Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Google presents Genie Generative Interactive Environments introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie...

684,259 Aufrufe • vor 2 Jahren •via X (Twitter)

9 Kommentare

Profilbild von AK
AKvor 2 Jahren

paper page:

Profilbild von AK
AKvor 2 Jahren

project page:

Profilbild von XR Multiverse
XR Multiversevor 2 Jahren

Google's warehouse of unused tech

Profilbild von crispyshh
crispyshhvor 2 Jahren

@apples_jimmy Text to Mario achieved externally

Profilbild von meowbooks --🩸/acc
meowbooks --🩸/accvor 2 Jahren

that's so cool

Profilbild von Matt Griswold
Matt Griswoldvor 2 Jahren

Can it make Wolfenstein? If not, why not.

Profilbild von Smoke-away
Smoke-awayvor 2 Jahren

🔥🔥🔥

Profilbild von Mat
Matvor 2 Jahren

all these papers, no public releases 🫠

Profilbild von Ollin Boer Bohan
Ollin Boer Bohanvor 2 Jahren

Demo page with more videos.

Ähnliche Videos

Tencent presents GameGen-O Open-world Video Game Generation We introduce GameGen-O, the first diffusion transformer model tailored for the generation of open-world video games. This model facilitates high-quality, open-domain generation by simulating a wide array of game engine features, such as innovative characters, dynamic environments, complex actions, and diverse events. Additionally, it provides interactive controllability, thus allowing for the gameplay simulation. The development of GameGen-O involves a comprehensive data collection and processing effort from scratch. We collect and build the first Open-World Video Game Dataset (OGameData), amassed extensive data from over a hundred of next-generation open-world games, employing a proprietary data pipeline for efficient sorting, scoring, filtering, and decoupled captioning. This robust and extensive OGameData forms the foundation of our model's training process. GameGen-O undergoes a two-stage training process, consisting of foundation model pretraining and instruction tuning. In the first phase, the model is pre-trained on the OGameData via the text-to-video and video continuation, endowing GameGen-O with the capability for open-domain video game generation. In the second phase, the pre-trained model is frozen, and we fine-tuned using a trainable InstructNet, which enables the production of subsequent frames based on multimodal structural instructions. This whole training process imparts the model with the ability to generate and interactively control content. In summary, GameGen-O represents a notable initial step forward in the realm of open-world video game generation via generative models. It underscores the potential of generative models to serve as an alternative to rendering techniques, which can efficiently combine creative generation with interactive capabilities.

AK

366,858 Aufrufe • vor 1 Jahr