MobileWan: Closing the Quality Gap for Mobile Video Diffusion

• URL: http://arxiv.org/abs/2607.06173v1
• Date: Tue, 07 Jul 2026 11:52:46 GMT
• Title: MobileWan: Closing the Quality Gap for Mobile Video Diffusion
• Abstract summary: MobileWan is the first 5B-scale video diffusion model deployable on a commercial mobile device.<n>Our system generates 5-second 480x832 videos at 16 FPS in 20 seconds end-to-end latency, achieving a VBench score of 83.79.
• Score: 53.20920841863923
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual fidelity and motion coherence. In contrast, existing mobile video diffusion models remain limited to relatively small parameter budgets, typically 0.4-1.8B, restricting generation quality. In this work, we show that high-quality mobile video generation does not require small models. Instead, we demonstrate that a server-scale 5B-parameter video diffusion transformer can be deployed efficiently on memory-constrained mobile hardware through recurrent reformulation and structured compression. Starting from Wan2.2-5B, we rely on a recurrence distillation framework that converts video generation into a chunk-wise autoregressive process with constant-memory attention computation. Combined with causal linear attention, the model operates as an RNN at inference time while preserving temporal coherence across chunks. We further propose a learnable attention head pruning method based on binary per-head gates optimized end-to-end using a noise-biased sparsity objective and distillation-based finetuning. Together with sampling-step distillation and memory-optimized VAE decoding, MobileWan becomes the first 5B-scale video diffusion model deployable on a commercial mobile device. Our system generates 5-second 480x832 videos at 16 FPS in 20 seconds end-to-end latency, achieving a VBench score of 83.79 and establishing a new state of the art in mobile video generation. Project page: https://qualcomm-ai-research.github.io/mobilewan

Related papers

• CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation [17.654969014220033]
  CineMobile generates 49-frame 480p videos with a per-step denoising latency of 0.6s on an NVIDIA H200 GPU and 20s on the MediaTek Dimensity 8400 Ultimate 5G platform.<n>CineMobile achieves a 40x speedup in generation while maintaining comparable visual quality.
  arXiv  Detail & Related papers  (2026-07-04T10:24:35Z)
• Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds [91.56929670753226]
  Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like smartphones.<n>We propose a series of novel optimizations to significantly accelerate video generation and enable practical deployment on mobile platforms.
  arXiv  Detail & Related papers  (2025-07-17T17:59:10Z)
• SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device [61.42406720183769]
  We propose a comprehensive acceleration framework to bring the power of the large-scale video diffusion model to the hands of edge users.<n>Our model, with only 0.6B parameters, can generate a 5-second video on an iPhone 16 PM within 5 seconds.
  arXiv  Detail & Related papers  (2024-12-13T18:59:56Z)
• From Slow Bidirectional to Fast Autoregressive Video Diffusion Models [48.35054927704544]
  Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies.<n>We address this limitation by adapting a pretrained bidirectional diffusion transformer to an autoregressive transformer that generates frames on-the-fly.<n>Our model achieves a total score of 84.27 on the VBench-Long benchmark, surpassing all previous video generation models.
  arXiv  Detail & Related papers  (2024-12-10T18:59:50Z)
• Mobile Video Diffusion [11.568267488097401]
  Video models have achieved impressive realism and controllability but are limited by computational demands.<n>This paper introduces the first mobile-optimized video diffusion model.<n>Our model, coined as MobileVD, is 523x more efficient (181 vs. 4.34 TFLOs) with a slight quality drop.
  arXiv  Detail & Related papers  (2024-12-10T15:19:10Z)
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
  Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds. We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache) We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
  arXiv  Detail & Related papers  (2024-11-04T18:59:44Z)
• Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling [125.95527079960725]
  Transformer-based models have achieved top performance on major video recognition benchmarks. Video Mobile-Former is the first Transformer-based video model which constrains the computational budget within 1G FLOPs.
  arXiv  Detail & Related papers  (2022-08-25T17:59:00Z)
• Real-Time Video Inference on Edge Devices via Adaptive Model Streaming [9.101956442584251]
  Real-time video inference on edge devices like mobile phones and drones is challenging due to the high cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient lightweight models for video inference on edge devices.
  arXiv  Detail & Related papers  (2020-06-11T17:25:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.