AI RESEARCH
One-step Latent-free Image Generation with Pixel Mean Flows
arXiv CS.CV
•
ArXi:2601.22158v3 Announce Type: replace Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a latent space. Recent advances have made encouraging progress on each aspect individually, paving the way toward one-step diffusion/flow without latents. In this work, we take a further step towards this goal and propose "pixel MeanFlow" (pMF). Our core guideline is to formulate the network output space and the loss space separately.