AI Paper Atlas

Research map / Video / Video generation

PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling

Sijie Wang, Qiang Wang, Shaohuai Shi

AAAI 2026 · Video › Video generation · approach: Efficient video diffusion models · 2 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
add PipeSP (pipelined Ulysses) at moderate resolution (ablation)OpenSoraPlan · 640x352x129 per-timestep (A6000)per-timestep latency (s): 2.10 -> 1.83 (1.15×)Improved
add PipeSP at low resolution (ablation)OpenSoraPlan · 640x352x65 per-timestep (A6000)per-timestep latency (s): 1.21 -> 1.69 (0.72×)Hurt
add PipeSP across configurations (ablation)OpenSoraPlan · per-timestep latency, 8 configs (A6000/L40)speedup: 0.97× to 1.15× (A6000); 0.96× to 1.06× (L40)Mixed
decouple diffusion and VAE (DeDiVAE) at low resolution (ablation)OpenSoraPlan · 480x352x65, 30 steps (A6000)latency (s): 314 -> 217 (1.45×)Improved
decouple diffusion and VAE (DeDiVAE) at highest resolution (ablation)OpenSoraPlan · 1024x576x129, 30 steps (A6000)latency (s): 1995 -> 2138 (0.93×)Hurt
add Aco attention co-processing on top of DeDiVAE+PipeSP at high workload (ablation)OpenSoraPlan · 1024x576x129, 30 steps (A6000)latency (s): 1936 -> 1690Improved
add Aco on top of DeDiVAE+PipeSP at low workload (ablation)OpenSoraPlan · 480x352x65, 30 steps (A6000)latency (s): 200 -> 261Hurt
add Aco on top of DeDiVAE+PipeSP at high workload (ablation)HunyuanVideo · 1024x576x129, 30 steps (A6000)latency (s): 3675 -> 3090Improved
decouple diffusion and VAE (DeDiVAE) versus offloadingHunyuanVideo · 480x352x129 peak memorypeak GPU memory (GB): 29.37 -> 41.44Hurt
decouple diffusion and VAE (DeDiVAE) versus offloadingOpenSoraPlan · 480x352x129 peak memorypeak GPU memory (GB): 18.4 -> 18.0Improved
use full PipeDiT instead of offloading baseline for 10 videosHunyuanVideo · 480x352x97, 10 steps (A6000)latency (s): 540 -> 165 (3.27×)Improved
use full PipeDiT instead of offloading baseline at longest timestepsHunyuanVideo · 1024x576x97, 50 steps (L40)latency (s): 6952 -> 6453 (1.08×)Improved

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