AITOPAI热报
How-toOfficialSelected

JEV model generates 3D indoor scenes in one second

我的 JEV 案例：https://t.co/KUnD8dF6NS

官方一手歸藏(guizang.ai)@op7418
Post
View the post
Why we picked it

Developers building interior-design, game or AR tools can replicate this workflow by pairing JEV with pre-built model libraries instead of generating 3D meshes from scratch.

Guizang (@op7418), a Chinese AI commentator, built a real-time 3D scene generator using the JEV model from TypeSafe AI. The system selects from dozens to hundreds of pre-built 3D models based on input text, running hundreds of concurrent judgments. It simultaneously handles the colouring, lighting, position and state of each asset, assembling a compliant indoor scene in one second. The demo, shared on X, shows text-to-scene assembly from existing assets rather than mesh generation from scratch.

Original · 歸藏(guizang.ai)

我的 JEV 案例：https://t.co/KUnD8dF6NS

我的 JEV 案例： x.com/op7418/status/… 歸藏(guizang.ai) @op7418 我用 @typesafeai JEV 模型做了一个实时 3D 场景生成器。 这个速度实在太夸张了！ 从预制的几十上百种 3D 模型里，根据输入的文案，进行并发几百次的判断。 同时对这些素材的着色、光照、位置以及状态进行处理，一秒完成符合要求的室内场景搭建。 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 1 👀 1173 ⚡

#JEV#TypeSafe AI#3D generation#Guizang

Keep reading

Recent stories with the same tag or section
ModelsBuildersOfficialSelected14:08
JEV 1.14.0 adds multimodal support, box output and 262K context

The update closes specific gaps analysts flagged weeks earlier, which is a rare case of a vendor visibly acting on public feedback. Developers building image and video pipelines can now get object coordinates directly from the model instead of adding a separate detection step. The 262K context also makes long multilingual document and media workflows viable on a single model.

#JEV#multimodal#context window#multilingual
官方一手歸藏(guizang.ai)@op7418Source
ProductsBuildersOfficialSelected13:11
JEV 1.14.0 adds multimodal support and 262K context

The "box" output type is the quiet highlight: returning object coordinates means JEV can now drive GUI-style automation and visual grounding workflows that text-only setups cannot. Developers building image-editing or agent pipelines can pair the 262K context with the new type to chain several visual steps in one request. Compared with tools that expose multimodality from day one, JEV took two releases to get there, so regression risk in 1.14.0 deserves a quick test.

#JEV#multimodal#coding assistants
官方一手歸藏(guizang.ai)@op7418Source