ReplicateImage to videoComing soon
kwaivgi/kling-v3-video
kwaivgi/kling-v3-video is an image to video tool from Replicate 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.
Priced by usagePricing
generate_audio / mode: false (default) / standard $0.2184, false (default) / pro (default) $0.2912, true / standard $0.3276, true / pro (default) $0.4368, false (default) / 4k $0.546, true / 4k $0.546 per second. Billed on duration, default 5.
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 |
|---|---|---|---|
prompt required | text | — | Text prompt for video generation. Max 2500 characters. |
mode | JSON | pro | 'standard' generates 720p, 'pro' generates 1080p, '4k' generates 4K. |
duration | number (whole) 3 to 15 | 5 | Video duration in seconds. |
end_image | text | null | Last frame image. Requires start_image. Supports .jpg/.jpeg/.png, max 10MB, min 300px. |
start_image | text | null | First frame image. Supports .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1. |
aspect_ratio | JSON | 16:9 | Aspect ratio. Ignored when start_image is provided. |
multi_prompt | text | null | JSON array of shot definitions for multi-shot mode. Each shot: {"prompt": "...", "duration": N}. Max 6 shots, min 1s per shot, total must equal duration. |
generate_audio | true or false | false | Generate native audio for the video. |
negative_prompt | text | Things you do not want to see in the video. Max 2500 characters. |
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": "replicate",
"model": "kwaivgi/kling-v3-video",
"input": {
"prompt": "<prompt>"
}
}'