real-time-generation

Tag

Cards List
#real-time-generation

Wizard: Manipulate Any World in Real Time via Agentic Control

Hugging Face Daily Papers ↗ · 2026-10-29 Cached

Wizard 提出一种游戏世界模型,通过解耦角色动画、场景操控与游戏逻辑,实现对未见过角色的关节级动作与实时交互控制,支持 24 FPS 交互并对新场景、角色和动作具备零样本泛化能力。

0 favorites 0 likes
#real-time-generation

From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping

Hugging Face Daily Papers ↗ · 2026-10-19 Cached

StreamingSwap is a real-time flow-matching framework for video face swapping that uses a Joint Rec-ID loss and context-efficient generation (Face-RoI + short-context rollout) to achieve 20 FPS on an RTX 4090 over videos up to 10 minutes, along with the HumanFaceVid 1,000-hour cinematic dataset.

0 favorites 0 likes
#real-time-generation

@PrajwalTomar_: AI video now costs less than a cent a second. Vivix (@VivixLabs_HQ) just dropped W1, a real-time interactive video mode…

X AI KOLs Timeline ↗ · 2026-10-12 Cached

Vivix Labs 发布实时交互式视频模型 W1,定价仅 $0.003/秒,价格约为 Seedance 2.5 单条片段的八十分之一,有望让实时交互视频成为常态。

0 favorites 0 likes
#real-time-generation

Odyssey 3

Product Hunt ↗ · 2026-10-08 Cached

Odyssey 3 是一个基础世界模型,能从提示生成交互式环境并实时预测其变化,其 Pro 版本在 Physics-IQ 视频到视频基准上取得最高分(66.1),还可用于控制机器人手臂、人形机器人、驾驶车辆及训练智能体。

0 favorites 0 likes
#real-time-generation

WorldSonus: Bringing Sound to Worlds

Hugging Face Daily Papers ↗ · 2026-10-06 Cached

WorldSonus is an interactive video-to-audio framework that brings real-time spatial sound synthesis to world models, using a streaming causal autoregressive diffusion architecture with a real-time factor of 0.41, chunk-indexed prompt scheduling for mid-stream sound control, and stereo supervision for spatial alignment.

0 favorites 0 likes
#real-time-generation

@DLKFZWilliam2: ALL IN Plot Real-Time Generated Gal Game!! Every technological revolution, from painting, to photography, to filming, t…

X AI KOLs Following ↗ · 2026-09-25 Cached

The tweet discusses the potential of AI to generate real-time games like Gal Games, drawing parallels to technological revolutions in media from painting to AI.

0 favorites 0 likes
#real-time-generation

Bringing Your Muse to Life (5 minute read)

TLDR AI ↗ · 2026-09-25 Cached

Meta AI introduces Muse Realtime Avatar, a state-of-the-art embodiment technology that turns voice into synchronized, expressive avatars in real time using a streaming Diffusion Transformer.

0 favorites 0 likes
#real-time-generation

PixVerse R2

Product Hunt ↗ · 2026-09-23 Cached

PixVerse R2 is a real-time world model that generates continuously evolving audiovisual worlds, accepting text, images, audio, and actions with session memory for interactive and controllable experiences.

0 favorites 0 likes
#real-time-generation

@10xmylife: What a handsome idea, what an awesome effect!

X AI KOLs Timeline ↗ · 2026-09-19 Cached

Jev can generate game levels in real time, offering faster and cheaper structured output that could significantly impact game development.

0 favorites 0 likes
#real-time-generation

@FinanceYF5: Now, you can speak directly to the game, letting it generate the entire world in real time. Someone used the GPT-Live-1…

X AI KOLs Following ↗ · 2026-09-14

A playable demo uses the GPT-Live-1 API to enable real-time world generation in games via voice commands, illustrating a new form of interactive media.

0 favorites 0 likes
#real-time-generation

@_philschmid: Gemini 3.7 Flash is so fast that it can generate entire interactive websites in real time as you browse. Type URL or id…

X AI KOLs Following ↗ · 2026-08-15 Cached

Gemini 3.7 Flash demonstrates the ability to generate interactive websites in real-time based on user input, showcasing its speed and capabilities in AI-driven web development.

0 favorites 0 likes
#real-time-generation

@heyshrutimishra: An AI world that never runs out. Imagine a game where there's no fixed map. The world builds itself as you move. You wa…

X AI KOLs Following ↗ · 2026-07-11 Cached

LingBot-World 2.0 is an open-source AI model that generates persistent, real-time game worlds at 720p 60fps, running for over 60 minutes without visual decay, using a 14B parameter model with a 1.3B lightweight version for single-GPU deployment.

0 favorites 0 likes
#real-time-generation

@FinanceYF5: 1/ Most AI "world models" suffer from visual collapse and scene drift after just a few minutes of running. @robbyant_brain just open-sourced LingBot-World 2.0 (Infinity): supports hour-level real-time generation, no quality degradation over long runs, stable 720p/60fps output. This is...

X AI KOLs Timeline ↗ · 2026-07-10 Cached

LingBot-World 2.0 (Infinity) has just been open-sourced, supporting hour-level real-time generation with no quality degradation over long runs and stable 720p/60fps output. It's a key step for robots to learn to predict the world.

0 favorites 0 likes
#real-time-generation

@Rayko_wang: You can actually make a real playable game now with Seedance 2.0 + GPT Image 2. Not static AI videos anymore, but actua…

X AI KOLs Timeline ↗ · 2026-05-15 Cached

A new demo called Reelquest uses Seedance 2.0 and GPT Image 2 to create a fully interactive, playable game where every frame is AI-generated based on user actions, requiring no coding or game engine.

0 favorites 0 likes
#real-time-generation

CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives

Hugging Face Daily Papers ↗ · 2026-05-12 Cached

CausalCine is a new academic framework for real-time, interactive multi-shot video generation that uses causal modeling and dynamic memory routing to improve cross-shot coherence in autoregressive models.

0 favorites 0 likes
#real-time-generation

Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs

Hugging Face Blog ↗ · 2026-04-09 Cached

Overworld releases Waypoint-1.5, a real-time video world model designed for everyday GPUs, featuring improved visual fidelity and new 360p and 720p tiers for broader hardware accessibility.

0 favorites 0 likes
#real-time-generation

Genie 4: A new generation of world simulation

YouTube AI Channels ↗ · 2026-10-28 Cached

Google DeepMind 发布 Genie 4,这是其迄今最真实、最可交互的世界模型,基于 Gemini 构建,支持实时交互、键盘导航与自然语言控制场景,正向可信测试者和 AI Ultra 用户推出研究预览。

0 favorites 0 likes
← Back to home

Submit Feedback