nyu-visionx/scale-rae-data
收藏Hugging Face2026-01-24 更新2026-02-07 收录
下载链接：
https://hf-mirror.com/datasets/nyu-visionx/scale-rae-data
下载链接
链接失效反馈官方服务：
资源简介：
该数据集与论文《Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders》相关，用于训练和评估Scale-RAE框架。Scale-RAE是一个研究如何扩展表示自动编码器（RAEs）以进行大规模、自由形式的文本到图像（T2I）生成的框架。数据集包含用于扩展RAE解码器超出ImageNet范围的数据，包括网络数据、合成数据、文本渲染数据，以及用于微调的高质量指令数据集。
This repository contains data associated with the paper Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders. The dataset is used for training and evaluating Scale-RAE, a framework that investigates scaling Representation Autoencoders (RAEs) for large-scale, freeform text-to-image (T2I) generation. It includes data used for scaling RAE decoders beyond ImageNet, featuring web, synthetic, and text-rendering data, as well as high-quality instruction datasets for fine-tuning.
提供机构：
nyu-visionx
