OpenAI Launches gpt-image-2 for API and Codex, Upgrading Text and Layout
OpenAI has released its new image-generation model, gpt-image-2, making it available to developers through the API and within Codex. The company describes it as its most capable image model yet, aimed at production workflows with stronger text rendering, structural layout, editing, resolution, and multilingual rendering.
Details shared about the update say it supports outputs up to 2K resolution and adds thousands of new export aspect ratios. Early developer feedback also points to practical gains: one integration used it as a tool for an AI agent to generate polished slide decks and app interfaces that resemble professional design work.
From the sources (10 posts)
@jeremyphowardRT @BoyuanChen0: This is what I’ve been cooking in the past 4 months . GPT Image 2 is over a massive 240 elo jump over the second place mod…
@steipeteRT @chatgpt21: GPT Image-2 creates the biggest Gap in imagen history 🤯
@therundownaiRT @TheRundownAI: OpenAI just released ChatGPT Images 2.0, and the results are WILD! The model can handle even the most unbelievable of s…
@teortaxestexRT @AcerFur: GPT-Image-2 on Heavy Thinking is now the new SoTA on the Image Reasoning Generation Benchmark (IRGB) with a score of 26.7%. St…
@mattshumer_GPT-Image-2 is absolutely fucking insane. I added it as a tool that Agent-S can use, and it's now generating slide decks + apps that look like they were designed by pros. This is easily the biggest step up in image generation I've seen in
@cointelegraph🔥 NEW: GPT-Image-2 from OpenAI tops Image Arena rankings, achieving the largest-ever lead in text-to-image performance.
@kimmonismusHoly! I did not expect OpenAI’s GPT-image to be such a big jump in quality and leaderboards. OpenAI was cooking. Makes me even more excited for spud
@wesrothOpenAI launched gpt-image-2 (Images 2.0), making it immediately available to developers via the API and within Codex. Billed as a production-grade model, the update brings massive improvements to text rendering, structural layout, and edit
@teortaxestex> When a thinking model is selected in ChatGPT, Images 2.0 can search the web for real-time information, create multiple distinct images from one prompt, double-check its own outputs, and even create functional QR codes. A lot of Image 2
@openaidevsgpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering. https://t.c