kling/kling-v2.6-t2v

文档
Schema

[Core Function] Kling V2.6 T2V is a stable, classic text-to-video model. [Strengths] It provides excellent semantic adherence, top stability, and supports 1080p generation with optional audio. [Best For] Highly recommended for: stable production workflows, 5s to 10s video generation, and scenarios requiring strict prompt adherence. [Limitations] Do NOT use this model if you need 4K resolution or durations longer than 10 seconds. It is superseded by V3 for high-end tasks. [Routing] Route to this model when users prefer the classic V2.6 aesthetic or specifically ask for a stable 1080p generation. Otherwise, use V3.

$0.0500~$0.1900/sec
text-to-video

输入

Video description text, supports Chinese and English
Negative prompt describing undesired elements
Video aspect ratio
16:9
Video duration in seconds
5
Generation mode: std (standard) or pro (professional)
std
Audio generation switch: on (enable) or off (disable). Only supported by V2.6 and later versions.
on

结果

暂无结果

运行模型后，结果将在这里显示。

Next:

README

参数

参数名 描述 类型 必填 枚举值
prompt Video description text, supports Chinese and English string 是 -
negative_prompt Negative prompt describing undesired elements string 否 -
aspect_ratio Video aspect ratio string 否 16:9, 9:16, 1:1
duration Video duration in seconds integer 否 5, 10
mode Generation mode: std (standard) or pro (professional) string 否 std, pro
sound Audio generation switch: on (enable) or off (disable). Only supported by V2.6 and later versions. string 否 on, off

价格

单位: $/sec

维度 价格
mode: pro / sound: off 0.0820
mode: pro / sound: on 0.1900
mode: std / sound: off 0.0500
mode: std / sound: on 0.0820