POST videos/image2video-frames — Kling API

Create Video From Image Frames

April 18, 2025 (October 20, 2026)

Request Headers
Request Body
Responses
Model
Examples
Try It

This endpoint generates a video from one or two images (start and end frames). Kling 4.0 also takes keyframes between them, up to 10 images in total, and the duration sets how many images you can use.

Model	Start Frame	Keyframes	Elements	Audio	Multi- shot
kling-v4-0	Required	Up to 9		always on	always on
kling-v3-0	Required		Up to 3	default on
kling-v3-0-turbo	Required			always on
kling-v2-6	Required			Native (Pro)
kling-v2-5	Required			SFX
kling-v2-1	Required			SFX
kling-v2-1-master	Required			SFX
kling-v1-6				SFX
kling-v1-5				SFX

Duration: kling-v4-0 supports 3–30s, kling-v3-0 / kling-v3-0-turbo support 3–15s, and all other models support 5s or 10s.
SFX = Sound Effects.
Native = Native Audio (model 2.6, pro mode, start frame only).

Kling 4.0 generates 720p (std) and 1080p (pro) video. Kling offers 1080p to paid Kling subscribers only. 4K and HDR are not available for 4.0 yet.

To use elements with Kling 4.0, use POST videos/omni with omni_version v4.

If your Kling account can’t use Kling 4.0 yet, the request returns a 403 error.

https://api.useapi.net/v1/kling/videos/image2video-frames

Request Headers

Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data

API token is required, see Setup useapi.net for details.

Request Body

{
  "email": "[email protected]",
  "image": "https://example.com/start-image.jpg",
  "keyframe_1": "https://example.com/keyframe-1.jpg",
  "image_tail": "https://example.com/end-image.jpg",
  "prompt": "A futuristic city with flying cars and tall buildings",
  "duration": "10",
  "model_name": "kling-v4-0",
  "mode": "pro",
  "replyUrl": "https://your-callback-url.com/webhook",
  "replyRef": "your-reference-id"
}

email is optional. Leave it out and the job goes to one of your accounts that has a free job slot, picked at random. Each account runs at most its maxJobs jobs at once, and GET scheduler/available shows the free slots. If no account has a free slot, the response is 429.
Pass email to run the job on that account (429 if it is busy). Uploaded files, elements, voices, avatars and earlier tasks belong to one account, so pass the email of the account they came from.
With more than one account, reading the task with GET tasks/task_id needs its account’s email. The response’s task.userId is that account’s session.userId in GET accounts, and GET scheduler lists each running task with its email.
image is required if image_tail is not provided. URL to the start frame image. Required for models 2.x, 3.0 and 4.0.
Image can be uploaded using POST /assets and the returned URLs can be used here.
image_tail is required if image is not provided. URL to the end frame image. Models 2.1 Master and 3.0 Turbo do not support this parameter. Image can be uploaded using POST /assets and the returned URLs can be used here.
keyframe_1 through keyframe_9 are optional, URLs to keyframe images placed between the start frame (image) and the end frame (image_tail), in order. Supported by kling-v4-0 only. They require image and must be consecutive, starting from keyframe_1. A video takes up to 10 images in total, so you can add up to 8 keyframes together with image_tail, or up to 9 without it. The total number of images (image, keyframe_N and image_tail) can be at most the duration in seconds plus one, and at most 10:

duration Max images in total

3 4

4 5

5 (default) 6

6 7

7 8

8 9

9 to 30 10

When you leave out duration and send more than 6 images, the duration becomes the number of images minus one, so 7 images make a 6-second video.

Images can be uploaded using POST /assets and the returned URLs can be used here.
element_1, element_2, element_3 are optional, references to saved elements (e.g. u_309377170505500) used to guide the generation alongside the start/end frames. Up to 3 combined. Supported by model 3.0 only. For elements with Kling 4.0, use POST videos/omni with omni_version v4.
prompt is optional, text description to guide the video generation. Maximum length: 8000 characters for model 4.0 and 2500 characters for every other model. Cannot be used together with multi-shot parameters (shot_N_prompt/shot_N_duration).
negative_prompt is optional, what not to include in the generated video. Models 2.5, 2.6, 3.0 and 4.0 do not support this parameter.
Maximum length: 2500 characters.
cfg_scale is optional, guidance scale for image-to-video generation. Models 2.x, 3.0 and 4.0 do not support this parameter.
Range: 0 to 1. Default: 0.5.
duration is optional, length of the video in seconds. Cannot be used together with multi-shot parameters (shot_N_prompt/shot_N_duration). Model 4.0: 3 to 30 seconds (default 5). Models 3.0 and 3.0 Turbo: 3 to 15 seconds (default 5). Other models: 5 (default) or 10.
model_name is optional, the AI model version to use. Supported values: kling-v4-0, kling-v3-0, kling-v3-0-turbo, kling-v2-6, kling-v2-5, kling-v2-1 (default), kling-v2-1-master, kling-v1-6, kling-v1-5. Models 3.0, 3.0 Turbo and 4.0 do not support aspect_ratio (derived from input image). Model 3.0 enables audio by default, set enable_audio: false to disable it. Model 3.0 Turbo (kling-v3-0-turbo) is a faster 3.0 variant: start frame only (no image_tail), std/pro modes (no 4k), audio always on (enable_audio not supported), and no element_N references or multi-shot. Model 4.0 (kling-v4-0) always generates stereo audio and takes 3 to 30 seconds. It takes keyframes but no element_N references.
mode is optional, quality level. Model 2.1 Master only supports pro mode. Supported values: std (standard, default), pro (higher quality, slower generation), or 4k (4K resolution, model 3.0 only). Model 2.6 supports std and pro, but pro is required when enable_audio is true. Model 3.0 adds support for 4k. Model 3.0 Turbo supports std and pro only. Model 4.0 supports std (720p) and pro (1080p). Kling offers 1080p to paid Kling subscribers only.
enable_audio is optional, add audio to the generated video. Supported values: false (default) or true. Model 3.0 defaults to audio enabled (including 4k); set enable_audio: false to disable. Models 3.0 Turbo and 4.0 always generate audio and do not accept this parameter. Model 2.6: Native Audio (AI-generated audio synced with video), requires mode: pro, not available with End Frame. Other models: Sound Effects (basic audio generation).
multi_shot is optional, let the model cut the video into several shots on its own (models 3.0 and 4.0). Supported values: false (default) or true. You write one ordinary prompt and Kling decides where the cuts fall — use shot_1_prompt below instead when you want to direct each shot yourself. Ignored when shot_1_prompt is present — directing the shots yourself already turns multi-shot on. Model 4.0 always lets the model use several shots, so it accepts only multi_shot: true. Models 3.0 and 4.0 accept this parameter. Every other model, including 3.0 Turbo, rejects it outright — even multi_shot: false.
shot_1_prompt through shot_6_prompt are optional, per-shot text prompts for multi-shot storytelling (models 3.0 and 4.0). Maximum length: 2500 characters per shot. Minimum 2 shots required. Cannot be used together with prompt or duration.
shot_1_duration through shot_6_duration are optional, per-shot duration in seconds. Each shot must have both prompt and duration. Total duration must be 3-15 seconds. Shots must be sequential with no gaps (e.g. shot_1 + shot_2, not shot_1 + shot_3).
maxJobs is optional, range from 1 to 50.
Specifies the maximum number of concurrent jobs.
replyUrl is optional, a callback URL to receive generation progress and result.
See GET /tasks/task_id for response model.
replyRef is optional, a reference identifier for the callback.

`duration`	Max images in total
`3`	4
`4`	5
`5` (default)	6
`6`	7
`7`	8
`8`	9
`9` to `30`	10

Notes:

At least one of image or image_tail must be provided.
If image_tail provided, the mode is automatically set to pro (models 2.x).
Element references (element_1-element_3) require model 3.0.
Keyframes (keyframe_1-keyframe_9) require kling-v4-0. The total number of images can be at most the duration plus one (4 to 10).
Model 3.0 Turbo supports the start frame only — no end frame (image_tail), element_N references, or multi-shot.

Responses

200 OK

{
  "task": {
    "id": 123456789,
    "userId": 12345,
    "type": "m2v_img2video_hq",
    "scene": "NORMAL_CREATION",
    "status": 5,
    "status_name": "submitted",
    "status_final": false,
    "taskInfo": {
      "type": "m2v_img2video_hq",
      "inputs": [
        {
          "name": "input",
          "inputType": "URL",
          "token": null,
          "blobStorage": null,
          "url": "https://example.com/start-image.jpg",
          "cover": null,
          "fromWorkId": null
        },
        {
          "name": "tail_image",
          "inputType": "URL",
          "token": null,
          "blobStorage": null,
          "url": "https://example.com/end-image.jpg",
          "cover": null,
          "fromWorkId": null
        }
      ],
      "arguments": [
        {
          "name": "prompt",
          "value": "A futuristic city with flying cars and tall buildings"
        },
        {
          "name": "negative_prompt",
          "value": "people, low quality, distorted"
        },
        {
          "name": "duration",
          "value": "5"
        },
        {
          "name": "kling_version",
          "value": "2.1"
        },
        {
          "name": "tail_image_enabled",
          "value": "true"
        }
      ],
      "extraArgs": {},
      "callbackPayloads": [],
      "scene": "NORMAL_CREATION"
    },
    "favored": false,
    "deleted": false,
    "viewed": false,
    "createTime": 1745376611075,
    "updateTime": 1745376611075
  },
  "works": [],
  "status": 5,
  "status_name": "submitted",
  "status_final": false,
  "message": "",
  "limitation": {
    "type": "m2v_img2video_hq",
    "remaining": 10000,
    "limit": 10000
  },
  "userPoints": {
    "points": [],
    "total": 0
  },
  "userTickets": {
    "ticket": []
  },
  "editProject": null
}

400 Bad Request

The parameters are invalid. When Kling refuses the submitted parameters, error carries Kling’s own message.
```
{
  "error": "image or image_tail is required"
}
```

401 Unauthorized

{
  "error": "Unauthorized",
  "code": 401
}

403 Forbidden

Your Kling account can’t use the requested model yet, for example Kling 4.0.

{
  "error": "This Kling account does not have access to the requested model or feature (AUTH.VPrivilegeEscalation)",
  "message": "Service busy (AUTH.VPrivilegeEscalation)"
}

404 Not Found

Kling was unable to locate one of the referenced assets. Make sure to use POST /assets to upload assets.

{
    "error": "Sorry, the requested resource was not found (VALID.ResourceNotFound)",
    "message": "Not Found"
}

500 Internal Server Error

Kling uses a 500 response to indicate moderation and other issues with the input. It may be hard to separate actual 500 errors from moderation errors, so use the error field text and your best judgement to tell them apart, since the message field most often has very generic and perhaps misleading text.
```
{
  "error": "The content you uploaded appears to violate the community guidelines. (CM_EXT.POther)",
  "message": "Service busy (CM_EXT.POther)"
}
```

When successful, the response includes a task ID which can be used to check the status using GET /tasks/task_id.

Model

{ // TypeScript, all fields are optional
    task: {
        id: number
        userId: number
        type: string
        scene: string
        status: number
        status_name: 'submitted' | 'failed' | 'processing' | 'succeed'
        status_final: boolean
        taskInfo: {
            type: string
            inputs: Array<{
                name: string
                inputType: string
                token: string | null
                blobStorage: any | null
                url: string
                cover: string | null
                fromWorkId: number | null
            }>
            arguments: Array<{
                name: string
                value: string
            }>
            extraArgs: Record<string, any>
            callbackPayloads: any[]
            scene: string
        }
        favored: boolean
        deleted: boolean
        viewed: boolean
        createTime: number
        updateTime: number
        viewTime: number
    }
    works: Array<any>
    status: number
    status_name: 'submitted' | 'failed' | 'processing' | 'succeed'
    status_final: boolean
    message: string
    error: string
    limitation: {
        type: string
        remaining: number
        limit: number
    }
    userPoints: {
        points: Array<{
            orderId: string
            type: string
            amount: number
            balance: number
            startTime: number
            endTime: number
        }>
        total: number
    }
    userTickets: {
        ticket: Array<{
            orderId: string
            type: string
            packageType: string
            amount: number
            balance: number
            startTime: number
            endTime: number
        }>
    }
    editProject: any | null
}

Examples

curl -X POST "https://api.useapi.net/v1/kling/videos/image2video-frames" \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer …" \
   -d '{
     "email": "[email protected]",
     "image": "https://example.com/start-image.jpg",
     "image_tail": "https://example.com/end-image.jpg",
     "prompt": "A futuristic city with flying cars and tall buildings",
     "negative_prompt": "people, low quality, distorted"
   }'

const token = "API token";
const email = "Previously configured account email";
const apiUrl = "https://api.useapi.net/v1/kling/videos/image2video-frames"; 
const response = await fetch(apiUrl, {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${token}`,
  },
  body: JSON.stringify({
    email: email,
    image: "https://example.com/start-image.jpg",
    image_tail: "https://example.com/end-image.jpg",
    prompt: "A futuristic city with flying cars and tall buildings",
    negative_prompt: "people, low quality, distorted"
  })
});
const result = await response.json();
console.log("response", {response, result});

import requests
token = "API token"
email = "Previously configured account email"
apiUrl = "https://api.useapi.net/v1/kling/videos/image2video-frames"
headers = {
    "Content-Type": "application/json", 
    "Authorization" : f"Bearer {token}"
}
data = {
    "email": email,
    "image": "https://example.com/start-image.jpg",
    "image_tail": "https://example.com/end-image.jpg",
    "prompt": "A futuristic city with flying cars and tall buildings",
    "negative_prompt": "people, low quality, distorted"
}
response = requests.post(apiUrl, headers=headers, json=data)
print(response, response.json())

Try It

API Token (see Setup useapi.net) email (previously configured via POST /accounts) image (required if image_tail not provided, start frame URL, use POST /assets) image_tail (required if image not provided, end frame URL, use POST /assets) keyframe_1 (optional, keyframe URL, kling-v4-0) keyframe_2 (optional, after keyframe_1) keyframe_3 (optional, after keyframe_2) keyframe_4 (optional, after keyframe_3) keyframe_5 (optional, after keyframe_4) keyframe_6 (optional, after keyframe_5) keyframe_7 (optional, after keyframe_6) keyframe_8 (optional, after keyframe_7) keyframe_9 (optional, after keyframe_8) element_1 (optional, saved element ID, v3.0 only) element_2 (optional, saved element ID, v3.0 only) element_3 (optional, saved element ID, v3.0 only) prompt (optional) negative_prompt (optional) cfg_scale (0-1, default: 0.5) duration (seconds, default: 5) model_name mode (quality level, default: std) enable_audio multi_shot (auto multi-shot, models 3.0 and 4.0) shot_1_prompt (v3/v4 multi-shot) shot_1_duration (seconds) shot_2_prompt (v3/v4 multi-shot) shot_2_duration (seconds) shot_3_prompt (v3/v4 multi-shot) shot_3_duration (seconds) shot_4_prompt (v3/v4 multi-shot) shot_4_duration (seconds) shot_5_prompt (v3/v4 multi-shot) shot_5_duration (seconds) shot_6_prompt (v3/v4 multi-shot) shot_6_duration (seconds) replyUrl (optional, callback URL) replyRef (optional, reference ID for callback)