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
product_demo kling-3.0

A sleek smartphone rotates slowly on a minimalist white surf...

A sleek smartphone rotates slowly on a minimalist white surface. Dramatic studio lighting creates elegant shadows. The phone's screen displays vibrant colors that pulse gently. Camera orbits around the device with smooth, professional movement. Clean, premium aesthetic.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/kling/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "kling-3.0",
  "prompt": "A sleek smartphone rotates slowly on a minimalist white surface. Dramatic studio lighting creates elegant shadows. The phone's screen displays vibrant colors that pulse gently. Camera orbits around the device with smooth, professional movement. Clean, premium aesthetic."
}
JSON
VI
视频
product_demo veo-3.1

Artisanal coffee poured into clear glass, golden brown casca...

Artisanal coffee poured into clear glass, golden brown cascading into foam, dark background, warm rim lighting, macro close-up, premium aesthetic.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/veo_3_1/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "veo-3.1",
  "prompt": "Artisanal coffee poured into clear glass, golden brown cascading into foam, dark background, warm rim lighting, macro close-up, premium aesthetic."
}
JSON
VI
视频
product_demo seedance-2.0

Studio product shot, matte black wireless earbuds on a refle...

Studio product shot, matte black wireless earbuds on a reflective acrylic surface, slow 180-degree camera orbit, softbox reflections, premium ecommerce lighting, shallow depth of field, no text, no logo distortion.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/seedance/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "seedance-2.0",
  "prompt": "Studio product shot, matte black wireless earbuds on a reflective acrylic surface, slow 180-degree camera orbit, softbox reflections, premium ecommerce lighting, shallow depth of field, no text, no logo distortion."
}
JSON
VI
视频
product_demo seedance-2.0

Extreme macro of amber liquid pouring into crystal glass in...

Extreme macro of amber liquid pouring into crystal glass in slow motion. Droplets hang in the air, catching backlight. Ice shifts and cracks. Dolly-out reveals full glass and bottle on dark bar counter. No voiceover, only the sound of liquid and ice.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/seedance/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "seedance-2.0",
  "prompt": "Extreme macro of amber liquid pouring into crystal glass in slow motion. Droplets hang in the air, catching backlight. Ice shifts and cracks. Dolly-out reveals full glass and bottle on dark bar counter. No voiceover, only the sound of liquid and ice."
}
JSON
VI
视频
product_demo veo-3.1

A steaming pizza is pulled from a wood-fired oven on a long...

A steaming pizza is pulled from a wood-fired oven on a long wooden peel. Cheese stretches as a slice is lifted. Close-up details of the bubbling crust and charred edges. Warm, rustic Italian restaurant ambiance. Food photography lighting with warm tones.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/veo_3_1/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "veo-3.1",
  "prompt": "A steaming pizza is pulled from a wood-fired oven on a long wooden peel. Cheese stretches as a slice is lifted. Close-up details of the bubbling crust and charred edges. Warm, rustic Italian restaurant ambiance. Food photography lighting with warm tones."
}
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。