Metraipolis › archive › dc_12eec67e445e

Moonworks Lunara: Modeling Artistic Intelligence — arXiv:2609.22272

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.22272
License (as archived): CC0-1.0
Archived: 2026-10-09T21:59:04.930Z
SHA-256 of the archived text: 0d481a4824135cdafe1e93a1404555bc04cb62fbab8bf31a3a773da84061aa7d
Stable URL of this page: https://metraipolis.com/documento/dc_12eec67e445e

How to cite

Moonworks Lunara: Modeling Artistic Intelligence — arXiv:2609.22272 — arXiv (en), https://arxiv.org/abs/2609.22272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_12eec67e445e (Metraipolis archive dc_12eec67e445e, sha256 0d481a4824135cdafe1e93a1404555bc04cb62fbab8bf31a3a773da84061aa7d)

BibTeX

@misc{dc12eec67e445e,
  title = {Moonworks Lunara: Modeling Artistic Intelligence — arXiv:2609.22272},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22272},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_12eec67e445e; sha256 0d481a4824135cdafe1e93a1404555bc04cb62fbab8bf31a3a773da84061aa7d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We formulate \emph{Artistic Intelligence} as exploration driven world realization, leaving space for creative possibility while preserving the semantic, artistic, and compositional structure that must remain true. Moonworks Lunara, a text-to-image model, implements this framework with a novel Diffusion Mixture Transformer architecture. A new training algorithm iteratively evolves the data distribution through informative sample acquisition and targeted injection of human-created art. We benchmark Lunara against seven image-generation models, including FLUX.2-Klein-4B, Qwen-Image (20B), and GPT-Image-1-Mini. With GPT-5.6 Sol as evaluator, Lunara ranks first in \emph{Aesthetic Quality (8.473 vs. 8.457 GPT-Image-1-mini)}, second in \emph{Emotional Resonance}, and remains competitive in \emph{Content Integrity}. A blind human evaluation over the same evaluation set corroborates the automated metrics, ranking Lunara first. It also stays among the strongest models under conventional measures including CLIPScore and LAION Aesthetic Predictor. On GenEval, Lunara achieves competitive performance against a broader set of 16 models, including GPT Image 2 and Seedream 4.0. These results place Lunara at the frontier with Artistic Intelligence while maintaining a sub-10B active-parameter footprint and sub-10-second inference latency. Lunara advances the general visual intelligence frontier by shifting the question from whether models can get images right to how deeply they can interpret meaning and realize it as imaginative, expressive worlds.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.22272 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T21:45:20.769Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).