Skip to content

Kling 3.0 Pro Image to Video

Integrate

Model id kling-video/v3/pro/image-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/kling-video/v3/pro/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
    "duration": 5,
    "generate_audio": false
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.56 560 API credits Run it on this page

Get API key
Kling Image to Video Native audioReference inputs3–15 s #cinematic#multi-shot

Animates a still image into a 3 to 15 second clip with native sound, an optional last frame and multi-shot prompts.

Examples

Input
Output · ~157 s

PromptThe paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.

5 sgenerate_audio: false$0.56 · 560 API credits

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

154 / 2500

Text instructions used to generate the video. Supply exactly one of prompt or multi_prompt.

•required start_image_url
Drop a file, or

URL pointing to the image used for video generation. File size must not exceed 50 MB; width and height must each be at least 300px, with an aspect ratio between 0.40 and 2.50.

duration 5 s

Output video length, measured in seconds.

Advanced negative_prompt · end_image · shot_type · cfg_scale · multi_prompt · elements
0 / 2500
end_image_url
Drop a file, or

URL pointing to the image used at the video's end. File size must not exceed 50 MB; width and height must each be at least 300px, with an aspect ratio between 0.40 and 2.50.

shot_type default customize

Choose how multi-shot generation plans its shots; selecting 'intelligent' delegates the shot structure to the model.

default 0.5

Set how closely generation follows your prompt using CFG, short for Classifier Free Guidance.

Prompt list that splits the video into multiple shots when supplied.

Characters or objects included as video elements, addressed in the prompt using @Element1, @Element2, etc. For each example, provide either a video or a set containing a frontal image plus reference images.

POST /run/kling-video/v3/pro/image-to-video?wait=20 quote → $0.56
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/kling-video/v3/pro/image-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
    "image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
    "duration": 5,
    "generate_audio": false
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Kling 3.0 Pro Image to Video

Kling's flagship image-to-video model keeps the subject of the start image stable while adding natural motion, camera moves and, by default, matching sound and speech. Give it an end image to control where the shot lands, split one generation into several shots with per-shot prompts, or pin recurring characters and objects with reference elements. The frame shape follows the start image.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptoptional
Typestring | null
≤ 2,500 characters
Text instructions used to generate the video. Supply exactly one of prompt or multi_prompt.
multi_promptoptional
Typeobject[]
Prompt list that splits the video into multiple shots when supplied.
multi_prompt[].promptrequired
Typestring
Text instructions for the current shot.
multi_prompt[].durationoptional
Typeenum
Default5
123456789101112131415
Length of the current shot, measured in seconds.
start_image_urlrequired image
Typeurl · image
URL pointing to the image used for video generation. File size must not exceed 50 MB; width and height must each be at least 300px, with an aspect ratio between 0.40 and 2.50.
durationoptional
Typeenum
Default5
3456789101112131415
Output video length, measured in seconds.
generate_audiooptional
Typeboolean
Defaulttrue
Native video audio generation toggle, supporting voices in Chinese or English and automatically translating any other language into English. For English speech, write acronyms and proper nouns in uppercase and everything else in lowercase.
end_image_urloptional end_image
Typeurl · image
URL pointing to the image used at the video's end. File size must not exceed 50 MB; width and height must each be at least 300px, with an aspect ratio between 0.40 and 2.50.
elementsoptional
Typeobject[]
Characters or objects included as video elements, addressed in the prompt using @Element1, @Element2, etc. For each example, provide either a video or a set containing a frontal image plus reference images.
elements[].frontal_image_urloptional
Typeurl · image
Front-facing image showing the element's main view. File size must not exceed 50 MB; width and height must each be at least 300px, with an aspect ratio between 0.40 and 2.50.
elements[].reference_image_urlsoptional
Typeurl[] · image
Supply 1–3 additional reference images showing different angles. Each image must have an aspect ratio between 0.40 and 2.50, measure at least 300px in both dimensions, and be no larger than 50.0MB.
elements[].video_urloptional
Typeurl · video
URL pointing to an element's video; only one element per request may include a video. The file must be at most 200 MB, with width and height each between 720px and 2160px. Duration must fall between 3 seconds and 10.05 seconds, and FPS between 24.0 and 60.0.
elements[].voice_idoptional
Typestring | null
Voice ID assigned to the element. References to that element use its assigned voice.
shot_typeoptional
Typeenum
Defaultcustomize
customizeintelligent
Choose how multi-shot generation plans its shots; selecting 'intelligent' delegates the shot structure to the model.
negative_promptoptional
Typestring
Defaultblur, distort, and low quality
≤ 2,500 characters
cfg_scaleoptional
Typenumber
Default0.5
0 – 1
Set how closely generation follows your prompt using CFG, short for Classifier Free Guidance.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kling-video/v3/pro/image-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 560,
    "usd": "0.56",
    "charged": 560,
    "refunded": 0
  },
  "input": {
    "prompt": "The banana manager turns to the camera, smiles and waves while coworkers keep typing, gentle handheld camera",
    "image": "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png",
    "duration": 5
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
video
object {url, content_type, file_name, file_size}Video produced by the model.

More models: Image to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/kling-video/v3/pro/image-to-video.md. All models and guides: https://doitong.com/developers/llms.txt