🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Congrats to all my colleagues who worked on this for the past year! Multimodality FTW!

This is very exciting! Congrats Ashish Vaswani and niki parmar. Looking forward to see the advancements by essential.ai 🙌🚀

Today, Gemini 1.5 pro can now support 2 million tokens 🤯

This was the most fun I had working on a project so far!!

Our video generation model Veo can create clips from a single reference image. 🖼️ These can follow the original visual style alongside instructions from a text prompt. Let’s take a look. 🧵

This is cool! While folks are rightfully excited about int8 training, I want to highlight the importance of local attention. Ashish Vaswani niki parmar Noam Shazeer et al. where the first ones introducing it in the image transformer paper. It is hugely overlooked unfortunately.

The Halfmoon 🌓 reveal: Congratulations to Reve on creating the world’s leading image generation model with Reve Image! Reve Image has been in the Artificial Analysis Image Arena over the past week and is the clear leader, beating strong competition including Recraft V3,

Artificial Analysis hello world 🌜

Halfmoon is Reve Image — and it’s the best image model in the world 🥇 (🔊)

Excited to see our hard work come to life today! Honored to work with an incredible team. From research to product, this journey has been nothing short of transformative. #ProductLaunch #Teamwork #Innovation

Today's visual generative models are mere stochastic parrots of imagery, much like early language models, which could only statistically mimic short sentences with little reasoning. In contrast, modern large language models (LLMs) can comprehend long documents, keep track of

Best image model in the world from Stability AI alumni the excellent Christian Cantrell Stephan Auerhahn and team. It really excels at cohesion for very long prompts (and just about everything else!), do give it a try & iterate away I hear more models are in the works 👀

Proud to announce Reve. Our AI foundational model designed for creativity, built from the ground up, is now ranked #1 globally in multiple image arenas. Reve Image 1.0 excels at prompt adherence, aesthetics, and typography. Experience it at preview.reve.art - with

Creative generative media has been my passion since my early days at Google Brain Research. I am beyond excited to finally share what we have been building for the past few months! The team is very small but the most creative and scientifically rigorous 😍 This is just the

Excited to come out of stealth at Reve! Today's text-to-image/video models, in contrast to LLMs, lack logic. Images seem plausible initially but fall apart under scrutiny: painting techniques don't match, props don't carry meaning, and compositions lack intention. (1/4)

Typography in generative models has been a hard problem to solve. Reve Image 1 does not only generate long text, but also it is very good at stylized typography. You can generate designs like this, it follows the prompt faithfully.

uhh guys its just a preview

Holy crap. Reve is REALLY good. No surprise that it's currently #1 in the Artificial Analysis text-to-image leaderboard -- ahead of Recraft v3, Imagen v3 and FLUX 1.1 Pro. This team cooked, and it shows.

We just hacked in a funnier version of the AI on preview.reve.art for April Fools Type "fun: " before any prompt and see what it makes!

Gemini diffusion is exciting! Letting models revise their answer is a powerful paradigm. Autoregressive models try to do this with CoT but diffusion makes this the main training objective. The main missing piece could be training efficiency. Can we make a single training step of