We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops -- through increased transformer depth/width or increased number of input tokens -- consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512x512 and 256x256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
translated by 谷歌翻译
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 fidelity using gradients from a classifier. We achieve an FID of 2.97 on ImageNet 128×128, 4.59 on ImageNet 256×256, and 7.72 on ImageNet 512×512, 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 3.94 on ImageNet 256×256 and 3.85 on ImageNet 512×512. We release our code at https://github.com/openai/guided-diffusion.
translated by 谷歌翻译
We present an end-to-end Transformer based Latent Diffusion model for image synthesis. On the ImageNet class conditioned generation task we show that a Transformer based Latent Diffusion model achieves a 14.1FID which is comparable to the 13.1FID score of a UNet based architecture. In addition to showing the application of Transformer models for Diffusion based image synthesis this simplification in architecture allows easy fusion and modeling of text and image data. The multi-head attention mechanism of Transformers enables simplified interaction between the image and text features which removes the requirement for crossattention mechanism in UNet based Diffusion models.
translated by 谷歌翻译
Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone which has been much neglected before. We systematically explore vision Transformers as diffusion learners for various generative tasks. With our improvements the performance of vanilla ViT-based backbone (IU-ViT) is boosted to be on par with traditional U-Net-based methods. We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept experiments verifying the effectiveness of a stronger encoder for generative tasks with ASymmetriC ENcoder Decoder (ASCEND). Our improvements achieve competitive results on CIFAR-10, CelebA, LSUN, CUB Bird and large-resolution text-to-image tasks. To the best of our knowledge, we are the first to successfully train a single diffusion model on text-to-image task beyond 64x64 resolution. We hope this will motivate people to rethink the modeling choices and the training pipelines for diffusion-based generative models.
translated by 谷歌翻译
我们表明,级联扩散模型能够在类条件的想象生成基准上生成高保真图像,而无需辅助图像分类器的任何帮助来提高样品质量。级联的扩散模型包括多个扩散模型的流水线,其产生越来越多的分辨率,以最低分辨率的标准扩散模型开始,然后是一个或多个超分辨率扩散模型,其连续上追随图像并添加更高的分辨率细节。我们发现级联管道的样本质量至关重要的是调节增强,我们提出的数据增强较低分辨率调节输入到超级分辨率模型的方法。我们的实验表明,调节增强防止在级联模型中采样过程中的复合误差,帮助我们在256×256分辨率下,在128x128和4.88,优于63.02的分类精度分数,培训级联管道。 %(TOP-1)和84.06%(TOP-5)在256x256,优于VQ-VAE-2。
translated by 谷歌翻译
Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive loglikelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs and GANs cover the target distribution. Finally, we show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable. We release our code at https://github.com/ openai/improved-diffusion.
translated by 谷歌翻译
利用深度学习的最新进展,文本到图像生成模型目前具有吸引公众关注的优点。其中两个模型Dall-E 2和Imagen已经证明,可以从图像的简单文本描述中生成高度逼真的图像。基于一种称为扩散模型的新型图像生成方法,文本对图像模型可以生产许多不同类型的高分辨率图像,其中人类想象力是唯一的极限。但是,这些模型需要大量的计算资源来训练,并处理从互联网收集的大量数据集。此外,代码库和模型均未发布。因此,它可以防止AI社区尝试这些尖端模型,从而使其结果复制变得复杂,即使不是不可能。在本文中,我们的目标是首先回顾这些模型使用的不同方法和技术,然后提出我们自己的文本模型模型实施。高度基于DALL-E 2,我们引入了一些轻微的修改,以应对所引起的高计算成本。因此,我们有机会进行实验,以了解这些模型的能力,尤其是在低资源制度中。特别是,我们提供了比Dall-e 2的作者(包括消融研究)更深入的分析。此外,扩散模型使用所谓的指导方法来帮助生成过程。我们引入了一种新的指导方法,该方法可以与其他指导方法一起使用,以提高图像质量。最后,我们的模型产生的图像质量相当好,而不必维持最先进的文本对图像模型的重大培训成本。
translated by 谷歌翻译
扩散模型是一类强大的生成模型类别,可以迭代地贬低样品生成数据。尽管许多作品都集中在此抽样过程中的迭代次数上,但很少有人专注于每次迭代的成本。我们发现,添加简单的VIT风格的修补转换可以大大减少扩散模型的采样时间和内存使用情况。我们通过对扩散模型目标的分析以及在LSUN教堂,Imagenet 256和FFHQ1024上进行的经验实验来证明我们的方法是合理的。我们在Tensorflow和Pytorch中提供了实现。
translated by 谷歌翻译
通过将图像形成过程分解成逐个申请的去噪自身额,扩散模型(DMS)实现了最先进的合成导致图像数据和超越。另外,它们的配方允许引导机构来控制图像生成过程而不会再刷新。然而,由于这些模型通常在像素空间中直接操作,因此强大的DMS的优化通常消耗数百个GPU天,并且由于顺序评估,推理是昂贵的。为了在保留其质量和灵活性的同时启用有限计算资源的DM培训,我们将它们应用于强大的佩带自动化器的潜在空间。与以前的工作相比,这种代表上的培训扩散模型允许第一次达到复杂性降低和细节保存之间的近乎最佳点,极大地提高了视觉保真度。通过将跨关注层引入模型架构中,我们将扩散模型转化为强大而柔性的发电机,以进行诸如文本或边界盒和高分辨率合成的通用调节输入,以卷积方式变得可以实现。我们的潜在扩散模型(LDMS)实现了一种新的技术状态,可在各种任务中进行图像修复和高竞争性能,包括无条件图像生成,语义场景合成和超级分辨率,同时与基于像素的DMS相比显着降低计算要求。代码可在https://github.com/compvis/lattent-diffusion获得。
translated by 谷歌翻译
非自动进取的生成变压器最近表现出令人印象深刻的图像产生性能,并且比自动回归对应物更快。但是,从视觉令牌的真实关节分布中进行的最佳并行采样仍然是一个开放的挑战。在本文中,我们介绍了代币批评,这是一种辅助模型,用于指导非自动性生成变压器的采样。鉴于掩盖和重建的真实图像,对代币批判性模型进行了训练,以区分哪种视觉令牌属于原始图像,哪些是由生成变压器采样的。在非自动回归迭代采样过程中,令牌批评者用于选择要接受的代币以及拒绝和重新取样的代币。再加上最先进的生成变压器令牌 - 批判性可显着提高其性能,并且在挑战性的课堂条件化成像生成中,就产生的图像质量和多样性之间的权衡取舍了最近的扩散模型和gan 。
translated by 谷歌翻译
生成时间连贯的高保真视频是生成建模研究中的重要里程碑。我们通过提出一个视频生成的扩散模型来取得这一里程碑的进步,该模型显示出非常有希望的初始结果。我们的模型是标准图像扩散体系结构的自然扩展,它可以从图像和视频数据中共同训练,我们发现这可以减少Minibatch梯度的方差并加快优化。为了生成长而更高的分辨率视频,我们引入了一种新的条件抽样技术,用于空间和时间视频扩展,该技术的性能比以前提出的方法更好。我们介绍了大型文本条件的视频生成任务,以及最新的结果,以实现视频预测和无条件视频生成的确定基准。可从https://video-diffusion.github.io/获得补充材料
translated by 谷歌翻译
We present the Recurrent Interface Network (RIN), a neural net architecture that allocates computation adaptively to the input according to the distribution of information, allowing it to scale to iterative generation of high-dimensional data. Hidden units of RINs are partitioned into the interface, which is locally connected to inputs, and latents, which are decoupled from inputs and can exchange information globally. The RIN block selectively reads from the interface into latents for high-capacity processing, with incremental updates written back to the interface. Stacking multiple blocks enables effective routing across local and global levels. While routing adds overhead, the cost can be amortized in recurrent computation settings where inputs change gradually while more global context persists, such as iterative generation using diffusion models. To this end, we propose a latent self-conditioning technique that "warm-starts" the latents at each iteration of the generation process. When applied to diffusion models operating directly on pixels, RINs yield state-of-the-art image and video generation without cascades or guidance, while being domain-agnostic and up to 10$\times$ more efficient compared to specialized 2D and 3D U-Nets.
translated by 谷歌翻译
作为生成部件作为自回归模型的向量量化变形式自动化器(VQ-VAE)的集成在图像生成上产生了高质量的结果。但是,自回归模型将严格遵循采样阶段的逐步扫描顺序。这导致现有的VQ系列模型几乎不会逃避缺乏全球信息的陷阱。连续域中的去噪扩散概率模型(DDPM)显示了捕获全局背景的能力,同时产生高质量图像。在离散状态空间中,一些作品已经证明了执行文本生成和低分辨率图像生成的可能性。我们认为,在VQ-VAE的富含内容的离散视觉码本的帮助下,离散扩散模型还可以利用全局上下文产生高保真图像,这补偿了沿像素空间的经典自回归模型的缺陷。同时,离散VAE与扩散模型的集成解决了传统的自回归模型的缺点是超大的,以及在生成图像时需要在采样过程中的过度时间的扩散模型。结果发现所生成的图像的质量严重依赖于离散的视觉码本。广泛的实验表明,所提出的矢量量化离散扩散模型(VQ-DDM)能够实现与低复杂性的顶层方法的相当性能。它还展示了在没有额外培训的图像修复任务方面与自回归模型量化的其他矢量突出的优势。
translated by 谷歌翻译
最近已被证明扩散模型产生高质量的合成图像,尤其是与指导技术配对,以促进忠诚的多样性。我们探索文本条件图像综合问题的扩散模型,并比较了两种不同的指导策略:剪辑指导和自由分类指导。我们发现后者是人类评估者的优选,用于光敏和标题相似度,并且通常产生光素质拟种样品。使用自由分类指导的35亿参数文本条件扩散模型的样本由人类评估者对来自Dall-E的人的人们青睐,即使后者使用昂贵的剪辑重新划分。此外,我们发现我们的模型可以进行微调,以执行图像修复,从而实现强大的文本驱动的图像编辑。我们在过滤的数据集中培训较小的模型,并在https://github.com/openai/glide-text2im释放代码和权重。
translated by 谷歌翻译
分类器指南是一种最近引入的方法,可在有条件扩散模型的培训后进行交易模式覆盖范围和样本保真度,其精神与其他类型的生成模型中的低温采样或截断相同。分类器指南将扩散模型的得分估计与图像分类器的梯度相结合,因此需要训练与扩散模型分开的图像分类器。它还提出了一个问题,即在没有分类器的情况下是否可以执行指导。我们表明,确实可以通过没有这样的分类器的纯生成模型来执行指导:在我们所谓的无分类器指导中,我们共同训练有条件的和无条件的扩散模型,我们结合了所得的条件和无条件得分估算样本质量和多样性之间的权衡类似于使用分类器指南获得的样本质量和多样性。
translated by 谷歌翻译
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. Our implementation is available at https://github.com/hojonathanho/diffusion.
translated by 谷歌翻译
虽然扩散概率模型可以产生高质量的图像内容,但仍然存在高分辨率图像的关键限制及其相关的高计算要求。最近的矢量量化图像模型已经克服了图像分辨率的这种限制,而是通过从之前的元素 - 明智的自回归采样生成令牌时,这是对图像分辨率的速度和单向的。相比之下,在本文中,我们提出了一种新的离散扩散概率模型,其通过使用无约束的变压器架构作为骨干来支持矢量量化令牌的并行预测。在培训期间,令牌以订单不可知的方式随机掩盖,变压器学会预测原始令牌。这种矢量量化令牌预测的并行性反过来促进了在计算费用的一小部分下的全球一致的高分辨率和多样性图像的无条件生成。以这种方式,我们可以产生超过原始训练集样本的图像分辨率,而另外提供每个图像似然估计(从生成的对抗方法的差点)。我们的方法在密度方面实现了最先进的结果(Lsun卧室:1.51; Lsun Churches:1.12; FFHQ:1.20)和覆盖范围(Lsun卧室:0.83; Lsun Churches:0.73; FFHQ:0.80),并执行竞争对手(LSUN卧室:3.64; LSUN教堂:4.07; FFHQ:6.11)在计算和减少训练套件要求方面提供优势。
translated by 谷歌翻译
我们介绍了文本到图像生成的矢量量化扩散(VQ-扩散)模型。该方法基于矢量量化变分性AutoEncoder(VQ-VAE),其潜像通过最近开发的去噪扩散概率(DDPM)的条件变体为基础。我们发现这种潜在空间方法非常适合于图像到图像生成任务,因为它不仅消除了具有现有方法的单向偏差,还允许我们结合掩模和更换的扩散策略,以避免积累错误,这是现有方法的严重问题。我们的实验表明,与具有类似数量的参数数量的传统自回归(AR)模型相比,VQ扩散产生明显更好的文本到图像生成结果。与以前的基于GAN的文本到图像方法相比,我们的VQ扩散可以通过大边缘处理更复杂的场景并提高合成的图像质量。最后,我们表明我们的方法中的图像生成计算可以通过Reparameter化进行高效。利用传统的AR方法,文本到图像生成时间随输出图像分辨率线性增加,因此即使对于正常尺寸图像也是相当耗时的。 VQ-扩散使我们能够在质量和速度之间实现更好的权衡。我们的实验表明,具有Reparameterization的VQ扩散模型比传统的AR方法快15倍,同时实现更好的图像质量。
translated by 谷歌翻译
扩散模型(DMS)显示出高质量图像合成的巨大潜力。但是,当涉及到具有复杂场景的图像时,如何正确描述图像全局结构和对象细节仍然是一项具有挑战性的任务。在本文中,我们提出了弗里多(Frido),这是一种特征金字塔扩散模型,该模型执行了图像合成的多尺度粗到1个降解过程。我们的模型将输入图像分解为依赖比例的矢量量化特征,然后是用于产生图像输出的粗到细门。在上述多尺度表示阶段,可以进一步利用文本,场景图或图像布局等其他输入条件。因此,还可以将弗里多应用于条件或跨模式图像合成。我们对各种无条件和有条件的图像生成任务进行了广泛的实验,从文本到图像综合,布局到图像,场景环形图像到标签形象。更具体地说,我们在五个基准测试中获得了最先进的FID分数,即可可和开阔图像的布局到图像,可可和视觉基因组的场景环形图像以及可可的标签对图像图像。 。代码可在https://github.com/davidhalladay/frido上找到。
translated by 谷歌翻译
We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding. The use of a pre-trained LLM enables fine-grained language understanding, translating to high-fidelity image generation and the understanding of visual concepts such as objects, their spatial relationships, pose, cardinality etc. Our 900M parameter model achieves a new SOTA on CC3M, with an FID score of 6.06. The Muse 3B parameter model achieves an FID of 7.88 on zero-shot COCO evaluation, along with a CLIP score of 0.32. Muse also directly enables a number of image editing applications without the need to fine-tune or invert the model: inpainting, outpainting, and mask-free editing. More results are available at https://muse-model.github.io
translated by 谷歌翻译