Abstract
Flow-based transformer models for image generation have achieved state-of-the-art performance with larger model parameters, but their inference deployment cost remains high. To enhance inference performance while maintaining generation quality, we propose progressive rectified flow transformers. We divide the rectified flow into different stages according to resolution, using fewer transformer layers at the low-resolution stages to generate image layouts and concept contours, and progressively adding more layers as the resolution increases. Experiments demonstrate that our approach achieves fast convergence and reduces inference time while ensuring generation quality. The main contributions of this paper are summarized as follows: (1) We introduce progressive rectified flow transformers that enable multi-resolution training, accelerating model convergence; (2) NAMI leverages piecewise flow and spatial cascading of Diffusion Transformer (DiT) to rapidly generate images, reducing inference time by 40% to generate a 1024 resolution image; (3) We propose NAMI-1K benchmark to evaluate human preference performance, aiming to mitigate distributional bias and prevent data leakage from open-source benchmarks. The results show that our model is competitive with state-of-the-art models.
Abstract (translated)
基于流的变压器模型在图像生成方面已经取得了最先进的性能，但随着模型参数的增大，其推理部署成本仍然很高。为了在保持生成质量的同时提高推理性能，我们提出了渐进式修正流变压器。我们将修正流根据分辨率划分为不同的阶段，在低分辨率阶段使用较少的变压器层来生成图像布局和概念轮廓，并逐步增加更多的层次以适应分辨率的增长。实验表明，我们的方法实现了快速收敛并减少了推理时间，同时确保了生成质量。 本文的主要贡献总结如下： 1. 我们介绍了渐进式修正流变压器，该模型支持多分辨率训练，加速了模型的收敛过程。 2. NAMI利用分段流和Diffusion Transformer (DiT)的空间级联来快速生成图像，在不降低生成质量的前提下将推理时间减少了40%，从而可以在1024分辨率下更快地生成图像。 3. 我们提出了NAMI-1K基准测试，以评估人类偏好的性能，并旨在减轻分布偏差并防止开源基准中的数据泄漏。结果表明，我们的模型在与现有最先进的模型竞争时具有竞争力。 通过这些方法和技术的结合使用，我们不仅提高了图像生成的速度和效率，还确保了模型能够更好地服务于各种应用场景的需求。
URL
https://arxiv.org/abs/2503.09242
