Tag
RoAR-VAE提出通过从受损隐变量中鲁棒地预测语义与重建信息来改进视觉tokenizer,在保持重建保真度的同时提升下游扩散模型的可学习性,平均生成基准提升2.19分,小文本重建精度较FLUX.1-VAE提升16.93个百分点。
UniAR presents a unified autoregressive framework that uses a single discrete visual tokenizer to bridge visual understanding and generation, achieving state-of-the-art results in image generation and editing.