正在加载视频...

视频加载失败

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 次观看 • 1 年前 •via X (Twitter)

11 条评论

A.I.Warper 的头像
A.I.Warper1 年前

Open sourced? 🤤

The Information 的头像
The Information1 年前

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

mrfakename 的头像
mrfakename1 年前

Very cool! Any plans to open source?

Vishal Jain 的头像
Vishal Jain1 年前

it only matters if it is open source

Jim Fan 的头像
Jim Fan1 年前

Interesting work!

Latent Spacer 的头像
Latent Spacer1 年前

Are you considering open weights?

Jerome Patel 的头像
Jerome Patel1 年前

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

Lachlan Phillips exo/acc 👾 的头像
Lachlan Phillips exo/acc 👾1 年前

Great tech demo until there's code or an API

MR BIZARRO 的头像
MR BIZARRO1 年前

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

Emily 的头像
Emily1 年前

Congratulations 🎉 please open-source the model 🙏

Kabooki AI 的头像
Kabooki AI1 年前

looks promising, open source soon?

相关视频

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 次观看 • 1 年前