Loading video...
Video Failed to Load
GoogleAI just released "Muse", a text-to-image generation/editing model via Masked Generative Transformers: - Achieves new SOTA - Zero-shot, Mask-free editing - Zero-shot Inpainting/Outpainting - 900M params 📄 Paper: ⚙️ Project:
630,453 views • 3 years ago •via X (Twitter)
10 Comments

Lior⚡3 years ago
Model details:

Peter Baylies3 years ago
@AlphaSignalAI The word is "announced", not "released".

Lior⚡3 years ago
How about "teased"

Lachlan Phillips exo/acc 👾3 years ago
@AlphaSignalAI Google's new AI can generate images in 1.3 seconds plus the 18 months it takes them to actually release the thing.

Carlos E. Perez3 years ago
@AlphaSignalAI Released to who? A bunch of academics reviewing papers?

Jason Scott3 years ago
@AlphaSignalAI @olivercameron How do we play with this?

SaaS Trash 🗑🔥3 years ago
@AlphaSignalAI @readwise save

Tycho3 years ago
@AlphaSignalAI The now hot competition between AI developers is great; gonna be an interesting 2023.

ChrisGPT 🌎3 years ago
@AlphaSignalAI With all this ChatGPT interest, they had to start flexing. Expect more of this…

Jarred Barber3 years ago
@AlphaSignalAI There's a 900M param model, but all examples are from the 3B param model.

