VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
hub
Fora: Fast-forward caching in diffusion transformer acceleration.arXiv preprint arXiv:2407.01425
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.
SpecEdit accelerates diffusion-based image editing up to 10x by using a low-resolution draft to identify edit-relevant tokens via semantic discrepancies for selective high-resolution denoising.
1.x-Distill achieves better quality and diversity than prior few-step distillation methods at 1.67 and 1.74 effective NFEs on SD3 models with up to 33x speedup.
DisCa replaces heuristic feature caching with a lightweight learnable neural predictor compatible with distillation, achieving 11.8× acceleration on video diffusion transformers with preserved generation quality.
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
SAFE-DiT accelerates DiT inference at high resolutions by eliding mask-induced dispatch tax in attention while preserving semantics via selective scheduling, delivering up to 5x speedup and large memory savings with visual quality maintained.
A test-time Kalman-style dual-state tracker of the output-to-input feature ratio enables error-bounded computation skipping in video diffusion without offline calibration.
LearniBridge learns shared low-rank calibration updates via LoRA to enable high-ratio feature caching in DiTs using only 3-5 samples, delivering up to 5.87x acceleration on FLUX with quality gains on video models.
ReCache learns recomputation schedules via policy gradients to maximize quality under a target compute budget for any caching mechanism in diffusion models.
FIS-DiT achieves 2.11-2.41x speedup on video DiT models in few-step regimes with negligible quality loss by exploiting frame-wise sparsity and consistency through a training-free interleaved execution strategy.
FlashClear delivers up to 122x faster object removal than prior diffusion models via adversarial step distillation and asymmetric attention caching while preserving visual quality.
MotionCache accelerates autoregressive video generation up to 6.28x by motion-weighted cache reuse based on inter-frame differences, with negligible quality loss on SkyReels-V2 and MAGI-1.
BAC accelerates transformer-based Diffusion Policy up to 3x by block-level adaptive feature caching using an Adaptive Caching Scheduler and Bubbling Union Algorithm to control error propagation.
ResilPhase accelerates DiT inference via stable ODE macro-trajectory extrapolation with derivative-free barycentric Lagrange extrapolator and bounded phase mapping, claiming SOTA fidelity at high acceleration ratios on FLUX.1-dev and HunyuanVideo.
A feedback controller that gates full versus cached Transformer steps using drift risk and a soft compute budget improves FLUX.1-dev quality at matched compute over fixed caching policies.
DiSC accelerates DiT and PixArt-Sigma diffusion models 3.47-4.74x over A100 GPUs by reusing cached tokens across denoising steps and reusing sparsity masks in attention, using hash-based bank distribution to run sparse workloads on standard compute units.
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.
Sparse ActionGen accelerates diffusion policies up to 4x for robot control via rollout-adaptive pruning and zig-zag activation reuse without performance loss.
citing papers explorer
-
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
-
ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
-
Test-time Sparsity for Extreme Fast Action Diffusion
Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.
-
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
SpecEdit accelerates diffusion-based image editing up to 10x by using a low-resolution draft to identify edit-relevant tokens via semantic discrepancies for selective high-resolution denoising.
-
1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
1.x-Distill achieves better quality and diversity than prior few-step distillation methods at 1.67 and 1.74 effective NFEs on SD3 models with up to 33x speedup.
-
DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
DisCa replaces heuristic feature caching with a lightweight learnable neural predictor compatible with distillation, achieving 11.8× acceleration on video diffusion transformers with preserved generation quality.
-
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
-
SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers
SAFE-DiT accelerates DiT inference at high resolutions by eliding mask-induced dispatch tax in attention while preserving semantics via selective scheduling, delivering up to 5x speedup and large memory savings with visual quality maintained.
-
NaviCache: Test-Time Self-Calibration Caching for Video Generation
A test-time Kalman-style dual-state tracker of the output-to-input feature ratio enables error-bounded computation skipping in video diffusion without offline calibration.
-
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
LearniBridge learns shared low-rank calibration updates via LoRA to enable high-ratio feature caching in DiTs using only 3-5 samples, delivering up to 5.87x acceleration on FLUX with quality gains on video models.
-
ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE
ReCache learns recomputation schedules via policy gradients to maximize quality under a target compute budget for any caching mechanism in diffusion models.
-
FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
FIS-DiT achieves 2.11-2.41x speedup on video DiT models in few-step regimes with negligible quality loss by exploiting frame-wise sparsity and consistency through a training-free interleaved execution strategy.
-
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
FlashClear delivers up to 122x faster object removal than prior diffusion models via adversarial step distillation and asymmetric attention caching while preserving visual quality.
-
Motion-Aware Caching for Efficient Autoregressive Video Generation
MotionCache accelerates autoregressive video generation up to 6.28x by motion-weighted cache reuse based on inter-frame differences, with negligible quality loss on SkyReels-V2 and MAGI-1.
-
Block-wise Adaptive Caching for Accelerating Diffusion Policy
BAC accelerates transformer-based Diffusion Policy up to 3x by block-level adaptive feature caching using an Adaptive Caching Scheduler and Bubbling Union Algorithm to control error propagation.
-
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
ResilPhase accelerates DiT inference via stable ODE macro-trajectory extrapolation with derivative-free barycentric Lagrange extrapolator and bounded phase mapping, claiming SOTA fidelity at high acceleration ratios on FLUX.1-dev and HunyuanVideo.
-
BeCARE: Budgeted Cache Refresh for Diffusion Transformer Acceleration
A feedback controller that gates full versus cached Transformer steps using drift risk and a soft compute budget improves FLUX.1-dev quality at matched compute over fixed caching policies.
-
DiSC: Resolution-Scalable Acceleration of Diffusion Models by Exploiting Sparsity and Cached Token Reuse with Hash-based Distribution
DiSC accelerates DiT and PixArt-Sigma diffusion models 3.47-4.74x over A100 GPUs by reusing cached tokens across denoising steps and reusing sparsity masks in attention, using hash-based bank distribution to run sparse workloads on standard compute units.
-
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while improving quality.
-
Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
Sparse ActionGen accelerates diffusion policies up to 4x for robot control via rollout-adaptive pruning and zig-zag activation reuse without performance loss.
- RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models
- AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers