NFTs

Training AI on your NFTs

Published

on

Last August, I introduced Metaversal readers to for TITLESan NFT remixing platform with an integrated payment allocation and split system.

After the initial launch of the app + protocol combination, the TITLES team stepped back and realized that issues of attribution and creative ownership were particularly significant in the emerging AI arts scene.

Recognizing this, they adapted existing tools to better support AI creatives. The first big step here is a feature they revealed today, the ability of artists to train their own custom AI models on NFTs they have created before.

The idea? Become a leading creator pool and creation hub for artist-trained AI models.

I was lucky enough to receive a preview of this new feature as the founder of TITLES Soren John was familiar with my collection of AI sketches, Stable Peastersand invited me to test creating a custom template so anyone could create and mint their own Stable Ps.

So I did! And I must say, the process was smooth and only took about 20 minutes. Here’s how the flow works if you’re interested in trying it out for yourself:

1. Go to titles.xyz/models and connect your wallet

2. In the “New Model” tab, select which of your NFT collections you want to train on – for example, here I selected Stable Peasters

3. Select 5 to 20 NFTs to train your model and finalize your model’s basic information – the more visually harmonious your selected inputs are, the smoother your model’s outputs will be, so be sure to curate carefully

4. Your model will take up to 20 minutes to complete the training; You can track your progress in the “Your Models” tab

If you don’t yet have any NFT collections you’ve created but still want to play around with creating AI remixes, try firing off some test prompts with my model SPRY01also known as Stable Peasters Readily Yours V1, as seen above.

You can enter as many prompts as you like without minting anything, but if you find a result you love, feel free to save the image or use the TITLES interface to mint the piece as an NFT on Base – just fill in the description and create the details as you wish and press “Publish” to finish.

What’s cool is that every time the results are minted like this in TITLES, the creator of the original model (e.g. me in the case of SPRY01) gets a small portion of the ETH from the minting. This approach allows AI creatives to directly earn and benefit from attribution while openly sharing their work with everyone else.

Looking ahead, keep an eye on TITLES as they improve and expand this custom AI tool in new directions, for example allowing 20+ NFT entries and so on.

In the coming months, the team also plans to launch a new AI-based NFT publishing protocol that will offer artists innovative ways to interact and profit from the results of their models. More on that later!

In the meantime, follow TITLES on twitter or Warpcast to stay up to date with the project, and if you create your own AI model or publish any of your own Stable Ps, don’t hesitate to hit me—I would love to see what you came up with and I would love to mint one of your editions as a souvenir!



Fuente

Leave a Reply

Your email address will not be published. Required fields are marked *

Información básica sobre protección de datos Ver más

  • Responsable: Miguel Mamador.
  • Finalidad:  Moderar los comentarios.
  • Legitimación:  Por consentimiento del interesado.
  • Destinatarios y encargados de tratamiento:  No se ceden o comunican datos a terceros para prestar este servicio. El Titular ha contratado los servicios de alojamiento web a Banahosting que actúa como encargado de tratamiento.
  • Derechos: Acceder, rectificar y suprimir los datos.
  • Información Adicional: Puede consultar la información detallada en la Política de Privacidad.

Trending

Exit mobile version