Emage：非自回归文本到图像生成
Emage: Non-Autoregressive Text-to-Image Generation
AI总结：
针对自回归和扩散模型推理延迟高的问题，提出非自回归文本到图像生成模型Emage，并行生成图像令牌，仅需16次推理即可达到竞争质量，延迟降低一个数量级。
摘要：
自回归模型和扩散模型推动了文本到图像生成领域的最新突破。尽管它们在生成高逼真图像方面取得了巨大成功，但这些模型的一个共同缺点是推理延迟高——自回归模型需要连续运行超过一千次以生成图像令牌，而扩散模型则需要通过数百步去噪过程将高斯噪声转换为图像。在这项工作中，我们探索了非自回归文本到图像模型，这些模型能够高效地并行生成数百个图像令牌。我们开发了多种模型变体，采用了不同的学习和推理策略、初始化文本编码器等。与需要运行一千次的自回归基线相比，我们的模型仅运行16次即可生成具有竞争力的图像质量，推理延迟降低了一个数量级。我们的非自回归模型拥有3.46亿参数，在一张V100 GPU上生成一张256×256的图像大约需要一秒。
英文摘要：
Autoregressive and diffusion models drive the recent breakthroughs on text-to-image generation. Despite their huge success of generating high-realistic images, a common shortcoming of these models is their high inference latency - autoregressive models run more than a thousand times successively to produce image tokens and diffusion models convert Gaussian noise into images with many hundreds of denoising steps. In this work, we explore non-autoregressive text-to-image models that efficiently generate hundreds of image tokens in parallel. We develop many model variations with different learning and inference strategies, initialized text encoders, etc. Compared with autoregressive baselines that needs to run one thousand times, our model only runs 16 times to generate images of competitive quality with an order of magnitude lower inference latency. Our non-autoregressive model with 346M parameters generates an image of 256$\times$256 with about one second on one V100 GPU.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
