One Threshold Is Not Enough: Prompt-Invariant Caching Schedules for Video Diffusion

arXiv:2607.12358 · cs.CV · Submitted 2026-07-14 · Read on arXiv

cs.CV

Submitted: 2026-07-14

Updated: 2026-09-26

Code: https://github.com/black-forest-labs/flux

Terminology

• Diffusion Model — 32× in this paper · explained in 8 episodes
• Diffusion Models — 25× in this paper · explained in 6 episodes
• Transformer — 16× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Evaluation Dimensions — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Timestep Embedding Modulated Noisy Input — 1× in this paper

Sources

• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
• SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
• Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
• Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
• VideoLCM: Video Latent Consistency Model
• FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
• $\Delta$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
• Real-Time Video Generation with Pyramid Attention Broadcast
• Adaptive Caching for Faster Video Generation with Diffusion Transformers
• FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
• Classifier-Free Diffusion Guidance
• Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
• DiCache: Let Diffusion Model Determine Its Own Cache
• Open-Sora: Democratizing Efficient Video Production for All
• Wan: Open and Advanced Large-Scale Video Generative Models
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
• VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models