Загрузка видео...

Не удалось загрузить видео

На главную

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To unleash the power of the foundation model, Seaweed-7B further enables a wide range...

77,502 просмотров • 1 год назад •via X (Twitter)

Комментарии: 11

Фото профиля A.I.Warper
A.I.Warper1 год назад

Open sourced? 🤤

Фото профиля The Information
The Information1 год назад

Meta AI researchers are fretting over the threat of Chinese AI, whose quality caught American firms, including OpenAI, by surprise.

Фото профиля mrfakename
mrfakename1 год назад

Very cool! Any plans to open source?

Фото профиля Vishal Jain
Vishal Jain1 год назад

it only matters if it is open source

Фото профиля Jim Fan
Jim Fan1 год назад

Interesting work!

Фото профиля Latent Spacer
Latent Spacer1 год назад

Are you considering open weights?

Фото профиля Jerome Patel
Jerome Patel1 год назад

Wow this is just great work, hoping to see it in Open-sourced version

Фото профиля Lachlan Phillips exo/acc 👾
Lachlan Phillips exo/acc 👾1 год назад

Great tech demo until there's code or an API

Фото профиля MR BIZARRO
MR BIZARRO1 год назад

If we all say "open source it" here, maybe they will....

Фото профиля Emily
Emily1 год назад

Congratulations 🎉 please open-source the model 🙏

Фото профиля Kabooki AI
Kabooki AI1 год назад

looks promising, open source soon?

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

367,108 просмотров • 1 год назад