按模态浏览 PROMPTS

图像 Prompts — 1438 个精选示例

面向 图像 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。

IM
图像
Landscape and Nature

Southern European hidden side street in late morning light,

Southern European hidden side street in late morning light, terracotta walls with layers of peeling cream, ochre, and dusty rose paint, narrow cobblestone lane, clay flower pots on iron-railed windowsills, single vintage bicycle leaning against a weathered wall, bougainvillea creating dappled shadows on the ground, travel photography with 28mm lens at mid-aperture

查看 API 代码
curl -X POST https://runapi.ai/api/v1/runapi/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "prompt": "Southern European hidden side street in late morning light, terracotta walls with layers of peeling cream, ochre, and dusty rose paint, narrow cobblestone lane, clay flower pots on iron-railed windowsills, single vintage bicycle leaning against a weathered wall, bougainvillea creating dappled shadows on the ground, travel photography with 28mm lens at mid-aperture"
}
JSON
IM
图像
Landscape and Nature

City avenue reclaimed by nature twenty years after human aba

City avenue reclaimed by nature twenty years after human abandonment, cracked asphalt split by tree roots pushing through, retail storefronts with shattered windows and young trees growing through the roofs, afternoon green-filtered light through the overhead canopy, muted greens, grey concrete, rust, and pale sky, quiet melancholy tone, photorealistic post-apocalyptic landscape

查看 API 代码
curl -X POST https://runapi.ai/api/v1/runapi/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "prompt": "City avenue reclaimed by nature twenty years after human abandonment, cracked asphalt split by tree roots pushing through, retail storefronts with shattered windows and young trees growing through the roofs, afternoon green-filtered light through the overhead canopy, muted greens, grey concrete, rust, and pale sky, quiet melancholy tone, photorealistic post-apocalyptic landscape"
}
JSON
IM
图像
Landscape and Nature

Floating rocky island archipelago above a vast cloud sea, ea

Floating rocky island archipelago above a vast cloud sea, each island hosting a different ecosystem — tropical jungle, walled medieval city, bare windswept cliffs — all connected by precarious rope bridges swaying in the wind, warm late afternoon light from the right, deep blue cloud sea below, saturated greens, warm sandstone, and deep azure sky, epic fantasy concept art

查看 API 代码
curl -X POST https://runapi.ai/api/v1/runapi/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "prompt": "Floating rocky island archipelago above a vast cloud sea, each island hosting a different ecosystem — tropical jungle, walled medieval city, bare windswept cliffs — all connected by precarious rope bridges swaying in the wind, warm late afternoon light from the right, deep blue cloud sea below, saturated greens, warm sandstone, and deep azure sky, epic fantasy concept art"
}
JSON
IM
图像
Landscape and Nature gpt-image-2

Solarpunk cityscape with extensive rooftop gardens and eleva

Solarpunk cityscape with extensive rooftop gardens and elevated transit lines connecting green towers, bright optimistic mood, clean vector illustration style with defined shapes and limited gradients, ample negative space in the upper-left quadrant for text overlay, 16:9 ratio, warm golden sunlight, no text

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "Solarpunk cityscape with extensive rooftop gardens and elevated transit lines connecting green towers, bright optimistic mood, clean vector illustration style with defined shapes and limited gradients, ample negative space in the upper-left quadrant for text overlay, 16:9 ratio, warm golden sunlight, no text"
}
JSON
常见问题

使用图像 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。