# FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

arXiv: https://arxiv.org/abs/2312.17681 · HTML: https://mlsanity.com/paper/2312.17681/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 47 of its 56 references that are in the map.
- First posted on arXiv 29 Dec 2023.

## Placed in

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

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [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)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [Structure and Content-Guided Video Synthesis with Diffusion Models](https://mlsanity.com/paper/2302.03011/) (2023)
- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [Pix2Video: Video Editing using Image Diffusion](https://mlsanity.com/paper/2303.12688/) (2023)
- [Text2LIVE: Text-Driven Layered Image and Video Editing](https://mlsanity.com/paper/2204.02491/) (2022)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)

## Built on by (most cited first, 30 of 79)

- [AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks](https://mlsanity.com/paper/2403.14468/) (2024)
- [ReVideo: Remake a Video with Motion and Content Control](https://mlsanity.com/paper/2405.13865/) (2024)
- [Diffusion Model-Based Video Editing: A Survey](https://mlsanity.com/paper/2407.07111/) (2024)
- [Video Editing via Factorized Diffusion Distillation](https://mlsanity.com/paper/2403.09334/) (2024)
- [Looking Backward: Streaming Video-to-Video Translation with Feature Banks](https://mlsanity.com/paper/2405.15757/) (2024)
- [Generative Video Propagation](https://mlsanity.com/paper/2412.19761/) (2024)
- [Exploring the Evolution of Physics Cognition in Video Generation: A Survey](https://mlsanity.com/paper/2503.21765/) (2025)
- [SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device](https://mlsanity.com/paper/2412.10494/) (2024)
- [Generative Video Motion Editing with 3D Point Tracks](https://mlsanity.com/paper/2512.02015/) (2025)
- [HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness](https://mlsanity.com/paper/2406.07754/) (2024)
- [Dynamic Concepts Personalization from Single Videos](https://mlsanity.com/paper/2502.14844/) (2025)
- [Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model](https://mlsanity.com/paper/2503.16942/) (2025)
- [Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models](https://mlsanity.com/paper/2409.19128/) (2024)
- [Optical-Flow Guided Prompt Optimization for Coherent Video Generation](https://mlsanity.com/paper/2411.15540/) (2024)
- [DIVE: Taming DINO for Subject-Driven Video Editing](https://mlsanity.com/paper/2412.03347/) (2024)
- [Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling](https://mlsanity.com/paper/2406.03035/) (2024)
- [OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Models](https://mlsanity.com/paper/2411.10501/) (2024)
- [DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency](https://mlsanity.com/paper/2408.07481/) (2024)
- [H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models](https://mlsanity.com/paper/2504.10567/) (2025)
- [Get In Video: Add Anything You Want to the Video](https://mlsanity.com/paper/2503.06268/) (2025)
- [Controllable Weather Synthesis and Removal with Video Diffusion Models](https://mlsanity.com/paper/2505.00704/) (2025)
- [TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer](https://mlsanity.com/paper/2506.18904/) (2025)
- [Generative World Renderer](https://mlsanity.com/paper/2604.02329/) (2026)
- [OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models](https://mlsanity.com/paper/2509.17627/) (2025)
- [AdaGaR: Adaptive Gabor Representation for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2601.00796/) (2026)
- [Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models](https://mlsanity.com/paper/2407.08701/) (2024)
- [Understanding Attention Mechanism in Video Diffusion Models](https://mlsanity.com/paper/2504.12027/) (2025)
- [Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA](https://mlsanity.com/paper/2507.17963/) (2025)
- [Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion](https://mlsanity.com/paper/2512.23709/) (2025)
- [GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator](https://mlsanity.com/paper/2603.25053/) (2026)

## Abstract (arXiv)

Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video frames. This paper proposes a consistent V2V synthesis framework by jointly leveraging spatial conditions and temporal optical flow clues within the source video. Contrary to prior methods that strictly adhere to optical flow, our approach harnesses its benefits while handling the imperfection in flow estimation. We encode the optical flow via warping from the first frame and serve it as a supplementary reference in the diffusion model. This enables our model for video synthesis by editing the first frame with any prevalent I2I models and then propagating edits to successive frames. Our V2V model, FlowVid, demonstrates remarkable properties: (1) Flexibility: FlowVid works seamlessly with existing I2I models, facilitating various modifications, including stylization, object swaps, and local edits. (2) Efficiency: Generation of a 4-second video with 30 FPS and 512x512 resolution takes only 1.5 minutes, which is 3.1x, 7.2x, and 10.5x faster than CoDeF, Rerender, and TokenFlow, respectively. (3) High-quality: In user studies, our FlowVid is preferred 45.7% of the time, outperforming CoDeF (3.5%), Rerender (10.2%), and TokenFlow (40.4%).