按模态浏览 PROMPTS

视频 Prompts — 38 个精选示例

面向 视频 生成工作流的 prompt 示例。按分类筛选,复制 prompt,或打开模型专属 API 代码。

VI
视频
lifestyle wan-2.6-text-to-video

Lifestyle — hands crafting pottery on a wheel

Close-up shot of skilled hands shaping wet clay on a spinning pottery wheel. The camera focuses on the hands and clay, showing fingers pressing inward to form the walls of a bowl. Muddy water splashes slightly with each rotation. The clay surface glistens under warm overhead workshop lighting. The potter's hands are steady and precise, pulling the clay upward in smooth practiced motions. Background is a soft blur of shelves with finished ceramics in earth-toned glazes. The wheel spins counterclockwise at a steady pace. Natural sound design — the wet squelch of clay and the hum of the wheel motor.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/wan/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "wan-2.6-text-to-video",
  "prompt": "Close-up shot of skilled hands shaping wet clay on a spinning pottery wheel. The camera focuses on the hands and clay, showing fingers pressing inward to form the walls of a bowl. Muddy water splashes slightly with each rotation. The clay surface glistens under warm overhead workshop lighting. The potter's hands are steady and precise, pulling the clay upward in smooth practiced motions. Background is a soft blur of shelves with finished ceramics in earth-toned glazes. The wheel spins counterclockwise at a steady pace. Natural sound design — the wet squelch of clay and the hum of the wheel motor."
}
JSON
常见问题

使用视频 prompts

好的%{model} prompt 应该包含什么?

有用的%{model} prompt 会清楚写出主体、风格、约束和输出目标。这里的示例足够短,便于复制;同时也足够具体,agent 或后端任务能保留生成意图。

这些 prompts 可以跨模型复用吗?

多数情况下可以。先从同一模态的 prompt 开始,再按模型调整画幅、时长、声音设置或风格控制。详情页会把保存过的参数列在 prompt 文本旁边。

在哪里找正确的模型 slug?

每张卡片都会显示 RunAPI 模型 slug。只想看一个模型的示例时,打开模型页;需要定价和能力细节时,进入模型目录页查看。

agent 可以直接调用这些 prompts 吗?

可以。安装 RunAPI MCP Server 后,复制 prompt 详情页里的 agent 指令。页面会把 prompt 文本、模型 slug 和 endpoint 路径放在一起,给 agent 足够上下文。