Gemini Omni Flash 1.2
Text to video · Image to video · Video editing
Starting price $0.0433 / second
By Luma AI
Luma Ray 3.2 makes 5 or 10 second clips from a prompt, animates a first frame toward an optional last frame, and restyles videos you upload.
luma/agent/ray/v3.2/video-to-videoThis model has other modes with their own ids: luma/agent/ray/v3.2/text-to-video, luma/agent/ray/v3.2/image-to-video.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "luma/agent/ray/v3.2/video-to-video",
"input": {
"prompt": "Turn the scene into a hand-painted watercolor world with soft paper texture. Keep the people, their movement and the camera path the same.",
"video_url": "https://example.com/input.mp4"
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "luma/agent/ray/v3.2/video-to-video", "quote_id": "QUOTE_ID", "input": {"prompt":"Turn the scene into a hand-painted watercolor world with soft paper texture. Keep the people, their movement and the camera path the same.","video_url":"https://example.com/input.mp4"}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | Text prompt describing how to edit the source video. |
video_urlrequired | string (URL) | URL of the source video to edit. |
user | string | Optional opaque identifier for the end user making the request. |
start_image_url | string (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. |
resolution | string (enum) | Resolution of the edited video. |
duration | string (enum) | Duration of the edited video. |
edit_strength | string (enum) | 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. |
auto_controls | boolean | Let the model derive the edit conditioning schedule from the source video. Cannot be combined with edit_strength. |
hdr | boolean | Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p. |
exr_export | boolean | Also export an EXR file alongside the MP4. Requires hdr=true and HDR access. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Luma Ray 3.2 renders at 540p, 720p or 1080p in six aspect ratios from 21:9 to 9:16. Text clips run 5 or 10 seconds, and a loop setting makes a 5 second clip whose end runs straight back into its start.
The image mode starts from your picture and can end on a last frame. The edit mode reworks a clip you upload from a written instruction; an edit strength scale runs from adhere, close to the source, through flex to reimagine, and a restyled first frame can steer the look.
Check object continuity and framing; replay the boundary when requesting a loop.