ProductsMulti-source

Intangible 2.0 发布 Canvas:用 AI 搭建和执导 3D 场景的工作台

Why we picked it

Intangible 的 Canvas 能把一段文字变成带光照和摄影机的 3D 场景,改一处物体后续渲染自动同步,还能接 Claude 帮你搭场景。JetZero 已经拿它展示还没试飞的飞机,做预演或产品可视化的团队可以看看。

Intangible 推出 2.0 版本,核心新功能 Canvas 是一个面向 3D 环境搭建与执导的 AI 工作台,可以把一段文字 brief 转成包含物体、参考素材、光照和摄影机的完整 3D 场景。用户能移动摄影机、重新摆放物体并生成不同机位的电影级镜头,同时保持底层场景一致;修改一个参考或物体后,改动会带入后续渲染,不需要从头反复生成。Canvas 还支持接入 Claude 等 AI 助手来搭建和修改场景,用户随时可以手动接管。

Body

这款产品的定位是从"让 AI 想象一个场景"转向"控制 AI 生成的世界",强调导演式的可控性而非一次性出图。航空初创公司 JetZero 已经在用 Intangible 可视化尚未试飞的飞机,用于向航空公司和投资人展示设计方案。对影视预演、广告和产品可视化方向的团队来说,这种"场景一致 + 多机位渲染"的工作流降低了对传统 3D 建模流程的依赖。

Original · rohanpaul_ai

If AI can generate an entire movie scene, you should be able to direct it.

Intangible just launched 2.0, introducing Canvas, an AI-powered workspace for building and directing 3D environments.

> Turn a written brief into a 3D scene with objects, references, lighting, and cameras.

> Move cameras, reposition objects, and generate different cinematic shots while keeping the underlying scene consistent.

> Edit a reference or object once and carry those changes into subsequent renders, instead of repeatedly generating everything from scratch.

> Connect Claude or other supported AI assistants to build and modify scenes, with the ability to take over manually at any point.

> JetZero is already using Intangible to visualize aircraft that haven't flown yet, helping present its designs to airlines and investors.

The interesting shift is from asking AI to imagine a scene to actually controlling the world it generates.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Intangible, Canvas, Claude, 3D 场景.

Source attribution: curated from rohanpaul_ai (@rohanpaul_ai). Cross-source corroboration: 3 independent sources have covered this development (including elvis, Claude), confirming industry-wide signal strength.