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
illustration seedream-5-lite-text-to-image

Children's book illustration — fox in autumn forest

Whimsical children's book illustration of a small red fox sitting on a moss-covered log in an autumn forest. Golden and amber leaves drift down around the fox, who looks upward with bright curious eyes. The trees are stylized with round, soft canopies in warm oranges, yellows, and deep reds. Soft watercolor textures with visible paper grain. Gentle, warm lighting as if the entire scene glows from within. The style is cozy and inviting, suitable for ages 3-7, with slightly oversized eyes on the fox for expressiveness.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/seedream/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "seedream-5-lite-text-to-image",
  "prompt": "Whimsical children's book illustration of a small red fox sitting on a moss-covered log in an autumn forest. Golden and amber leaves drift down around the fox, who looks upward with bright curious eyes. The trees are stylized with round, soft canopies in warm oranges, yellows, and deep reds. Soft watercolor textures with visible paper grain. Gentle, warm lighting as if the entire scene glows from within. The style is cozy and inviting, suitable for ages 3-7, with slightly oversized eyes on the fox for expressiveness."
}
JSON
IM
图像
illustration flux-2-flex-text-to-image

Flat illustration — remote work setup

Flat vector illustration of a cozy home office setup viewed from slightly above. A wooden desk holds an open laptop, a potted monstera plant, a ceramic coffee mug with steam rising, scattered sticky notes, and a pair of round glasses. A cat sleeps curled up on an ergonomic chair beside the desk. The wall behind has a pegboard with headphones hanging and a small shelf with three books. Warm, pastel color palette — dusty pink walls, sage green plant, cream desk. Clean lines, no outlines, geometric shapes with subtle grain texture overlay. Suitable for a blog header illustration.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/flux_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "flux-2-flex-text-to-image",
  "prompt": "Flat vector illustration of a cozy home office setup viewed from slightly above. A wooden desk holds an open laptop, a potted monstera plant, a ceramic coffee mug with steam rising, scattered sticky notes, and a pair of round glasses. A cat sleeps curled up on an ergonomic chair beside the desk. The wall behind has a pegboard with headphones hanging and a small shelf with three books. Warm, pastel color palette — dusty pink walls, sage green plant, cream desk. Clean lines, no outlines, geometric shapes with subtle grain texture overlay. Suitable for a blog header illustration."
}
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。