WaveSpeedImage to videoComing soon
WaveSpeedkwaivgi/kling-video-o3-std/reference-to-video
kwaivgi/kling-video-o3-std/reference-to-video is an image to video tool from WaveSpeed that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.
This tool is listed but not yet available to run.
Price pendingPricing
Price pending.
Limits
- Runs
- In the background
- Returns
- video
- Longest queue wait
- 3600s
- Run deadline
- 3600s
- Largest inline input
- 1024 KB
- Largest input file
- 500 MB
- Largest output
- 4768 MB
- Outputs per run
- 16
Input
| Field | Kind | Default | Description |
|---|---|---|---|
sound | true or false | false | Whether to generate audio for the video. |
video | URL or file | — | The reference video URL. Supported formats: .mp4/.mov, up to 200MB, 3-15 seconds (longer videos are trimmed to 15s), width and height between 700px and 3840px. |
images | list | — | Reference images. With a reference video: image elements <= 4; without a reference video: <= 7 |
prompt | text | — | The positive prompt for the generation. Refer to input images as <<<image_1>>>, <<<image_2>>>, ... in array order and the input video as <<<video_1>>>. |
duration | one of 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | 5 | The duration of the generated media in seconds (3-15). |
shot_type | one of customize, intelligence | customize | Shot type for the generation. |
aspect_ratio | one of 16:9, 9:16, 1:1 | 16:9 | The aspect ratio of the generated video. |
multi_prompt | JSON | — | List of multi-prompt elements for the generation. |
keep_original_sound | true or false | true | Whether to keep the original sound from the reference video. |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "wavespeed",
"model": "kwaivgi/kling-video-o3-std/reference-to-video",
"input": {}
}'