
OpenAI's new image model GPT-Image-2 has leaked It seems to have extremely good world knowledge and great text rendering Possibly better than Nano Banana Pro It's on @arena under code names: - maskingtape-alpha - gaffertape-alpha - packingtape-alpha
André
826 posts

@Andrelos05
Um mero investidor em criptomoedas, designer, entusiasta da web3 e de IA

OpenAI's new image model GPT-Image-2 has leaked It seems to have extremely good world knowledge and great text rendering Possibly better than Nano Banana Pro It's on @arena under code names: - maskingtape-alpha - gaffertape-alpha - packingtape-alpha





Gotta say I'm super excited about @OpenAI GPT-IMAGE-2 because it will be a new SOTA: The best image model in the world. But I'm sure @GoogleDeepMind will soon counter it with a new Nano Banana. Race is on! This is my "hyper detailed city scene' test prompt with GPT-IMAGE-2:



Revealing HappyHorse-1.0 as the latest video model from Alibaba! @HappyHorseATH has landed in #1 or #2 across all of the leaderboards in the Artificial Analysis Video Arena. In our ‘without audio’ leaderboards, HappyHorse-1.0 is comfortably in first place. In our ‘with audio’ leaderboards, its Elo score is almost identical to ByteDance’s Dreamina Seedance 2.0. HappyHorse-1.0 was created by @AlibabaGroup, and it supports all four video generation modalities: Text to Video and Image to Video, each with and without native audio. API access is planned for launch on April 30. See below for example generations of HappyHorse-1.0 in the Artificial Analysis Video Arena 🧵

HappyHorse is still in the stable. 🐴 No official website yet — anything you've seen out there isn't us. We're part of Alibaba's ATH AI Innovation Unit, and when we're ready, you'll know. Stay tuned. #HappyHorse #Alibaba #ATH