kling-v3.0-pro

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Kling Video v3.0 Pro

Kling Video v3.0 Pro

Generate high-end cinematic video with synchronized audio through Frevana's OpenRouter video endpoint using
kwaivgi/kling-v3.0-pro
.
通过 Frevana 的 OpenRouter 视频端点使用
kwaivgi/kling-v3.0-pro
生成带有同步音频的高端电影级视频。

Model Characteristics

模型特性

  • Model ID:
    kwaivgi/kling-v3.0-pro
  • Resolution:
    720p
    (fixed)
  • Aspect Ratios:
    16:9
    (default),
    9:16
    ,
    1:1
  • Durations:
    3
    to
    15
    seconds (default:
    5
    )
  • Frame Control: Supports both
    first_frame
    and
    last_frame
    (image-to-video)
  • Input References: Reference images (
    image_url
    ); audio and video references are unsupported
  • Audio: Synchronized audio generation supported (default: enabled)
  • Seed: Deterministic seed is not supported by this model
  • Passthrough Controls:
    negative_prompt
    ,
    cfg_scale
  • Model ID:
    kwaivgi/kling-v3.0-pro
  • Resolution:
    720p
    (固定)
  • Aspect Ratios:
    16:9
    (默认)、
    9:16
    、
    1:1
  • Durations:
    3
    至
    15
    秒(默认:
    5
    )
  • Frame Control:同时支持
    first_frame
    和
    last_frame
    (图生视频)
  • Input References:参考图像(
    image_url
    );不支持音频和视频参考
  • Audio:支持同步音频生成(默认:启用)
  • Seed:此模型不支持确定性 seed
  • Passthrough Controls:
    negative_prompt
    、
    cfg_scale

Prerequisites & Authentication

前置条件与身份验证

  • FREVANA_TOKEN
    (or
    --token
    ) or
    FREVANA_API_KEY
    (or
    --api-key
    ) in the environment
  • Optional
    FREVANA_AGENT_APP_INSTANCE_ID
    (or
    --agent-app-instance-id
    ) sent as
    x-frevana-agent-app-instance-id
  • curl
    ,
    bash
    , and
    python3
  • 环境中需设置
    FREVANA_TOKEN
    (或
    --token
    )或
    FREVANA_API_KEY
    (或
    --api-key
    )
  • 可选设置
    FREVANA_AGENT_APP_INSTANCE_ID
    (或
    --agent-app-instance-id
    ),并通过
    x-frevana-agent-app-instance-id
    发送
  • curl
    、
    bash
    和
    python3

Invocation

调用方式

bash
undefined
bash
undefined

Text-to-video: submit and wait for video completion

Text-to-video: submit and wait for video completion

bash skills/kling-v3.0-pro/scripts/generate_video.sh
--prompt "A cinematic close-up of an astronaut's visor reflecting a distant exploding nebula"
--duration 6
--aspect-ratio 16:9
--download-dir ./output
bash skills/kling-v3.0-pro/scripts/generate_video.sh
--prompt "A cinematic close-up of an astronaut's visor reflecting a distant exploding nebula"
--duration 6
--aspect-ratio 16:9
--download-dir ./output

Image-to-video with first and last frame

Image-to-video with first and last frame

bash skills/kling-v3.0-pro/scripts/generate_video.sh
--prompt "The camera smoothly circles the character in dramatic studio lighting"
--first-frame ./first.png
--last-frame ./last.png
--duration 5
--download-dir ./output
bash skills/kling-v3.0-pro/scripts/generate_video.sh
--prompt "The camera smoothly circles the character in dramatic studio lighting"
--first-frame ./first.png
--last-frame ./last.png
--duration 5
--download-dir ./output

Status check

Status check

bash skills/kling-v3.0-pro/scripts/generate_video.sh status --job-id <JOB_ID>
undefined
bash skills/kling-v3.0-pro/scripts/generate_video.sh status --job-id <JOB_ID>
undefined

Allowed Options

允许使用的选项

  • -p, --prompt TEXT
    : Text description of the video (required for create)
  • --prompt-file PATH
    : Path to file containing prompt
  • --model MODEL
    : Model slug (default:
    kwaivgi/kling-v3.0-pro
    )
  • --duration SEC
    : Duration in seconds (
    3
    -
    15
    , default:
    5
    )
  • --aspect-ratio RATIO
    :
    16:9
    ,
    9:16
    ,
    1:1
    (default:
    16:9
    )
  • --resolution RES
    :
    720p
    (default:
    720p
    )
  • --size WIDTHxHEIGHT
    : Exact output dimensions; overrides
    --resolution
    and
    --aspect-ratio
  • --first-frame, --image PATH/URL
    : Image path or URL for first frame
  • --last-frame PATH/URL
    : Image path or URL for last frame
  • --reference-image PATH/URL
    : Add a reference image; repeat for multiple images
  • --reference-audio URL
    : Unsupported by this model
  • --reference-video URL
    : Unsupported by this model
  • --audio
    : Generate synchronized audio (default: true)
  • --no-audio
    : Disable audio generation
  • --negative-prompt TEXT
    : Negative prompt (e.g. "blurry, distorted, artifacts")
  • --cfg-scale NUM
    : CFG guidance scale (e.g. 0.5)
  • --wait
    : Wait for job completion and download/output (default in CLI)
  • --no-wait
    : Submit job and return immediately with Job ID
  • --poll-interval SEC
    : Seconds between status checks (default:
    10
    )
  • --max-wait SEC
    : Maximum seconds to wait before timeout (default:
    600
    )
  • --download-dir DIR
    : Directory to download completed MP4 video
  • -o, --output FILE
    : Path to save output JSON or MP4 file
  • -t, --text-only
    : Output only the video URL or downloaded file path
  • --dry-run
    : Print request payload JSON and exit without network calls
  • --token TOKEN
    : Frevana Bearer token override
  • --api-key KEY
    : Frevana API key override
  • --agent-app-instance-id ID
    : Agent App instance ID override
  • -p, --prompt TEXT
    :视频的文本描述(创建任务时必填)
  • --prompt-file PATH
    :包含 prompt 的文件路径
  • --model MODEL
    :模型 slug(默认:
    kwaivgi/kling-v3.0-pro
    )
  • --duration SEC
    :时长,单位为秒(
    3
    -
    15
    ,默认:
    5
    )
  • --aspect-ratio RATIO
    :
    16:9
    、
    9:16
    、
    1:1
    (默认:
    16:9
    )
  • --resolution RES
    :
    720p
    (默认:
    720p
    )
  • --size WIDTHxHEIGHT
    :精确的输出尺寸;会覆盖
    --resolution
    和
    --aspect-ratio
  • --first-frame, --image PATH/URL
    :首帧图像的路径或 URL
  • --last-frame PATH/URL
    :尾帧图像的路径或 URL
  • --reference-image PATH/URL
    :添加参考图像;可重复使用以添加多张图像
  • --reference-audio URL
    :此模型不支持
  • --reference-video URL
    :此模型不支持
  • --audio
    :生成同步音频(默认:true)
  • --no-audio
    :禁用音频生成
  • --negative-prompt TEXT
    :Negative prompt(例如 "blurry, distorted, artifacts")
  • --cfg-scale NUM
    :CFG guidance scale(例如 0.5)
  • --wait
    :等待任务完成并下载或输出结果(CLI 中默认启用)
  • --no-wait
    :提交任务后立即返回 Job ID
  • --poll-interval SEC
    :状态检查的间隔秒数(默认:
    10
    )
  • --max-wait SEC
    :超时前等待的最长秒数(默认:
    600
    )
  • --download-dir DIR
    :下载已完成 MP4 视频的目录
  • -o, --output FILE
    :保存输出 JSON 或 MP4 文件的路径
  • -t, --text-only
    :仅输出视频 URL 或已下载文件的路径
  • --dry-run
    :打印请求 payload JSON 并退出,不发起网络调用
  • --token TOKEN
    :覆盖 Frevana Bearer token
  • --api-key KEY
    :覆盖 Frevana API key
  • --agent-app-instance-id ID
    :覆盖 Agent App instance ID

Guardrails

约束与防护规则

  • For semantic requests such as "720p landscape" or "square video", use
    --resolution
    with
    --aspect-ratio
    .
  • Use
    --size
    only when the user explicitly requires exact
    WIDTHxHEIGHT
    pixels; it overrides and replaces both semantic dimension fields in the request payload.
  • Validate that
    --duration
    is between 3 and 15 seconds.
  • Validate that
    --resolution
    is
    720p
    .
  • Validate that
    --aspect-ratio
    is one of
    16:9
    ,
    9:16
    , or
    1:1
    .
  • --size
    is format-checked locally but not matched against a static model allowlist; model/provider compatibility is validated by the API.
  • Do not pass
    --seed
    ; Kling Pro does not support deterministic seed.
  • Frame images and input references may be sent together; OpenRouter gives
    frameImages
    precedence and treats the request as image-to-video.
  • 对于“720p landscape”或“square video”等语义请求,使用
    --resolution
    配合
    --aspect-ratio
    。
  • 仅当用户明确要求精确的
    WIDTHxHEIGHT
    像素时使用
    --size
    ;它会覆盖并替换请求 payload 中的两个语义尺寸字段。
  • 验证
    --duration
    是否处于 3 至 15 秒之间。
  • 验证
    --resolution
    是否为
    720p
    。
  • 验证
    --aspect-ratio
    是否为
    16:9
    、
    9:16
    或
    1:1
    。
  • --size
    仅在本地检查格式,但不会与静态模型允许列表进行匹配;模型或提供商兼容性由 API 验证。
  • 不要传入
    --seed
    ;Kling Pro 不支持确定性 seed。
  • 帧图像和输入参考可以同时发送;OpenRouter 会优先使用
    frameImages
    ,并将请求视为图生视频。