# Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

arXiv: https://arxiv.org/abs/2504.14470 · HTML: https://mlsanity.com/paper/2504.14470/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 68 references that are in the map.
- First posted on arXiv 20 Apr 2025.

## Builds on (most cited first, 30 of 53)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [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)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [ShareGPT4Video: Improving Video Understanding and Generation with Better Captions](https://mlsanity.com/paper/2406.04325/) (2024)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [Open-Sora Plan: Open-Source Large Video Generation Model](https://mlsanity.com/paper/2412.00131/) (2024)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models](https://mlsanity.com/paper/2410.10733/) (2024)
- [Investigating Tradeoffs in Real-World Video Super-Resolution](https://mlsanity.com/paper/2111.12704/) (2021)
- [Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution](https://mlsanity.com/paper/2312.06640/) (2023)
- [Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT](https://mlsanity.com/paper/2406.18583/) (2024)
- [ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models](https://mlsanity.com/paper/2310.07702/) (2023)
- [SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization](https://mlsanity.com/paper/2411.10958/) (2024)
- [DemoFusion: Democratising High-Resolution Image Generation With No ](https://mlsanity.com/paper/2311.16973/) (2023)

## Built on by (most cited first, 13 of 13)

- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions](https://mlsanity.com/paper/2508.03077/) (2025)
- [PocketSR: The Super-Resolution Expert in Your Pocket Mobiles](https://mlsanity.com/paper/2510.03012/) (2025)
- [HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming](https://mlsanity.com/paper/2512.21338/) (2025)
- [FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation](https://mlsanity.com/paper/2511.14712/) (2025)
- [Frequency-Aware Flow Matching for High-Quality Image Generation](https://mlsanity.com/paper/2604.15521/) (2026)
- [JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion](https://mlsanity.com/paper/2608.03974/) (2026)
- [StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models](https://mlsanity.com/paper/2509.17993/) (2025)
- [Stable Score Distillation](https://mlsanity.com/paper/2507.09168/) (2025)
- [ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images](https://mlsanity.com/paper/2603.23326/) (2026)
- [PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution](https://mlsanity.com/paper/2605.25801/) (2026)
- [Cross-Subject Mind Decoding from Inaccurate Representations](https://mlsanity.com/paper/2507.19071/) (2025)
- [SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation](https://mlsanity.com/paper/2605.06356/) (2026)

## Abstract (arXiv)

Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities in high-quality video generation, scaling them to 2K resolution remains computationally prohibitive due to quadratic growth in memory and processing costs. In this work, we propose Turbo2K, an efficient and practical framework for generating detail-rich 2K videos while significantly improving training and inference efficiency. First, Turbo2K operates in a highly compressed latent space, reducing computational complexity and memory footprint, making high-resolution video synthesis feasible. However, the high compression ratio of the VAE and limited model size impose constraints on generative quality. To mitigate this, we introduce a knowledge distillation strategy that enables a smaller student model to inherit the generative capacity of a larger, more powerful teacher model. Our analysis reveals that, despite differences in latent spaces and architectures, DiTs exhibit structural similarities in their internal representations, facilitating effective knowledge transfer. Second, we design a hierarchical two-stage synthesis framework that first generates multi-level feature at lower resolutions before guiding high-resolution video generation. This approach ensures structural coherence and fine-grained detail refinement while eliminating redundant encoding-decoding overhead, further enhancing computational efficiency.Turbo2K achieves state-of-the-art efficiency, generating 5-second, 24fps, 2K videos with significantly reduced computational cost. Compared to existing methods, Turbo2K is up to 20× faster for inference, making high-resolution video generation more scalable and practical for real-world applications.