mlsanityData to 7 Oct 2026

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

arXiv 2512.16093 ↗First posted 18 Dec 2025cs.CV cs.AI cs.LGcited by 31

On the map: Diffusion models → Video generation

Abstract (arXiv)

We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1) Attention acceleration: TurboDiffusion uses low-bit SageAttention and trainable Sparse-Linear Attention (SLA) to speed up attention computation. (2) Step distillation: TurboDiffusion adopts rCM for efficient step distillation. (3) W8A8 quantization: TurboDiffusion quantizes model parameters and activations to 8 bits to accelerate linear layers and compress the model. In addition, TurboDiffusion incorporates several other engineering optimizations. We conduct experiments on the Wan2.2-I2V-14B-720P, Wan2.1-T2V-1.3B-480P, Wan2.1-T2V-14B-720P, and Wan2.1-T2V-14B-480P models. Experimental results show that TurboDiffusion achieves 100-200x speedup for video generation even on a single RTX 5090 GPU, while maintaining comparable video quality. The GitHub repository, which includes model checkpoints and easy-to-use code, is available at https://github.com/thu-ml/TurboDiffusion.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 6 of its 7 references that are in the map. First posted on arXiv 18 Dec 2025.

Builds on

6 of 7 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention28 Sep

Other references · 5

  1. 2024SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Accelerationcited by 158
  2. 2024SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantizationcited by 113
  3. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
  4. 2025SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Trainingcited by 63
  5. 2025SageAttention2++: A More Efficient Implementation of SageAttention2cited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 31.

31 papers.

Sort:

By area:

  1. 2026Helios: Real Real-Time Long Video Generation Modelcited by 56
  2. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  3. 2026SLA2: Sparse-Linear Attention with Learnable Routing and QATcited by 21
  4. 2026SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuningcited by 16
  5. 2026KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernelscited by 10
  6. 2026SageBwd: A Trainable Low-bit Attentioncited by 7
  7. 2026BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimizationcited by 6
  8. 2026MonarchRT: Efficient Attention for Real-Time Video Generationcited by 6
  9. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 6
  10. 2026Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generationcited by 6
  11. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  12. 2026Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Frameworkcited by 5
19 more
  1. 2026Vidu S1: A Real-Time Interactive Video Generation Modelcited by 4
  2. 2026Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generationcited by 4
  3. 2026Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policiescited by 2
  4. 2026Speculative Decoding for Autoregressive Video Generationcited by 2
  5. 2026CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusioncited by 2
  6. 2026OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learningcited by 1
  7. 2026FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusioncited by 0
  8. 20266Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Modelscited by 0
  9. 2026DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR Conditioningcited by 0
  10. 2026Reward Lightning: Fast Video Generation via Homologous Preference Distillationcited by 0
  11. 2026Optimal Transport Q-Learning for Flow Policy Steering and Accelerationcited by 0
  12. 2026Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlationscited by 0
  13. 2026OSVE: One Step Video Editing with One Step Diffusion Modelscited by 0
  14. 2026KVAE: Family of Tokenizers for Multimodal Generative Modelscited by 0
  15. 2026TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillationcited by 0
  16. 2026DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generationcited by 0
  17. 2026SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to 265× Single-GPU Acceleration of Visual Generationcited by 0
  18. 2026Accelerating Video Diffusion via Training-Free Trajectory Routingcited by 0
  19. 2026PARK: Accurate Block Retrieval for Sparse Attention in Video Diffusion Transformerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VORTA: Efficient Video Diffusion via Routing Sparse Attention
  2. 2025SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation
  3. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
  4. 2026SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
  5. 2025Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
  6. 2025VSA: Faster Video Diffusion with Trainable Sparse Attention
  7. 2026Veda: Scalable Video Diffusion via Distilled Sparse Attention
  8. 2025SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity