Self-Evaluation Unlocks Any-Step Text-to-Image Generation

TL;DR

Self-E introduces a novel self-evaluating training method for text-to-image generation that supports any-step inference, achieving high quality with fewer steps and outperforming traditional models in speed and scalability.

Contribution

It presents the first from-scratch, any-step text-to-image model using self-evaluation, bridging local supervision and global matching for efficient high-quality generation.

Findings

Excels in few-step generation with high quality.

Competitive with state-of-the-art models at 50 steps.

Performance improves monotonically with more inference steps.

Abstract

We introduce the Self-Evaluating Model (Self-E), a novel, from-scratch training approach for text-to-image generation that supports any-step inference. Self-E learns from data similarly to a Flow Matching model, while simultaneously employing a novel self-evaluation mechanism: it evaluates its own generated samples using its current score estimates, effectively serving as a dynamic self-teacher. Unlike traditional diffusion or flow models, it does not rely solely on local supervision, which typically necessitates many inference steps. Unlike distillation-based approaches, it does not require a pretrained teacher. This combination of instantaneous local learning and self-driven global matching bridges the gap between the two paradigms, enabling the training of a high-quality text-to-image model from scratch that excels even at very low step counts. Extensive experiments on large-scale text-to-image benchmarks show that Self-E not only excels in few-step generation, but is also competitive with state-of-the-art Flow Matching models at 50 steps. We further find that its performance improves monotonically as inference steps increase, enabling both ultra-fast few-step generation and high-quality long-trajectory sampling within a single unified model. To our knowledge, Self-E is the first from-scratch, any-step text-to-image model, offering a unified framework for efficient and scalable generation.