mlsanityData to 14 Oct 2026

Enhance-A-Video: Better Generated Video for Free

arXiv 2502.07508 ↗First posted 11 Feb 2025cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based generated videos, named Enhance-A-Video. The core idea is enhancing the cross-frame correlations based on non-diagonal temporal attention distributions. Thanks to its simple design, our approach can be easily applied to most DiT-based video generation frameworks without any retraining or fine-tuning. Across various DiT-based video generation models, our approach demonstrates promising improvements in both temporal consistency and visual quality. We hope this research can inspire future explorations in video generation enhancement.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 27 of its 30 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

27 of 30 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2017Deep reinforcement learning from human preferencescited by 3,912
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  7. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  8. 2022Video Diffusion Modelscited by 2,305
  9. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  10. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  11. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  12. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
15 more
  1. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  2. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 546
  3. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generationcited by 302
  4. 2024StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Textcited by 251
  5. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  6. 2024The Effect of Sampling Temperature on Problem Solving in Large Language Modelscited by 170
  7. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  8. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 132
  9. 2024Is Temperature the Creativity Parameter of Large Language Models?cited by 93
  10. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attentioncited by 89
  11. 2022Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learningcited by 86
  12. 2024EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagationcited by 77
  13. 2022Temporally Consistent Transformers for Video Generationcited by 44
  14. 2024VideoGigaGAN: Towards Detail-rich Video Super-Resolutioncited by 30
  15. 2025DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradationscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 192
  2. 2025OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Modelscited by 16
  3. 2025We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedbackcited by 10
  4. 2026LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusioncited by 10
  5. 2025Rethinking Reward Signals in Video GRPO: When Scores Become Targetscited by 6
  6. 2026PhysVid: Physics Aware Local Conditioning for Generative Video Modelscited by 6
  7. 2025DiTraj: training-free trajectory control for video diffusion transformercited by 5
  8. 2026Early Failure Detection and Intervention in Video Diffusion Modelscited by 1
  9. 2026SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generationcited by 1
  10. 2026Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalancecited by 1
  11. 2026Motif-Video 2B: Technical Reportcited by 0