FlowCodec: One-Step Flow Prior for Generative Image Compression

2026-06-18

AI Summary

This work addresses the challenge of achieving high-quality image compression at ultra-low bitrates (<0.05 bpp), where balancing reconstruction fidelity and model complexity remains difficult. The authors propose FlowCodec, a framework that leverages the generative priors of pretrained text-to-image models—such as Qwen-Image-2512 and FLUX.1-dev—without requiring additional conditioning signals or auxiliary networks. FlowCodec employs a two-stage mechanism combining latent variable compression with single-step streaming to enable efficient reconstruction. By introducing only 0.54% trainable parameters relative to the backbone model, it flexibly supports multi-bitrate compression. Experimental results demonstrate that the method significantly outperforms existing approaches in perceptual metrics (LPIPS and DISTS), while simultaneously achieving higher PSNR and faster encoding speed.

Abstract

Diffusion-based image compression methods, leveraging powerful generative priors, have demonstrated remarkable perceptual quality at ultra-low bitrates. However, adapting modern generative models to image compression often relies on carefully engineered conditioning or auxiliary branches, together with substantial retraining, and these costs grow as the models scale. This motivates an open question: Can stronger generative priors be integrated into compression through a simpler, more extensible design? To answer this, we propose FlowCodec, a streamlined framework that plugs pretrained large-scale text-to-image priors (e.g., Qwen-image-2512 and FLUX.1-dev) into ultra-low-bitrate codecs. FlowCodec decomposes the pipeline into two decoupled stages: (1) Latent Compression, which maps clean latents to bitrate-constrained noisy latents; and (2) Latent Transport, which leverages the pretrained prior to refine the noisy latents toward the clean ones in a single step. Notably, FlowCodec requires neither additional conditioning signals nor auxiliary networks. Furthermore, with lightweight adaptation, it can flexibly support multiple bitrates while keeping the number of trainable parameters below 0.54% of the generative backbone. Experiments show that FlowCodec preserves high visual quality at bitrates below 0.05 bits per pixel. The Qwen-image variant significantly outperforms existing methods in terms of LPIPS and DISTS, while both variants deliver higher PSNR and clearly faster encoding than existing one-step diffusion-based methods, with the FLUX variant also maintaining competitive decoding speed.

Problem

• generative image compression
• diffusion models
• ultra-low bitrate
• pretrained priors
• compression framework

Innovation

• generative image compression
• flow prior
• one-step refinement
• pretrained diffusion models
• ultra-low bitrate