在潜在空间直接缩放，提升文本生成图像的效率与质量
LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image Generation
- 在潜在空间而非像素空间进行分辨率缩放，避免失真
- 生成1024×1024图像时，TOPIQ评分提升246%
- 无需改动主干网络，支持灵活多分辨率生成
流匹配和扩散模型在文本到图像生成中表现优异，通过迭代去噪生成逼真图像。为加速生成，常见策略是在低分辨率下提前去噪。但传统在像素空间降采样与上采样的方法常引入伪影和失真，因上采后图像重新编码进入潜在空间导致画质下降。为此，我们提出【潜在空间缩放生成（LSSGen）】框架，通过轻量级潜在上采样器直接在潜在空间执行分辨率缩放。不修改Transformer或U-Net结构，同时提升效率与视觉质量，并支持灵活多分辨率生成。全面评估显示，LSSGen显著优于传统缩放方法。在生成1024²图像且速度相近时，TOPIQ得分最高提升246%。
原文摘要 · Abstract (English)
Flow matching and diffusion models have shown impressive results in text-to-image generation, producing photorealistic images through an iterative denoising process. A common strategy to speed up synthesis is to perform early denoising at lower resolutions. However, traditional methods that downscale and upscale in pixel space often introduce artifacts and distortions. These issues arise when the upscaled images are re-encoded into the latent space, leading to degraded final image quality. To address this, we propose {\bf Latent Space Scaling Generation (LSSGen)}, a framework that performs resolution scaling directly in the latent space using a lightweight latent upsampler. Without altering the Transformer or U-Net architecture, LSSGen improves both efficiency and visual quality while supporting flexible multi-resolution generation. Our comprehensive evaluation covering text-image alignment and perceptual quality shows that LSSGen significantly outperforms conventional scaling approaches. When generating $1024^2$ images at similar speeds, it achieves up to 246\% TOPIQ score improvement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。