mlsanityData to 7 Oct 2026

Mobile Video Diffusion

arXiv 2412.07583 ↗First posted 10 Dec 2024cs.CV cs.AIcited by 17

On the map: Diffusion models → Video generation

Abstract (arXiv)

Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper introduces the first mobile-optimized video diffusion model. Starting from a spatio-temporal UNet from Stable Video Diffusion (SVD), we reduce memory and computational cost by reducing the frame resolution, incorporating multi-scale temporal representations, and introducing two novel pruning schema to reduce the number of channels and temporal blocks. Furthermore, we employ adversarial finetuning to reduce the denoising to a single step. Our model, coined as MobileVD, is 523x more efficient (1817.2 vs. 4.34 TFLOPs) with a slight quality drop (FVD 149 vs. 171), generating latents for a 14x512x256 px clip in 1.7 seconds on a Xiaomi-14 Pro. Our results are available at https://qualcomm-ai-research.github.io/mobile-video-diffusion/

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 53 of its 76 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

53 of 76 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Pyramidal Flow Matching for Efficient Video Generative Modeling8 Oct
  2. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  3. 2024SF-V: Single Forward Video Generation Model6 Jun
  4. 2024FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing10 Mar
  5. 2024Object-Centric Diffusion for Efficient Video Editing11 Jan
  6. 2023Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis20 Dec
  7. 2023RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models7 Dec
  8. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  9. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  10. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models18 Apr
  11. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators23 Mar
  12. 2023Structure and Content-Guided Video Synthesis with Diffusion Models6 Feb
1 more
  1. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Models20 Nov

Other references · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  9. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  10. 2023Consistency Modelscited by 1,778
  11. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  12. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
28 more
  1. 2023Adversarial Diffusion Distillationcited by 741
  2. 2022On Distillation of Guided Diffusion Modelscited by 721
  3. 2018Which Training Methods for GANs do actually Converge?cited by 672
  4. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  5. 2023Improved Techniques for Training Consistency Modelscited by 430
  6. 2023Video-P2P: Video Editing with Cross-attention Controlcited by 312
  7. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  8. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 277
  9. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  10. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  11. 2022Post-training Quantization on Diffusion Modelscited by 262
  12. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  13. 2018cGANs with Projection Discriminatorcited by 253
  14. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  15. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  16. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  17. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  18. 2024Compact Language Models via Pruning and Knowledge Distillationcited by 142
  19. 2022Generating Long Videos of Dynamic Scenescited by 113
  20. 2024On the Content Bias in Fr'echet Video Distancecited by 51
  21. 2023Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizationscited by 45
  22. 2024AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Datacited by 42
  23. 2024SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flowcited by 30
  24. 2024Isomorphic Pruning for Vision Modelscited by 21
  25. 2024Beyond FVD: Enhanced Evaluation Metrics for Video Generation Qualitycited by 21
  26. 2023Clockwork Diffusion: Efficient Generation With Model-Step Distillationcited by 18
  27. 2023Softmax Bias Correction for Quantized Generative Modelscited by 15
  28. 2023Squeezing Large-Scale Diffusion Models for Mobilecited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 7.

17 papers.

Sort:

By area:

  1. 2025QVGen: Pushing the Limit of Quantized Video Generative Modelscited by 20
  2. 2025On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devicescited by 14
  3. 2025Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformercited by 13
  4. 2025MoAlign: Motion-Centric Representation Alignment for Video Diffusion Modelscited by 13
  5. 2025Neodragon: Mobile Video Generation using Diffusion Transformercited by 10
  6. 2025Taming Diffusion Transformer for Efficient Mobile Video Generation in Secondscited by 8
  7. 2026ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformerscited by 6
  8. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 6
  9. 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillationcited by 6
  10. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  11. 2025MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devicescited by 4
  12. 2026PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inferencecited by 3
5 more
  1. 2026MobileWan: Closing the Quality Gap for Mobile Video Diffusioncited by 3
  2. 2025TurboVSR: Fantastic Video Upscalers and Where to Find Themcited by 2
  3. 2025V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Modelscited by 1
  4. 2025On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devicescited by 0
  5. 2026Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MoViE: Mobile Diffusion for Video Editing
  2. 2025Survey of Video Diffusion Models: Foundations, Implementations, and Applications
  3. 2024Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
  4. 2024SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
  5. 2025USV: Unified Sparsification for Accelerating Video Diffusion Models
  6. 2022Video Diffusion Models
  7. 2025AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
  8. 2024Accelerating Video Diffusion Models via Distribution Matching