Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as is standard in language modeling. We propose Self-conditioned Embedding Diffusion, a continuous diffusion mechanism that operates on token embeddings and allows to learn flexible and scalable diffusion models for both conditional and unconditional text generation. Through qualitative and quantitative evaluation, we show that our text diffusion models generate samples comparable with those produced by standard autoregressive language models - while being in theory more efficient on accelerator hardware at inference time. Our work paves the way for scaling up diffusion models for text, similarly to autoregressive models, and for improving performance with recent refinements to continuous diffusion.

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.

在本文中，我们提出了一种新的生成模型，逐步逐步的去噪AutoEncoder（Sundae），不依赖于自回归模型。类似地与去噪扩散技术，在从随机输入开始并从随机输入开始并每次直到收敛改善它们时，日出施加Sundae。我们提出了一个简单的新改进运算符，它比扩散方法更少迭代，同时在定性地在自然语言数据集上产生更好的样本。Sundae在WMT'14英语到德语翻译任务上实现最先进的结果（非自回归方法），在巨大清洁的常见爬网数据集和Python代码的数据集上对无条件语言建模的良好定性结果来自GitHub。通过在模板中填充任意空白模式，Sundae的非自动增加性质开辟了超出左右提示的可能性。

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the two powerful models and enjoy the best of both worlds. On the one hand, diffusion models offer a promising training strategy that helps improve the generation quality. On the other hand, pre-trained denoising language models (e.g., BERT) can be used as a good initialization that accelerates convergence. We explore training BERT to learn the reverse process of a discrete diffusion process with an absorbing state and elucidate several designs to improve it. First, we propose a new noise schedule for the forward diffusion process that controls the degree of noise added at each step based on the information of each token. Second, we investigate several designs of incorporating the time step into BERT. Experiments on unconditional text generation demonstrate that DiffusionBERT achieves significant improvement over existing diffusion models for text (e.g., D3PM and Diffusion-LM) and previous generative masked language models in terms of perplexity and BLEU score.

Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have presented diffusion as an alternative to autoregressive language generation. We instead view diffusion as a complementary method that can augment the generative capabilities of existing pre-trained language models. We demonstrate that continuous diffusion models can be learned in the latent space of a pre-trained encoder-decoder model, enabling us to sample continuous latent representations that can be decoded into natural language with the pre-trained decoder. We show that our latent diffusion models are more effective at sampling novel text from data distributions than a strong autoregressive baseline and also enable controllable generation.

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.

Diffusion models have achieved state-of-the-art synthesis quality on visual and audio tasks, and recent works adapt them to textual data by diffusing on the embedding space. But the difference between the continuous data space and the embedding space raises challenges to the diffusion model, which have not been carefully explored. In this paper, we conduct systematic studies and analyze the challenges threefold. Firstly, the data distribution is learnable for embeddings, which may lead to the collapse of the loss function. Secondly, as the norm of embedding varies between popular and rare words, adding the same noise scale will lead to sub-optimal results. In addition, we find that noises sampled from a standard Gaussian distribution may distract the diffusion process. To solve the above challenges, we propose Difformer, a denoising diffusion probabilistic model based on Transformer, which consists of three techniques including utilizing an anchor loss function, a layer normalization module for embeddings, and a norm factor to the Gaussian noise. All techniques are complementary to each other and critical to boosting the model performance together. Experiments are conducted on benchmark datasets over two seminal text generation tasks including machine translation and text summarization. The results show that Difformer significantly outperforms the embedding diffusion baselines, while achieving competitive results with strong autoregressive baselines.

Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous diffusion models to natural language, and text diffusion models are less studied. Sequence-to-sequence text generation is one of the essential natural language processing topics. In this work, we apply diffusion models to approach sequence-to-sequence text generation, and explore whether the superiority generation performance of diffusion model can transfer to natural language domain. We propose SeqDiffuSeq, a text diffusion model for sequence-to-sequence generation. SeqDiffuSeq uses an encoder-decoder Transformers architecture to model denoising function. In order to improve generation quality, SeqDiffuSeq combines the self-conditioning technique and a newly proposed adaptive noise schedule technique. The adaptive noise schedule has the difficulty of denoising evenly distributed across time steps, and considers exclusive noise schedules for tokens at different positional order. Experiment results illustrate the good performance on sequence-to-sequence generation in terms of text quality and inference time.

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。

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。

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 。

DeNoising扩散模型代表了计算机视觉中最新的主题，在生成建模领域表现出了显着的结果。扩散模型是一个基于两个阶段的深层生成模型，一个正向扩散阶段和反向扩散阶段。在正向扩散阶段，通过添加高斯噪声，输入数据在几个步骤中逐渐受到干扰。在反向阶段，模型的任务是通过学习逐步逆转扩散过程来恢复原始输入数据。尽管已知的计算负担，即由于采样过程中涉及的步骤数量，扩散模型对生成样品的质量和多样性得到了广泛赞赏。在这项调查中，我们对视觉中应用的denoising扩散模型的文章进行了全面综述，包括该领域的理论和实际贡献。首先，我们识别并介绍了三个通用扩散建模框架，这些框架基于扩散概率模型，噪声调节得分网络和随机微分方程。我们进一步讨论了扩散模型与其他深层生成模型之间的关系，包括变异自动编码器，生成对抗网络，基于能量的模型，自回归模型和正常流量。然后，我们介绍了计算机视觉中应用的扩散模型的多角度分类。最后，我们说明了扩散模型的当前局限性，并设想了一些有趣的未来研究方向。

产生人类想要的声音效果是一个重要的话题。但是，在这一领域，很少有研究声音发电。在这项研究中，我们调查了以文本提示为条件的声音，并提出了一个新型的文本对生成框架，该框架由文本编码器组成，矢量量化了变异自动编码器（VQ-VAE），解码器和歌手。该框架首先使用解码器将从文本编码器提取的文本特征传递到借助VQ-VAE的MEL光谱图中，然后使用Vocoder将生成的MEL光谱图转换为波形。我们发现，解码器显着影响发电性能。因此，我们专注于在这项研究中设计一个好的解码器。我们从传统的自动回解码器开始，该解码器已被证明是以前的Sound Generation Works中的最先进方法。但是，AR解码器始终按顺序预测MEL-SPECTROGIN图令牌，这引入了单向偏见和错误问题的积累。此外，使用AR解码器，声音生成时间随着声音持续时间线性增加。为了克服AR解码器引入的缺点，我们提出了一个基于离散扩散模型的非自动回形解码器，称为DiffSound。具体而言，DIFFSOUND可以在一个步骤中预测所有MEL光谱图令牌，然后在下一步中完善预测的令牌，因此可以在几个步骤后获得最优于预测的结果。我们的实验表明，与AR解码器相比，我们提出的差异不仅产生更好的文本到单一生成结果，而且还具有更快的生成速度，例如MOS：3.56 \ textit {v.s} 2.786，并且生成速度为五个比AR解码器快的时间。

我们提出了位扩散：一种简单而通用的方法，用于通过连续扩散模型生成离散数据。我们方法背后的主要思想是首先将离散数据表示为二进制位，然后训练连续扩散模型，以将这些位模拟为实数，我们称为模拟位。为了生成样品，模型首先生成模拟位，然后将其阈值阈值以获得表示离散变量的位。我们进一步提出了两种简单的技术，即自我调节和不对称的时间间隔，从而导致样本质量的显着改善。尽管它很简单，但提出的方法可以在离散图像生成和图像字幕任务中实现强大的性能。对于离散图像生成，我们在CIFAR-10（具有3K离散的8位代币）和Imagenet-64x64（具有12K离散的8位代币）上都显着改善了先前的最新技术，超过了最好的自动回归性自动回应。样品质量（通过FID衡量）和效率的模型。对于MS-Coco数据集上的图像字幕，与自回归模型相比，我们的方法可实现竞争成果。

We introduce M-VADER: a diffusion model (DM) for image generation where the output can be specified using arbitrary combinations of images and text. We show how M-VADER enables the generation of images specified using combinations of image and text, and combinations of multiple images. Previously, a number of successful DM image generation algorithms have been introduced that make it possible to specify the output image using a text prompt. Inspired by the success of those models, and led by the notion that language was already developed to describe the elements of visual contexts that humans find most important, we introduce an embedding model closely related to a vision-language model. Specifically, we introduce the embedding model S-MAGMA: a 13 billion parameter multimodal decoder combining components from an autoregressive vision-language model MAGMA and biases finetuned for semantic search.

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.

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.

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。

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.

Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data. However, the gradient of the log-likelihood function, i.e., the score function, is not properly defined for discrete spaces. This makes it non-trivial to adapt \textcolor{\cdiff}{the score-based modeling} to categorical data. In this paper, we extend diffusion models to discrete variables by introducing a stochastic jump process where the reverse process denoises via a continuous-time Markov chain. This formulation admits an analytical simulation during backward sampling. To learn the reverse process, we extend score matching to general categorical data and show that an unbiased estimator can be obtained via simple matching of the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.