Tag: images

Meta launches Muse Image generator, teases video model

A sample from Muse Image, Alexandr Wang as a plushie. (Picture: Meta)
Muse Image catapulted directly to the second place on Arena.ai’s leaderboard in the categories for Text-to-Image and Image Edit, ahead of Nano Banana 2 and just behind GPT-Image-2.

It’s the first image generator from the Superintelligence Lab and pairs with Muse Spark to reason, search the web, and plan before it generates an image.

Meta also says it knows you from your Facebook and Instagram feeds, giving it a layer of contextual awareness, and it lets you tag any Instagram account for inclusion in your images.

The latter is automatically enabled, meaning anyone on Meta.ai can tag your Instagram content in AI generations, unless you explicitly opt out.

Continue reading “Meta launches Muse Image generator, teases video model”

OpenAI brings web search, thinking to ChatGPT Images 2.0

A stoat on a goat on a boat in a moat, approaching photorealism. (Picture: generated)
The new image model for ChatGPT does not only offer higher fidelity, but more precision in how it renders pictures. According to OpenAI, it’s a sea change:

— If we think of Dall-e as cave drawings, and Images 1.0 as ancient art, then Images 2.0 is the Renaissance, OpenAI claims, according to Gizmodo.

It is a little bit faster to generate, and offers better instruction following, more accurate object placement — and reasoning with web search.

That means it can render multiple images from a single prompt, and «double-check» its outputs, as well as offering the latest information in the picture.

As for the benchmarks, GPT Image 2.0 has entered LMArena’s leaderboards at #1 for Text-to-Image with a whopping 242 point lead, and is 125 points ahead on Single-Image-Edit and up 90 on Multi-Image Edit.

The model is available today across all of ChatGPT’s tiers. For the thinking mode, you’ll need a paid Plus, Pro or Business subscription.

Read more: OpenAI’s announcement, Launch thread, Gizmodo and The Verge.

Grok on X produced an estimated 3 million sexualized images in free-for-all

X has restricted «undressing» pictures, but investigations remain. (Picture: generated)
During the period from the initial launch of the editing feature on December 29th to its paywalling on January 9th, X.com became «an industrial-scale machine» for production of sexual abuse material, writes The Guardian.

The 3 million pictures produced means an average of 190 images per minute, and a sexualized picture of children every 41 seconds, Engadget reports.

This was revealed by a study from Center for Countering Digital Hate, which analyzed 20,000 images from the total and extrapolated the figure for all days using AI.

After an outrage from most corners of the globe, X decided to «technically block» the feature even for paying customers on January 14th.

X.com is still under investigation over the matter from a whole host of countries and U.S. states, including California, The U.K. and Korea, to name a few.

Read more: The actual study, comments from The Guardian, writeup by Engadget.

OpenAI launches GPT Image 1.5, up to 4x faster and more precise, lifelike

This lifelike image of Sam Altman as Hugh Hefner was generated in one shot.
One-shotted: “Generate a picture of Sam Altman in the style of Hugh Hefner, in a smoking jacket with a cigar and a whiskey.” (Picture: GPT Image 1.5)
The new image model is faster by a wide margin, and way better at composing detailed, lifelike images.

It also «adheres to your intent more reliably» and keeps elements of the picture, like lighting, composition, and appearance across the editing phase.

The outputs are also much more lifelike, making it ever more difficult to discern AI images from reality.

Does it beat Nano Banana? Yes, it does, according to the almost gold-standard LMArena benchmark, where it instantly climbed to the top spot on «Text-to-image» and «Image Edit.»

At the same time, OpenAI is launching a new feature called ChatGPT Image on the web, which is a handy way to access predefined styles for your pictures and share those you like.

They are even seasonally aware enough to let you turn pictures into Christmas cards.

Read more: OpenAI’s announcement (includes lots of examples), ChatGPT Image. Writeups on Engadget, TechCrunch. Discussion on r/Singularity.

Google unveils «nano banana» as a state-of-the-art image generator

Imagination is the limit with Gemini 2.5 Flash Image, which sports better character accuracy across scenes.
Butterfly dress in an NYC scene? No problem with nano banana. (Picture: Google)
After catching buzz on social media, the new generator was uncloaked as Gemini 2.5 Flash Image — and instantly landed on top of the leaderboards.

The trick to creating believable artificial images is to preserve the realism and character consistency across edits, Google says — and the new model has a «particular focus on maintaining a character’s likeness from one image to the next.»

Available in the Gemini app for free, it fares especially better than the competition on image editing and changing the scenery of a photo.

Continue reading “Google unveils «nano banana» as a state-of-the-art image generator”

OpenAI drastically improves ChatGPT image generation

Karl Marx goes shopping, from OpenAI.
Moving from Dall-E to native GPT 4o images makes for higher quality and more lifelike detail — and they also updated their terms of service.

Rolling out to users on Free, Pro and Plus tiers, the image generation should be live pretty much by the time of this writing, letting you generate just about anything you can imagine from a text prompt – within reason.

Accessing a world of knowledge
Since it uses GPT 4o, the generator has access to a world of knowledge and context that was missing from the previous generators, writes Mashable.

Continue reading “OpenAI drastically improves ChatGPT image generation”

Adobe garanterer opphavsretten til bilder fra Firefly

Adobes KI-genererte bilder kommer nå med opphavsrettsgaranti.
Det kan være risikabelt å bruke AI-genererte bilder offentlig. Adobe garanterer derimot for sine. (Bilde: Adobe.)
Adobe er så sikre på at de innehar opphavsretten til bildene generert med den kunstige intelligensen deres at de tilbyr å påta seg alle erstatningskrav.

Det sier de i en ny uttalelse på hjemmesiden til Adobe Firefly, først oppdaget TechCrunch.

Continue reading “Adobe garanterer opphavsretten til bilder fra Firefly”

Blokksystemet i WordPress

Tester litt til. Her er et bilde av Vladimir Putin.

Det har skjedd en del med WordPress siden sist.

Uansett er nyheten i dag at det har vært et attentatforsøk på Vladimir Putin begynnelsen av krigen mot Ukraina, ifølge forsvarsstaben til Ukraina.

Uten å overdrive er det trygt å anta an han overlevde.

Ellers har lite skjedd. Må bare fylle på litt tekst her for å se hvordan det flyter.

Men klarer vi å få teksten til å flyte også under bildet hvis vi skriver langt om dette?

Vladimir Putin
Vladimir Putin fra shopcatalog.com

Poenget med teknotum er egentlig at det skal være en teknoblogg, men vi kommer til å dekke samfunn, populærkultur og kanskje også litt politikk, også.

Dessuten var akkurat dette et fint bilde av Putin, synes jeg.

Må få på en sans serif skrift og rammer rundt bildene.