Tag
PixText 将局部文本修正建模为像素空间的分组图像生成，仅生成目标区域并保留未编辑内容，借助 MeanFlow 实现四步快速生成，在新提出的 TextRefinementBench 上以 83.06% 的字形通过率大幅超越最强基线。
FlashRender is a few-step generative rendering framework that accelerates video synthesis by aligning representations and using mean-flow objectives, achieving comparable quality to multi-step methods with significantly reduced sampling cost.