| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | runninghub.ai | chromewebstore.google.com |
| 定價模式 | 免費增值 | 免費 |
| 每月造訪次數 | 310.56萬 (3,105,554) | 0 (0) |
| 月流量變化量 | -123.77萬 (-28.5%) | 0 (—) |
| 主要市場與市佔 | 🇨🇳 中國 (52.7%) | 🌐 全球 (—) |
| 每月直接造訪 | 229.72萬 | 0 |
| 使用者評分 | 4.4 | 4.5 |
| 支援平台 | 網站 | 瀏覽器擴充功能 |

RunningHub is a cloud platform for running ComfyUI workflows online, building AI apps, and generating images and videos with hosted models and APIs.
Run, import, and share ComfyUI workflows in the cloud without local GPU hardware.
Publish a workflow as a single-click AI app that anyone can run with simple inputs.
Use hosted image and video models, including self-developed upscaling and enhancement tools, from one dashboard.
Integrate generation into your product via workflow, model, LLM, and app APIs.

瀏覽器原生大模型,觸手可及,私密又離線
大型語言模型打包在擴充功能內,並在瀏覽器隔離沙盒中執行,無需伺服器、帳號或 API 金鑰即可上手。
所有請求都在你的機器上完成,提示詞與資料不經過第三方伺服器,離線時也能繼續運作。
網站與擴充功能可透過 window.ai 介面申請呼叫你的模型,讓瀏覽器成為網頁應用共享的 AI 執行環境。
你可以決定哪些應用可以存取模型,並檢視跨應用的歷史提示與回覆紀錄。
專項更強面向電影級影片與圖像的 AI 原生創作套件
免費 / 開源在本機或雲端執行與打造開源 AI 模型
一站式 AI 影片、圖像與代理式內容創作工作室
專項更強在瀏覽器中免費生成 AI 圖像與影片,並託管模型

專項更強Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
專項更強Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.

免費 / 開源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.
免費 / 開源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.