AsymFlow achieves 1.57 FID on ImageNet in pixel space

Hansheng Chen introduces AsymFlow, a flow-based image generation method that retains velocity information in a low-rank subspace instead of using JiT x0-prediction. The model operates directly in pixel space without a VAE and records an FID of 1.57 on ImageNet, the highest among published pixel-space flow models. When used to finetune FLUX.2 klein, the resulting checkpoint outperforms the base model on HPSv3, DPG, and GenEval, ranking first overall on HPSv3 while delivering sharper textures and roughly 40 percent faster inference. The work was shared by researchers including Kosta Derpanis at York University.

Original post

AJ#471@JM_ALEXIA@WILDMINDAI

WI

Wildminder@WILDMINDAI

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming https://hanshengchen.com/asymflow/

5:08 AM · May 14, 2026 View on X