mlsanityData to 14 Oct 2026

Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

arXiv 2501.08453 ↗First posted 14 Jan 2025cs.CV cs.LGcited by 60

On the map: Diffusion models → Video generation

Abstract (arXiv)

We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames, while maintaining temporal coherence across sequences. (2) To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework that incorporates hybrid parallelism and other memory reduction techniques, enabling efficient training of long video sequences on distributed systems. (3) Additionally, our enhanced data processing pipeline ensures the creation of Vchitect T2V DataVerse, a high-quality million-scale training dataset through rigorous annotation and aesthetic evaluation. Extensive benchmarking demonstrates that Vchitect-2.0 outperforms existing methods in video quality, training efficiency, and scalability, serving as a suitable base for high-fidelity video generation.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 28 of its 70 references that are in the map. First posted on arXiv 14 Jan 2025.

Builds on

28 of 70 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  2. 2024VEnhancer: Generative Space-Time Enhancement for Video Generation10 Jul
  3. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generation30 Oct
  4. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation27 Sep
  5. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  6. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  7. 2023Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation17 Apr
  8. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Models20 Nov
  9. 2022Imagen Video: High Definition Video Generation with Diffusion Models5 Oct

Other references · 19

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  5. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  6. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  7. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  8. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  9. 2023VideoChat: Chat-Centric Video Understandingcited by 857
  10. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  11. 2023Ring Attention with Blockwise Transformers for Near-Infinite Contextcited by 457
  12. 2023DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Modelscited by 245
7 more
  1. 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 146
  2. 2018PipeDream: Fast and Efficient Pipeline Parallel DNN Trainingcited by 117
  3. 2021M6: A Chinese Multimodal Pretrainercited by 91
  4. 2020PyTorch Distributed: Experiences on Accelerating Data Parallel Trainingcited by 90
  5. 2021ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Trainingcited by 61
  6. 2024VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Modelscited by 45
  7. 2018GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelismcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 37; 2026: 23.

60 papers.

Sort:

By area:

  1. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 315
  2. 2025WorldScore: A Unified Evaluation Benchmark for World Generationcited by 156
  3. 2025VSA: Faster Video Diffusion with Trainable Sparse Attentioncited by 104
  4. 2025Mixture of Contexts for Long Video Generationcited by 95
  5. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  6. 2025Goku: Flow Based Video Generative Foundation Modelscited by 67
  7. 2025RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Controlcited by 57
  8. 2025CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Modelscited by 52
  9. 2025Omni-Video: Democratizing Unified Video Understanding and Generationcited by 40
  10. 2025VideoScore2: Think before You Score in Generative Video Evaluationcited by 40
  11. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 40
  12. 20254DNeX: Feed-Forward 4D Generative Modeling Made Easycited by 34
38 more
  1. 2025DreamRelation: Relation-Centric Video Customizationcited by 23
  2. 2025WorldLens: Full-Spectrum Evaluations of Driving World Models in Real Worldcited by 23
  3. 2025PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generationcited by 23
  4. 2025LongVie: Multimodal-Guided Controllable Ultra-Long Video Generationcited by 22
  5. 2025Bidirectional Sparse Attention for Faster Video Diffusion Trainingcited by 19
  6. 2025UniVid: The Open-Source Unified Video Modelcited by 19
  7. 2026Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editingcited by 19
  8. 2026Latent Spatial Memory for Video World Modelscited by 17
  9. 2025Think Before You Diffuse: Infusing Physical Rules into Video Diffusioncited by 16
  10. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  11. 2026Demystifying Video Reasoningcited by 14
  12. 2025Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesiscited by 13
  13. 2025Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibilitycited by 13
  14. 2025M4V: Multimodal Mamba for Efficient Text-to-Video Generationcited by 12
  15. 2025Uniform Discrete Diffusion with Metric Path for Video Generationcited by 12
  16. 2025Light-X: Generative 4D Video Rendering with Camera and Illumination Controlcited by 12
  17. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  18. 2025MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMscited by 10
  19. 2025ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answeringcited by 9
  20. 2025MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videoscited by 9
  21. 2025LongVie 2: Multimodal Controllable Ultra-Long Video World Modelcited by 9
  22. 2025KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animationcited by 8
  23. 2026VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine Systemcited by 8
  24. 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generationcited by 6
  25. 2025Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generationcited by 6
  26. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6
  27. 2026Chain of Event-Centric Causal Thought for Physically Plausible Video Generationcited by 6
  28. 2025Taming Flow-based I2V Models for Creative Video Editingcited by 5
  29. 2026VidLeaks: Membership Inference Attacks Against Text-to-Video Modelscited by 5
  30. 2026Spectral Progressive Diffusion for Efficient Image and Video Generationcited by 5
  31. 2026DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformerscited by 4
  32. 2026Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generationcited by 4
  33. 2026TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generationcited by 4
  34. 2026VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latentscited by 3
  35. 2025USV: Unified Sparsification for Accelerating Video Diffusion Modelscited by 2
  36. 2025Flowception: Temporally Expansive Flow Matching for Video Generationcited by 2
  37. 2026PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolutioncited by 2
  38. 2025Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesiscited by 1

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
  2. 2024Towards Precise Scaling Laws for Video Diffusion Transformers
  3. 2025Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers
  4. 2025Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks
  5. 2025Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
  6. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  7. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  8. 2025Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers