# Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

arXiv: https://arxiv.org/abs/2411.18664 · HTML: https://mlsanity.com/paper/2411.18664/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 27 Nov 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks](https://mlsanity.com/paper/2202.10571/) (2022)
- [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://mlsanity.com/paper/2210.00939/) (2022)
- [CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models](https://mlsanity.com/paper/2406.08070/) (2024)
- [Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching](https://mlsanity.com/paper/2406.01733/) (2024)
- [Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond](https://mlsanity.com/paper/2304.04968/) (2023)
- [Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance](https://mlsanity.com/paper/2403.17377/) (2024)
- [Restart Sampling for Improving Generative Processes](https://mlsanity.com/paper/2306.14878/) (2023)
- [Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention](https://mlsanity.com/paper/2408.00760/) (2024)
- [Diffusion Models Beat GANs on Image Classification](https://mlsanity.com/paper/2307.08702/) (2023)
- [TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation](https://mlsanity.com/paper/1901.09953/) (2019)

## Built on by (most cited first, 30 of 34)

- [Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback](https://mlsanity.com/paper/2412.02617/) (2024)
- [Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models](https://mlsanity.com/paper/2508.12880/) (2025)
- [Emergent Temporal Correspondences from Video Diffusion Transformers](https://mlsanity.com/paper/2506.17220/) (2025)
- [Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control](https://mlsanity.com/paper/2509.15130/) (2025)
- [Guiding a Diffusion Transformer with the Internal Dynamics of Itself](https://mlsanity.com/paper/2512.24176/) (2025)
- [Steering Guidance for Personalized Text-to-Image Diffusion Models](https://mlsanity.com/paper/2508.00319/) (2025)
- [Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2509.21893/) (2025)
- [Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers](https://mlsanity.com/paper/2510.11538/) (2025)
- [Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models](https://mlsanity.com/paper/2506.10978/) (2025)
- [Towards Suturing World Models: Learning Predictive Models for Robotic Surgical Tasks](https://mlsanity.com/paper/2503.12531/) (2025)
- [MusicInfuser: Making Video Diffusion Listen and Dance](https://mlsanity.com/paper/2503.14505/) (2025)
- [AudioMoG: Guiding Audio Generation with Mixture-of-Guidance](https://mlsanity.com/paper/2509.23727/) (2025)
- [ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA](https://mlsanity.com/paper/2603.10256/) (2026)
- [Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation](https://mlsanity.com/paper/2602.22570/) (2026)
- [One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers](https://mlsanity.com/paper/2603.12245/) (2026)
- [Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers](https://mlsanity.com/paper/2605.07503/) (2026)
- [SPG: Improving Motion Diffusion by Smooth Perturbation Guidance](https://mlsanity.com/paper/2503.02577/) (2025)
- [Steering Video Diffusion Transformers with Massive Activations](https://mlsanity.com/paper/2603.17825/) (2026)
- [Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion](https://mlsanity.com/paper/2609.36014/) (2026)
- [ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models](https://mlsanity.com/paper/2510.22201/) (2025)
- [Guiding Token-Sparse Diffusion Models](https://mlsanity.com/paper/2601.01608/) (2026)
- [SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation](https://mlsanity.com/paper/2602.05534/) (2026)
- [Early Failure Detection and Intervention in Video Diffusion Models](https://mlsanity.com/paper/2603.14320/) (2026)
- [Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance](https://mlsanity.com/paper/2603.20584/) (2026)
- [Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation](https://mlsanity.com/paper/2607.09581/) (2026)
- [Guiding Visual Autoregressive Models through Spectrum Weakening](https://mlsanity.com/paper/2511.22991/) (2025)
- [DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders](https://mlsanity.com/paper/2512.13690/) (2025)
- [Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration](https://mlsanity.com/paper/2603.24800/) (2026)
- [Probability-Conserving Flow Guidance](https://mlsanity.com/paper/2605.20079/) (2026)
- [Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation](https://mlsanity.com/paper/2607.02968/) (2026)

## Abstract (arXiv)

Diffusion models have emerged as a powerful tool for generating high-quality images, videos, and 3D content. While sampling guidance techniques like CFG improve quality, they reduce diversity and motion. Autoguidance mitigates these issues but demands extra weak model training, limiting its practicality for large-scale models. In this work, we introduce Spatiotemporal Skip Guidance (STG), a simple training-free sampling guidance method for enhancing transformer-based video diffusion models. STG employs an implicit weak model via self-perturbation, avoiding the need for external models or additional training. By selectively skipping spatiotemporal layers, STG produces an aligned, degraded version of the original model to boost sample quality without compromising diversity or dynamic degree. Our contributions include: (1) introducing STG as an efficient, high-performing guidance technique for video diffusion models, (2) eliminating the need for auxiliary models by simulating a weak model through layer skipping, and (3) ensuring quality-enhanced guidance without compromising sample diversity or dynamics unlike CFG. For additional results, visit https://junhahyung.github.io/STGuidance.