Vidu API Documentation

Last updated: May 8, 2026 · Base URL: https://api.imagine-future.com · Alternate: https://api.futurelabsai.dev

🌐 Base URL

Primary: https://api.imagine-future.com
Alternate: https://api.futurelabsai.dev
Both domains point to the same API service. You can use either one. If the primary domain is unreachable, switch to the alternate.

Video Generating

Text to Video

POST https://api.imagine-future.com/ai/avu/text2video

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model	String	Required	Model name. Accepted values: `viduq3-turbo` — Faster generation speed than viduq3-pro `viduq3-pro` — Supports audio-visual synchronization, supports video shot segmentation `viduq2` — New Model `viduq1` — Clear image, smooth transition, stable camera operation
style	String	Optional	The style of output video. Defaults to `general`. `general` — General style. Allows style control through prompts `anime` — Anime style. Optimized for anime aesthetics ⚠️ This parameter is not effective when using q2 or q3 models
prompt	String	Required	Text prompt. A textual description for video generation, with a maximum length of 5000 characters
duration	Int	Optional	Video duration (seconds): `viduq3-pro`, `viduq3-turbo`: default 5s, range 1–16 `viduq2`: default 5s, range 1–10 `viduq1`: default 5s, only 5s
seed	Int	Optional	Random seed. Defaults to a random seed number. Manually set values will override the default
aspect_ratio	String	Optional	The aspect ratio of the output video. Defaults to `16:9`. Accepted: `16:9`, `9:16`, `3:4`, `4:3`, `1:1` ⚠️ 3:4 & 4:3 only support q2 & q3 models
resolution	String	Optional	Resolution: `viduq3-pro`, `viduq3-turbo` (1-16s): default 720p, available: 540p, 720p, 1080p `viduq2` (1-10s): default 720p, available: 540p, 720p, 1080p `viduq1` (5s): default 1080p, available: 1080p
movement_amplitude	String	Optional	The movement amplitude of objects in the frame. Defaults to `auto`. Accepted: `auto`, `small`, `medium`, `large` ⚠️ This parameter does not take effect when using q2 & q3 models
bgm	Bool	Optional	Whether to add background music. Default: `false` ⚠️ q3 model not available; BGM does not take effect when q2 duration is 9 or 10 seconds
audio	Bool	Optional	Whether to use direct audio-video generation capability. Default: `true` `false` — No direct audio-video generation, outputs silent video `true` — Requires audio-video synchronization, outputs video with sound ⚠️ Only q3 models support this parameter
payload	String	Optional	Transparent transmission parameters. No processing, only data transmission, max 1048576 characters
off_peak	Bool	Optional	Off-peak mode. Default: `false` `true` — Off-peak generate mode (lower points, 48h completion) `false` — Normal generate mode
callback_url	String	Optional	Callback URL for task status updates

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3-pro",
  "prompt": "In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog. The background consists of enchanting white and golden lights, creating a minimalist still life and an impressive panoramic scene.",
  "duration": 5,
  "seed": 0,
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "movement_amplitude": "auto",
  "off_peak": false
}' \
  https://api.imagine-future.com/ai/avu/text2video

Response Example

JSON — 200 OK

{
  "task_id": "916198978159124480",
  "type": "text2video",
  "state": "created",
  "model": "viduq3-pro",
  "style": "general",
  "prompt": "In an ultra-realistic fashion photography style...",
  "duration": 5,
  "seed": 1920759782,
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "movement_amplitude": "auto",
  "created_at": "2026-02-03T09:19:33.696Z",
  "credits": 80,
  "off_peak": false
}

Image to Video

POST https://api.imagine-future.com/ai/avu/img2video

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model	String	Required	Model name. Accepted values: `viduq3-turbo`, `viduq3-pro`, `viduq2`, `viduq1`
images	Array	Required	Array of image URLs. The input image(s) to generate video from. Accepts 1 image URL
prompt	String	Required	Text prompt describing the desired video motion and content, max 5000 characters
duration	Int	Optional	Video duration (seconds). Same ranges as Text to Video
seed	Int	Optional	Random seed
aspect_ratio	String	Optional	Output aspect ratio. Defaults to `16:9`
resolution	String	Optional	Resolution. Default 720p. Available: 540p, 720p, 1080p
movement_amplitude	String	Optional	Movement amplitude. Default: `auto`. Accepted: `auto`, `small`, `medium`, `large`
off_peak	Bool	Optional	Off-peak mode. Default: `false`
callback_url	String	Optional	Callback URL for task status updates

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3-pro",
  "images": [
    "https://your-image-url.com/image.png"
  ],
  "prompt": "The astronaut waved and the camera moved up.",
  "duration": 5,
  "seed": 0,
  "resolution": "1080p",
  "movement_amplitude": "auto",
  "off_peak": false
}' \
  https://api.imagine-future.com/ai/avu/img2video

Response Example

JSON — 200 OK

{
  "task_id": "916201234567890123",
  "type": "img2video",
  "state": "created",
  "model": "viduq3-pro",
  "images": ["https://your-image-url.com/image.png"],
  "prompt": "The astronaut waved and the camera moved up.",
  "duration": 5,
  "seed": 1920759782,
  "resolution": "1080p",
  "movement_amplitude": "auto",
  "created_at": "2026-02-03T09:25:00.000Z",
  "credits": 80,
  "off_peak": false
}

Start End to Video

Generate a video by providing both a start frame and an end frame. The model interpolates between them to create smooth transition video.

POST https://api.imagine-future.com/ai/avu/start-end2video

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model	String	Required	Model name. Accepted values: `viduq3-turbo`, `viduq3-pro`, `viduq2`, `viduq1`
images	Array	Required	Array of exactly 2 image URLs — [start_frame, end_frame]
prompt	String	Optional	Text prompt describing the desired transition, max 5000 characters
duration	Int	Optional	Video duration (seconds). Same ranges as Text to Video
seed	Int	Optional	Random seed
resolution	String	Optional	Resolution. Default 720p
off_peak	Bool	Optional	Off-peak mode. Default: `false`
callback_url	String	Optional	Callback URL for task status updates

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3-pro",
  "images": [
    "https://your-images.com/start-frame.jpg",
    "https://your-images.com/end-frame.jpg"
  ],
  "prompt": "Smooth transition from day to night",
  "duration": 5,
  "seed": 0,
  "resolution": "720p",
  "off_peak": false
}' \
  https://api.imagine-future.com/ai/avu/start-end2video

Reference to Video

Generate a video using reference images for subject/style consistency. The model maintains visual elements from the reference while creating new motion.

POST https://api.imagine-future.com/ai/avu/reference2video

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model	String	Required	Model name. Accepted values: `viduq3-turbo`, `viduq3-pro`, `viduq2`, `viduq1`
images	Array	Required	Array of reference image URLs (1–4 images)
prompt	String	Required	Text prompt for video generation, max 5000 characters
duration	Int	Optional	Video duration (seconds). Default 5s
seed	Int	Optional	Random seed
aspect_ratio	String	Optional	Output aspect ratio. Default `16:9`
resolution	String	Optional	Resolution. Default 720p
off_peak	Bool	Optional	Off-peak mode. Default: `false`
callback_url	String	Optional	Callback URL for task status updates

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "viduq3-pro",
  "images": [
    "https://your-images.com/reference-character.jpg"
  ],
  "prompt": "The character walks through a garden, camera following from behind",
  "duration": 5,
  "seed": 0,
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "off_peak": false
}' \
  https://api.imagine-future.com/ai/avu/reference2video

Template Generating

Generate videos based on predefined templates. Templates provide structured prompts and motion presets for consistent output.

POST https://api.imagine-future.com/ai/avu/template2video

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model	String	Required	Model name
template_id	String	Required	Template ID for the desired generation template
images	Array	Required	Array of image URLs to use with the template
prompt	String	Optional	Additional text prompt to modify template output
duration	Int	Optional	Video duration (seconds)
resolution	String	Optional	Resolution. Default 720p
callback_url	String	Optional	Callback URL for task status updates

Image Generating

Reference to Image

Generate images using reference images for subject/style consistency.

POST https://api.imagine-future.com/ai/avu/ref2image/nano

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model	String	Required	Model name
images	Array	Required	Array of reference image URLs
prompt	String	Required	Text prompt for image generation
aspect_ratio	String	Optional	Output aspect ratio. Default `16:9`
resolution	String	Optional	Resolution
seed	Int	Optional	Random seed
callback_url	String	Optional	Callback URL for task status updates

Task Management

Get Creation

Retrieve the details and current status of a specific task by its task ID.

GET https://api.imagine-future.com/ai/avu/tasks/{task_id}/creations

Request Headers

Field	Value	Description
Authorization	`Token {your api key}`	Replace {} with your API Key

Path Parameters

Field	Type	Required	Description
task_id	String	Required	The task ID returned from any generation request

Response Fields

Field	Type	Description
task_id	String	Task ID
type	String	Task type (text2video, img2video, etc.)
state	String	Task state: `created`, `queueing`, `processing`, `success`, `failed`
model	String	Model used
prompt	String	Input prompt
creations	Array	Array of generated outputs (available when state is `success`)
creations[].url	String	Download URL for the generated video/image
creations[].cover_url	String	Cover image URL
created_at	String	Task creation time (ISO 8601)
credits	Number	Credits consumed
err_code	String	Error code (when state is `failed`)

Example Request

cURL

curl -H "Authorization: Token {your_api_key}" \
  https://api.imagine-future.com/ai/avu/tasks/916198978159124480/creations

Response Example (Success)

JSON — 200 OK

{
  "task_id": "916198978159124480",
  "type": "text2video",
  "state": "success",
  "model": "viduq3-pro",
  "prompt": "An astronaut walking through fog...",
  "creations": [
    {
      "url": "https://cdn.imagine-future.com/video/result.mp4",
      "cover_url": "https://cdn.imagine-future.com/video/cover.jpg"
    }
  ],
  "created_at": "2026-02-03T09:19:33.696Z",
  "credits": 80
}

💡 Polling Recommendation

Poll the Get Creation endpoint every 5–10 seconds until state changes to success or failed.

Get Task List

Retrieve a list of all tasks with optional filtering and pagination.

GET https://api.imagine-future.com/ai/avu/tasks/{task_id}/creations

💡 Note

To query a specific task, use GET /ai/avu/tasks/{task_id}/creations. There is no bulk task list endpoint — query tasks individually by their task_id.

Request Headers

Field	Value	Description
Authorization	`Token {your api key}`	Replace {} with your API Key

Query Parameters

Field	Type	Required	Description
task_id	String	Required	The task ID to query (path parameter)

Example Request

cURL

curl -H "Authorization: Token {your_api_key}" \
  "https://api.imagine-future.com/ai/avu/tasks/916198978159124480/creations"

Cancel Generation

Cancel a pending or processing task. Only tasks in created or queueing state can be cancelled.

POST https://api.imagine-future.com/ai/avu/tasks/{task_id}/cancel

Request Headers

Field	Value	Description
Authorization	`Token {your api key}`	Replace {} with your API Key

Path Parameters

Field	Type	Required	Description
task_id	String	Required	The task ID to cancel

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  https://api.imagine-future.com/ai/avu/tasks/916198978159124480/cancel

⚠️ Note

Credits consumed by tasks that have already started processing may not be fully refunded upon cancellation.

Solutions

One Click AI MV

One Click AI MV is a complete solution that generates music videos from images and audio. It supports creating MV tasks, querying progress, editing individual shots, and composing final videos.

💡 Base URL

All One Click AI MV endpoints use https://api.imagine-future.com/ai/avu/one-click/mv as the base path.

1. Create MV Task

POST https://api.imagine-future.com/ai/avu/one-click/mv

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {your api key} with your token

Request Body Parameters

Field	Type	Required	Description
images	Array[String]	Required	Model images or style images for MV generation. Supports Base64-encoded images or image URLs (must be accessible) Supports 1 to 7 images Formats: png, jpeg, jpg, webp Aspect ratio must be less than 1:4 or 4:1 Max image size: 50 MB (base64 decoded ≤ 10M)
audio_url	String	Required	Audio for MV generation. Supports Base64 encoding or audio URL Supports 1 audio file Formats: mp3, wav, aac, m4a Synthesized audio output: 10–180 seconds Shot list only output: 10–300 seconds Base64 decoded ≤ 20M
prompt	String	Optional	Text description for the MV video. Max 3000 characters
aspect_ratio	String	Optional	Output aspect ratio. Default: `16:9`. Accepted: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`
resolution	String	Optional	Clarity. Default: `720p`. Available: `540p`, `720p`, `1080p`
add_subtitle	Bool	Optional	Whether subtitles are needed. Default: `false`
srt_url	String	Optional	Subtitle file URL
language	String	Optional	Audio language type. Default: automatic. Enum: `en`, `zh`
callback_url	String	Optional	Callback URL for task status updates. Vidu will POST status changes (`processing`, `success`, `failed`) to this URL. Retries 3 times on failure
lip_sync	Bool	Optional	Whether to enable lip-sync (digital human). Default: `false` `true` — Enable lip-sync, adds 4 credits per second `false` — No lip-sync ⚠️ Note 1: Does not support non-real-person content ⚠️ Note 2: Does not support non-frontal-face video clips

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "images": ["https://your-image-url.com/image.png"],
  "prompt": "",
  "audio_url": "https://your-audio-url.com/audio.mp3",
  "duration": 15,
  "aspect_ratio": "16:9",
  "lip_sync": false
}' \
  https://api.imagine-future.com/ai/avu/one-click/mv

Response Example

JSON — 200 OK

{
  "id": "your_id_here"
}

2. Query MV Task

GET https://api.imagine-future.com/ai/avu/one-click/mv/{id}

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {your api key} with your token

Path Parameters

Field	Type	Required	Description
id	String	Required	Clip ID or Subtask ID

Example Request

cURL

curl -X GET \
  -H "Authorization: Token {your_api_key}" \
  https://api.imagine-future.com/ai/avu/one-click/mv/{id}

Response Fields

Field	Subfield	Type	Description
id		String	Task ID
state		String	Processing status: `created`, `processing`, `success`, `failed`
err_code		String	Error code (see error code table for details)
err_msg		String	Error-related information
created_at		String	Creation time (ISO 8601)
signed_url		String	URL of generated video (available if video is less than 3 minutes)
job_records		Array	Shot list + Composite Video records
	type	String	`generate_video` (Video Storyboard) or `compose` (Compose All Storyboards)
	index	Int	Shot Index
	jobs	Array	Single shot modification history
	jobs[].id	String	Job ID
	jobs[].state	String	`created`, `processing`, `success`, `failed`
	jobs[].signed_url	String	URL of the storyboard or composite product

Response Example

JSON — 200 OK

{
  "id": "901243326567555072",
  "type": "mv",
  "state": "success",
  "job_records": [
    {
      "type": "generate_video",
      "jobs": [
        {
          "id": "901245331704909824",
          "type": "generate_video",
          "state": "success",
          "signed_url": "signed_url",
          "mv_generate_video_input": {
            "duration": 3,
            "prompt": "2.5d building style, bright tones...",
            "lyric_text": "Intro"
          },
          "index": 0
        }
      ],
      "index": 0
    },
    {
      "type": "compose",
      "jobs": [
        {
          "id": "901245503243554816",
          "type": "compose",
          "state": "success",
          "signed_url": "signed_url",
          "index": 0
        }
      ],
      "index": 0
    }
  ],
  "created_at": "2025-12-24T02:51:34.070650Z",
  "signed_url": "signed_url"
}

3. Edit MV Task

Edit a specific shot in the MV by providing a new prompt. This regenerates the selected shot while keeping others intact.

POST https://api.imagine-future.com/ai/avu/one-click/mv/{id}/edit

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {your api key} with your token

Request Body Parameters

Field	Type	Required	Description
id	String	Required	Task ID (placed in the URL path)
job_id	String	Required	ID of the shot to be edited
prompt	String	Required	New text description for the shot. Max 3000 characters
callback_url	String	Optional	Callback URL for task status updates

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "job_id": "901334076999344129",
  "prompt": "2.5D modeling style, cheerful atmosphere, close-up, the protagonist dances on the beach, waves lapping at the ankles, camera follows the spinning motion"
}' \
  https://api.imagine-future.com/ai/avu/one-click/mv/{your_id}/edit

Response Example

JSON — 200 OK

{
  "id": "your_job_id_here"
}

4. Compose MV Task

Compose (synthesize) selected shots into the final MV video. Provide the list of shot job IDs to include in the final composition.

POST https://api.imagine-future.com/ai/avu/one-click/mv/{id}/compose

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {your api key} with your token

Request Body Parameters

Field	Type	Required	Description
id	String	Required	Task ID (placed in the URL path)
job_ids	Array[String]	Required	List of shot job IDs to be synthesized into the final video
callback_url	String	Optional	Callback URL for task status updates

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "job_ids": [
    "id1",
    "id2",
    "id3",
    "id4",
    "id5",
    "id6"
  ]
}' \
  https://api.imagine-future.com/ai/avu/one-click/mv/{your_id}/compose

Response Example

JSON — 200 OK

{
  "id": "your_job_id_here"
}

💡 MV Workflow

The typical workflow is: Create MV Task → Query Task (poll until shots are generated) → Edit Task (optional, refine individual shots) → Compose Task (combine shots into final video).

Kling AI

Kling AI integration provides Motion Control (apply motion from a reference video to a static image) and Avatar/Digital Human (generate lip-synced video from image + text/audio) capabilities.

🔑 Authentication

Kling endpoints use the same authentication as other API endpoints: Authorization: Token {your_api_key}

Motion Control

Apply the motion from a reference video to a static image, generating a new video that combines the image content with the reference motion.

POST https://api.imagine-future.com/ai/kling/v1/videos/motion-control

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model_name	String	Optional	Model name, e.g. `kling-v2-6`. If not provided, the server will use the default model
image_url	String	Required	Reference image URL or Base64 encoded string. Formats: jpg/jpeg/png, max 10MB, size 300px–65536px, aspect ratio 1:2.5–2.5:1
video_url	String	Required	Motion reference video URL. Formats: mp4/mov, max 100MB, size 340px–3850px, duration 3–30s (depends on character_orientation)
mode	String	Required	Generation mode: `std` — Standard mode (cost-effective) `pro` — Professional mode (high quality)
character_orientation	String	Required	Character orientation: `image` — Based on image orientation (video ≤ 10s) `video` — Based on video orientation (video ≤ 30s)
prompt	String	Optional	Text prompt, max 2500 characters. Describe scene content, camera movements, etc.
keep_original_sound	String	Optional	Whether to keep original sound from reference video. `yes` = keep, `no` = remove
callback_url	String	Optional	Callback URL. Task status changes will be POST-ed to this URL
external_task_id	String	Optional	Custom task ID, must be unique per user. If not provided, the system will automatically use the internal task ID

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "model_name": "kling-v2-6",
  "image_url": "https://your-image-url.com/person.jpg",
  "video_url": "https://your-video-url.com/dance-motion.mp4",
  "mode": "pro",
  "character_orientation": "image",
  "prompt": "A person dancing gracefully in a garden",
  "keep_original_sound": "no"
}' \
  https://api.imagine-future.com/ai/kling/v1/videos/motion-control

Response Example

JSON — 200 OK

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "req_abc123def456",
  "data": {
    "task_id": "881704293106061404",
    "task_status": "submitted",
    "task_status_msg": "",
    "task_info": {
      "external_task_id": "your_custom_id_or_system_id"
    },
    "created_at": 1715180000000,
    "updated_at": 1715180000000
  }
}

Avatar (Digital Human)

Generate a lip-synced digital human video from a reference image combined with text (TTS) or audio input. The model produces natural facial expressions and lip movements.

POST https://api.imagine-future.com/ai/kling/v1/videos/avatar/image2video

Request Headers

Field	Value	Description
Content-Type	`application/json`	Data Exchange Format
Authorization	`Token {your api key}`	Replace {} with your API Key

Request Body Parameters

Field	Type	Required	Description
model_name	String	Optional	Model name, e.g. `kling-v2-6`. If not provided, the server will use the default model
image	String	Required	Person reference image URL or Base64. Must contain a clear face
sound_file	String	Optional	Audio file URL. Drives lip-sync and motion from audio. Either `sound_file` or `text` must be provided
text	String	Optional	Text for TTS-driven lip-sync. The system converts text to speech and generates corresponding lip animation. Either `text` or `sound_file` must be provided
prompt	String	Optional	Action description prompt. Guides body language and facial expressions of the digital human
mode	String	Required	Generation mode: `std` — Standard mode `pro` — Professional mode
callback_url	String	Optional	Callback URL. Task status changes will be POST-ed to this URL
external_task_id	String	Optional	Custom task ID, must be unique per user. If not provided, the system will automatically use the internal task ID

⚠️ Important

Either text or sound_file must be provided. If both are omitted, the request will be rejected.

Example Request

cURL

curl -X POST \
  -H "Authorization: Token {your_api_key}" \
  -H "Content-Type: application/json" \
  -d '{
  "model_name": "kling-v2-6",
  "image": "https://your-image-url.com/portrait.jpg",
  "text": "Hello everyone, welcome to our product demonstration.",
  "mode": "pro",
  "prompt": "The person speaks confidently with natural hand gestures"
}' \
  https://api.imagine-future.com/ai/kling/v1/videos/avatar/image2video

Response Example

JSON — 200 OK

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "req_xyz789abc012",
  "data": {
    "task_id": "882901234567890123",
    "task_status": "submitted",
    "task_status_msg": "",
    "task_info": {
      "external_task_id": "your_custom_id_or_system_id"
    },
    "created_at": 1715180100000,
    "updated_at": 1715180100000
  }
}

Query Kling Task

Query the current status of a Kling task. Supports querying by either the system task ID or the Kling-assigned task ID. The system automatically syncs task state and handles credit deduction when the task reaches a terminal state.

GET https://api.imagine-future.com/ai/kling/v1/tasks/{taskId}?endpoint=videos/motion-control

Request Headers

Field	Value	Description
Authorization	`Token {your api key}`	Replace {} with your API Key

Path Parameters

Field	Type	Required	Description
taskId	String	Required	Task ID — can be either the system's internal task ID or the Kling-assigned task_id

Query Parameters

Field	Type	Required	Description
endpoint	String	Optional	Query endpoint. Default: `videos/motion-control`. For Avatar tasks use: `videos/avatar/image2video`

Response Fields

Field	Type	Description
code	Integer	Response code. `0` = success
message	String	Response message
data.task_id	String	Kling task ID
data.task_status	String	Task status: `submitted`, `processing`, `succeed`, `failed`
data.task_status_msg	String	Status description or error message
data.task_info.external_task_id	String	External task ID (your custom ID or system-assigned)
data.task_result.videos	Array	Generated video list (available when task_status is `succeed`)
data.task_result.videos[].url	String	Video download URL (expires in 30 minutes)
data.task_result.videos[].duration	String	Video duration in seconds
data.created_at	Long	Task creation timestamp (ms)
data.updated_at	Long	Last update timestamp (ms)

Example Request — Motion Control Task

cURL

curl -H "Authorization: Token {your_api_key}" \
  "https://api.imagine-future.com/ai/kling/v1/tasks/881704293106061404?endpoint=videos/motion-control"

Example Request — Avatar Task

cURL

curl -H "Authorization: Token {your_api_key}" \
  "https://api.imagine-future.com/ai/kling/v1/tasks/882901234567890123?endpoint=videos/avatar/image2video"

Response Example (Success)

JSON — 200 OK

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "req_query_001",
  "data": {
    "task_id": "881704293106061404",
    "task_status": "succeed",
    "task_status_msg": "",
    "task_info": {
      "external_task_id": "system_generated_task_id"
    },
    "task_result": {
      "videos": [
        {
          "id": "video_001",
          "url": "https://cdn.klingai.com/video/result_xxx.mp4",
          "duration": "8"
        }
      ]
    },
    "created_at": 1715180000000,
    "updated_at": 1715180500000
  }
}

Response Example (Processing)

JSON — 200 OK

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "req_query_002",
  "data": {
    "task_id": "881704293106061404",
    "task_status": "processing",
    "task_status_msg": "",
    "task_info": {
      "external_task_id": "system_generated_task_id"
    },
    "task_result": null,
    "created_at": 1715180000000,
    "updated_at": 1715180200000
  }
}

💡 Task Status Mapping

Kling uses different status names than our system internally. The mapping is:

submitted → Task created, waiting in queue
processing → Task is being processed
succeed → Generation complete, video available
failed → Task failed, check task_status_msg for details

💡 Polling Recommendation

Poll the Query Task endpoint every 10–15 seconds until task_status changes to succeed or failed. Video URLs expire after 30 minutes — download promptly.

Pricing

Credits consumed per generation vary by model, resolution, duration, and features.

ViduQ3

Model	Feature	Resolution	Duration	Credits
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	540p	5s	20
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	720p	5s	40
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	1080p	5s	80
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	720p	8s	64
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	1080p	8s	128
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	720p	16s	128
`viduq3-pro`	Text/Image/StartEnd/Ref to Video	1080p	16s	256
`viduq3-turbo`	Text/Image/StartEnd/Ref to Video	720p	5s	20
`viduq3-turbo`	Text/Image/StartEnd/Ref to Video	1080p	5s	40
`viduq3-turbo`	Text/Image/StartEnd/Ref to Video	720p	8s	32
`viduq3-turbo`	Text/Image/StartEnd/Ref to Video	1080p	8s	64

ViduQ2

Model	Feature	Resolution	Duration	Credits
`viduq2`	Text/Image to Video	540p	5s	10
`viduq2`	Text/Image to Video	720p	5s	20
`viduq2`	Text/Image to Video	1080p	5s	40
`viduq2`	Text/Image to Video	720p	8s	32
`viduq2`	Text/Image to Video	1080p	8s	64
`viduq2`	Text/Image to Video	720p	10s	40
`viduq2`	Text/Image to Video	1080p	10s	80

ViduQ1

Model	Feature	Resolution	Duration	Credits
`viduq1`	Text/Image to Video	1080p	5s	40

Image General Features

Feature	Description	Credits
Reference to Image	Generate image from reference images + prompt	10

Template Features

Feature	Description	Credits
Template to Video	Generate video from template + images	Varies by template

Digital Human

Feature	Description	Credits
Digital Human Video	Generate digital human video content	Contact sales

Kling AI

Feature	Mode	Description	Credits
Motion Control	`std`	Apply video motion to image (standard)	Based on duration
Motion Control	`pro`	Apply video motion to image (professional)	Based on duration
Avatar	`std`	Digital human lip-sync video (standard)	Based on duration
Avatar	`pro`	Digital human lip-sync video (professional)	Based on duration

Video Extension & Multi Frame Generation

Feature	Description	Credits
Video Extension	Extend existing video with additional frames	Same as original generation
Multi Frame Generation	Generate video with multiple keyframe control	Based on duration & resolution

Solutions

💼 Enterprise Solutions

For custom pricing plans, volume discounts, and enterprise solutions, please contact the Futurelabs AI sales team.

Vidu API Documentation

Table of Contents

Video Generating

Other Generating

Task Management

Solutions

Kling AI

Video Generating

Text to Video

Request Headers

Request Body Parameters

Example Request

Response Example

Image to Video

Request Headers

Request Body Parameters

Example Request

Response Example

Start End to Video

Request Headers

Request Body Parameters

Example Request

Reference to Video

Request Headers

Request Body Parameters

Example Request

Template Generating

Request Headers

Request Body Parameters

Image Generating

Reference to Image

Request Headers

Request Body Parameters

Task Management

Get Creation

Request Headers

Path Parameters

Response Fields

Example Request

Response Example (Success)

Get Task List

Request Headers

Query Parameters

Example Request

Cancel Generation

Request Headers

Path Parameters

Example Request

Solutions

One Click AI MV

1. Create MV Task

Request Headers

Request Body Parameters

Example Request

Response Example

2. Query MV Task

Request Headers

Path Parameters

Example Request

Response Fields

Response Example

3. Edit MV Task

Request Headers

Request Body Parameters

Example Request

Response Example

4. Compose MV Task

Request Headers

Request Body Parameters

Example Request

Response Example

Kling AI

Motion Control

Request Headers

Request Body Parameters

Example Request

Response Example

Avatar (Digital Human)

Request Headers

Request Body Parameters