long-video-generation

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Helios: Real Real-Time Long Video Generation Model

[CVPR 2025] StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

[ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".

Official PyTorch implementation of TATS: A Long Video Generation Framework with Time-Agnostic VQGAN and Time-Sensitive Transformer (ECCV 2022)

[CVPR 2026 Highlight] VideoCoF: Unified Video Editing with Temporal Reasoner

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

[CVPR 2026] Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

CVPRW 2025 paper Progressive Autoregressive Video Diffusion Models: https://arxiv.org/abs/2410.08151

[ArXiv 26] EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration

official code for "magicworld: towards long-horizon stability for interactive video world exploration"

[ICCV 2025] TokensGen: Harnessing Condensed Tokens for Long Video Generation

[ECCV 2026] Official implementation of "MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens"

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

Official code of Memento: Reconstruct to Remember for Consistent Long Video Generation

The paper list of the survey "The Past Frames the Future: Memory Mechanisms for Autoregressive Video Generation"

Helios: Real Real-Time Long Video Generation Model