AI Paper Atlas

Research map / Video / Video generation

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

Jingjing Ren, Wenbo Li, Zhongdao Wang, Haoze Sun, Bangzhen Liu, Haoyu Chen, Jiaqi Xu, Aoxue Li, Shifeng Zhang, Bin Shao, Yong Guo, Lei Zhu

ICCV 2025 · Video › Video generation · approach: Autoregressive long video generation · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
synchronize teacher and student timesteps in feature distillation instead of data fine-tuning (ablation)LTX-Video student · Distillation ablationMUSIQ: 60.36 -> 64.73Improved
synchronize teacher and student timesteps instead of fixing teacher t=0.1 (ablation)LTX-Video student · Distillation ablationMUSIQ: 61.12 -> 64.73Improved
add data fine-tuning to basic LTX (ablation)LTX-Video · Distillation ablationMUSIQ: 58.80 -> 60.36No clear effect
synchronized-timestep distillation vs basic LTX on semantic score (ablation)LTX-Video · Distillation ablationSeman.: 22.47 -> 24.48Improved
use late-step LR features (t=0.1) instead of t=t_hr guidance (ablation)Turbo2K two-stage · Guidance ablationSeman.: 18.53 -> 24.60Improved
use feature guidance (t=0.1) instead of LR latent guidance (ablation)Turbo2K two-stage · Guidance ablationMUSIQ: 49.42 -> 52.98Improved
use feature guidance (t=0.1) instead of LR latent guidance (ablation)Turbo2K two-stage · Guidance ablationNIQE: 5.04 -> 4.03Improved
compare Turbo2K 4B against CogVideoX-2B at 49 frames 2KTurbo2K · 2K inference times/step: 94.68 -> 5.08Improved
Turbo2K vs CogVideoX-5B VBench totalTurbo2K · VBench-LongTotal Score: 81.61 -> 82.78Improved
Turbo2K vs HunyuanVideo VBench totalTurbo2K · VBench-LongTotal Score: 83.24 -> 82.78Hurt
Turbo2K vs RealBasicVSR as upscalerTurbo2K · VSR comparisonMUSIQ: 51.48 -> 52.45Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy