# Overworld发布实时交互式视频扩散模型Waypoint-1 - 来源：Hugging Face：Blog（RSS） - 发布时间：2026-01-20 08:00 - AIHOT 分数：73 - AIHOT 标记：精选 - AIHOT 链接：https://aihot.virxact.com/items/cmoegbhak009vslxxtzhg8qp7 - 原文链接：https://huggingface.co/blog/waypoint-1 ## 精选理由 零延迟交互式视频生成，游戏和创意应用开发者的福音。 ## AI 摘要 Overworld推出实时交互式视频扩散模型Waypoint-1，用户可通过文本、鼠标和键盘实时控制生成可步入的虚拟世界。该模型基于帧因果校正流变换器架构，在1万小时游戏视频及对应控制数据上训练，从一开始就专注于交互体验，支持零延迟的自由操控。其配套的高性能推理库WorldEngine在消费级硬件上可实现流畅运行，例如Waypoint-1-Small在RTX 5090上能以30 FPS（4步去噪）或60 FPS（2步去噪）生成画面。模型采用扩散强制预训练和自我强制后训练来确保生成长序列的稳定性。 ## 正文 Waypoint-1: Real-time Interactive Video Diffusion from Overworld Published January 20, 2026 Andrew Lapp lapp0 Overworld Louis Castricato LouisCastricato Overworld Scott Fox ScottieFox Overworld Shahbuland Matiana shahbuland Overworld David Rossi xAesthetics Overworld Waypoint-1 Weights on the Hub Waypoint-1-Small Waypoint-1-Medium (Coming Soon!) Try Out The Model Overworld Stream: https://overworld.stream What is Waypoint-1? Waypoint-1 is Overworld’s real-time-interactive video diffusion model, controllable and prompted via text, mouse, and keyboard. You can give the model some frames, run the model, and have it create a world you can step into and interact with. The backbone of the model is a frame-causal rectified flow transformer trained on 10,000 hours of diverse video game footage paired with control inputs and text captions. Waypoint-1 is a latent model, meaning that it is trained on compressed frames. The standard among existing world models has become taking pre-trained video models and fine-tuning them with brief and simplified control inputs. In contrast, Waypoint-1 is trained from the get-go with a focus on interactive experiences. With other models, controls are simple: you can move and rotate the camera once every few frames, with severe latency issues. With Waypoint-1 you are not limited at all as far as controls are concerned. You can move the camera freely with the mouse, and input any key on the keyboard, and all this with zero latency. Each frame is generated with your controls as context. Additionally, the model runs fast enough to provide a seamless experience even on consumer hardware. How was it trained? Waypoint-1 was pre-trained via diffusion forcing, a technique with which the model learns to denoise future frames given past frames. A causal attention mask is applied such that a token in any given frame can only attend to tokens in its own frame, or past frames, but not future frames. Each frame is noised randomly, and as such the model learns to denoise each frame separately. During inference, you can then denoise new frames one at a time, allowing you to generate a procedural stream of new frames. While diffusion forcing presents a strong baseline, randomly noising all frames is misaligned with a frame-by-frame autoregressive rollout. This inference mismatch results in error accumulation, and noisy long rollouts. To address this problem we post-train with self forcing, a technique that trains the model to produce realistic outputs under a regime which matches inference behavior. Self-forcing via DMD has the added benefit of one-pass CFG, and few-step denoising. The Inference Library: WorldEngine WorldEngine is Overworld’s high‑performance inference library for interactive world model streaming. It provides the core tooling for building inference applications in pure Python, optimized for low latency, high throughput, extensibility, and developer simplicity. The runtime loop is designed for interactivity: it consumes context frame images, keyboard/mouse inputs, and text, and outputs image frames for real‑time streaming. On Waypoint‑1‑Small (2.3B) running on a 5090, WorldEngine sustains ~30,000 token‑passes/sec (single denoising pass; 256 tokens per frame) and achieves 30 FPS at 4 steps or 60 FPS at 2 steps Performance comes from four targeted optimizations: AdaLN feature caching: Avoids repeated AdaLN conditioning projections through caching and reusing so long as prompt conditioning and timesteps stay the same between fwd passes. Static Rolling KV Cache + Flex Attention Matmul fusion: Standard inference optimization using fused QKV projections. Torch Compile using torch.compile(fullgraph=True, mode="max-autotune", dynamic=False) from world_engine import WorldEngine, CtrlInput engine = WorldEngine("Overworld/Waypoint-1-Small", device="cuda") engine.set_prompt("A game where you herd goats in a beautiful valley") img = pipeline.append_frame(uint8_img) for controller_input in [ CtrlInput(button={48, 42}, mouse=[0.4, 0.3]), CtrlInput(mouse=[0.1, 0.2]), CtrlInput(button={95, 32, 105}), ]: img = engine.gen_frame(ctrl=controller_input) Build with World Engine We’re running a world_engine hackathon on 1/20/2026 - You can RSVP here. Teams of 2-4 are welcome and the prize is a 5090 GPU on the spot. We’d love to see what you can come up with to extend the world_engine and it should be a great event to meet like-minded founders, engineers, hackers and investors. We hope you can join us at 10am PST on January 20th for 8 hours of friendly competition! Stay in Touch Website Discord (Developers) Discord (Models/Players) X/Twitter More Articles from our Blog announcementdiffusionworld-model Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs +1 30 April 9, 2026 announcementopen-sourcecommunity The Open Source Community is backing OpenEnv for Agentic RL +14 82 June 8, 2026 Community Deekshith-Dade Jan 21 Is this the first open source world model? ProgramerSalar Jan 24 good model, i understand it's very difficult to train diffusion model. VEFAorg Jan 26 Very Exciting! Nice work, team! 💪💎 · or to comment