Image created with Ideogram 3.0. Image prompt: Lower-East-Side street-corner photograph reminiscent of a late-80s album cover: weathered red-brick tenement with exterior fire-escapes, canvas awning shading racks of vintage clothes; above the awning, a hand-painted board reads ‘Images SPORTSWEAR’; a hanging blade sign in cursive script reads ‘Images Boutique’; contact sheets of 35mm images flutter on a clothesline strung between windows; warm golden-hour light, subtle 35mm film grain, muted yet punchy color palette, gritty NYC vibe.
o3, give me a screenshot from that one safety video in the 1950s about how to care for your giant killer squid”” “”great, a second shot from when it all goes wrong for poor Timmy.”” “”show me that one moment people always talk about”” (this was all the first output from the AI) https://x.com/emollick/status/1923861434271740005
I thought my “”otter on a plane using Wifi”” benchmark was already done, but Veo 3 adds higher quality… and sound Here is “”an otter on a plane using wifi on their phone, the flight attendant asks them “”do you want a drink ?”” and the otter nods”” (One of the first set of 4 videos) https://x.com/emollick/status/1925018308182524391
You can also create comics 💬, packaging 🥫, stylized stamps 💮 and more – all with improved spelling and new layouts. https://x.com/GoogleDeepMind/status/1924892789638070732
Google presents LightLab Controlling Light Sources in Images with Diffusion Models https://x.com/_akhaliq/status/1923135902827642901
Google’s new Imagen 4 Ultra comes 3rd in the Artificial Analysis Image Arena, falling just short of OpenAI’s GPT-4o and ByteDance’s Seedream 3.0 After a few days in the Artificial Analysis Image Arena, Imagen 4 Ultra appears to be a noticeable but small upgrade over Imagen 3, https://x.com/ArtificialAnlys/status/1925803621792227637
o3, show me a photo of the most stereotypical X and LinkedIn feeds as seen on a mobile device. Really lean into it.”” https://x.com/emollick/status/1922866235307356423
tis the year of any-to-any/omni models BAGEL by @BytedanceTalk 7B native multimodal model that understands and generates both image + text outperforms leading VLMs like Qwen 2.5-VL 👏 and has Apache 2.0 license 😱 https://x.com/mervenoyann/status/1925218434964472067
Dropping this Website to Image Generator tomorrow! Built with @GoogleAI’s new Imagen 4 and Gemini Flash 👀 https://x.com/ericciarla/status/1925340344109162721
Having AI create never-built architectures: o3, here is the documentation for the never-built Level 4 chamber at the long-term nuclear waste storage facility, meant to ward away humans from ever entering for 10,000 years (“This is not a place of honor”) Show me a photo of it. https://x.com/emollick/status/1923081995799634157
Get ready for Imagen 4 🎨 capable of creating richer images, with more nuanced colors, intricate details and superior typography. Tap each photo below to see more. 👀 https://x.com/GoogleDeepMind/status/1924892780876464362
o3, show me a page from the instruction manual for a machine that turns everything into crabs”” Intrigued by the warning it created: “”make the warning page of what happens if you insert a crab into the Universal Crabbifier”” “”show me a security camera still…”” (all zero shot) https://x.com/emollick/status/1924566292117307857
You can now generate images in your desired aspect ratio in Grok! https://x.com/MichelleShieh/status/1923489497007915425
