Discussion

• @sama Sam Altman on x

  Here is a manga made by ChatGPT Images 2.0 of @gabeeegoooh and me looking for more GPUs: [image]

• @deryatr_ Derya Unutmaz on x

  I was part of the ChatGPT Pro Community early testing group for the new Imagegen 2.0 model for some time. I'll go out on a limb and say that Imagegen 2.0 is truly revolutionary, and the best image AI model ever released until now! I'll share many mind blowing examples soon! [imag…

• @jsngr Jordan Singer on x

  same prompts: UI from ChatGPT Images 2.0 [image]

• @mweinbach Max Weinbach on x

  ChatGPT Image v2 is pretty insane ngl [image]

• @adele__li Adele Li on x

  Introducing ChatGPT Images 2.0 A new generation of image creation: sharper details, stronger visual composition, cleaner text rendering, and more control from idea to final asset https://openai.com/... [image]

• @emollick Ethan Mollick on x

  I have been using GPT ImageGen-2 for the past weeks I didn't think that better image-generators would be a big deal but it turns out that there is a quality threshold I didn't expect, where you can now get text, slides, academic papers Look at what it does with my “otter test”! […

• @gavinpurcell Gavin Purcell on x

  i regert to inform their competitors that yes, indeed, openai cooked with gpt image 2 [image]

• @openai @openai on x

  Made with ChatGPT Images 2.0 [video]

• @altryne Alex Volkov on x

  Peter (@petergostev) showed me this image, and I still can't wrap my head around just how big the jump from GPT image v2 and the rest of image generation is. If you've followed AI at all, this is an out of distribution jump! GPT-Image-2 is the Claude Mythos of Image models! 🔥 [im…

• @chatgpt21 Chris on x

  GPT Image-2 creates the biggest Gap in imagen history 🤯 [image]

• @sama Sam Altman on x

  Gabe is incredibly talented and a great leader. Happy to see this, but not surprised.

• @deredleritt3r Prinz on x

  I was absolutely delighted to be part of a group of early testers of ChatGPT Images 2.0. Images 2.0 is the first model I have ever tried that feels ready for real enterprise workflows. This is because: - It is a *reasoning* model, which means that it will search the web, use [ima…

• @richlightshed @richlightshed on x

  New OpenAI image 2.0 is insane — look how it turned this into that in seconds [image]

• @viemccoy @viemccoy on x

  this is the first image model I've used internally where I haven't been muttering “fuck I wish this was midjourney” under my breath while using it. it's really, really good. can't wait to see what everyone makes with it :)

• @adele__li Adele Li on x

  SOTA models are rare. Clear wins are even rarer. ImageGen 2.0 doesn't just edge ahead, it's in its own league

• @snsf Srinivas Narayanan on x

  Introducing ChatGPT Images 2.0 — a major leap in image generation. Advanced reasoning backed into the creation process, stronger multilingual support, better text rendering,, richer layouts, more precise control and more. Available in ChatGPT, Codex and the API.

• @figma @figma on x

  No bad ideas when you're playing with ChatGPT Images 2.0 → Smarter visuals → Better editing and aesthetics Rolling out in Figma and Figma Weave [image]

• @emollick Ethan Mollick on x

  Though the images are very good, ChatGPT Image 2.0 does have the typical imagegen problem, which is that editing can be “stubborn”, and attempts to get the AI to change details work well for the first round or two, but then progress slows. Putting the image in a new chat helps.

• @yuchenj_uw Yuchen Jin on x

  Just tried gpt-image-2. It is really good. OpenAI is finally leading the image gen again. [image]

• @openai @openai on x

  Stronger Across Languages ChatGPT Images 2.0 can produce images with non-English text that's not only rendered correctly but with language that flows coherently. This makes the model more globally useful and helps people create visuals that work in the languages they actually [im…

• @openai @openai on x

  ChatGPT Images 2.0 is a step change in detailed instruction following, placing and relating objects accurately, and rendering dense text, with the ability to generate across aspect ratios. It's also accurate across languages and uses its expanded visual and world knowledge to

• @openai @openai on x

  Greater Precision and Control ChatGPT Images 2.0 can conceptualize more sophisticated images, and then actually bring that vision to life effectively. It's able to follow instructions, preserve requested details, and render the fine-grained elements that often break image [image]

• @openai @openai on x

  Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images [video]

• @arena @arena on x

  GPT-Image-2 takes #1 in every single Text-to-Image category — all 7 of them. Surpassing the next leading model (Nano-banana-2 with web-search) across the board. Here's the drill-down on improvements vs. its predecessor, GPT-Image-1.5-High-Fidelity: - #1 Product, Branding & [image…

• @arena @arena on x

  Exciting news - GPT-Image-2 by @OpenAI has claimed the #1 spot across all Image Arena leaderboards! A clean sweep with a record-breaking +242 point lead in Text-to-Image - the largest gap we've seen to date. - #1 Text-to-Image (1512), +242 over #2 (Nano-banana-2 with web-search […

• @chatgpt21 Chris on x

  I think it's safe to say GPT images. V2 is state of the art [image]

• @simonw Simon Willison on x

  True to form, I've already seen OpenAI themselves refer to the new image model as “ChatGPT Images 2.0”, “Image gen 2” and “gpt-image-2”

• @gdb Greg Brockman on x

  really incredible what you're now able to create with a little bit of compute. excited for new applications in areas like education, professional settings (slides, marketing materials, etc), and productivity (such as creating diagrams for code documentation). [image]

• @ml_angelopoulos Anastasios Nikolas Angelopoulos on x

  GPT-Image-2 literally broke the @arena chart. This is the largest gap we have ever seen in the history of arena IIRC [image]