FluxC：用 Flux 做零样本有损图像压缩
Flux as a Codec: Zero-Shot Lossy Compression with Flux
有人把 Flux 当压缩算法用了，零样本做有损压缩，低码率下还能打赢专门训练的神经压缩模型，思路挺新鲜。
arXiv 论文提出 FluxC，把图像生成模型 Flux 用作零样本编解码器的压缩先验。论文从编码成本、比特分配、重建方法三个维度分析，比较了 ancestral sampling、单步 ODE 和多步 ODE 三种重建方式。结果显示 ODE 重建在低码率下的失真低于 ancestral sampling，实验覆盖高斯源和自然图像。FluxC 在部分测试中成绩超过近期的神经图像压缩方法。
Flux as a Codec: Zero-Shot Lossy Compression with Flux
We propose FluxC, a zero-shot codec that uses Flux as a compression prior. Although DiffC has shown that pretrained diffusion models can serve as zero-shot codecs, we ask how the choice of coding path and reconstruction method affects rate--distortion--perception behavior. We analyze FluxC along three axes: coding cost and bit allocation, reconstruction method, and low rate distortion. At matched signal-to-noise ratio (SNR), we show that the path choice does not affect the ideal information rate, but changes how bits are allocated across time steps. For reconstruction, we compare ancestral sampling, one-step ODE reconstruction, and many-step ODE reconstruction. Our analysis shows that ODE-based reconstruction can achieve lower distortion than ancestral sampling, especially in the low rate regime. Experiments on Gaussian sources and natural images support this prediction. Moreover, FluxC performs competitively with, and in some cases outperforms, recent neural image compression methods, suggesting that Flux can serve as a principled zero-shot codec.
