Vitalik Buterin endorses TiTok AI for onchain image storage

Josh O"Sullivan12 hours agoVitalik Buterin endorses TiTok AI for onchain image storageTiTok AI, a new method for efficient onchain image compression, could be a useful tool for blockchain applications.3086 Total views3 Total sharesListen to article 0:00NewsOwn this piece of crypto historyCollect this article as NFTJoin us on social networksEthereum co-founder Vitalik Buterin has endorsed the new Token for Image Tokenizer (TiTok) compression method for its potential blockchain application.

Not to be confused with the social media platform TikTok, the new TiTok compression method significantly reduces image size, making it more practical for storage on the blockchain.

Buterin highlighted TiTok’s blockchain potential on the decentralized social media platform Farcaster, stating “320 bits is basically a hash. Small enough to go on chain for every user.”

The development could have significant implications for digital image storage of profile pictures (PFPs) and non-fungible tokens (NFTs).Source: Thomas

Related:Traders: Ethereum is the ‘most bullish altcoin’ as ETH reclaims $3.5KTiTok image compression

Developed by ByteDance and Technical University Munich researchers, TiTok allows the compression of an image into 32 small data pieces (bits) without losing quality.

According to the TiTok research paper, advanced artificial intelligence (AI) image compression enables TiTok to compress a 256x256 pixel image into “32 discrete tokens.”

TiTok is a 1-dimensional (1D) image tokenization framework that “breaks grid constraints existing in 2D tokenization methods,” leading to more flexible and compact images.“As a result, it leads to a substantial speed-up on the sampling process (e.g., 410 × faster than DiT-XL/2) while obtaining a competitive generation quality.”TiTok research paper displaying image compression size comparisons. Source: TiTok

Related:Spot Ethereum ETFs may begin trading by July 2 — Bloomberg AnalystMachine learning imagery

TiTok utilizes machine learning and advanced AI, using transformer-based models to convert images into tokenized representations.

The method uses region redundancy, meaning it identifies and uses redundant information in different regions of the image to reduce the overall data size of the end product.“Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images.”

According to the research paper, TiTok’s "compact latent representation” can yield “substantially more efficient and effective representations than conventional techniques.”Illustration of image reconstruction (a) and generation (b) with the TiTok framework (c). Source: TiTok

Related:Vitalik Buterin-backed Nocturne protocol shuts down operations overnightTiTok, not TikTok

Despite the similar name, TikTok, the social media platform, did not receive endorsement from Buterin.

The Ethereum co-founder, highlighting TiTok’s blockchain potential, lends credibility to the new AI-driven image compression method.“Unlike the existing 2D VQ models that consider the image latent space as a 2D grid, we provide a more compact formulation to tokenize an image into a 1D latent sequence.”

The proposed new method can “represent an image with 8 to 64 times” fewer tokens than “2D tokenizers,” and the team hopes the research can shed light on “more efficient image representation.”

Magazine:$1M bet ChatGPT won’t lead to AGI, Apple’s intelligent AI use, AI millionaires surge: AI Eye# Blockchain# Decentralization# Ethereum# Technology# Vitalik Buterin# Tokens# Blockchain Storage# Web3# NFTAdd reaction