Intangible 2.0 发布：用真实 3D 场景为 AI 视频生成提供可控性
如果你试过 Sora 或 Runway 就知道改一个镜头有多痛苦，Intangible 2.0 的做法是在生成底下垫一个真实 3D 场景，改一次就全镜头生效。做短视频、广告预演或者想认真做片子的人都值得试试。
Intangible 推出 2.0 版本，定位为整合图像、视频和 3D 模型的统一 AI 工作室。其核心思路是在每次生成底下保留一个真实 3D 场景，创作者可以摆放物体、移动相机、渲染多个镜头，而无需重建整个场景。
新功能 Canvas 可以把一段文字简报转换成带相机、参考图、图片和视频的 3D 场景（set）。由于改动作用于底层场景本身，修改会自动同步到不同镜头，解决了当前 AI 视频生成中创意控制难的痛点。
这类底层 3D 场景的做法与 Runway、Sora 等纯生成式路线不同，更接近传统影视工作流，可能让 AI 视频工具真正进入实际制片流程。
Creative control is still one of the biggest challenges in AI video generation. Intangible is approaching this with a real 3D scene underneath every generation, letting creators position objects, move cameras, and render multiple shots without rebuilding the entire scene. Its new Canvas can turn a written brief into a 3D set with cameras, references, images, and video. It also lets you make changes to the underlying scene so they carry across different shots. This could be an important step toward making AI useful for actual film production. Bharat Vasan 🇺🇸 @bharatvasan Today, excited to launch Intangible 2.0. Finally, one AI studio for image, video and 3D models. 🚀 It's an ambitious leap to translate the idea in your head onto a screen. Whether you're an aspiring Spielberg or a founder building a new product, it'll help you tell your story. To prove it, I put my cofounder @cmigos in his own action sequence, 100% shot in @intangibleai :)
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, AI视频生成, Runway, Sora.
Source attribution: curated from elvis (@omarsar0). Cross-source corroboration: 3 independent sources have covered this development (including 小互, Claude), confirming industry-wide signal strength.
