
- Image to video
- Video editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Luma Ray 3.2. Review your own result before publishing.
A starting point.
Plan one scene, or use the separate image/video operations to animate a still or edit footage.
Before you publish.
Check object continuity and framing; replay the boundary when requesting a loop.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
The default needs prompt. Choose duration of 5s or 10s and resolution of 540p, 720p or 1080p. loop supports 5s text generations.
Image-to-video adds image_url and end_image_url. Video editing requires video_url; auto_controls cannot be combined with edit_strength.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for luma/agent/ray/v3.2/text-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 6000 |
aspect_ratio | Text | Optional | 3:4, 4:3, 1:1, 9:16, 16:9, 21:9 |
duration | Text | Optional | 5s, 10s |
loop | On/off | Optional | — |
resolution | Text | Optional | 540p, 720p, 1080p |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Other modes and their inputs
Open the operation you need and check its inputs. Settings from one mode do not automatically apply to another.
Image to videoluma/agent/ray/v3.2/image-to-video
Supported inputs
These fields come from the current studio form for luma/agent/ray/v3.2/image-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 6000 |
aspect_ratio | Text | Optional | 3:4, 4:3, 1:1, 9:16, 16:9, 21:9 |
end_image_url | Text | Optional | — |
image_url | Text | Optional | Min. characters: 1 |
keyframe_indexes | List | Optional | Min. items: 1 · Max. items: 64 |
loop | On/off | Optional | — |
resolution | Text | Optional | 540p, 720p, 1080p |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Video editingluma/agent/ray/v3.2/video-to-video
Supported inputs
These fields come from the current studio form for luma/agent/ray/v3.2/video-to-video. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 6000 |
video_url | Text | Required | Min. characters: 1 |
auto_controls | On/off | Optional | — |
duration | Text | Optional | 5s, 10s |
edit_strength | Text | Optional | — |
keyframe_indexes | List | Optional | Min. items: 1 · Max. items: 64 |
resolution | Text | Optional | 540p, 720p, 1080p |
start_image_url | Text | Optional | — |
user | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Luma Ray 3.2 through the API.
Start with this model ID for the endpoint featured on this page:
luma/agent/ray/v3.2/text-to-video
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Available modes
- text-to-video ·
luma/agent/ray/v3.2/text-to-video - image-to-video ·
luma/agent/ray/v3.2/image-to-video - video-to-video ·
luma/agent/ray/v3.2/video-to-video
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.