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
Vintage and Retro gpt-image-2

Modern pencil illustration of a vintage travel poster for th

Modern pencil illustration of a vintage travel poster for the Amalfi Coast, Italy. Classic 1960s white convertible car on a curved seaside road, deep blue Mediterranean sea with small white sailboats, pastel-colored hillside village cascading down the cliff, warm golden sunlight, retro 1950s tourism poster style, subtle screen print texture with slight color misregistration

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": "Modern pencil illustration of a vintage travel poster for the Amalfi Coast, Italy. Classic 1960s white convertible car on a curved seaside road, deep blue Mediterranean sea with small white sailboats, pastel-colored hillside village cascading down the cliff, warm golden sunlight, retro 1950s tourism poster style, subtle screen print texture with slight color misregistration"
}
JSON
IM
图像
Vintage and Retro gpt-image-2

Realistic front page of a vintage newspaper with cinematic b

Realistic front page of a vintage newspaper with cinematic black-and-white aesthetic. Bold sans-serif headline across the top. Multiple columns of small justified text. Fictitious publication name, date, and issue number in the masthead. Decorative horizontal rules between sections. Fine aged paper texture with visible grain, subtle ink imperfections, and slight yellowing. 4:5 aspect ratio.

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": "Realistic front page of a vintage newspaper with cinematic black-and-white aesthetic. Bold sans-serif headline across the top. Multiple columns of small justified text. Fictitious publication name, date, and issue number in the masthead. Decorative horizontal rules between sections. Fine aged paper texture with visible grain, subtle ink imperfections, and slight yellowing. 4:5 aspect ratio."
}
JSON
IM
图像
Vintage and Retro

Retro 80s sci-fi movie poster, neon typography in hot pink a

Retro 80s sci-fi movie poster, neon typography in hot pink and electric blue, bright saturated colors, grain texture, vaporwave aesthetic, synthwave sunset gradient in background, illustrated central layout with a chrome robot silhouette, palm trees flanking the sides, scan lines across the image

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": "Retro 80s sci-fi movie poster, neon typography in hot pink and electric blue, bright saturated colors, grain texture, vaporwave aesthetic, synthwave sunset gradient in background, illustrated central layout with a chrome robot silhouette, palm trees flanking the sides, scan lines across the image"
}
JSON
IM
图像
Vintage and Retro

pixel art, 16-bit retro game style, warrior knight character

pixel art, 16-bit retro game style, warrior knight character sprite with sword and shield, standing pose, clean pixel borders, limited color palette of 16 colors, inspired by classic SNES RPG games, game asset, transparent background, 32x32 pixel grid visible

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": "pixel art, 16-bit retro game style, warrior knight character sprite with sword and shield, standing pose, clean pixel borders, limited color palette of 16 colors, inspired by classic SNES RPG games, game asset, transparent background, 32x32 pixel grid visible"
}
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。