{"name":"worldforge","repo":"designfuchen/worldforge","url":"https://midorreal.com/project/designfuchen-worldforge","repository":"https://github.com/designfuchen/worldforge","description":"WorldForge 世界工坊 — Squeeze 100% out of Google Colab GPUs (RTX PRO 6000 Blackwell 98GB VRAM + 176GB DDR5 RAM + 30TB Google Drive) inside a Native macOS SwiftUI Studio App","facts":{"license":{"value":"MIT","source":"https://github.com/designfuchen/worldforge","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/designfuchen/worldforge","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/designfuchen/worldforge/releases","checked":"22 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/designfuchen/worldforge/graphs/contributors","checked":"22 Nov 2026"},"archived":{"value":"no","source":"https://github.com/designfuchen/worldforge","checked":"22 Nov 2026"}},"stars":223.0,"writeup":{"what_it_is":"WorldForge (世界工坊) is a hybrid system that runs 3D world and image/video generation models on Google Colab cloud GPUs, controlled from a native macOS SwiftUI app. It includes a local Python daemon with no pip dependencies, a remote FastAPI orchestrator on the Colab VM, and local Apple Silicon post-processing such as frame interpolation.","audience":"Creators and developers using Google Colab GPUs to generate images, videos and 3D worlds on a Mac.","claims":[{"kind":"specific","claim":"Runs on Colab RTX PRO 6000 Blackwell with 98GB VRAM and 176GB DDR5 RAM","excerpt":"RTX PRO 6000 Blackwell Server Edition","status":"not_checked"},{"kind":"specific","claim":"Local daemon uses only the Python 3 standard library","excerpt":"100% Python 3 标准库（零 pip 依赖）","status":"not_checked"},{"kind":"specific","claim":"Includes a one-click GPU benchmark for TFLOPS and bandwidth","excerpt":"一键 1.5 秒云端显卡极限算力压测","status":"not_checked"},{"kind":"broad","claim":"Native SwiftUI app with a 120Hz smooth experience","excerpt":"120Hz 原生丝滑创作体验","status":"too_broad"},{"kind":"specific","claim":"Reduces model switching time to roughly 1.2 to 1.5 seconds","excerpt":"30～50GB 模型切换仅需 **1.2～1.5 秒**","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-13"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":29,"reality":13,"gap":16,"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":"2026-11-08T06:30:03+00:00","text":"Repository created","source":"https://github.com/designfuchen/worldforge"}],"cite":"worldforge is a GitHub project at https://github.com/designfuchen/worldforge written mainly in Python, described there as \"WorldForge 世界工坊 - Squeeze 100% out of Google Colab GPUs (RTX PRO 6000 Blackwell 98GB VRAM + 176GB DDR5 RAM + 30TB Google Drive) inside a Native macOS SwiftUI Studio App\".","attribution":"Data from Mid or Real, https://midorreal.com/project/designfuchen-worldforge, checked 22 November 2026. Attribution with a link is required.","still_real":null}