PixelFlow直接在像素空间生成图像，无需预训练VAE，效果媲美顶级模型。
PixelFlow: Pixel-Space Generative Models with Flow
- 直接在像素空间建模，省去VAE编码器，全链路可端到端训练。
- 在256×256 ImageNet上实现1.98的FID，图像质量接近最优水平。
- 适合追求高质量图像生成与可训练性的研究者与开发者。
我们提出PixelFlow，一类直接在原始像素空间进行图像生成的模型，区别于主流的潜在空间模型。该方法通过消除对预训练变分自编码器（VAE）的需求，简化了生成流程，并支持整个模型端到端可训练。借助高效的级联流建模，PixelFlow在像素空间实现了可接受的计算开销。在256×256 ImageNet类别条件图像生成基准上，其取得1.98的FID。定性文本到图像生成结果表明，PixelFlow在图像质量、艺术表现力和语义控制方面均表现出色。我们希望这一新范式能为下一代视觉生成模型带来启发与机遇。代码与模型已开源于https://github.com/ShoufaChen/PixelFlow。
原文摘要 · Abstract (English)
We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256$\times$256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models. Code and models are available at https://github.com/ShoufaChen/PixelFlow.
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。