使用 Cloudflare Workers AI 免费搭建 stable-diffusion 绘画 API

终于 Cloudflare Workers AI 模型增加了 @cf/stabilityai/stable-diffusion-xl-base-1.0，目前可以免费白嫖，记录一下使用过程。

准备

• Cloudflare 账号
• Node 环境

1.安装 Wrangler

sudo npm install -g wrangler

2.授权

wrangler login

执行这个命令后会跳转到浏览器 Cloudflare 授权界面，操作授权即可。

3.初始化项目

wrangler init

根据提示选择配置，模版选择 "Hello World"。

╭ Create an application with Cloudflare Step 1 of 3
│
├ In which directory do you want to create your application?
│ dir ./tiny-frog-cc56
│
├ What type of application do you want to create?
│ type "Hello World" Worker
│
├ Do you want to use TypeScript?
│ no typescript
│
├ Copying files from "hello-world" template
│
├ Retrieving current workerd compatibility date
│ compatibility date 2023-10-30
│
├ Do you want to use git for version control?
│ yes git
│
╰ Application created

╭ Installing dependencies Step 2 of 3
│
├ Installing dependencies
│ installed via `npm install`
│
├ Committing new files
│ git commit
│
╰ Dependencies Installed

╭ Deploy with Cloudflare Step 3 of 3
│
├ Do you want to deploy your application?
│ no deploy via `npm run deploy`
│
├  APPLICATION CREATED  Deploy your application with npm run deploy
│
│ Navigate to the new directory cd tiny-frog-cc56
│ Run the development server npm run start
│ Deploy your application npm run deploy
│ Read the documentation https://developers.cloudflare.com/workers
│ Stuck? Join us at https://discord.gg/cloudflaredev
│
╰ See you again soon!

4.安装 AI 相关依赖和配置

npm install --save @cloudflare/ai

在 wrangler.toml 添加：

[ai]
binding = "AI"

5.修改 src/index.js

import { Ai } from '@cloudflare/ai'

export default {
  async fetch(request, env) {

    const url = new URL(request.url);

    const prompt = url.searchParams.get("prompt");

    const ai = new Ai(env.AI);

    const inputs = {
        prompt: prompt,
    };

    const response = await ai.run("@cf/stabilityai/stable-diffusion-xl-base-1.0", inputs);

    return new Response(response, {
        headers: {
            "content-type": "image/png",
        },
    });

  }
}

6.运行

wrangler dev --remote

浏览器访问 http://127.0.0.1:8787/?prompt=cyberpunk%20cat ，prompt 参数就是提示词。

7.部署

其实本地运行就够了，如果想放到线上，执行以下部署命令:

wrangler deploy