Happy Oyster supported two modes of virtual world creation, according to ATH: a directing mode for building a world based on text and image prompts and a wandering mode for exploring that world.
Advertisement
Unlike conventional AI video tools, which generate one-off clips that top out at a dozen seconds or a few minutes, Happy Oyster could generate video clips of up to three minutes showing virtual worlds, the company said. In addition, the model could continuously respond to instructions throughout the generation process, as opposed to the conventional, one-shot AI paradigm, the company said.

Advertisement
The launch came a day after San Francisco-based World Labs, co-founded by Li, a Stanford professor, in early 2024, unveiled Spark 2.0, an open-source 3D Gaussian splatting rendering engine that aims to give even less powerful devices, such as smartphones, the ability to view large-scale and detailed 3D images.

Don't Miss:
-
FBI Most Wanted “Chapo Isidro,” Leader of BLO/Guasave Cartel Arrested in Sinaloa, “El Musico” Possibly Killed
-
DEA’s #FugitiveFriday asks for tips on “El Tano” García Corrales, found dead in Sinaloa in 2024
-
Mocorito, Sinaloa: “El Pagador” and “El Chendo” of La FEA, arrested again 15 months after walking free
-
Zapopan: Marines arrest “El Topo,” alleged Los Deltas leader linked to journalist’s kidnapping; three gunmen killed
-
Open Position: English Language Editor

Trump Enjoyed His Asian Spectacle. He Came Home Empty-Handed
Medical device makers have gotten worse at disclosing when their products harm people, new study finds. The FDA let them.
Anatomy of a Chinese loanbook