mlsanityData to 7 Oct 2026

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

arXiv 2411.18664 ↗First posted 27 Nov 2024cs.CVcited by 33

On the map: Diffusion models → Diffusion foundations and sampling

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.

Key facts. Cited by 33 papers in the map (data through 7 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.

Builds on

30 of 61 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention1 Aug
  2. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models12 Jun
  3. 2024Guiding a Diffusion Model with a Bad Version of Itself4 Jun
  4. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching3 Jun
  5. 2024Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance26 Mar
  6. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers16 Jan
  7. 2023Diffusion Models Beat GANs on Image Classification17 Jul
  8. 2023Restart Sampling for Improving Generative Processes26 Jun
  9. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed15 May
  10. 2022Scalable Diffusion Models with Transformers19 Dec
  11. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  12. 2022Classifier-Free Diffusion Guidance26 Jul
3 more
  1. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  3. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 15

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  6. 2022Video Diffusion Modelscited by 2,280
  7. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  8. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  9. 2024Movie Gen: A Cast of Media Foundation Modelscited by 614
  10. 2020Hopfield Networks is All You Needcited by 461
  11. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 332
  12. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
3 more
  1. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  2. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  3. 2019TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 15; 2026: 17.

33 papers.

Sort:

By area:

  1. 2024Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedbackcited by 45
  2. 2025Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Modelscited by 35
  3. 2025Emergent Temporal Correspondences from Video Diffusion Transformerscited by 30
  4. 2025Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Controlcited by 14
  5. 2025Guiding a Diffusion Transformer with the Internal Dynamics of Itselfcited by 12
  6. 2025Steering Guidance for Personalized Text-to-Image Diffusion Modelscited by 7
  7. 2025Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformerscited by 7
  8. 2025Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformerscited by 6
  9. 2025Towards Suturing World Models: Learning Predictive Models for Robotic Surgical Taskscited by 5
  10. 2025AudioMoG: Guiding Audio Generation with Mixture-of-Guidancecited by 5
  11. 2026ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRAcited by 5
  12. 2025MusicInfuser: Making Video Diffusion Listen and Dancecited by 4
21 more
  1. 2025Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Modelscited by 4
  2. 2026One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformerscited by 3
  3. 2025SPG: Improving Motion Diffusion by Smooth Perturbation Guidancecited by 2
  4. 2026Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generationcited by 2
  5. 2025ACG: Action Coherence Guidance for Flow-based Vision-Language-Action modelscited by 1
  6. 2026Guiding Token-Sparse Diffusion Modelscited by 1
  7. 2026SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generationcited by 1
  8. 2026Early Failure Detection and Intervention in Video Diffusion Modelscited by 1
  9. 2026Improving Diffusion Generalization with Weak-to-Strong Segmented Guidancecited by 1
  10. 2026Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformerscited by 1
  11. 2026Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generationcited by 1
  12. 2025Guiding Visual Autoregressive Models through Spectrum Weakeningcited by 0
  13. 2025DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoderscited by 0
  14. 2026Steering Video Diffusion Transformers with Massive Activationscited by 0
  15. 2026Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibrationcited by 0
  16. 2026Probability-Conserving Flow Guidancecited by 0
  17. 2026Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulationcited by 0
  18. 2026Keyframe-Anchored Identity Preservation for Sequential-Action Video Generationcited by 0
  19. 2026Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generationcited by 0
  20. 2026Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusioncited by 0
  21. 2026Future Video Generation Better Aligns with the Human Visual Cortex than Observed Videocited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
  2. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs
  3. 2026Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
  4. 2024Guiding a diffusion model using sliding windows
  5. 2023Accelerating Guided Diffusion Sampling with Splitting Numerical Methods
  6. 2026Efficient Video Diffusion Models: Advancements and Challenges
  7. 2025HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
  8. 2026Learned End-to-End Guidance Schedules for Diffusion Models