Papers1 provider · 1 record
June 1, 2023· 2023 IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom)
conference-paper

Utilizing Latent Codes for Minting AI-Generated Digital Assets into NFTs

Abstract

The use of Artificial Intelligence (AI) generators to create digital artwork as the content of Non-Fungible Tokens (NFTs) is prevalent. Typically, when minting AI-generated digital artwork into NFTs, the data of digital artwork is stored in the cloud or decentralized storage system, and a Uniform Resource Identifier (URI) or Content Identifier (CID) of the data is stored in the smart contract of NFTs to access the data. This makes AI art NFTs suffer from potential asset loss as conventional NFTs. Can AI be utilized to enhance the availability of AI-generated digital assets as NFT content? In this paper, we propose a new method for minting AI-generated digital assets into NFTs. The key idea of our approach is to store the latent codes of the generated assets on the blockchain instead of URI or CID in conventional NFTs. Here, the latent codes are intermediate variables in the process of generating digital assets by the generator and could restore the assets through the generator. Meanwhile, to be able to restore assets, the universal generator is stored on a distributed system, and its high popularity guarantees its availability. Experiments demonstrate the feasibility of our method. In addition, the integrity and the availability of assets minted by the proposed method and the existing ones are discussed, concluding that our approach has better availability while safeguarding integrity.

Community

0 comments
Use Connect Wallet in the navigation

No discussion yet

Be the first to share a question or observation.