We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a series of ablations. For conditional image synthesis, we further improve sample quality with classifier guidance: a simple, compute-efficient method for trading off diversity for sample quality using gradients from a classifier. We achieve an FID of 2.97 on ImageNet 128$\times$128, 4.59 on ImageNet 256$\times$256, and 7.72 on ImageNet 512$\times$512, and we match BigGAN-deep even with as few as 25 forward passes per sample, all while maintaining better coverage of the distribution. Finally, we find that classifier guidance combines well with upsampling diffusion models, further improving FID to 3.85 on ImageNet 512$\times$512. We release our code at https://github.com/openai/guided-diffusion
翻译:我们显示,扩散模型能够达到比目前最先进的基因化模型高的图像样本质量。 我们通过一系列推理来找到更好的结构来无条件图像合成。 对于有条件的图像合成,我们通过分类指导进一步提高样本质量:一种简单、计算高效的方法,使用分类器的梯度来交换样本质量的多样性,我们通过图像网128$times128, 4.59在图像网256$times256美元,7.72在图像网512$times512中公布,我们用图像网512$times512比BigGAN-deepep,即使每个样本只有多达25个远端的通道,同时保持更好的分布范围。最后,我们发现,分类指南结合了扩大的推广模型,在图像网512$time512上进一步将FID提高到3.85。 我们在https://github.com/opinai/guided-difulation上公布我们的代码。 最后,我们发现,在图像网512$512。