Kwaivgi Kling V3 Turbo Std Image To Video
Playground
Try it on WaveSpeedAI!Kling V3 Turbo Standard Image to Video converts first-frame images and optional prompts into 720P videos, with single-prompt generation and multi-shot storyboard support. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Kling V3 Turbo Standard Image-to-Video generates fast, affordable 720p videos from a first-frame reference image. It supports optional text guidance and multi-shot storyboard generation.
Why Choose This?
-
First-frame image animation
Turn a still image into a video using the image as the starting frame. -
Fast 720p output
Use the standard model for efficient image-to-video generation. -
Lower cost generation
Create and iterate on image-driven videos at a lower per-second price. -
Multi-shot storyboard support
Usemulti_promptto define multiple prompted segments with separate durations. -
Standard video output
The generated video is returned as a URL in the standard WaveSpeed prediction response.
Parameters
| Parameter | Required | Description |
|---|---|---|
| image | Yes | First-frame reference image URL. JPG and PNG images work best. |
| prompt | No | Optional text prompt to guide the generated video. Mutually exclusive with multi_prompt. |
| multi_prompt | No | Multi-shot storyboard. Each item includes a prompt and duration. Mutually exclusive with prompt. |
| duration | No | Video duration in seconds for single-prompt generation. Options: 3 to 15. Default: 5. |
How to Use
- Upload an image — Provide the first-frame reference image.
- Enter a prompt (optional) — Describe the desired motion, camera movement, or scene change.
- Or create a storyboard — Use
multi_promptto define multiple prompted segments. - Set duration — Choose the video duration for single-prompt generation, or set durations per shot in
multi_prompt. - Submit — Generate the animated video output.
Output
Returns generated video URL(s) in the standard WaveSpeed prediction response.
The generated video is returned as MP4 video.
Pricing
Pricing is $0.112 per second.
WaveSpeed bills by the generated video duration. If multi_prompt is provided, billing uses the selected duration plus the sum of all segment durations.
| Generated Duration | Price |
|---|---|
| 3s | $0.336 |
| 5s | $0.56 |
| 10s | $1.12 |
| 15s | $1.68 |
Billing Rules
- Billing is based on generated video duration.
- Single-prompt requests use the
durationparameter. multi_promptrequests usedurationplus the sum of all segment durations.- Each second costs $0.112.
Best Use Cases
- Image animation — Animate still images into short video clips.
- Affordable video drafts — Test image-to-video ideas at lower cost.
- Product motion concepts — Create motion previews from product or object images.
- Character and scene animation — Add movement to portraits, scenes, or illustrated frames.
- Storyboard generation — Build multi-shot videos from one starting image.
Pro Tips
- Use a sharp, high quality image with a clear subject.
- Add motion and camera details in the prompt for stronger control.
- Use
multi_promptwhen you want multiple guided segments. - Keep total
multi_promptduration within the model limit. - Make sure the image URL is publicly accessible.
Notes
imageis required.promptis optional.promptandmulti_promptare mutually exclusive.durationis used for single-prompt generation.multi_promptsupports per-shot durations.- The total generated duration must not exceed 15 seconds.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": "5"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v3-turbo-std/image-to-video" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| image | string | Yes | - | First-frame reference image. Supported formats: .jpg/.jpeg/.png; max 50MB; min 300px per side; aspect ratio within 1:2.5 to 2.5:1. | |
| prompt | string | No | - | Optional text prompt to guide the video. Mutually exclusive with multi_prompt. | |
| multi_prompt | array<object> | No | - | 0 ~ 6 items | Multi-shot storyboard. Total duration must not exceed 15 seconds. Mutually exclusive with prompt. |
| duration | string | No | 5 | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Video length in seconds. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |