MobileWan: Closing the Quality Gap for Mobile Video Diffusion

We significantly advance the quality of Mobile Video Generation compared to the previous state-of-the-art (a) and produce high quality videos (b) comparable to the ones produced by server models. Our user study preferred MobileWan videos 80% of the time over Neodragon

In this work, we challenge the assumption that mobile video generation requires small diffusion models. Instead, we show that a server-scale 5B-parameter video DiT can be deployed efficiently on memory-constrained mobile hardware through recurrent reformulation and structured compression. Starting from Wan2.2-5B, we introduce a recurrence distillation framework that converts a pretrained transformer into a chunk-wise autoregressive model with near-constant memory attention computation. Rather than attending over the full video sequence, the model generates videos chunk-by-chunk while restricting attention to a small local token set. To preserve temporal coherence across chunks, we combine this formulation with a causal linear attention mechanism, enabling the diffusion transformer to operate as an RNN during inference.
We further introduce a learnable head pruning method tailored for video DiT's. Our approach relies on binary per-head gates optimized end-to-end with sparsity regularization and a noise-biased learning strategy that improves the pruning robustness. Combined with recurrent distillation, aggressive sampling-step distillation, and memory-optimized VAE decoding, these optimizations together enable, for the first time, deployment of a 5B-scale video diffusion model on a commercial mobile device. We present MobileWan, a high-quality on-device video diffusion system built on these principles.

Major contributions:

• We introduce MobileWan, a novel on-device video diffusion system that brings the 5B-parameter Wan2.2 model to mobile hardware, substantially narrowing the quality gap between mobile and server-scale video generation. Through system-level optimizations, we demonstrate the generation of 5-second 480x832 videos at 16 fps in 20 seconds, achieving 83.79 VBench. To foster further research on mobile video diffusion, we will release our models and training recipes.
• We show that by distilling all transformer blocks into recurrent structures, the DiT inference can be formulated as an RNN over frames, reducing the peak memory footprint as required for deploying large models on mobile devices.
• We propose a noise-biased, learnable head-pruning method that combines per-head gating, sparsity regularization, and targeted timestep sampling, enabling more aggressive and effective pruning than heuristic alternatives under stringent compression settings.

Overview of the temporally chunked hybrid attention arrangement without (left) and with chunk overlap (right).