-
04:50
(UTC +08:00)
Lists (2)
Sort Name ascending (A-Z)
Stars
VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation
Audio-guided facial video restoration and visual dubbing demos
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻;拆解结果按 VIDEO.md 格式输出。
Real-time generative rendering for interactive worlds, from any visual reference.
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
Code for Connected Self Forcing: Beyond Local Learning in Video Autoregression.
SolarRenderer: Few-Step Generative Reference Rendering
A Unified Large-Scale Benchmark for World Generation toward World Intelligence
Reverse engineer anything with agents, from app behavior down to native binaries.
Self Gradient Forcing (SGF) recovers the missing context-gradient path for self-generated causal memory through a bounded two-pass replay, enabling models trained with only a 5-second window to ext…
WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon
Autoregressive video generation with decoupled context-writing and denoising parameters, enabling up to 24-hour generation from 5s training windows.
高性价比人生指南: 长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。
[Arxiv 2026] WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Qwen's most powerful open-source image generation model
[MM 2024] DiffTV: Identity-preserved thermal-to-visible face translation via feature alignment and dual-stage conditions
[NeurIPS 2026] RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
Official implementation of EVOKE: Endless Interactive World with Bounded State and Long-Horizon Supervision. A three-step, CFG-free interactive world model. SOTA on WBench.
OpenGame: Open Agentic Coding for Games
Official Implementation for Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout
Official implementation of WorldinWorld
Programmable World Model: explicit world state, generative rendering.
Official SeedVR2 Video Upscaler for ComfyUI
Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset
VideoDeltaNet-H3: Live T2VA / I2VA / FL2VA / Ref2VA-like generation based on Minimax H3.
Open data and scalable training for long-horizon video world models.
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control