# Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models

arXiv: https://arxiv.org/abs/2504.12626 · HTML: https://mlsanity.com/paper/2504.12626/

## Key facts

- Cited by 143 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 61 of its 74 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 61)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Improved Distribution Matching Distillation for Fast Image Synthesis](https://mlsanity.com/paper/2405.14867/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Flexible Diffusion Modeling of Long Videos](https://mlsanity.com/paper/2205.11495/) (2022)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Q-Diffusion: Quantizing Diffusion Models](https://mlsanity.com/paper/2302.04304/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)

## Built on by (most cited first, 30 of 143)

- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025)
- [Video World Models with Long-term Spatial Memory](https://mlsanity.com/paper/2506.05284/) (2025)
- [Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation](https://mlsanity.com/paper/2505.18875/) (2025)
- [Mixture of Contexts for Long Video Generation](https://mlsanity.com/paper/2508.21058/) (2025)
- [STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer](https://mlsanity.com/paper/2508.10893/) (2025)
- [Yume: An Interactive World Generation Model](https://mlsanity.com/paper/2507.17744/) (2025)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [Large Video Planner Enables Generalizable Robot Control](https://mlsanity.com/paper/2512.15840/) (2025)
- [Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation](https://mlsanity.com/paper/2506.19852/) (2025)
- [Wan-S2V: Audio-Driven Cinematic Video Generation](https://mlsanity.com/paper/2508.18621/) (2025)
- [Captain Cinema: Towards Short Movie Generation](https://mlsanity.com/paper/2507.18634/) (2025)
- [Lyra 2.0: Explorable Generative 3D Worlds](https://mlsanity.com/paper/2604.13036/) (2026)
- [DeepVerse: 4D Autoregressive Video Generation as a World Model](https://mlsanity.com/paper/2506.01103/) (2025)
- [Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory](https://mlsanity.com/paper/2602.02393/) (2026)
- [Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion](https://mlsanity.com/paper/2602.07775/) (2026)
- [Pack and Force Your Memory: Long-form and Consistent Video Generation](https://mlsanity.com/paper/2510.01784/) (2025)
- [Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models](https://mlsanity.com/paper/2603.25716/) (2026)
- [AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation](https://mlsanity.com/paper/2605.13724/) (2026)
- [VideoMemory: Toward Consistent Video Generation via Memory Integration](https://mlsanity.com/paper/2601.03655/) (2026)
- [Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation](https://mlsanity.com/paper/2603.21366/) (2026)
- [Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization](https://mlsanity.com/paper/2602.02958/) (2026)
- [FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation](https://mlsanity.com/paper/2506.01144/) (2025)
- [LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation](https://mlsanity.com/paper/2508.03694/) (2025)
- [Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation](https://mlsanity.com/paper/2508.03334/) (2025)
- [Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis](https://mlsanity.com/paper/2509.09595/) (2025)
- [LoViC: Efficient Long Video Generation with Context Compression](https://mlsanity.com/paper/2507.12952/) (2025)

## Abstract (arXiv)

We present a neural network structure, FramePack, to train next-frame (or next-frame-section) prediction models for video generation. FramePack compresses input frame contexts with frame-wise importance so that more frames can be encoded within a fixed context length, with more important frames having longer contexts. The frame importance can be measured using time proximity, feature similarity, or hybrid metrics. The packing method allows for inference with thousands of frames and training with relatively large batch sizes. We also present drift prevention methods to address observation bias (error accumulation), including early-established endpoints, adjusted sampling orders, and discrete history representation. Ablation studies validate the effectiveness of the anti-drifting methods in both single-directional video streaming and bi-directional video generation. Finally, we show that existing video diffusion models can be finetuned with FramePack, and analyze the differences between different packing schedules.