{"name":"deepopen-3d-webs","repo":"deepopen-com/deepopen-3d-webs","url":"https://midorreal.com/project/deepopen-com-deepopen-3d-webs","repository":"https://github.com/deepopen-com/deepopen-3d-webs","description":"Image-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser 图像驱动的三维场景生成系统","facts":{"language":{"value":"Python","source":"https://github.com/deepopen-com/deepopen-3d-webs","checked":"22 Nov 2026"},"homepage":{"value":"https://www.deepopen.com","source":"https://www.deepopen.com","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/deepopen-com/deepopen-3d-webs/releases","checked":"20 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/deepopen-com/deepopen-3d-webs/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/deepopen-com/deepopen-3d-webs","checked":"22 Nov 2026"}},"stars":1103.0,"writeup":{"what_it_is":"DeepOpen-3d-webs is an image-driven 3D scene generation system. A user supplies a reference image and a prompt, and the system generates scene results along a camera trajectory that can be previewed, replayed and traced. It ships as a Docker image and listens on port 8090 by default.","audience":"Creators, designers, teachers and demo presenters working on 3D scene concepts","claims":[{"kind":"specific","claim":"Runs in demo mode without a GPU, with pages, gallery demos and task replay still usable","excerpt":"Without a GPU, the pages, the gallery's 3D demos, and task replay all remain usable.","status":"not_checked"},{"kind":"specific","claim":"Web app ships as a Docker image and listens on port 8090 by default","excerpt":"The web app ships as a Docker image and listens on port `8090` by default.","status":"not_checked"},{"kind":"specific","claim":"Offers three generation trajectories and three render trajectories","excerpt":"Generation trajectories: Look Around, Overhead Orbit, Spin in Place 360","status":"not_checked"},{"kind":"specific","claim":"Full mode requires an NVIDIA GPU with 16 GB VRAM recommended","excerpt":"`LD_DEMO_MODE=0` requires an NVIDIA GPU (16 GB VRAM recommended)","status":"not_checked"},{"kind":"specific","claim":"Full mode downloads model weights on startup and needs about 30 GB of cache","excerpt":"Full mode downloads the diffusion and ZoeDepth weights on startup; allow about 30 GB of cache.","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":16,"reality":19,"gap":-3,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-26T12:13:47+00:00","text":"Repository created","source":"https://github.com/deepopen-com/deepopen-3d-webs"}],"cite":"deepopen-3d-webs is a GitHub project at https://github.com/deepopen-com/deepopen-3d-webs written mainly in Python, described there as \"Image-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser 图像驱动的三维场景生成系统\".","attribution":"Data from Mid or Real, https://midorreal.com/project/deepopen-com-deepopen-3d-webs, checked 22 November 2026. Attribution with a link is required.","still_real":null}