GitHub 热门项目：VAR

GitHub 项目：VAR 仓库地址：https://github.com/FoundationVision/VAR 星级：8688 | 作者：FoundationVision 项目描述：[NeurIPS 2024 最佳论文奖][GPT 击败扩散?] [视觉生成中的缩放定律?] 官方实现。 “视觉自回归建模：通过下一代预测生成可扩展图像”。用于自回归图像生成的*超简单、用户友好且最先进的*代码库！ =================================================== 自述文件内容： # VAR：一种新的视觉生成方法将 GPT 式模型提升到超越扩散? 和观察到的缩放定律? [![演示平台](https://img.shields.io/badge/Play%20with%20VAR%21-VAR%20demo%20platform-lightblue)](https://opensource.bytedance.com/gmpt/t2i/invite) [![arXiv](https://img.shields.io/badge/arXiv%20paper-2404.02905-b31b1b.svg)](https://arxiv.org/abs/2404.02905) [![huggingface 权重](https://img.shields.io/badge/%F0%9F%A4%97%20Weights-FoundationVision/var-yellow)](https://huggingface.co/FoundationVision/var) [![SOTA](https://img.shields.io/badge/State%20of%20the%20Art-Image%20Generation%20on%20ImageNet%20 %28AR%29-32B1B4?徽标=数据%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iNjA2IiBoZWlnaHQ9IjYwNiIgeG 1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIiB4bWxuczp4bGluaz0iaHR0cDovL3d3dy53My5vcmcvMTk5OS94bGlua yIgb3ZlcmZsb3c9ImhpZGRlbiI%2BPGRlZnM%2BPGNsaXBQYXRoIGlkPSJjbGlwMCI%2BPHJlY3QgeD0iLTEiIHk9Ii0xIiB3aW R0aD0iNjA2IiBoZWlnaHQ9IjYwNiIvPjwvY2xpcFBhdGg%2BPC9kZWZzPjxnIGNsaXAtcGF0aD0idXJsKCNjbGlwMCkiIHRyYW 5zZm9ybT0idHJhbnNsYXRlKDEgMSkiPjxyZWN0IHg9IjUyoSigeT0iNjYiIHdpZHROPSI1NiIgaGVpZ2h0PSI0NzMiIGZpbGw9I iM0NEYRjYiLz48cmVjdCB4PSIxOSIgeT0iNjYiIHdpZHROPSI1NyIgaGVpZ2h0PSI0NzMiIGZpbGw9IiM0NEYyRjYiLz48cmVj DCB4PSIyNzQiIHk9IjE1MSIgd2lkdGg9IjU3IiBoZWlnaHQ9IjMwMiIgZmlsbD0iIzQ0RjJGNiIvPjxyZWN0IHg9IjEwNCIgeT0 iMTUxIiB3aWR0aD0iNTciIGhlaWdodD0iMzayIiBmaWxsPSIjNDRGMky2Ii8%2BPHJly3QgeD0iNDQ0IiB5PSIxNTEiIHdpZHR OPSI1NyIgaGVpZ2h0PSIzMDIiIGZpbGw9IiM0NEYyRjYiLz48cmVjdCB4PSIzNTkiIHK9IjE3MCIgd2lkdGg9IjU2IiBoZWlnaH Q9IjI2NCIgZmlsbD0iIzQ0RjJGNiIvPjxyZWN0IHg9IjE4OCIgeT0iMTcwIiB3aWR0aD0iNTciIGhlaWdodD0iMjY0IiBmaWxsP SIjNDRGMky2Ii8%2BPHJly3QgeD0iNzYiIHK9IjY2IiB3aWR0aD0iNDCIIGhlaWdodD0iNTciIGZpbGw9Iim0NEYyRjYiLz48cm VjDCB4PSI0ODIiIHK9IjY2IiB3aWR0aD0iNDCIIGhlaWdodD0iNTciIGZpbGw9IiM0NEYyRjYiLz48cmVjdCB4PSI3NiIgeT0i NDgyIiB3aWR0aD0iNDciIGhlaWdodD0iNTciIGZpbGw9IiM0NEYyRjYiLz48cmVjdCB4PSI0ODIiIHk9IjQ4MiIgd2lkdGg9IjQ 3IiBoZWlnaHQ9IjU3IiBmaWxsPSIjNDRGMkY2Ii8%2BPC9nPjwvc3ZnPg%3D%3D)](https://paperswithcode.com/sota/image- Generation-on-imagenet-256x256?tag_filter=485&p=visual-autoregressive-modeling-scalable-image)