Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 2 лет назад •via X (Twitter)

Комментарии: 9

Фото профиля AK
AK2 лет назад

paper page:

Фото профиля AK
AK2 лет назад

project page:

Фото профиля XR Multiverse
XR Multiverse2 лет назад

Google's warehouse of unused tech

Фото профиля crispyshh
crispyshh2 лет назад

@apples_jimmy Text to Mario achieved externally

Фото профиля meowbooks --🩸/acc
meowbooks --🩸/acc2 лет назад

that's so cool

Фото профиля Matt Griswold
Matt Griswold2 лет назад

Can it make Wolfenstein? If not, why not.

Фото профиля Smoke-away
Smoke-away2 лет назад

🔥🔥🔥

Фото профиля Mat
Mat2 лет назад

all these papers, no public releases 🫠

Фото профиля Ollin Boer Bohan
Ollin Boer Bohan2 лет назад

Demo page with more videos.

Похожие видео

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 просмотров • 1 год назад