Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
Authors:
- Jian HanJHJian Han
- Jinlai LiuJLJinlai Liu
- Yi JiangYJYi Jiang
- Bin YanBYBin Yan
- Yuqi ZhangYZYuqi Zhang
- Zehuan YuanZYZehuan Yuan
- Bingyue PengBPBingyue Peng
- Xiaobing LiuXLXiaobing Liu
Preprint
Abstract
We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction. Infinity redefines visual autoregressive model under a bitwise token prediction framework with an infinite-vocabulary tokenizer & classifier and bitwise self-correction mechanism, remarkably improving the generation capacity and details. By theoretically scaling the tokenizer vocabulary size to infinity and concurrently scaling the transformer size, our method significantly unleashes powerful scaling capabilities compared to vanilla VAR. Infinity sets a new record for autoregressive text-to-image models, outperforming top-tier diffusion models like SD3-Medium and SDXL. Notably, Infinity surpasses SD3-Medium by improving the GenEval benchmark score from 0.62 to 0.73 and the ImageReward benchmark score from 0.87 to 0.96, achieving a win rate of 66%. Without extra optimization, Infinity generates a high-quality 1024x1024 image in 0.8 seconds, making it 2.6x faster than SD3-Medium and establishing it as the fastest text-to-image model. Models and codes will be released to promote further exploration of Infinity for visual generation and unified tokenizer modeling.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic ModelsMachine Intelligence Research, 2025
- PIXART-$\Sigma $: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation2024
- An Image is Worth 32 Tokens for Reconstruction and Generation2024
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction2024
- RoFormer: Enhanced transformer with Rotary Position EmbeddingNeurocomputing, 2023