模型市场支持← 返回应用

Kling

Kling 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 15 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
KlingText to Videokling/text-to-video
KlingImage to Videokling/image-to-video
Kling V25 TurboImage to Videokling/v25-turbo-image-to-video-pro
Kling V25 TurboText to Videokling/v25-turbo-text-to-video-pro
KlingLip Synckling/ai-avatar-standard
KlingLip Synckling/ai-avatar-pro
Kling V2 1 MasterImage to Videokling/v2-1-master-image-to-video
Kling V2 1 MasterText to Videokling/v2-1-master-text-to-video
Kling V2 1 ProImage to Videokling/v2-1-pro
Kling V2 1 StandardImage to Videokling/v2-1-standard
KlingImage to Videokling/motion-control
KlingImage to Videokling/motion-control-v3
Kling 3.0Image to Videokling/kling-3-0
Kling V3 TurboText to Videokling/v3-turbo-text-to-video
Kling V3 TurboImage to Videokling/v3-turbo-image-to-video

Kling · Text to Video

POSTText to Videokling/text-to-video
input 字段
promptstring必填

Text prompt for video generation (max 1000 chars)

soundboolean必填

Specifies whether the generated video contains audio

aspect_ratioenum<string>必填

Defines the video aspect ratio

durationenum<string>必填

Video duration in seconds

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "sound": false,
    "aspect_ratio": "1:1",
    "duration": "5"
  }
}'

Kling · Image to Video

POSTImage to Videokling/image-to-video
input 字段
promptstring必填

Text prompt for video generation (max 1000 chars)

image_urlsarray<string>必填

Image URLs for video generation; max 1 file, JPEG/PNG, max 10MB

soundboolean必填

Specifies whether the generated video contains audio

durationenum<string>必填

Video duration in seconds

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "sound": false,
    "duration": "5"
  }
}'

Kling V25 Turbo · Image to Video

POSTImage to Videokling/v25-turbo-image-to-video-pro
input 字段
promptstring必填

Text prompt describing the video to generate (max 2500 chars)

image_urlstring必填

URL of the image to be used for the video (max 10MB)

tail_image_urlstring可选

Tail frame image of video (max 10MB)

durationenum<string>可选

The duration of the generated video in seconds

negative_promptstring可选

Elements to exclude from the video (max 500 chars)

cfg_scalenumber可选

CFG scale controlling adherence to prompt (0-1, step 0.1)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v25-turbo-image-to-video-pro",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_url": "https://example.com/input.jpg",
    "tail_image_url": "https://example.com/input.jpg",
    "duration": "5",
    "negative_prompt": "example",
    "cfg_scale": 0.5
  }
}'

Kling V25 Turbo · Text to Video

POSTText to Videokling/v25-turbo-text-to-video-pro
input 字段
promptstring必填

Text description of video to generate (max 2500 chars)

durationenum<string>可选

Generated video length in seconds

aspect_ratioenum<string>可选

Video frame aspect ratio

negative_promptstring可选

Elements to avoid in generation (max 2500 chars)

cfg_scalenumber可选

Guidance scale controlling prompt adherence (0-1, step 0.1)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v25-turbo-text-to-video-pro",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "duration": "5",
    "aspect_ratio": "16:9",
    "negative_prompt": "example",
    "cfg_scale": 0.5
  }
}'

Kling · Lip Sync

POSTLip Synckling/ai-avatar-standard
input 字段
image_urlstring必填

URL of the image to use as your avatar (JPEG/PNG, max 10MB)

audio_urlstring必填

URL of the audio file (MP3/WAV/AAC/M4A/OGG, max 100MB, 5min)

promptstring必填

Text direction for video generation (max 5000 chars)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/ai-avatar-standard",
  "input": {
    "image_url": "https://example.com/input.jpg",
    "audio_url": "https://example.com/reference.mp3",
    "prompt": "A cinematic red panda surfing through neon rain at dusk."
  }
}'

Kling · Lip Sync

POSTLip Synckling/ai-avatar-pro
input 字段
image_urlstring必填

URL of image file to use as avatar (JPEG/PNG, max 10MB)

audio_urlstring必填

URL of audio file for speech (MP3/WAV/AAC/MP4/OGG, max 100MB, 5min)

promptstring必填

Text prompt for video generation (max 5000 chars)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/ai-avatar-pro",
  "input": {
    "image_url": "https://example.com/input.jpg",
    "audio_url": "https://example.com/reference.mp3",
    "prompt": "A cinematic red panda surfing through neon rain at dusk."
  }
}'

Kling V2 1 Master · Image to Video

POSTImage to Videokling/v2-1-master-image-to-video
input 字段
promptstring必填

Text describing the video to generate (max 5000 chars)

image_urlstring必填

URL of image for video generation (JPEG/PNG, max 10MB)

durationenum<string>可选

Duration of generated video in seconds

negative_promptstring可选

Elements to exclude from video generation (max 500 chars)

cfg_scalenumber可选

Guidance scale controlling prompt adherence (0-1, step 0.1)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v2-1-master-image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_url": "https://example.com/input.jpg",
    "duration": "5",
    "negative_prompt": "example",
    "cfg_scale": 0.5
  }
}'

Kling V2 1 Master · Text to Video

POSTText to Videokling/v2-1-master-text-to-video
input 字段
promptstring必填

Text describing the video to generate (max 5000 chars)

durationenum<string>可选

Generated video length in seconds

aspect_ratioenum<string>可选

Video frame aspect ratio

negative_promptstring可选

Elements to avoid in video (max 500 chars)

cfg_scalenumber可选

Guidance scale adherence to prompt (0-1, step 0.1)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v2-1-master-text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "duration": "5",
    "aspect_ratio": "16:9",
    "negative_prompt": "example",
    "cfg_scale": 0.5
  }
}'

Kling V2 1 Pro · Image to Video

POSTImage to Videokling/v2-1-pro
input 字段
promptstring必填

Text prompt describing the video to generate (max 5000 chars)

image_urlstring必填

URL of the image to be used for the video (max 10MB)

durationstring可选

Duration of the generated video in seconds

negative_promptstring可选

Terms to avoid in the generated video (max 500 chars)

cfg_scalenumber可选

CFG scale measuring adherence to prompt (0-1, step 0.1)

tail_image_urlstring可选

URL of the image for the end of the video (max 10MB)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v2-1-pro",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_url": "https://example.com/input.jpg",
    "duration": "5",
    "negative_prompt": "example",
    "cfg_scale": 0.5,
    "tail_image_url": "https://example.com/input.jpg"
  }
}'

Kling V2 1 Standard · Image to Video

POSTImage to Videokling/v2-1-standard
input 字段
promptstring必填

Text prompt describing the desired video content (max 5000 chars)

image_urlstring必填

URL of the image to be used for the video (max 10MB)

durationstring可选

Length of generated video in seconds

negative_promptstring可选

Elements to avoid in the generated video (max 500 chars)

cfg_scalenumber可选

Guidance scale controlling prompt adherence (0-1, step 0.1)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v2-1-standard",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_url": "https://example.com/input.jpg",
    "duration": "5",
    "negative_prompt": "example",
    "cfg_scale": 0.5
  }
}'

Kling · Image to Video

POSTImage to Videokling/motion-control
input 字段
promptstring可选

Text description of desired output (max 2500 chars)

input_urlsarray<string>必填

Single image URL showing subject's head, shoulders, torso

video_urlsarray<string>必填

Single video URL (3-30s) showing subject's head, shoulders, torso

character_orientationstring必填

Character orientation: image for picture pose or video for video pose

modestring必填

Output resolution: 720p or 1080p

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/motion-control",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "input_urls": [
      "https://example.com/file"
    ],
    "video_urls": [
      "https://example.com/reference.mp4"
    ],
    "character_orientation": "image",
    "mode": "720p"
  }
}'

Kling · Image to Video

POSTImage to Videokling/motion-control-v3
input 字段
promptstring可选

Text prompt (0-2500 chars) to guide animation generation

input_urlsarray<string>必填

URL of the reference image showing the subject

video_urlsarray<string>必填

URL of the motion video defining the motion pattern

modestring可选

Video quality: std (720p) or pro (1080p)

character_orientationstring可选

Reference for character orientation (video recommended)

background_sourcestring可选

Background source selection

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/motion-control-v3",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "input_urls": [
      "https://example.com/file"
    ],
    "video_urls": [
      "https://example.com/reference.mp4"
    ],
    "mode": "std",
    "character_orientation": "video",
    "background_source": "input_video"
  }
}'

Kling 3.0 · Image to Video

POSTImage to Videokling/kling-3-0
input 字段
promptstring可选

Video generation prompt (single-shot mode)

image_urlsarray<string>可选

First/last frame image URLs for reference

soundboolean可选

Enable/disable sound effects for video

durationstring必填

Total video duration in seconds (3-15)

aspect_ratiostring可选

Video aspect ratio; auto-adapts if images provided

modestring可选

Generation mode controlling resolution output

multi_shotsboolean可选

Enable multi-shot mode for multiple shots

multi_promptarray<object>可选

Shot array with prompt/duration (multi-shot mode)

kling_elementsarray<object>可选

Referenced elements (images/video/audio) max 3

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/kling-3-0",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "sound": false,
    "duration": 5,
    "aspect_ratio": "16:9",
    "mode": "pro",
    "multi_shots": false,
    "multi_prompt": [],
    "kling_elements": []
  }
}'

Kling V3 Turbo · Text to Video

POSTText to Videokling/v3-turbo-text-to-video
input 字段
promptstring必填

Text description of the video to generate (max 2500 chars)

durationstring必填

Duration of generated video in seconds (3s-15s range)

aspect_ratiostring必填

Aspect ratio of the generated video frame

resolutionstring必填

Resolution of the generated video

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v3-turbo-text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}'

Kling V3 Turbo · Image to Video

POSTImage to Videokling/v3-turbo-image-to-video
input 字段
promptstring必填

Text prompt describing the video to generate (max 2500 chars)

image_urlsarray<string>必填

URL of image for video (JPEG/PNG, max 10MB)

durationstring可选

Video duration in seconds (3s-15s range)

resolutionstring可选

Output video resolution

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling/v3-turbo-image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "duration": 5,
    "resolution": "720p"
  }
}'