按年被提到
20232023 · 2 次2026
视觉、语音与图像生成›扩散模型·arXiv:2303.01469 · cs.LG

Consistency Models

Yang Song, Prafulla Dhariwal, Mark Chen, Ilya Sutskever · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-04-12 · 最近 2023-11-10
2不同的人
2活跃月份
2讨论串
255被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new family of models that generate high quality samples by directly mapping noise to data. They support fast one-step generation by design, while still allowing multistep sampling to trade compute for sample quality. They also support zero-shot data editing, such as image inpainting, colorization, and super-resolution, without requiring explicit training on these tasks. Consistency models can be trained either by distilling pre-trained diffusion models, or as standalone generative models altogether. Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 for one-step generation. When trained in isolation, consistency models become a new family of generative models that can outperform existing one-step, non-adversarial generative models on standard benchmarks such as CIFAR-10, ImageNet 64x64 and LSUN 256x256.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论billconan · 2023-11

“to my defense, if you look at the original paper https://arxiv.org/pdf/2303.01469.pdf the exact neural network used for the prediction method is omitted. apparently many neural networks can be used for this prediction method as long as they fulfill certain requirements. > why was diffusion necessary in the past? in the paper, one way to train a consis…”

Real-time image editing using latent consistency models原评论 ↗
被提交为 story · 1 次