FARMER: Flow AutoRegressive Transformer over Pixels

TL;DR

FARMER is a novel generative framework combining Normalizing Flows and Autoregressive models for efficient, high-quality image synthesis from raw pixels, with exact likelihoods and scalable training.

Contribution

It introduces a unified model with a dimension reduction scheme and inference acceleration techniques for improved pixel-based image generation.

Findings

FARMER achieves competitive performance with existing models.

It provides exact likelihood estimation for images.

The model demonstrates scalable training and fast inference.

Abstract

Directly modeling the explicit likelihood of the raw data distribution is key topic in the machine learning area, which achieves the scaling successes in Large Language Models by autoregressive modeling. However, continuous AR modeling over visual pixel data suffer from extremely long sequences and high-dimensional spaces. In this paper, we present FARMER, a novel end-to-end generative framework that unifies Normalizing Flows (NF) and Autoregressive (AR) models for tractable likelihood estimation and high-quality image synthesis directly from raw pixels. FARMER employs an invertible autoregressive flow to transform images into latent sequences, whose distribution is modeled implicitly by an autoregressive model. To address the redundancy and complexity in pixel-level modeling, we propose a self-supervised dimension reduction scheme that partitions NF latent channels into informative and redundant groups, enabling more effective and efficient AR modeling. Furthermore, we design a one-step distillation scheme to significantly accelerate inference speed and introduce a resampling-based classifier-free guidance algorithm to boost image generation quality. Extensive experiments demonstrate that FARMER achieves competitive performance compared to existing pixel-based generative models while providing exact likelihoods and scalable training.