Abstract_art版本abstractv1.0 (ID: 426148)

This is an ethically trained AI model, with CC content, specifically designed for generating abstract art. Take 3 days on a single RTX 3090. Training from scratch, or almost, the tokenizer end up verry inconsistent the prompt don't actually change much of the model. It should be able to output black and white icons but doesn't works But for a prove of concept I hope you enjoy

Where used 569 images:

https://www.pexels.com/pt-br/@anniroenkae/ 30 images

https://opengameart.org/content/700-rpg-icons 533 images

regularized 6 geometric shapes images

All images generate with this model can be use by comercial and research, I am working on expanding this model to more concepts. Currently we have a datatset of around half million CC and CC0 images, we appreciate anyone how want to contribute whit images or help the datatset classification.

This model was trained and developed tool place in Brazil, and comply with national copyright legislation https://www.planalto.gov.br/ccivil_03/leis/l9610.htm it might differ if from you country.

描述:

训练词语: