rw-integrate-image

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Integrate Image Generation

集成图像生成

PREREQUISITE: Run
+rw-check-compatibility
first. Run
+rw-fetch-api-reference
to load the latest API reference before integrating. Requires
+rw-setup-api-key
for API credentials. Requires
+rw-integrate-uploads
when the user has local reference images.
Help users add Runway image generation to their server-side code.
前置要求: 先运行
+rw-check-compatibility
。集成前运行
+rw-fetch-api-reference
加载最新API参考文档。需要通过
+rw-setup-api-key
配置API凭证。若用户使用本地参考图,需先执行
+rw-integrate-uploads
帮助用户在服务端代码中添加Runway图像生成功能。

Available Models

可用模型

ModelBest ForCostSpeed
gen4_image
Highest quality5 credits (720p), 8 credits (1080p)Standard
gen4_image_turbo
Fast generation2 creditsFast
gemini_2.5_flash
Google Gemini model5 creditsStandard
Model selection guidance:
  • Default recommendation:
    gen4_image
    — best quality
  • Budget/speed:
    gen4_image_turbo
    — cheapest and fastest
模型适用场景成本生成速度
gen4_image
最高画质5积分(720p),8积分(1080p)标准
gen4_image_turbo
快速生成2积分快速
gemini_2.5_flash
Google Gemini模型5积分标准
模型选择指南:
  • 默认推荐:
    gen4_image
    —— 画质最佳
  • 预算/速度优先:
    gen4_image_turbo
    —— 成本最低且生成最快

Security

安全注意事项

referenceImages[].uri
is fetched server-side by the Runway API — treat it like any outbound fetch:
  • Prefer
    runway://
    URIs
    from
    +rw-integrate-uploads
    — scoped to your account, no arbitrary web content.
  • If accepting URLs from clients, validate first: require
    https://
    , allowlist trusted hosts, reject private addresses. See the Express.js example below.
  • Never forward
    req.body.referenceImages
    straight into
    textToImage.create
    . The SDK snippets below use raw URLs for brevity — they aren't production templates.
  • Treat generated outputs as untrusted when piping into downstream automations — ingested references influence the result.
referenceImages[].uri
由Runway API在服务端获取——需像处理任何外部请求一样对待:
  • 优先使用
    +rw-integrate-uploads
    返回的
    runway://
    URI
    ——此类URI绑定到你的账户,不会加载任意网络内容。
  • 若接受客户端传入的URL,需先验证:要求使用
    https://
    协议,仅允许可信域名,拒绝私有地址。详见下方Express.js示例。
  • 切勿直接将
    req.body.referenceImages
    传入
    textToImage.create
    。下方SDK示例为简洁起见使用原始URL,但它们并非生产环境模板。
  • 当下游自动化流程使用生成结果时,需将其视为不可信内容——参考图会影响生成结果。

Endpoint:
POST /v1/text_to_image

接口:
POST /v1/text_to_image

Basic Text-to-Image

基础文本转图像

javascript
// Node.js SDK
import RunwayML from '@runwayml/sdk';

const client = new RunwayML();

const task = await client.textToImage.create({
  model: 'gen4_image',
  promptText: 'A serene Japanese garden with cherry blossoms and a koi pond',
  ratio: '1280:720'
}).waitForTaskOutput();

const imageUrl = task.output[0];
python
undefined
javascript
// Node.js SDK
import RunwayML from '@runwayml/sdk';

const client = new RunwayML();

const task = await client.textToImage.create({
  model: 'gen4_image',
  promptText: 'A serene Japanese garden with cherry blossoms and a koi pond',
  ratio: '1280:720'
}).waitForTaskOutput();

const imageUrl = task.output[0];
python
undefined

Python SDK

Python SDK

from runwayml import RunwayML
client = RunwayML()
task = client.text_to_image.create( model='gen4_image', prompt_text='A serene Japanese garden with cherry blossoms and a koi pond', ratio='1280:720' ).wait_for_task_output()
image_url = task.output[0]
undefined
from runwayml import RunwayML
client = RunwayML()
task = client.text_to_image.create( model='gen4_image', prompt_text='A serene Japanese garden with cherry blossoms and a koi pond', ratio='1280:720' ).wait_for_task_output()
image_url = task.output[0]
undefined

With Reference Images

结合参考图

Reference images let you guide the generation with visual references. Use
@Tag
syntax in the prompt to reference specific images.
Recommended: upload via
+rw-integrate-uploads
and pass the returned
runway://
URI.
javascript
import fs from 'fs';

const refUpload = await client.uploads.createEphemeral(
  fs.createReadStream('/path/to/reference.jpg')
);

const task = await client.textToImage.create({
  model: 'gen4_image',
  promptText: 'A portrait in the style of @Reference',
  referenceImages: [
    { uri: refUpload.runwayUri, tag: 'Reference' }
  ],
  ratio: '1280:720'
}).waitForTaskOutput();
External URLs also work — only pass origins you control (see Security):
javascript
const task = await client.textToImage.create({
  model: 'gen4_image',
  promptText: '@EiffelTower painted in the style of @StarryNight',
  referenceImages: [
    { uri: 'https://cdn.yourapp.com/eiffel-tower.jpg', tag: 'EiffelTower' },
    { uri: 'https://cdn.yourapp.com/starry-night.jpg', tag: 'StarryNight' }
  ],
  ratio: '1280:720'
}).waitForTaskOutput();
python
task = client.text_to_image.create(
    model='gen4_image',
    prompt_text='@EiffelTower painted in the style of @StarryNight',
    reference_images=[
        {"uri": "https://cdn.yourapp.com/eiffel-tower.jpg", "tag": "EiffelTower"},
        {"uri": "https://cdn.yourapp.com/starry-night.jpg", "tag": "StarryNight"}
    ],
    ratio='1280:720'
).wait_for_task_output()
参考图可通过视觉参考引导图像生成。在提示词中使用
@Tag
语法引用特定图像。
推荐方式: 通过
+rw-integrate-uploads
上传图片,传入返回的
runway://
URI。
javascript
import fs from 'fs';

const refUpload = await client.uploads.createEphemeral(
  fs.createReadStream('/path/to/reference.jpg')
);

const task = await client.textToImage.create({
  model: 'gen4_image',
  promptText: 'A portrait in the style of @Reference',
  referenceImages: [
    { uri: refUpload.runwayUri, tag: 'Reference' }
  ],
  ratio: '1280:720'
}).waitForTaskOutput();
外部URL也可使用——仅传入你可控的源(详见安全注意事项):
javascript
const task = await client.textToImage.create({
  model: 'gen4_image',
  promptText: '@EiffelTower painted in the style of @StarryNight',
  referenceImages: [
    { uri: 'https://cdn.yourapp.com/eiffel-tower.jpg', tag: 'EiffelTower' },
    { uri: 'https://cdn.yourapp.com/starry-night.jpg', tag: 'StarryNight' }
  ],
  ratio: '1280:720'
}).waitForTaskOutput();
python
task = client.text_to_image.create(
    model='gen4_image',
    prompt_text='@EiffelTower painted in the style of @StarryNight',
    reference_images=[
        {"uri": "https://cdn.yourapp.com/eiffel-tower.jpg", "tag": "EiffelTower"},
        {"uri": "https://cdn.yourapp.com/starry-night.jpg", "tag": "StarryNight"}
    ],
    ratio='1280:720'
).wait_for_task_output()

Common Parameters

通用参数

ParameterTypeDescription
model
stringModel ID (required)
promptText
stringText description of the image (required)
ratio
stringAspect ratio, e.g.
'1280:720'
,
'720:1280'
,
'1080:1080'
referenceImages
arrayOptional. Array of
{ uri, tag }
objects for visual guidance
参数类型描述
model
string模型ID(必填)
promptText
string图像的文本描述(必填)
ratio
string宽高比,例如
'1280:720'
'720:1280'
'1080:1080'
referenceImages
array可选。用于视觉引导的
{ uri, tag }
对象数组

Integration Pattern

集成模式

  1. Prefer uploads over URLs — Default to
    +rw-integrate-uploads
    so inputs are
    runway://
    URIs. External URLs only from origins you control (see Security).
  2. Write the server-side handler — Create an API route or server function.
  3. Handle the output — Download and store the image, don't serve signed URLs to clients.
  4. Add error handling — Wrap in try/catch.
  1. 优先使用上传而非URL——默认使用
    +rw-integrate-uploads
    ,确保输入为
    runway://
    URI。仅从你可控的源获取外部URL(详见安全注意事项)。
  2. 编写服务端处理器——创建API路由或服务端函数。
  3. 处理输出结果——下载并存储图像,不要将签名URL直接提供给客户端。
  4. 添加错误处理——使用try/catch包裹代码。

Example: Express.js API Route

示例:Express.js API路由

javascript
import RunwayML from '@runwayml/sdk';
import express from 'express';

const client = new RunwayML();
const app = express();
app.use(express.json());

// `runway://` URIs bypass this check; external URLs must match the allowlist.
const ALLOWED_MEDIA_HOSTS = new Set(['cdn.yourapp.com', 'uploads.yourapp.com']);

function validateReferenceImages(refs) {
  if (!Array.isArray(refs)) throw new Error('referenceImages must be an array');
  return refs.map(({ uri, tag }) => {
    if (typeof uri !== 'string' || typeof tag !== 'string') {
      throw new Error('each reference needs a uri and tag');
    }
    if (uri.startsWith('runway://')) return { uri, tag };
    const u = new URL(uri);
    if (u.protocol !== 'https:') throw new Error('https required');
    if (!ALLOWED_MEDIA_HOSTS.has(u.hostname)) throw new Error('untrusted media host');
    return { uri: u.toString(), tag };
  });
}

app.post('/api/generate-image', async (req, res) => {
  try {
    const { prompt, model = 'gen4_image', ratio = '1280:720', referenceImages } = req.body;

    const task = await client.textToImage.create({
      model,
      promptText: prompt,
      ratio,
      ...(referenceImages && { referenceImages: validateReferenceImages(referenceImages) })
    }).waitForTaskOutput();

    res.json({ imageUrl: task.output[0] });
  } catch (error) {
    console.error('Image generation failed:', error);
    res.status(400).json({ error: error.message });
  }
});
For browser uploads: POST files to your server, upload via
+rw-integrate-uploads
, and pass the
runway://
URI. Don't accept raw URLs from the browser.
javascript
import RunwayML from '@runwayml/sdk';
import express from 'express';

const client = new RunwayML();
const app = express();
app.use(express.json());

// `runway://` URI无需此检查;外部URL必须匹配白名单。
const ALLOWED_MEDIA_HOSTS = new Set(['cdn.yourapp.com', 'uploads.yourapp.com']);

function validateReferenceImages(refs) {
  if (!Array.isArray(refs)) throw new Error('referenceImages must be an array');
  return refs.map(({ uri, tag }) => {
    if (typeof uri !== 'string' || typeof tag !== 'string') {
      throw new Error('each reference needs a uri and tag');
    }
    if (uri.startsWith('runway://')) return { uri, tag };
    const u = new URL(uri);
    if (u.protocol !== 'https:') throw new Error('https required');
    if (!ALLOWED_MEDIA_HOSTS.has(u.hostname)) throw new Error('untrusted media host');
    return { uri: u.toString(), tag };
  });
}

app.post('/api/generate-image', async (req, res) => {
  try {
    const { prompt, model = 'gen4_image', ratio = '1280:720', referenceImages } = req.body;

    const task = await client.textToImage.create({
      model,
      promptText: prompt,
      ratio,
      ...(referenceImages && { referenceImages: validateReferenceImages(referenceImages) })
    }).waitForTaskOutput();

    res.json({ imageUrl: task.output[0] });
  } catch (error) {
    console.error('Image generation failed:', error);
    res.status(400).json({ error: error.message });
  }
});
浏览器上传说明:将文件POST到你的服务端,通过
+rw-integrate-uploads
上传,然后传入
runway://
URI。不要直接接受浏览器传入的原始URL。

Example: Next.js API Route

示例:Next.js API路由

typescript
// app/api/generate-image/route.ts
import RunwayML from '@runwayml/sdk';
import { NextRequest, NextResponse } from 'next/server';

const client = new RunwayML();

export async function POST(request: NextRequest) {
  const { prompt, referenceImages } = await request.json();

  try {
    const task = await client.textToImage.create({
      model: 'gen4_image',
      promptText: prompt,
      ratio: '1280:720',
      ...(referenceImages && { referenceImages })
    }).waitForTaskOutput();

    return NextResponse.json({ imageUrl: task.output[0] });
  } catch (error) {
    return NextResponse.json(
      { error: error instanceof Error ? error.message : 'Generation failed' },
      { status: 500 }
    );
  }
}
typescript
// app/api/generate-image/route.ts
import RunwayML from '@runwayml/sdk';
import { NextRequest, NextResponse } from 'next/server';

const client = new RunwayML();

export async function POST(request: NextRequest) {
  const { prompt, referenceImages } = await request.json();

  try {
    const task = await client.textToImage.create({
      model: 'gen4_image',
      promptText: prompt,
      ratio: '1280:720',
      ...(referenceImages && { referenceImages })
    }).waitForTaskOutput();

    return NextResponse.json({ imageUrl: task.output[0] });
  } catch (error) {
    return NextResponse.json(
      { error: error instanceof Error ? error.message : 'Generation failed' },
      { status: 500 }
    );
  }
}

Example: FastAPI Route

示例:FastAPI路由

python
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from runwayml import RunwayML

app = FastAPI()
client = RunwayML()

class ImageRequest(BaseModel):
    prompt: str
    model: str = "gen4_image"
    ratio: str = "1280:720"
    reference_images: list[dict] | None = None

@app.post("/api/generate-image")
async def generate_image(req: ImageRequest):
    try:
        params = {
            "model": req.model,
            "prompt_text": req.prompt,
            "ratio": req.ratio,
        }
        if req.reference_images:
            params["reference_images"] = req.reference_images

        task = client.text_to_image.create(**params).wait_for_task_output()
        return {"image_url": task.output[0]}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))
python
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from runwayml import RunwayML

app = FastAPI()
client = RunwayML()

class ImageRequest(BaseModel):
    prompt: str
    model: str = "gen4_image"
    ratio: str = "1280:720"
    reference_images: list[dict] | None = None

@app.post("/api/generate-image")
async def generate_image(req: ImageRequest):
    try:
        params = {
            "model": req.model,
            "prompt_text": req.prompt,
            "ratio": req.ratio,
        }
        if req.reference_images:
            params["reference_images"] = req.reference_images

        task = client.text_to_image.create(**params).wait_for_task_output()
        return {"image_url": task.output[0]}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

Tips

提示

  • Output URLs expire in 24-48 hours. Download images to your own storage immediately.
  • Reference images use
    @Tag
    syntax
    in the prompt — the tag must match the
    tag
    field in the
    referenceImages
    array.
  • For local files, always upload via
    +rw-integrate-uploads
    first, then use the
    runway://
    URI.
  • gen4_image_turbo
    is the cheapest option at 2 credits per image — good for prototyping.
  • 输出URL的有效期为24-48小时。请立即将图片下载到你自己的存储服务中。
  • 参考图在提示词中使用
    @Tag
    语法
    ——标签必须与
    referenceImages
    数组中的
    tag
    字段匹配。
  • 对于本地文件,务必先通过
    +rw-integrate-uploads
    上传,再使用
    runway://
    URI。
  • **
    gen4_image_turbo
    **是成本最低的选项,每张图片仅需2积分——适合原型开发。