HybridPrompt: Bridging Generative Priors and Traditional Codecs for Mobile Streaming

TL;DR

HybridPrompt combines traditional codecs and generative neural models to enable real-time, high-quality 1080p video streaming on mobile devices by optimizing the synergy between the two paradigms.

Contribution

It introduces a hybrid video system that encodes keyframes with generative models and uses traditional codecs for other frames, optimized end-to-end for efficiency and quality.

Findings

Achieves 150 FPS decoding on smartphones.

Outperforms pure neural methods in speed by orders of magnitude.

Improves perceptual quality with an 8% LPIPS gain over traditional codecs.

Abstract

In Video on Demand (VoD) scenarios, traditional codecs are the industry standard due to their high decoding efficiency. However, they suffer from severe quality degradation under low bandwidth conditions. While emerging generative neural codecs offer significantly higher perceptual quality, their reliance on heavy frame-by-frame generation makes real-time playback on mobile devices impractical. We ask: is it possible to combine the blazing-fast speed of traditional standards with the superior visual fidelity of neural approaches? We present HybridPrompt, the first generative-based video system capable of achieving real-time 1080p decoding at over 150 FPS on a commercial smartphone. Specifically, we employ a hybrid architecture that encodes Keyframes using a generative model while relying on traditional codecs for the remaining frames. A major challenge is that the two paradigms have conflicting objectives: the "hallucinated" details from generative models often misalign with the rigid prediction mechanisms of traditional codecs, causing bitrate inefficiency. To address this, we demonstrate that the traditional decoding process is differentiable, enabling an end-to-end optimization loop. This allows us to use subsequent frames as additional supervision, forcing the generative model to synthesize keyframes that are not only perceptually high-fidelity but also mathematically optimal references for the traditional codec. By integrating a two-stage generation strategy, our system outperforms pure neural baselines by orders of magnitude in speed while achieving an average LPIPS gain of 8% over traditional codecs at 200kbps.