zf-kbot/md-me-video-editor-0706

Public
7.4K runs

Run zf-kbot/md-me-video-editor-0706 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
apikey
string
API 密钥
mode
None
i2v
任务类型
input_image
string
主参考图,接入 BerniniStudio.image0
reference_image
string
第二参考图,接入 BerniniStudio.image1
video
string
源视频,接入 BerniniStudio.source_video
prompt
string
让 image0 中的主体自然动起来,动作自然连贯
视频提示词,可用 image0 / image1 指代参考图
negative_prompt
string
低质量视频
负向提示词
megapixels
number
0.4

Min: 0.1

Max: 1

目标百万像素,视频宽高会按输入媒体比例计算
duration
number
3

Min: 1

Max: 10

视频时长(秒),内部会换算成 4n+1 帧
fps
None
16
输出帧率
aspect_ratio
None
16:9
纯文生视频时使用的画面比例
seed
integer
-1
随机种子,-1 为随机
steps
integer
4

Min: 1

Max: 20

采样步数
split_step
integer
2

Min: 1

Max: 19

高低噪声模型切换步数,必须小于 steps
use_default_neg
boolean
True
启用 BerniniStudio 默认负向词

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "title": "Output"
}