Kenji Hata
@kenjihata
researcher @OpenAI, 4o image gen
With the new generation capabilities in ChatGPT, you'll realize that its attention to detail and instruction following are unmatched. youtube.com/watch?v=ELwb_e…
great work!
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).
We've improved image generation in the API. Editing with faces, logos, and fine-grained details is now much higher fidelity with features preserved. 🔍 Edit specific objects, create marketing assets with your logo, or adjust facial expressions, poses, and outfits on people.
what a boss
S1NNER 🏆 World No.1 Jannik Sinner defeats Carlos Alcaraz to claim his first Wimbledon title 🇮🇹
Earlier this month, we launched the Image Edit Arena. Today, the Image Edit Leaderboard 🏆 goes LIVE, powered by more models and all your community votes. 🏆 In 1st place: GPT-Image-1 by @OpenAI 💠 2nd-4th: Flux 1 Kontext Max, Pro & Dev by @bfl_ml 💠 5th: Gemini 2.0 Flash…
Image Editing just got real on LMArena 🖼️✨ Introducing Image Edit Arena: where AI editing models go head-to-head on your images. Upload, edit, vote. It's that simple. Who edits it best? You decide🫵 Learn how it works in thread 🧵
got to see this in real time. eye opening experience
today i collected some out of distribution data "pale swedish man burns characters to his back with sun screen, a hand is seen to the bottom left of the image, shot on an iphone 15"
OpenAI's image generator is a HUGE LEAP towards AGI All said and done, they are still about 6-12 months ahead of anyone else
excited for all the new use cases developers can build now!
Image gen is now available in the API! We’re launching gpt-image-1, making ChatGPT’s powerful image generation capabilities available to developers worldwide starting today. ✅ More accurate, high fidelity images 🎨 Diverse visual styles ✏️ Precise image editing 🌎 Rich world…
about to board my flight to Singapore for ICLR. if you have any food recs or just wanna hang, lmk!
openai's perception team is really awesome, especially @jhyuxm !!!
“Thinking with Images” has been one of our core bets in Perception since the earliest o-series launch. We quietly shipped o1 vision as a glimpse—and now o3 and o4-mini bring it to life with real polish. Huge shoutout to our amazing team members, especially: - @mckbrando, for…
I’m absolutely blown away by @OpenAI’s new o3 model! I’ve had early access and haven’t put it down for days. This release feels like the milestone we experienced with o1-preview and o1-pro, but smarter and more reliable in every way, it truly cranks everything up to eleven! In…
go make the pictures you love :)
All of your image creations, all in one place. Introducing the new library for your ChatGPT image creations—rolling out now to all Free, Plus, and Pro users on mobile and chatgpt.com.
GPT-4.1 (and -mini and -nano) are now available in the API! these models are great at coding, instruction following, and long context (1 million tokens). benchmarks are strong, but we focused on real-world utility, and developers seem very happy. GPT-4.1 family is API-only.
same
The past couple weeks at OAI have been extremely difficult for me. Time and time again I've had to argue with people about the "right" way to pronounce Ghibli. It's a "J" and this is a hill I'm willing to die on.
It's been so fun getting to work on 4o image gen and see it go viral. This model is crazy good at style transfer + text rendering. All of these were made by ChatGPT!
the bar will keep going up!
I don't really want to be the person to say this, but Midjournes v7 is not the leap I expected. And OpenAI has raised the bar significantly with GPT-4o image.
this will be fixed
Please, @sama, fix "the green/yellow tint" of your amazing Image generator.