search
HomeTechnology peripheralsAIByteDouBao's new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.
The AIxiv column is a column where this site publishes academic and technical content. In the past few years, the AIxiv column of this site has received more than 2,000 reports, covering top laboratories from major universities and companies around the world, effectively promoting academic exchanges and dissemination. If you have excellent work that you want to share, please feel free to contribute or contact us for reporting. Submission email: liyazhou@jiqizhixin.com; zhaoyunfeng@jiqizhixin.com
In the rapid development of generative models, Image Tokenization plays a very important role, such as VAE that Diffusion relies on or VQGAN that Transformer relies on. . These Tokenizers encode the image into a more compact latent space, making it more efficient to generate high-resolution images.

However, existing Tokenizers usually map the input image to a downsampled 2D matrix in the latent space. This design implicitly limits the mapping relationship between tokens and images, making it difficult to Effectively utilize redundant information in the image (for example, adjacent areas often have similar features) to obtain a more effective image encoding.

In order to solve this problem, ByteDance Beanbao Big Model Team and Technical University of Munich proposed a new 1D image Tokenizer: TiTok. This Tokenizer breaks the design limitations of 2D Tokenizer and can compress the entire image to a more compact Token sequence.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

  • Paper link: https://arxiv.org/abs/2406.07550
  • Project link: https://yucornetto.github.io/projects/titok.html
  • Code link: https://github.com/bytedance/1d-tokenizer

For a 256 x 256 resolution image, TiTok only needs a minimum of 32 Tokens to express it, which is 256 or 1024 Tokens than the usual 2D Tokenizer significantly reduced. For a 512 x 512 resolution image, TiTok requires at least 64 Tokens, which is 64 times smaller than Stable Diffusion’s VAE Tokenizer. In addition, on the task of ImageNet image generation, using TiTok as the Tokenizer generator has significantly improved the generation quality and generation speed.

At 256 resolution, TiTok achieved an FID of 1.97, significantly exceeding MaskGIT’s 4.21 using the same generator. At 512 resolution TiTok can achieve an FID of 2.74, which not only exceeds DiT (3.04), but also accelerates image generation by an astonishing 410 times compared to DiT! The best variant of TiTok achieved an FID of 2.13, significantly exceeding DiT while still achieving a 74x acceleration.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

                                                                                                                                                        ​                                                                                                                                                                                                                                                                           with tokens required for images to result in significantly faster generation speeds , but while maintaining high-quality image generation.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

Model structure

The structure of TiTok is very simple. The encoder and decoder parts are each a ViT. During the encoding process, a set of latent tokens will be spliced ​​after the image patches. After passing through the encoder, only the latent tokens are retained and the quantization process is performed. The obtained quantized latent tokens will be spliced ​​together with a set of mask tokens and sent to the decoder to reconstruct the image from the mask token sequence.
Study on the properties of 1D Tokenization

The researchers conducted a series of experimental studies on different numbers of tokens used to represent images, different tokenizer sizes, reconstruction performance, generation performance, linear probing accuracy, and training and Comparison of reasoning speed. During this process, the researchers found that (1) only 32 Tokens can achieve good reconstruction and generation effects (2) By increasing the model size of Tokenizer, researchers can use fewer Tokens to represent images ( 3) When fewer Tokens are used to represent pictures, Tokenizer will learn stronger semantic information. (4) When fewer Tokens are used to represent pictures, training and inference speeds are significantly improved.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

In addition, the video shows the reconstructed images using different Tokenizer sizes and the number of Tokens. It can be seen that a larger Tokenizer can reconstruct better quality images with limited Tokens. In addition, when there are only limited tokens, the model is more inclined to retain salient areas and achieve better reconstruction results.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

Experimental verification

The researchers mainly compared with other methods at the 256 x 256 resolution and 512 x 512 resolution of ImageNet-1k. It can be seen that although TiTok uses a limited number of Tokens, it can achieve comparable reconstruction results (rFID) with other methods that use more Tokens. Using a smaller number of Tokens allows TiTok to maintain a higher generated image quality (gFID) At the same time, it has a significantly faster generation speed than other methods.

For example, TiTok-L-32 achieved a gFID score of 2.77 and can generate images at a speed of 101.6 images per second, which is significantly faster than other Diffusion Models (169 times faster than DiT) or Transformer Models (339 times faster than ViT-VQGAN).

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

TiTok’s advantage of using fewer tokens is more obvious in higher-resolution image generation, where TiTok-L-64 can be completed using only 64 tokens Reconstruction and generation of high-quality 512 resolution images. The quality of the generated images is not only higher than DiT (2.74 v.s. 3.04), but the generation speed is increased by nearly 410 times.

ByteDouBaos new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.

Conclusion

In this article, the researcher focuses on a new 1D Image Tokenizer and proposes a new Tokenizer to break the limitations of the existing 2D Tokenizer and make it more advanced Good use of redundant information in images. TiTok only needs a small number of Tokens (such as 32) to represent images, while still being able to perform high-quality image reconstruction and generation. In ImageNet's 256 resolution and 512 resolution generation experiments, TiTok not only achieved generation quality that exceeded Diffusion Models, but also achieved a hundred times faster generation speed.

About the Doubao Large Model Team

ByteDance Doubao Large Model Team was established in 2023 and is committed to developing the industry's most advanced AI large model technology and becoming a world-class research team. Contribute to technological and social development.

The Doubao Big Model team has long-term vision and determination in the field of AI. Its research directions cover NLP, CV, speech, etc., and it has laboratories and research positions in China, Singapore, the United States and other places. Relying on the platform's sufficient data, computing and other resources, the team continues to invest in related fields. It has launched a self-developed general large model to provide multi-modal capabilities. It supports 50+ businesses such as Doubao, Buttons, and Jimeng downstream, and is open to the public through the Volcano Engine. Corporate customers. At present, Doubao APP has become the AIGC application with the largest number of users in the Chinese market.

Welcome to join the Bytedance Beanbao Big Model Team, click the link below to enter the Bytedance Top Seed plan:
https://mp.weixin.qq.com/s/ZjQ-v6reZXhBP6G27cbmlQ

The above is the detailed content of ByteDouBao's new image Tokenizer: only 32 tokens are needed to generate an image, and the speed is increased by up to 410 times.. For more information, please follow other related articles on the PHP Chinese website!

Statement
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
How to Run LLM Locally Using LM Studio? - Analytics VidhyaHow to Run LLM Locally Using LM Studio? - Analytics VidhyaApr 19, 2025 am 11:38 AM

Running large language models at home with ease: LM Studio User Guide In recent years, advances in software and hardware have made it possible to run large language models (LLMs) on personal computers. LM Studio is an excellent tool to make this process easy and convenient. This article will dive into how to run LLM locally using LM Studio, covering key steps, potential challenges, and the benefits of having LLM locally. Whether you are a tech enthusiast or are curious about the latest AI technologies, this guide will provide valuable insights and practical tips. Let's get started! Overview Understand the basic requirements for running LLM locally. Set up LM Studi on your computer

Guy Peri Helps Flavor McCormick's Future Through Data TransformationGuy Peri Helps Flavor McCormick's Future Through Data TransformationApr 19, 2025 am 11:35 AM

Guy Peri is McCormick’s Chief Information and Digital Officer. Though only seven months into his role, Peri is rapidly advancing a comprehensive transformation of the company’s digital capabilities. His career-long focus on data and analytics informs

What is the Chain of Emotion in Prompt Engineering? - Analytics VidhyaWhat is the Chain of Emotion in Prompt Engineering? - Analytics VidhyaApr 19, 2025 am 11:33 AM

Introduction Artificial intelligence (AI) is evolving to understand not just words, but also emotions, responding with a human touch. This sophisticated interaction is crucial in the rapidly advancing field of AI and natural language processing. Th

12 Best AI Tools for Data Science Workflow - Analytics Vidhya12 Best AI Tools for Data Science Workflow - Analytics VidhyaApr 19, 2025 am 11:31 AM

Introduction In today's data-centric world, leveraging advanced AI technologies is crucial for businesses seeking a competitive edge and enhanced efficiency. A range of powerful tools empowers data scientists, analysts, and developers to build, depl

AV Byte: OpenAI's GPT-4o Mini and Other AI InnovationsAV Byte: OpenAI's GPT-4o Mini and Other AI InnovationsApr 19, 2025 am 11:30 AM

This week's AI landscape exploded with groundbreaking releases from industry giants like OpenAI, Mistral AI, NVIDIA, DeepSeek, and Hugging Face. These new models promise increased power, affordability, and accessibility, fueled by advancements in tr

Perplexity's Android App Is Infested With Security Flaws, Report FindsPerplexity's Android App Is Infested With Security Flaws, Report FindsApr 19, 2025 am 11:24 AM

But the company’s Android app, which offers not only search capabilities but also acts as an AI assistant, is riddled with a host of security issues that could expose its users to data theft, account takeovers and impersonation attacks from malicious

Everyone's Getting Better At Using AI: Thoughts On Vibe CodingEveryone's Getting Better At Using AI: Thoughts On Vibe CodingApr 19, 2025 am 11:17 AM

You can look at what’s happening in conferences and at trade shows. You can ask engineers what they’re doing, or consult with a CEO. Everywhere you look, things are changing at breakneck speed. Engineers, and Non-Engineers What’s the difference be

Rocket Launch Simulation and Analysis using RocketPy - Analytics VidhyaRocket Launch Simulation and Analysis using RocketPy - Analytics VidhyaApr 19, 2025 am 11:12 AM

Simulate Rocket Launches with RocketPy: A Comprehensive Guide This article guides you through simulating high-power rocket launches using RocketPy, a powerful Python library. We'll cover everything from defining rocket components to analyzing simula

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Tools

PhpStorm Mac version

PhpStorm Mac version

The latest (2018.2.1) professional PHP integrated development tool

WebStorm Mac version

WebStorm Mac version

Useful JavaScript development tools

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

SublimeText3 Linux new version

SublimeText3 Linux new version

SublimeText3 Linux latest version

SAP NetWeaver Server Adapter for Eclipse

SAP NetWeaver Server Adapter for Eclipse

Integrate Eclipse with SAP NetWeaver application server.