BriefGPT - AI 论文速递
·
视频电梯：用多功能的文本到图像扩散模型提升视频生成质量
📝
内容提要
Text-to-video diffusion models still lag behind compared to text-to-image models, so this paper introduces VideoElevator, a training-free and plug-and-play method that improves T2V performance...
🏷️
标签
➡️
