MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It achieves minute-long video rollouts with real-time interactivity by combining a 3D cache for spatial recall, compressed temporal memory, stabilization training on drifted histories, and few-step distillation, addressing key challenges in video world models.
Who it is for
- Researchers in video generation and world models
- AI game developers seeking interactive long-horizon environments
- Creative professionals exploring controllable video synthesis
- Computer vision researchers studying spatial-temporal consistency
Use cases
- Interactive navigation of generated 3D-like video scenes with camera control
- Long-horizon storytelling with mid-generation prompt switching
- Real-time video world simulation for prototyping game environments
- Benchmarking and research on stable long-duration video generation
Strengths
- Real-time interaction via camera modulation and chunk-level prompt switching (≲1.33s chunks)
- Long-horizon memory consistency using explicit 3D cache and frame-history embeddings
- Stability over minute-long rollouts via drift training and error bank re-injection
- Open-source inference code and pretrained weights available on GitHub and Hugging Face
Considerations
- Only inference code released; training code and training data are not yet available
- Requires external third-party weights (Gemma text encoder, Depth-Anything-3) with gated access and separate downloads
- Released under a non-commercial license (LTX-2 Community License) restricting commercial use
README quick start
AlayaWorld: Long-Horizon and Playable Video World Generation
Alaya Lab
An interactive autoregressive world model with real-time camera control, prompt switching, and long-horizon memory consistency.
📰 News
- [2026-07-21] Full Technical Report released.
- [2026-07-16] Inference code released and pretrained weights available on 🤗 Hugging Face. See Quick Start.
- [2026-07-08] Project page and technical report released.
🚀 Release Roadmap
- Inference code
- Pretrained weights — 🤗 AlayaLab/AlayaWorld
- Training code
- Training data (partial)
✨ Core Properties
AlayaWorld is built around four core properties — interaction, consistency, stability, and runtime.
🎮 Interaction
Two control channels: a rendered 3D cache with lightweight AdaLN camera modulation for grounded, trajectory-aware navigation, and chunk-level prompt switching to introduce new events mid-generation.
🧠 Consistency
Two forms of complementary memory: an explicit 3D cache reprojected to the queried view for spatial recall, plus a compressed frame-history embedding for temporal continuity, so revisited places stay recognizable.
🛡️ Stability
Long-horizon stability from training on drifted histories and an error bank that re-injects accumulated artifacts into both memory and target, preventing errors from compounding over minute-long rollouts.
⚡ Runtime
Real-time interaction via few-step DMD distillation and short temporal chunks, with prompt switching at chunk boundaries to minimize both visual and semantic latency.
🏃 Quick Start
Inference is image-to-video: give the model a first-frame image, a camera trajectory, and a text prompt, and it rolls out a video chunk by chunk along the camera path (1 chunk ≈ 1.33s @ 24fps; ~45 chunks ≈ 1 minute).
1. Environment — a CUDA GPU and PyTorch ≥ 2.6 (the DiT uses flex_attention).
2. Weights — the model runs on four pieces. Only merged_infer.safetensors
(AlayaWorld's own weights) is hosted on our 🤗 repo; the text encoder and the
depth model are third-party — get them from their original sources:
| Path under checkpoints/ | Source |
Description
Full-stack open-source interactive long-horizon world model.
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.