Kenji Hata (@kenjihata) 's Twitter Profile
Kenji Hata

@kenjihata

multimodal research @OpenAI
4o image gen

ID: 836305120140746752

linkhttp://kenjihata.github.io calendar_today27-02-2017 20:00:53

115 Tweet

3,3K Followers

92 Following

Michelle Qin (@michelleqin_) 's Twitter Profile Photo

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!

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!
Sam Altman (@sama) 's Twitter Profile Photo

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.

Derya Unutmaz, MD (@deryatr_) 's Twitter Profile Photo

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

I’m absolutely blown away by <a href="/OpenAI/">OpenAI</a>’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
Bindu Reddy (@bindureddy) 's Twitter Profile Photo

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

lmarena.ai (formerly lmsys.org) (@lmarena_ai) 's Twitter Profile Photo

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 Black Forest Labs 💠 5th: Gemini 2.0 Flash

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 <a href="/OpenAI/">OpenAI</a> 
💠 2nd-4th: Flux 1 Kontext Max, Pro &amp; Dev by <a href="/bfl_ml/">Black Forest Labs</a> 
💠 5th: Gemini 2.0 Flash
OpenAI Developers (@openaidevs) 's Twitter Profile Photo

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.