Denis Rossiev ᯅ/acc(@Enuriru) 's Twitter Profile Photo

OpenAI just introduced SORA: new text2video model.

While everyone is just posting mind-blowing examples, I want to talk about the consequences.

A thread 🧵🔽

account_circle
Ziwei Liu(@liuziwei7) 's Twitter Profile Photo

🔥🔥We are excited to announce , an open-source project for video generative models Hugging Face

📽️LaVie (Text2Video Model)
- Code: github.com/Vchitect/LaVie
- huggingface.co/spaces/Vchitec…

📽️SEINE (Image2Video Model)
- Code: github.com/Vchitect/SEINE
- huggingface.co/spaces/Vchitec…

account_circle
KEITO💻AIディレクター(@keitowebai) 's Twitter Profile Photo

OpenAIの動画生成AI「Sora」がマジで凄すぎる!

2024/02/16にOpenAIから発表されたtext2videoのサービス「Sora」がクオリティが非常に高いと話題。しかも、ただクオリティが高いだけでは無く、やれる事も多くあるようです。

そこでSoraで可能”らしい”事をまとめます。
(現時点のレポートを参照)

account_circle
Tanishq Mathew Abraham, Ph.D.(@iScienceLuvr) 's Twitter Profile Photo

Stability AI is releasing Stable Video Diffusion! 🔥

This is a new image-to-video model that can produce 14-25 frames at resolution 576x1024 given a context frame of the same size. Text2video model coming soon.

Announcement: stability.ai/news/stable-vi…
Paper:

account_circle
PixVerse(@PixVerse_) 's Twitter Profile Photo

🪄New style update, 3D Animation choice available!! ✨

From fairytales to graduation and finding love, our journey is full of challenges.👸🫅
May you always keeping the passion alive.

More on app.pixverse.ai 🤩

account_circle
Satoshi Nakajima @NounsDAO 🇺🇦(@snakajima) 's Twitter Profile Photo

OpenAI が最長60秒のビデオをプロンプトから生成できるtext2videoモデル、Soraをアナウンス。これは「雪と桜の東京を楽しみながらショッピングするカップルをカメラで追いかける様子(意訳)」というプロンプトで生成された映像。

account_circle
Burkan Yılmaz(@BurkanYilmaz) 's Twitter Profile Photo

İşte bunlar hep SDXL, düzgün konfigürasyonlarla neler çıkıyor ortaya.
AnimateDiff, Text2Video derken stable diffusion’ını unutmamak lazım.

İşte bunlar hep SDXL, düzgün konfigürasyonlarla neler çıkıyor ortaya.
AnimateDiff, Text2Video derken stable diffusion’ını unutmamak lazım.
account_circle
Omer Bar Tal(@omerbartal) 's Twitter Profile Photo

Text2video models are getting interesting!📽️

Check out how we leverage their space-time features in a zero-shot manner for transferring motion across objects and scenes!

diffusion-motion-transfer.github.io
Led by Danah Yatim Rafail Fridman,Yoni Kasten Tali Dekel
[1/3]

account_circle
TAO Community Hub(@TAOCommunityHub) 's Twitter Profile Photo

Bittensor's $TAO Subnet Competition Spurs Innovation: Introducing New Subnet 5: Fractal-text2video!

In the ever-evolving landscape of decentralized networks, competition is not just a game; it's a driving force for innovation and quality. Bittensor, a decentralized network known

Bittensor's $TAO Subnet Competition Spurs Innovation: Introducing New Subnet 5: Fractal-text2video!

In the ever-evolving landscape of decentralized networks, competition is not just a game; it's a driving force for innovation and quality. Bittensor, a decentralized network known
account_circle
Min Choi(@minchoi) 's Twitter Profile Photo

This AI 'benchmark' started with this viral post 'Will Smith eating spaghetti' generated by Modelscope text2video back in March 2023

account_circle
Dave Villalva(@DaveJWVillalva) 's Twitter Profile Photo

Want to become an astronaut?

With @RunwayML’s improved Text2Video model, I journeyed beyond the stars 🚀🌌

Here's how to create your own interstellar adventure:

account_circle