# FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

arXiv: https://arxiv.org/abs/2506.01144 · HTML: https://mlsanity.com/paper/2506.01144/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 55 of its 69 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 55)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [Lumiere: A Space-Time Diffusion Model for Video Generation](https://mlsanity.com/paper/2401.12945/) (2024)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)

## Built on by (most cited first, 22 of 22)

- [UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation](https://mlsanity.com/paper/2510.10575/) (2025)
- [Self-Refining Video Sampling](https://mlsanity.com/paper/2601.18577/) (2026)
- [Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising](https://mlsanity.com/paper/2511.08633/) (2025)
- [MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training](https://mlsanity.com/paper/2511.21592/) (2025)
- [TempoControl: Temporal Attention Guidance for Text-to-Video Models](https://mlsanity.com/paper/2510.02226/) (2025)
- [Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization](https://mlsanity.com/paper/2511.20647/) (2025)
- [FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models](https://mlsanity.com/paper/2601.20857/) (2026)
- [HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding](https://mlsanity.com/paper/2603.15228/) (2026)
- [Steering Video Diffusion Transformers with Massive Activations](https://mlsanity.com/paper/2603.17825/) (2026)
- [TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation](https://mlsanity.com/paper/2602.00268/) (2026)
- [MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation](https://mlsanity.com/paper/2603.14073/) (2026)
- [Early Failure Detection and Intervention in Video Diffusion Models](https://mlsanity.com/paper/2603.14320/) (2026)
- [SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation](https://mlsanity.com/paper/2606.11969/) (2026)
- [NeoMap: Training-free Novel-View Synthesis from Single Images and Videos](https://mlsanity.com/paper/2607.01962/) (2026)
- [Twins: Learn to Predict Unified Representations with Focal Loss](https://mlsanity.com/paper/2607.22531/) (2026)
- [Envision: Embodied Visual Planning via Goal-Imagery Video Diffusion](https://mlsanity.com/paper/2512.22626/) (2025)
- [VDCook:DIY video data cook your MLLMs](https://mlsanity.com/paper/2603.05539/) (2026)
- [TeDiO: Temporal Diagonal Optimization for Training-Free Coherent Video Diffusion](https://mlsanity.com/paper/2605.14136/) (2026)
- [Compositional Video Generation via Inference-Time Guidance](https://mlsanity.com/paper/2605.14988/) (2026)
- [All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation](https://mlsanity.com/paper/2609.27901/) (2026)
- [HiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation](https://mlsanity.com/paper/2610.02197/) (2026)
- [TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback](https://mlsanity.com/paper/2610.14153/) (2026)

## Abstract (arXiv)

Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external conditioning signals to enforce temporal consistency. In this work, we explore whether a meaningful temporal representation can be extracted directly from the predictions of a pre-trained model without any additional training or auxiliary inputs. We introduce FlowMo, a novel training-free guidance method that enhances motion coherence using only the model's own predictions in each diffusion step. FlowMo first derives an appearance-debiased temporal representation by measuring the distance between latents corresponding to consecutive frames. This highlights the implicit temporal structure predicted by the model. It then estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling. Extensive experiments across multiple text-to-video models demonstrate that FlowMo significantly improves motion coherence without sacrificing visual quality or prompt alignment, offering an effective plug-and-play solution for enhancing the temporal fidelity of pre-trained video diffusion models.