Adele Li retweeted
GPT Image 2.6 Flare generates images almost twice as fast as GPT Image 2.5 Flare
Median generation time in our independent benchmark, at max quality: about 30 seconds for GPT Image 2.6 Flare, about 55 seconds for GPT Image 2.5 Flare.
And it scores higher on both AA-Image-T2I v2.1 and AA-Image-Editing v2.1 too!
Adele Li retweeted
OpenAI's GPT Image 2.6 takes #1 and #2 on both AA-Image-T2I v2.1 and AA-Image-Editing v2.1. GPT Image 2.6 Flare is almost twice as fast as GPT Image 2.5 Flare with slightly better quality, and GPT Image 2.6 Sunburst takes the top spot with longer generation times
OpenAI released GPT Image 2.6 on November 4 in ChatGPT, Codex and the API. The API offers two models, GPT Image 2.6 Flare and GPT Image 2.6 Sunburst, which follow GPT Image 2.5 Flare and Sunburst. Both support Text to Image and Image Editing, and add animated GIF and SVG output. OpenAI added a complexity setting to the API, which controls how much the model plans before rendering. We benchmarked both models at max quality, with complexity at its API default of high.
In our testing, GPT Image 2.6 Flare is almost twice as fast as GPT Image 2.5 Flare while delivering slightly better quality. Its median Text to Image generation time fell from about 55 to 30 seconds, and its editing time fell from about 58 to 32 seconds. GPT Image 2.6 Sunburst goes the other way: it takes longer than GPT Image 2.5 Sunburst, at about 2 minutes 15 seconds per image, and takes the #1 spot. Its largest Text to Image gains are in Reasoning, Text Rendering, Lighting and Material, and it is strongest in UIUX Design.
Both models cost $30 per 1M image output tokens, the same as GPT Image 2.5. That is about $0.21 per 1024x1024 image at max quality ($211 per 1k images).
GPT Image 2.6 is available in ChatGPT and Codex across all tiers, and in the OpenAI API.
Congratulations to @OpenAI on the release!
See below for our analysis of GPT Image 2.6 in the Artificial Analysis Image Arena 🧵
Adele Li retweeted
Wild stat. We are now generate more than 4B images per week across ChatGPT and the API, up from the more than 3B per week only 8 weeks ago.
Adele Li retweeted
Today, we’re bringing GPT-Image-2.6 to Codex and the API.
Image-2.6 Flare and Sunburst, our two new API image models, generate images 50% faster than before.
At medium or high quality, Sunburst keeps details more consistent from one edit to the next.
Adele Li retweeted
You can now text your dot on iMessage.
We know how y’all feel about green bubbles, so our team worked overtime to get you blue ones. Let us know what you think!
By popular request, you can now text your dot.
Give it a task to take off your plate or something to keep an eye on, using text, photos, or even voice notes. It will text you proactively with relevant updates.
Safe, secure texting via iMessage or RCS. You’re the only one who can text your dot, and your dot can only text you. Rolling out now as a preview for Pro users in the US.
Adele Li retweeted
The coolest thing about Space Slides in ChatGPT is that it raises the ceiling on slide quality.
With imagegen, I can make things I was never able to make before.
ChatGPT Slides has new ways to get your deck ready—and get everyone on the same page.
• Work together in real time in ChatGPT: Share decks, edit together, and leave comments. Ask ChatGPT or your dot to turn feedback into updates.
• Edit right on the slide: Click to change text, update charts, and move or resize images and shapes.
To get started, ask ChatGPT to "create ChatGPT slides" from a conversation or a file you've shared. Present in ChatGPT, or export to PowerPoint or Google Slides.
Available on Pro, Business, and Enterprise plans.
chatgpt.com/features/slides/
Adele Li retweeted
ChatGPT PM @AarushSelvan describes how AI has upended product management:
In the SaaS era, product management was built around mostly deterministic software.
With AI, the role is now more about defining what “good” looks like and steering a probabilistic system toward it.
“You sort of have to start from scratch a little bit and be comfortable with non-determinism.”
“Getting very comfortable with evals and how do we measure progress is something that’s a really important skill.”
“No longer can a designer build a weather card or a sports card and be like, ‘This is how it’s going to appear when it triggers,’ because the model can just generate that on the fly.”
Adele Li retweeted
it turns out the hardest part of generative UI isn't generating the UI.
models have been able to generate good-looking HTML for a while. the more interesting challenge is getting it to feel like it actually belongs in chatgpt. one of our big bets with Intelligent UI was that you didn't have to choose -- that you could keep ~all of the power of HTML and still have it feel fast and native, like it was always part of chat
the other half of the problem is model judgement. how do we post-train gpt-6 to know when an interface would actually help? what should it show or let you do? how do we make it useful and beautiful without taking over the conversation?
none of this was obvious when we started, and there's plenty we're still figuring out. luckily, one of my favorite things about openai is that if you believe in an idea, you can just go build it, even if it takes a lot of prototypes to get there
really excited this is finally out, and incredibly proud of the team. onwards!
Adele Li retweeted
I couldn't be more excited to share that we're rolling out GPT-6 and Intelligent UI for our 1.2B weekly ChatGPT users, starting today.
Intelligent UI is a new way for ChatGPT to instantly give you visual and interactive responses on the fly. I think in a couple years, we'll be quite surprised that ChatGPT was once mostly text responses.
My favorite example is: "Explain the offsides rule in soccer". It'll generate an interactive explainer that helps you understand how offsides works. And it does it quickly. The potential for learning complex topics is amazing.
This was a labor of love that involved ambitious new research, thoughtful user experience design, and just endless grit. The team did it with high spirits, urgency, and a lot of pride. In particular @AarushSelvan, @ManukaStratta, @EthanKgtvz, @_awchen, @michpokrass, @isafulf, @ZackSultan, @ericmitchellai and many others. Hope you all enjoy!
Adele Li retweeted
Introducing dots — always-on agents built to handle everything. Stoked for you to give it a try.
openai.com/index/introducing…
Adele Li retweeted
🐐 using ChatGPT Voice:
I’m excited to announce my partnership with OpenAI. We have some interesting things coming up, and I can’t wait to share them with you.
I’ve always been curious... One question usually leads to another, and ChatGPT has certainly encouraged that habit. But it has also proved useful when I’ve needed to get things done, like planning my last trip with the family.
That’s what I’m looking forward to with this partnership. Discovering what else I can do with ChatGPT, sharing what I find useful, and encouraging more people to give it a try with something they care about.
A question, an idea, something you’ve always wanted to explore. There are so many places to start.
Looking forward to exploring together.
#Partnership
Adele Li retweeted
Astra x GPT-Images 2.5!
Combining Astra's agentic perception with Image 2.5's consistency leads to some super fun results!
Astra can create, edit, and animate coarse guidance, then render it with GPT-Image
🧵
Adele Li retweeted
OpenAI’s GPT Images 2.5 takes the top two spots on the Artificial Analysis Image Arena, generating higher quality images in less than half the time, while keeping the same price as GPT Image 2
Nearly five months after GPT Image 2’s release, OpenAI has released GPT Image 2.5 Flare and Sunburst. OpenAI positions Flare as the model choice for most applications, designed for everyday image generation at lower latency than GPT Image 2. Sunburst is positioned by OpenAI as offering higher quality for detailed creative work and tighter control across edits, but taking longer to generate images. Both models handle Text to Image and Image Editing.
Flare and Sunburst take the top two spots on both Artificial Analysis image leaderboards, with Flare #1 in Text to Image and Sunburst #1 in Image Editing. Our evaluation of both models was performed at “max” quality.
The largest gains were in Image Editing, with the biggest improvements over GPT Image 2 in:
➤ Composition & Framing: camera changes, zoom-outs and layout changes that must keep the scene intact, where Sunburst now holds the widest lead of any editing action.
➤ Text or Symbol Edits: changes to words, numbers, logos and symbols within an existing image, where Sunburst's gain over GPT Image 2 is second only to Composition & Framing.
These gains come at the same estimated output price as GPT Image 2 (high) for 1024 × 1024 images at the evaluated quality settings.
Both models are available through the OpenAI API. OpenAI has also released ChatGPT Images 2.5 in ChatGPT, ChatGPT Work, and Codex.
Congratulations to @OpenAI on the release!
See below for our analysis and example outputs of GPT Image 2.5 Flare and Sunburst in the Artificial Analysis Image Arena 🧵
