模型 PROMPTS

nano-banana-2 Prompts — 1027 个精选示例

通过 RunAPI 使用 nano-banana-2 的示例。复制 prompt 后，可在 Claude Code、Codex、Cursor、Windsurf 或后端 API 中使用。

模型

nano-banana-2

模态: 图像
提供方: Google
Endpoint: Text To Image

1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. 重启 Claude Code
3. 粘贴这个 prompt：生成一张图像："Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"

1. codex plugin install runapi-mcp@agents
2. 重启 Codex
3. 粘贴这个 prompt：生成一张图像："Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"

1. npx @runapi.ai/mcp init cursor
2. 重启 Cursor
3. 粘贴这个 prompt：生成一张图像："Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"

1. npx @runapi.ai/mcp init windsurf
2. 重启 Windsurf
3. 粘贴这个 prompt：生成一张图像："Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"

curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "nano-banana-2",
  "prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
}
JSON

import { NanoBananaClient } from "@runapi.ai/nano-banana";

const client = new NanoBananaClient({
  apiKey: process.env.RUNAPI_API_KEY,
});

const result = await client.textToImage.run({
  "model": "nano-banana-2",
  "prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
});
console.log(result.id);

require "runapi/nano_banana"

client = RunApi::NanoBanana::Client.new
result = client.text_to_image.run(
  model: "nano-banana-2",
  prompt: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
)
puts result.id

package main

import (
  "context"
  "fmt"
  "log"
  "net/http"
  "os"
  "strings"
)

func main() {
  body := strings.NewReader("{\"model\":\"nano-banana-2\",\"prompt\":\"Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”\"}")
  req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/nano_banana/text_to_image", body)
  if err != nil {
    log.Fatal(err)
  }

  req.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
  req.Header.Set("Content-Type", "application/json")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
    log.Fatal(err)
  }
  defer resp.Body.Close()

  fmt.Println(resp.Status)
}

nano-banana-2 /api/v1/nano_banana/text_to_image 获取 API Key

分类全部分类 double-exposure Food & Drink Illustration & 3D Photography Poster Design Product & Brand UI & Graphic

图像

Food & Drink nano-banana-2

{ "production_manifest": { "metadata": { "series...

{ "production_manifest": { "metadata": { "series_id": "CIN-FOOD-2025", "aspect_ratio": "9:16", "resolution_target": "8k_uhd" }, "technical_stack": { "hardware": { "camera": "ARRI Alexa 65", "lens_profile": "Large format cinematic prime" }, "film_emulation": { "stock": "Kodak Portra 400", "characteristics": ["Fine grain", "Natural skin tones", "Warm highlights"] }, "lighting_rig": { "style": "Cinematic soft glow", "atmosphere": "Timeless indoor", "diffusion": "High" } }, "artistic_direction": { "visionary_style": "Greta Gerwig", "composition_rule": "Graphic centered symmetry", "physics_engine": "Suspended animation / Zero gravity", "background_specification": "Flat off-white / Studio bone" }, "variant_registry": [ { "id": "VAR-001", "flavor_profile": "Dark Chocolate Chip & Oat", "tonal_emotion": "Playful, cheeky yet chic", "ingredients": { "primary_solids": ["Dark chocolate chip cookies"], "fluid_fx": ["Oat milk splash"], "debris": ["Cookie crumbs"] } }, { "id": "VAR-002", "flavor_profile": "Red Velvet", "tonal_emotion": "Bold, playful chic", "ingredients": { "primary_solids": ["Red velvet cake pieces"], "fluid_fx": ["Cream cheese frosting swirls"], "debris": ["Cocoa dust", "Fine red cake crumbs"] } }, { "id": "VAR-003", "flavor_profile": "Pistachio Macaron", "tonal_emotion": "Refined, playful chic", "ingredients": { "primary_solids": ["Pistachio macarons"], "fluid_fx": ["Cream filling swirls"], "debris": ["Crushed pistachio nuts"] } }, { "id": "VAR-004", "flavor_profile": "Strawberry Shortcake", "tonal_emotion": "Sweet, playful yet chic", "ingredients": { "primary_solids": ["Fresh strawberry slices"], "fluid_fx": ["Whipped cream swirls"], "debris": ["Shortcake biscuit crumbs"] } } ] } }

/api/v1/nano_banana/text_to_image

查看 API 代码

curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "nano-banana-2",
  "prompt": "{ \"production_manifest\": { \"metadata\": { \"series_id\": \"CIN-FOOD-2025\", \"aspect_ratio\": \"9:16\", \"resolution_target\": \"8k_uhd\" }, \"technical_stack\": { \"hardware\": { \"camera\": \"ARRI Alexa 65\", \"lens_profile\": \"Large format cinematic prime\" }, \"film_emulation\": { \"stock\": \"Kodak Portra 400\", \"characteristics\": [\"Fine grain\", \"Natural skin tones\", \"Warm highlights\"] }, \"lighting_rig\": { \"style\": \"Cinematic soft glow\", \"atmosphere\": \"Timeless indoor\", \"diffusion\": \"High\" } }, \"artistic_direction\": { \"visionary_style\": \"Greta Gerwig\", \"composition_rule\": \"Graphic centered symmetry\", \"physics_engine\": \"Suspended animation / Zero gravity\", \"background_specification\": \"Flat off-white / Studio bone\" }, \"variant_registry\": [ { \"id\": \"VAR-001\", \"flavor_profile\": \"Dark Chocolate Chip & Oat\", \"tonal_emotion\": \"Playful, cheeky yet chic\", \"ingredients\": { \"primary_solids\": [\"Dark chocolate chip cookies\"], \"fluid_fx\": [\"Oat milk splash\"], \"debris\": [\"Cookie crumbs\"] } }, { \"id\": \"VAR-002\", \"flavor_profile\": \"Red Velvet\", \"tonal_emotion\": \"Bold, playful chic\", \"ingredients\": { \"primary_solids\": [\"Red velvet cake pieces\"], \"fluid_fx\": [\"Cream cheese frosting swirls\"], \"debris\": [\"Cocoa dust\", \"Fine red cake crumbs\"] } }, { \"id\": \"VAR-003\", \"flavor_profile\": \"Pistachio Macaron\", \"tonal_emotion\": \"Refined, playful chic\", \"ingredients\": { \"primary_solids\": [\"Pistachio macarons\"], \"fluid_fx\": [\"Cream filling swirls\"], \"debris\": [\"Crushed pistachio nuts\"] } }, { \"id\": \"VAR-004\", \"flavor_profile\": \"Strawberry Shortcake\", \"tonal_emotion\": \"Sweet, playful yet chic\", \"ingredients\": { \"primary_solids\": [\"Fresh strawberry slices\"], \"fluid_fx\": [\"Whipped cream swirls\"], \"debris\": [\"Shortcake biscuit crumbs\"] } } ] } }"
}
JSON

图像

Food & Drink nano-banana-2

2x2 grid, do this for 4 famous cuisines: function dish(AA){...

2x2 grid, do this for 4 famous cuisines: function dish(AA){ <instruction> Input A is a Famous Dish / Culinary Tradition / Signature Dessert / Regional Specialty. Analyze: - ingredient hierarchy, cooking method, plating logic - origin region, historical story, ritual or social context - flavor architecture translated into visual composition - symbolic ingredients, cookware, and dining environment - chef or tradition lineage Goal: A "sauce pour environment." A giant ladle, piping bag, or sauce boat is pouring the primary sauce, cream, glaze, broth, or puree onto a table. The flowing edible medium rises into a detailed 3D world of the dish: ingredients, preparation stages, origin landscape, and plated final form merging together. Rules: - the poured substance must remain recognizably edible while forming the scene - include knives, cutting board, handwritten recipe notes, ingredient trays, steam, spice dust, region-appropriate tools - include a tiny chef or grandmother figure preparing a miniature version nearby - include a food critic headline, market receipt, or origin-story clipping - semantically infer cuisine-specific vessels, table culture, garnish logic, and environment - no random food pile; composition must reveal flavor structure and culinary history - lighting: appetizing natural kitchen light with rich edible texture Output: ONE image, 4:5, culinary-process diorama aesthetic </instruction> Output: 2x2 grid, each grid with a different dish(AA) output }

/api/v1/nano_banana/text_to_image

查看 API 代码

curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "nano-banana-2",
  "prompt": "2x2 grid, do this for 4 famous cuisines: function dish(AA){ <instruction> Input A is a Famous Dish / Culinary Tradition / Signature Dessert / Regional Specialty. Analyze: - ingredient hierarchy, cooking method, plating logic - origin region, historical story, ritual or social context - flavor architecture translated into visual composition - symbolic ingredients, cookware, and dining environment - chef or tradition lineage Goal: A \"sauce pour environment.\" A giant ladle, piping bag, or sauce boat is pouring the primary sauce, cream, glaze, broth, or puree onto a table. The flowing edible medium rises into a detailed 3D world of the dish: ingredients, preparation stages, origin landscape, and plated final form merging together. Rules: - the poured substance must remain recognizably edible while forming the scene - include knives, cutting board, handwritten recipe notes, ingredient trays, steam, spice dust, region-appropriate tools - include a tiny chef or grandmother figure preparing a miniature version nearby - include a food critic headline, market receipt, or origin-story clipping - semantically infer cuisine-specific vessels, table culture, garnish logic, and environment - no random food pile; composition must reveal flavor structure and culinary history - lighting: appetizing natural kitchen light with rich edible texture Output: ONE image, 4:5, culinary-process diorama aesthetic </instruction> Output: 2x2 grid, each grid with a different dish(AA) output }"
}
JSON

常见问题

使用 nano-banana-2 prompts

%{model} 是什么？

%{model} 是 RunAPI 统一模型目录中的模型。这些 prompts 展示了 agent 和后端服务可以复用的实际输入模式。

如何使用这些 prompts？

安装 RunAPI MCP Server 后，复制任意 prompt 并粘贴到 Claude Code、Codex、Cursor 或 Windsurf。开发者也可以复制 API 示例直接调用。

浏览这些 prompts 要付费吗？

浏览和复制 prompt 示例是免费的。只有当你使用 API key 调用 RunAPI 模型生成内容时，才会产生费用。

这些 prompts 可以用于生产环境吗？

可以。把每个 prompt 当作起点，再补充品牌规则、输出尺寸、安全约束和你的业务上下文。