研究人员开发了SEGA，一种新颖的无需训练的方法，用于提高文本到图像生成中使用的扩散Transformer的分辨率外推能力。SEGA在去噪过程中自适应地调整潜在表示不同频率分量的注意力。与现有方法相比，这种方法提高了生成图像在更高分辨率下的结构连贯性和精细细节保真度。 AI
影响 提高了扩散Transformer模型在更高分辨率下的图像生成质量。
排序理由 该集群包含一篇详细介绍提高扩散Transformer性能的新方法的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
SEGA improves high-resolution text-to-image generation by adaptively scaling attention across RoPE components based on spatial-frequency structure during denoising steps.
arXiv:2605.22668v1 Announce Type: new Abstract: Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate t…
Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by modifying inference-time attention behavi…