ComfyUI 每月有 4,379,348 次造訪,月增率 +13.4%,定價模式為需聯絡報價、免費。Immersity (LeiaPix) 每月有 6,617 次造訪,成長率 -62.5%,定價模式為需聯絡報價。

把日常照片與影片變成沉浸式 3D 體驗
| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | comfy.org | leiapix.com |
| 定價模式 | 需聯絡報價、免費 | 需聯絡報價 |
| 每月造訪次數 | 437.93萬 (4,379,348) | 6617 (6,617) |
| 月流量變化量 | +51.71萬 (+13.4%) | -1.1萬 (-62.5%) |
| 主要市場與市佔 | 🇺🇸 美國 (18.4%) | 🇮🇳 印度 (39.6%) |
| 每月直接造訪 | 154.94萬 | 2599 |
| 使用者評分 | 4.8 | 4.1 |
| 支援平台 | 網站 | 網站 |

以節點為基礎的視覺 AI 工作台,涵蓋圖像、影片、3D 與音訊
在無限畫布上串接模型、取樣器、條件輸入、LoRA 與輸出節點,每一步都清楚可見、隨時可調。
同一介面支援圖像生成、影片、3D 資產與音訊或音樂工作流,相容主流開源與合作夥伴模型。
可用自有 GPU 在本機執行 ComfyUI,硬體不足時也能在雲端開啟相同工作流。
把任何工作流部署為生產 API,讓你的應用或代理按需生成內容。

把日常照片與影片變成沉浸式 3D 體驗
上傳照片,AI 估算深度圖並建立帶自然運動視差的分層 3D 場景。
把一般影片變成帶深度資訊的畫面,讓場景顯得立體而非扁平。
產生短循環的深度動畫,非常適合專輯封面、產品圖與社群內容。
匯出的空間內容可跨手機、平板、空間顯示器以及 Apple Vision Pro、Meta Quest 等頭顯使用。
Hyper3D Rodin is an AI 3D asset generator that converts text prompts or reference images into detailed, editable 3D models with ready-to-use UVs. It pairs generative 3D with ControlNet-style spatial guidance, partial editing, texture, HDRI and avatar tools, an API, MCP access and plug-ins for major 3D pipelines.
Hyper3D Rodin is an AI 3D asset generator that converts text prompts or reference images into detailed, editable 3D models with ready-to-use UVs. It pairs generative 3D with ControlNet-style spatial guidance, partial editing, texture, HDRI and avatar tools, an API, MCP access and plug-ins for major 3D pipelines.

VIVA (vivago.ai) is an AI creation platform built around a conversational agent, letting you generate videos and images, enhance footage to high resolution, and edit visuals with tools like Magic Brush and Magic Eraser.
VIVA (vivago.ai) is an AI creation platform built around a conversational agent, letting you generate videos and images, enhance footage to high resolution, and edit visuals with tools like Magic Brush and Magic Eraser.
數分鐘內將文字、圖片與影片轉換為可投入生產的 3D 資產

專項更強Focuses on custom game asset training and node workflows, but lacks ComfyUI's infinite open-source node flexibility.
提供專為 ComfyUI 與 Stable Diffusion 預先配置的專用雲端執行個體,可取代本地工作站設定。
提供專為 ComfyUI 與 Stable Diffusion 預先配置的專用雲端執行個體,可取代本地工作站設定。
用 AI 把任何 2D 照片變成可 3D 列印的 STL 檔案
幾分鐘內把單張圖片或文字提示變成可用的 3D 模型

TRELLIS 3D AI is a browser-based generator that turns a single photo into a textured, downloadable 3D model in seconds. Upload an image, let the platform's TRELLIS-style pipeline reconstruct geometry and surface detail, preview the result in an interactive 3D viewer, and export it as GLB, OBJ, STL, GLTF, USDZ or PLY. No modeling software or prior 3D experience is required.
TRELLIS 3D AI is a browser-based generator that turns a single photo into a textured, downloadable 3D model in seconds. Upload an image, let the platform's TRELLIS-style pipeline reconstruct geometry and surface detail, preview the result in an interactive 3D viewer, and export it as GLB, OBJ, STL, GLTF, USDZ or PLY. No modeling software or prior 3D experience is required.
用 AI 把平面圖片變成可直接使用的 3D 模型