| 维度 / 指标 | ![]() | ![]() |
|---|---|---|
| 官方域名 | srefhunt.com | userapi.ai |
| 定价模式 | 免费 | 免费增值,付费 |
| 月访问量 | 8011 (8,011) | 516.4万 (5,163,985) |
| 月度环比流量变化 | -2118 (-20.9%) | +8.38万 (+1.6%) |
| 主要市场与份额 | 🇺🇸 美国 (32.9%) | 🇺🇸 美国 (13.3%) |
| 直接访问 / 月 | 3191 | 380.7万 |
| 用户评分 | 4.5 | 4.2 |
| 支持的平台 | 网站 | 网站 |

免费、社区驱动的 Midjourney SREF 代码、提示词与 AI 工具
数千个精选 --sref 风格代码,按 3D、动漫、赛博朋克、油画、水彩、复古、超现实等类别整理,每条都含预览图、标签和一键复制值。
分别收录 Midjourney 提示词和 Nano Banana 提示词,并提供可搜索的图片提示词库,让你从已验证的结果出发,而非面对空白页。
Prompt Enhancer 可将粗略想法改写为详细提示词,Image to Prompt 反向将图片转为文字,免费文生图生成器可在浏览器中把提示词变为作品。
图文与视频分步指南讲解 SREF 代码是什么、如何创建,以及如何结合 --v、--ar 和 --style 参数获得一致效果。

非官方 Midjourney API——在你自己的应用中生成图像。
通过 REST API 调用 Imagine、Upscale、Variation、Blend、Describe、Animate、Upsample、Pan 与 Inpaint,实现脚本化图像生成。
在 UserAPI Cloud 账户上运行,无需 Midjourney 订阅或 Discord token,失败任务自动退款。
在单一管理面板中管理多个图像生成账户、调度与密钥。
提供 Python、Node.js、PHP 现成示例,并有 n8n 与 Make.com 自动化官方集成。

一个 API 接入 1500+ 生产级生成式媒体模型
免费 / 开源MeiGen is a community-driven gallery of trending AI image and video prompts collected from X and the wider AI art scene. Browse by category or model, copy a prompt, or remix it directly in a built-in canvas powered by leading image models, then save, favourite, or download the result. It also ships as a mobile app, an MCP server, and a ChatGPT plugin for use inside other tools.
免费 / 开源MeiGen is a community-driven gallery of trending AI image and video prompts collected from X and the wider AI art scene. Browse by category or model, copy a prompt, or remix it directly in a built-in canvas powered by leading image models, then save, favourite, or download the result. It also ships as a mobile app, an MCP server, and a ChatGPT plugin for use inside other tools.
可直接复制的落地页与首屏 AI 提示词
PromptHero is a discovery and creation hub for generative AI. You can search a vast library of curated prompts for models like Midjourney, Stable Diffusion, FLUX, Nano Banana, Veo and Sora, then use the built-in generator to turn your own ideas into images and videos in one place.
PromptHero is a discovery and creation hub for generative AI. You can search a vast library of curated prompts for models like Midjourney, Stable Diffusion, FLUX, Nano Banana, Veo and Sora, then use the built-in generator to turn your own ideas into images and videos in one place.

Replicate is a cloud API for running, fine-tuning, and deploying machine learning models. Spin up open-source and hosted models — from image, video, and audio generation to speech synthesis, captioning, and LLM inference — with one line of code, or package your own model with Cog and put it behind a production-ready API.
Replicate is a cloud API for running, fine-tuning, and deploying machine learning models. Spin up open-source and hosted models — from image, video, and audio generation to speech synthesis, captioning, and LLM inference — with one line of code, or package your own model with Cog and put it behind a production-ready API.
一个兼容 OpenAI 的 API,接入 500+ 图像、视频、音频与大模型

Runware is an AI inference platform that exposes an enormous model catalog — images, video, audio, LLMs and 3D — through a single API endpoint, alongside serverless GPU compute and reserved capacity running on modular data centers the company designs and operates itself. It is aimed at developers and product teams who want to ship generative features without managing infrastructure.
Runware is an AI inference platform that exposes an enormous model catalog — images, video, audio, LLMs and 3D — through a single API endpoint, alongside serverless GPU compute and reserved capacity running on modular data centers the company designs and operates itself. It is aimed at developers and product teams who want to ship generative features without managing infrastructure.
一个 API 调用 LLM、图像、视频与音频模型,直达生产环境