imagestringrequired
Image to use as the first frame of the video.
Kling O3 Standard Reference to Video
30% OFF
kwaivgi/kling-video/o3/standard/reference-to-videoKling O3 Standard Reference to Video by Kuaishou generates a 3-15 second 720p video that keeps characters and objects from reference images consistent with optional native audio.
Try the model
Playground
Input
Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Image to use as the first frame of the video.
This field is required.
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each · up to 6
Additional reference image URLs. Together with `image`, at most 7 images are accepted; do not repeat `image` in this list.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Image to use as the last frame of the video.
Video duration in seconds (3-15s). Allowed values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
Whether to generate native audio for the video.
The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. Allowed values: customize, intelligent.
List of prompts for multi-shot video generation.
The aspect ratio of the generated image. Allowed values: 16:9, 9:16, 1:1.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "image": "https://static.sandbase.ai/examples/fb9a6cca-db34-4948-8787-c06984fb52dd/input/b747bb75-d99a-46be-a52e-a7e16e8e1a5f.png", "prompt": "@Element1 and @Element2 is having dinner at this table on @Image1" }
Kling O3 Standard Reference to Video
Kling O3 Standard reference-to-video, the cost-efficient O3 tier. A start frame plus up to 6 reference images keep characters, objects, and style consistent; refer to them as @Image1, @Image2 in the prompt.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 2,500 characters. |
image | image URL, required | — | Start frame. JPEG, PNG, or WebP URL. |
images | image URL[] (≤6) | — | Reference images, referred to as @Image1, @Image2, … in the prompt. |
end_image | image URL | — | Optional last frame. |
duration | 3–15 | 5 | Output length in seconds. |
generate_audio | boolean | false | Generate native audio with the clip. |
shot_type | customize / intelligent | customize | customize follows your multi_prompt shot list; intelligent lets the model plan the cuts. |
multi_prompt | object[] | — | Optional list of shots, each with its own prompt and duration. |
aspect_ratio | 16:9 / 9:16 / 1:1 | 16:9 | Output frame shape. |
Billing
You pay for output seconds: $0.084 without audio and $0.112 with generate_audio.
| Output | Without audio | With audio |
|---|---|---|
| 3s | $0.252 | $0.336 |
| 5s (default) | $0.42 | $0.56 |
| 10s | $0.84 | $1.12 |
| 15s | $1.26 | $1.68 |
Failed runs are not charged.
Prompting
- Name each reference in the prompt: “@Image1 walks into the room from @Image2”.
- Keep one clear subject per reference image.
Limits
- Clips are 3–15 seconds.
Also on SandBase
Other Kling O3 Standard endpoints and tiers: kwaivgi/kling-video/o3/standard/text-to-video, kwaivgi/kling-video/o3/standard/image-to-video, kwaivgi/kling-video/o3/standard/edit, kwaivgi/kling-video/o3/standard/video-to-video, kwaivgi/kling-video/o3/pro/reference-to-video, kwaivgi/kling-video/o3/4k/reference-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "kwaivgi/kling-video/o3/standard/reference-to-video",
"image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/speech-to-video/input_image_0.png",
"images": [
"https://static.sandbase.ai/examples/alibaba/wan/2.2/speech-to-video/input_image_0.png"
],
"prompt": "@Element1 and @Element2 is having dinner at this table on @Image1",
"duration": 8,
"shot_type": "customize",
"aspect_ratio": "16:9",
"generate_audio": false
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
imagesarray
Additional reference image URLs. Together with `image`, at most 7 images are accepted; do not repeat `image` in this list.
promptstringrequired
Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both.
durationinteger
Video duration in seconds (3-15s).
Default: 5
Possible values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
end_imagestring
Image to use as the last frame of the video.
shot_typestring
The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.
Default: "customize"
Possible values: "customize", "intelligent"
aspect_ratiostring
The aspect ratio of the generated image.
Default: "16:9"
Possible values: "16:9", "9:16", "1:1"
multi_promptarray
List of prompts for multi-shot video generation.
generate_audioboolean
Whether to generate native audio for the video.
Default: false
{
"model": "kwaivgi/kling-video/o3/standard/reference-to-video",
"image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/speech-to-video/input_image_0.png",
"images": [
"https://static.sandbase.ai/examples/alibaba/wan/2.2/speech-to-video/input_image_0.png"
],
"prompt": "@Element1 and @Element2 is having dinner at this table on @Image1",
"duration": 8,
"shot_type": "customize",
"aspect_ratio": "16:9",
"generate_audio": false
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/c7c574950d973894d1a2.jpg",
"source": "Kling AI official schema mirror",
"source_url": "https://kling.ai/document-api/guides/get-started/overview",
"url": "https://static.sandbase.ai/examples/fb9a6cca-db34-4948-8787-c06984fb52dd/output/18d6ad48-7049-44bf-bbf9-caca372b73a9.mp4"
}
]