Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 Aufrufe • vor 3 Jahren •via X (Twitter)

10 Kommentare

Profilbild von Lior⚡
Lior⚡vor 3 Jahren

Model details:

Profilbild von Peter Baylies
Peter Bayliesvor 3 Jahren

@AlphaSignalAI The word is "announced", not "released".

Profilbild von Lior⚡
Lior⚡vor 3 Jahren

How about "teased"

Profilbild von Lachlan Phillips exo/acc 👾
Lachlan Phillips exo/acc 👾vor 3 Jahren

@AlphaSignalAI Google's new AI can generate images in 1.3 seconds plus the 18 months it takes them to actually release the thing.

Profilbild von Carlos E. Perez
Carlos E. Perezvor 3 Jahren

@AlphaSignalAI Released to who? A bunch of academics reviewing papers?

Profilbild von Jason Scott
Jason Scottvor 3 Jahren

@AlphaSignalAI @olivercameron How do we play with this?

Profilbild von SaaS Trash 🗑🔥
SaaS Trash 🗑🔥vor 3 Jahren

@AlphaSignalAI @readwise save

Profilbild von Tycho
Tychovor 3 Jahren

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

Profilbild von ChrisGPT 🌎
ChrisGPT 🌎vor 3 Jahren

@AlphaSignalAI With all this ChatGPT interest, they had to start flexing. Expect more of this…

Profilbild von Jarred Barber
Jarred Barbervor 3 Jahren

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

Ähnliche Videos