Tootfinder

OpenAI says that paid users can now edit DALL-E images in ChatGPT across web, iOS, and Android, using a selection tool and additional text prompts (Ina Fried/Axios)
https://www.axios.com/2024/04/03/chatgpt-dalle-openai-editing-images

Paid ChatGPT customers can now use AI to edit DALL-E images
It's one more way AI is simplifying complex media editing tasks.

Live-Webinar: KI am Arbeitsplatz
Lernen Sie, KI-basierte Dienste wie ChatGPT, Midjourney oder DALL-E für Ihre tägliche Arbeit zu nutzen. Das Webinar behandelt auch die rechtlichen Aspekte.
https://www.

Linkshare: Edit DALL-E Images in ChatGPT: https://tceajmg.micro.blog/2024/04/04/linkshare-edit-dalle.html

Claymation Cats!
DALL-E 3 created these for me in a "Cat riding a motorcycle" test and they turned out better than I thought!
Then, I got cut off for using the OpenAI system too much. I had to wait 9 minutes between each image generation... and I pay for that?! Hmph!
#AI #AIart

Live-Webinar: KI am Arbeitsplatz
Lernen Sie, KI-basierte Dienste wie ChatGPT, Midjourney oder DALL-E für Ihre tägliche Arbeit zu nutzen. Das Webinar behandelt auch die rechtlichen Aspekte.
https://www.

Bilder bearbeiten mit OpenAIs Dall-E
Inpaintings mit Dall-E: OpenAIs Bildgenerator bekommt eine Funktion, mit der man generierte Bilder nachträglich bearbeiten kann.
https://www.heise.de/news/B…

#Datenhörnchen:
Warum die flauschigen Helden des Internets den Durchblick haben
Im digitalen Dschungel des Internets gibt es eine Spezies, die oft übersehen wird: die Datenhörnchen. Die flauschigen Kreaturen haben sich in den Tiefen des Cyberspace angesiedelt und sind zu wahren Helden geworden, wenn es um Datenschutz und Sicherheit geht. Doch warum sind gerade sie so wicht…

netzolino
Im digitalen Dschungel des Internets gibt es eine Spezies, die oft übersehen wird: die Datenhörnchen. Die flauschigen Kreaturen haben sich in den Tiefen des Cyberspace angesiedelt und sind zu wahren Helden geworden, wenn es um Datenschutz und Sicherheit geht. Doch warum sind gerade sie so wichtig?

today I wondered, can I get Bing (dall-e 3) to generate a sexy picture of an anthropomorphic toaster?
verdict: it's completely unable to generate a normal picture of a sideways toaster. "toaster lying on its side" and similar prompts just produced upright toasters, sometimes with explosions or other oddities.
"sideways toaster fallen over and lying on its side, pointing its slots at the viewer" produced boxy alien machines posed in weird angles, sometimes…

Haven't read this piece but the image is interesting, because it's clearly AI generated but it looks just like Icelandic glacier lagoon Jokulsarlon with Breiðamerkurjökull glacier in the background, possibly the most photographed glacier on earth. Photos of it crop up absolutely everywhere. Which is presumably how DALL-E learned what a glacier is.

Now that’s interesting: DALL-E 3 will content-tag its output with C2PA: https://petapixel.com/2024/02/08/ai-images-generated-on-dall-e-now-contain-the-content-authenticity-tag/
The effect is that unless you remove…

AI Images Generated on DALL-E Now Contain the Content Authenticity Tag
It's not foolproof, but it's a start.

On this last day of Earth Day Month, remember that as a web builder there is at least one easy step you can take to be less awful to the planet (and future you):
https://adrianroselli.com/2024/04/what-you-can-do-as-a-web-builder-on-earth-day.htm…

What You Can Do as a Web Builder on Earth Day
One easy thing you can do for the earth is not use “AI” tools. Consider this as a programmer, web developer, web designer, copywriter, webmaster, etc. The tools include anything branded as generative AI, LLMs, computer vision tools, ChatGPT, Bard, Grok, Dall-e, Midjourney, and so on. If you are also…

From ChatGPT, DALL-E 3 to Sora: How has Generative AI Changed Digital Humanities Research and Services?
Jiangfeng Liu, Ziyi Wang, Jing Xie, Lei Pei
https://arxiv.org/abs/2404.18518

From ChatGPT, DALL-E 3 to Sora: How has Generative AI Changed Digital Humanities Research and Services?
Generative large-scale language models create the fifth paradigm of scientific research, organically combine data science and computational intelligence, transform the research paradigm of natural language processing and multimodal information processing, promote the new trend of AI-enabled social science research, and provide new ideas for digital humanities research and application. This article profoundly explores the application of large-scale language models in digital humanities research,…

La Pasqua ebraica, chiamata Pesach (pascha, in aramaico), celebra la liberazione degli Ebrei dall'Egitto grazie a Mosè e riunisce due riti: l'immolazione dell'agnello e il pane azzimo
========///\\\=========
La Pasqua è la solennitŠ cristiana che celebra la Risurrezione di Gesù, con l'instaurazione della Nuova alleanza e l'avvento del Regno di Dio.

KI-Update kompakt: KI-TÜV, DALL-E fürs Militär, GreenBotAI, Sora
Das "KI-Update" liefert werktäglich eine Zusammenfassung der wichtigsten KI-Entwicklungen.
https://www.

Come è cambiata la Russia di Putin a due anni dall’invasione dell’Ucraina, di Giovanni Savino
#Russia

Come è cambiata la Russia di Putin a due anni dall'invasione dell'Ucraina - Valigia Blu
Due anni dopo l’annuncio dell’avvio dell’operazione speciale militare, nome ufficiale dato dal Cremlino alla guerra contro l’Ucraina, le sensazioni sembrano contrastare quelle del primo anniversario, quando si riteneva pressoché certa la vittoria ucraina e si dava per scontato la riconquista non solo del Donbas ma anche della Crimea, annessa dalla Russia nel 2014. A distanza di dodici mesi, a queste previsioni se ne sono sostituite altre, dal tono identico ma di segno opposto, sul trio…

#Sora: "We're just over a year into the existence (and proliferation) of ChatGPT, DALL-E, and other image generators, and despite the obvious (and reasonable) fear that these products will continue to erode the foundations of the already unstable economies of the #creativearts, we keep running in…

Subprime Intelligence
Please scroll to the bottom for news on my next big project, Better Offline, coming this Wednesday! Last week, Sam Altman debuted OpenAI's "Sora," a text-to-video AI model that turns strings of text into full-blown videos, much like how OpenAI's DALL-E turns text into images. These videos — which are usually

On this last day of Earth Day Month, remember that as a web builder there is at least one easy step you can take to be less awful to the planet (and future you):
https://adrianroselli.com/2024/04/what-you-can-do-as-a-web-builder-on-earth-day.htm…

What You Can Do as a Web Builder on Earth Day
One easy thing you can do for the earth is not use “AI” tools. Consider this as a programmer, web developer, web designer, copywriter, webmaster, etc. The tools include anything branded as generative AI, LLMs, computer vision tools, ChatGPT, Bard, Grok, Dall-e, Midjourney, and so on. If you are also…

A look at Adobe's careful adoption of AI, pushed by Dall-E and Midjourney, as it tries to differentiate its tools by emphasizing brand safety and IP protections (Bloomberg)
https://www.bloomberg.com/news/features/20

Adobe Targets OpenAI, Midjourney With Lawyer-Proof AI Artbot
Dall-E and Midjourney pushed the Photoshop behemoth to develop Firefly, a suite of AI tools. Will creatives get on board?

Altijd interessant leesvoer: Ed Zitron, die zich deze keer zorgen maakt over de profitability van generatieve AI. https://www.wheresyoured.at/sam-altman-fried

Subprime Intelligence
Please scroll to the bottom for news on my next big project, Better Offline, coming this Wednesday! Last week, Sam Altman debuted OpenAI's "Sora," a text-to-video AI model that turns strings of text into full-blown videos, much like how OpenAI's DALL-E turns text into images. These videos — which are usually

This is a great tour 'behind the curtain' of LLMs: https://www.wheresyoured.at/sam-altman-fried/ Strongly recommend anyone who's either really excited or scared about the 'AI' hype read this...

If you have time for a #longread I found this #ai news letter a fairly interesting if slightly depressing take on the current state of the industry: https://www.

Subprime Intelligence
Please scroll to the bottom for news on my next big project, Better Offline, coming this Wednesday! Last week, Sam Altman debuted OpenAI's "Sora," a text-to-video AI model that turns strings of text into full-blown videos, much like how OpenAI's DALL-E turns text into images. These videos — which are usually

One option is to externalize these choices from the image generator. You can imagine adding a "race bit" to the input that says "if you have a character make it race X" and then roll some race dice on input. This is what it feels like Google has done.
Another option is to give the choice to a better equipped AI. Dall-E does this by having GPT rewrite prompts. This still isn't good at distribution, but can use the LLM's superior knowledge to catch things like…

OpenAI says DALL-E 3 will embed watermarks to images with C2PA metadata and acknowledges the metadata can easily be removed either accidentally or intentionally (Emilia David/The Verge)
https://www.theverge.com/2024/2/6/24063954/ai-waterm…

OpenAI is adding new watermarks to DALL-E 3
OpenAI will add watermarks from the C2PA in all images generated by ChatGPT and the DALL-E 3 model, as more companies look to tag AI-generated content.

#AI generates high-quality #images 30 times faster in a single step
Novel method makes tools like Stable Diffusion and DALL-E-3 faster by simplifying the image-generating process to a single step while maintaining or enhancing image quality.

Having lots of fun with DALL-E. I have zero artistic ability but know what I like and generally quite bad at interpreting images - even emoji. So it’s pretty cool to be able to take things that I imagine - I want a similar scene out on a wall in my entertainment room at least now I can show someone.
The boy likes adding monsters to everything so he got a custom GPT that’s adds monsters to everything and then draw a Minecraft version of everything since that’s what he wants anyway hehe…

Urteil in Prag: KI-generiertes Bild kann von jedermann frei genutzt werden
Eine Firma ließ sich von DALL-E ein Bild erzeugen, das eine Kanzlei für die eigene Webseite übernahm. Ein tschechisches Gericht sieht keine Rechtsverletzung.

Come è cambiata la Russia di Putin a due anni dall’invasione dell’Ucraina, di Giovanni Savino
#Russia

Come è cambiata la Russia di Putin a due anni dall'invasione dell'Ucraina - Valigia Blu
Due anni dopo l’annuncio dell’avvio dell’operazione speciale militare, nome ufficiale dato dal Cremlino alla guerra contro l’Ucraina, le sensazioni sembrano contrastare quelle del primo anniversario, quando si riteneva pressoché certa la vittoria ucraina e si dava per scontato la riconquista non solo del Donbas ma anche della Crimea, annessa dalla Russia nel 2014. A distanza di dodici mesi, a queste previsioni se ne sono sostituite altre, dal tono identico ma di segno opposto, sul trio…

#30DaysOfBiking, Day 21: Took part in the mass bicycle tour #slowUp #Ticino (htt…

Liebe Kinder, vergesst diese altmodischen Bilderbücher. Mit KI könnt ihr viel mehr über Säugetiere lernen! Auch auf schwedisch. https://wandering.shop/@janellecshane/111723840790298763

Janelle Shane (@janellecshane@wandering.shop)
Attached: 1 image learn the mammals with the help of dall-e3! https://www.aiweirdness.com/learn-the-mammals-with-dall-e3/

https://www.lummi.ai/
Die Welt ist toll diese Tage, eine Seite mit freien AI-generierten Stock bilder.

Lummi: Free AI-Generated Stock Photos & Royalty-Free Images
Discover Lummi: Photos Sans Photographer. The ultimate source for free AI-generated stock photos and royalty-free images. Perfect for designers, marketers, and creatives. No photographers, just algorithms like OpenAI's Dall-e and Midjourney. Browse our extensive library today

Live-Webinar: KI am Arbeitsplatz
Lernen Sie, KI-basierte Dienste wie ChatGPT, Midjourney oder DALL-E für Ihre tägliche Arbeit zu nutzen. Das Webinar behandelt auch die rechtlichen Aspekte.
https://www.

The boring history of Gaia BH3 from isolated binary evolution
Giuliano Iorio, Stefano Torniamenti, Michela Mapelli, Marco Dall'Amico, Alessandro A. Trani, Sara Rastello, Cecilia Sgalletta, Stefano Rinaldi, Guglielmo Costa, Bera A. Dhal-Lahtinen, Gaston J. Escobar, Erika Korb, M. Paola Vaccaro, Elena Lacchin, Benedetta Mestichelli, Ugo Niccol\`o di Carlo, Mario Spera, Manuel Arca Sedda

The boring history of Gaia BH3 from isolated binary evolution
Gaia BH3 is the first observed dormant black hole (BH) with a mass of $\approx{30}$ M$_\odot$ and represents the first confirmation that such massive BHs are associated with metal-poor stars. Here, we explore the isolated binary formation channel for Gaia BH3 focusing on the old and metal-poor stellar population of the Milky Way halo. We use our open-source population synthesis code SEVN to evolve $3.2 \times 10^8$ binaries exploring 16 sets of parameters. We find that systems like Gaia BH3 for…

From Christiane Paul 's illuminating webinar today with @… students:
* Hype aside, DALL-E et al. are just the new kid on the block for artists, who've been working with AI since the 60s.
* Artists have been pushing the boundaries of AI at least as much as AI has pushed the boundaries of art.
Edited recording to come later this week!

@… dall'articolo: parcheggio da furbetto
https://blog.urbanfile.org/wp-content/

I see my problem is I consistently fail to conslider conqusences. https://mastodon.social/@rands/111928566422565512

rands (@rands@mastodon.social)
Attached: 1 image I asked DALL-E to draw me a flowchart that explained how to make a decision. Look closely. This is spot on.

A look at Adobe's very cautious gambit to add AI to Creative Cloud, pushed by Dall-E and Midjourney, and questions over whether creatives will embrace the tools (Bloomberg)
https://www.bloomberg.com/news/features/20

Adobe Targets OpenAI, Midjourney With Lawyer-Proof AI Artbot
Dall-E and Midjourney pushed the Photoshop behemoth to develop Firefly, a suite of AI tools. Will creatives get on board?

Dall'archivio dell'Ornitorinco: L'ovvio è invisibile agli occhi.
https://ornitorincoelegante.it/ovvio-invisibile-agli-occhi/

L'Ovvio è Invisibile agli Occhi
Storia di come ci sia sfuggita per secoli una cosa che oggi sembra ovvia, nonostante ce l'avessimo davanti agli occhi.

Okay, so this is how NightCafe and DALL-E 3 render a "photo" of a cat riding a rocket into space.
Hmph! This doesn't seem right at a 12 credits price per image!
#AI #AIart #NightCafe

#OpenAI has new features in the pipeline for #GPT4 and #DALLE3

OpenAI integriert eine Art Wasserzeichen in generierte Bilder
Bilder von ChatGPT und Dall-E 3 nutzen künftig C2PA. Der offene Standard erklärt in den Metadaten, woher ein Bild stammt.
https://www.

Think about how out of dept and substance you are if you "illustrate" your articles with pointless doodles like this one. And this is only the visible part. Do you even know what you don't know? Cheating is an admission to failure.
Here's the link to you stupid article: https://n…

"Olympics on steroids" takes a high-tech, F1-style angle on athletics
It seems the Enhanced Games are on like Donkey Kong, with multi-million dollar investments from Peter Thiel and other high-profile VCs. Performance-enhancing drugs are welcome – indeed, this could become an early preview of a transhuman Olympics.

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Yutaro Yamada, Khyathi Chandu, Yuchen Lin, Jack Hessel, Ilker Yildirim, Yejin Choi
https://arxiv.org/abs/2402.09052

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Diffusion-based image generation models such as DALL-E 3 and Stable Diffusion-XL demonstrate remarkable capabilities in generating images with realistic and unique compositions. Yet, these models are not robust in precisely reasoning about physical and spatial configurations of objects, especially when instructed with unconventional, thereby out-of-distribution descriptions, such as "a chair with five legs". In this paper, we propose a language agent with chain-of-3D-thoughts (L3GO), an inferen…

#LastBoost

DALL-E Parton on Twitter
“does... does wikipedia want me to fuck the pope”

Ieri, per la prima volta dall'inizio della guerra, hanno riaperto i forni nel nord di Gaza
https://mondoweiss.net/2024/04/bakeries-finally-reopen-in-northern-gaza-as-palestinians-continue-to-fight-famine/…

Bakeries finally reopen in northern Gaza as Palestinians continue to fight famine
Bakeries are finally re-opening in northern Gaza for the first time since October. “The enemy has tried killing, death, starvation, and destruction and has not succeeded,” Omar Jundia tells Mondoweiss, as he waits for his first fresh bread in months.

Liebe Kinder, vergesst diese altmodischen Bilderbücher. Mit KI könnt ihr viel mehr über Säugetiere lernen! Auch auf schwedisch. https://wandering.shop/@janellecshane/111723840790298763

Janelle Shane (@janellecshane@wandering.shop)
Attached: 1 image learn the mammals with the help of dall-e3! https://www.aiweirdness.com/learn-the-mammals-with-dall-e3/

My friend told me about someone they knew who married a flower. I asked if he "misses Mrs. Narcissus" which isn't amazing wordplay, but pretty damn good for something I came up with in a #dream.

“What You Can Do as a Web Builder on Earth Day”
https://adrianroselli.com/2024/04/what-you-can-do-as-a-web-builder-on-earth-day.html
Not thrilled with “web builder,” but wasn’t sure what else to broadly describe us all.
Su…

What You Can Do as a Web Builder on Earth Day
One easy thing you can do for the earth is not use “AI” tools. Consider this as a programmer, web developer, web designer, copywriter, webmaster, etc. The tools include anything branded as generative AI, LLMs, computer vision tools, ChatGPT, Bard, Grok, Dall-e, Midjourney, and so on. If you are also…

@… dall'articolo: parcheggio da furbetto
https://blog.urbanfile.org/wp-content/

How Spammers and Scammers Leverage AI-Generated Images on Facebook for Audience Growth
Renee DiResta, Josh A. Goldstein
https://arxiv.org/abs/2403.12838 ht…

How Spammers and Scammers Leverage AI-Generated Images on Facebook for Audience Growth
Much of the research and discourse on risks from artificial intelligence (AI) image generators, such as DALL-E and Midjourney, has centered around whether they could be used to inject false information into political discourse. We show that spammers and scammers - seemingly motivated by profit or clout, not ideology - are already using AI-generated images to gain significant traction on Facebook. At times, the Facebook Feed is recommending unlabeled AI-generated images to users who neither foll…

Okay!
Here are the cartoonish "Cat Riding a Rocket into Space" from NightCafe and DALL-E 3.
I used up the 5 free "Pro" images -- and then made these results "bigger" by paying for them in credits.
Hmm. None were censored, but the inspiration is not great... right?
#AI #NightCafe

Live-Webinar: KI am Arbeitsplatz
Lernen Sie, KI-basierte Dienste wie ChatGPT, Midjourney oder DALL-E für Ihre tägliche Arbeit zu nutzen. Das Webinar behandelt auch die rechtlichen Aspekte.
https://www.

Gravitational wave luminosity distance-weighted anisotropies
A. Begnoni, L. Valbusa Dall Armi, D. Bertacca, A. Raccanelli
https://arxiv.org/abs/2404.12351 …

Gravitational wave luminosity distance-weighted anisotropies
Measurements of the luminosity distance of propagating gravitational waves can provide invaluable information on the geometry and content of our Universe. Due to the clustering of cosmic structures, in realistic situations we need to average the luminosity distance of events coming from patches inside a volume. In this work we evaluate, in a gauge-invariant and fully-relativistic treatment, the impact of cosmological perturbations on such averaging process. We find that clustering, lensing and …

Balanced triple product $p$-adic $L$-functions and Stark points
Luca Dall'Ava, Aleksander Horawa
https://arxiv.org/abs/2403.05183 https://

Balanced triple product $p$-adic $L$-functions and Stark points
Let $E$ be an elliptic curve over $\mathbb{Q}$ and $\varrho_1, \varrho_2 \colon \mathrm{Gal}(H/\mathbb{Q}) \to \mathrm{GL}_2(L)$ be two odd Artin representations. We use $p$-adic methods to investigate the part of the Mordell-Weil group $E(H) \otimes L$ on which the Galois group acts via $\varrho_1 \otimes \varrho_2$. When the rank of the group is two, Darmon-Lauder-Rotger used a dominant triple product $p$-adic $L$-function to study this group, and gave an Elliptic Stark Conjecture which relat…

Validation of homogenized finite element models of human metastatic vertebrae using digital volume correlation
Chiara Garavelli, Alessandra Aldieri, Marco Palanca, Enrico Dall'Ara, Marco Viceconti
https://arxiv.org/abs/2402.09828

Validation of homogenized finite element models of human metastatic vertebrae using digital volume correlation
The incidence of vertebral fragility fracture is increased by the presence of preexisting pathologies such as metastatic disease. Computational tools could support the fracture prediction and consequently the decision of the best medical treatment. Anyway, validation is required to use these tools in clinical practice. To address this necessity, in this study subject-specific homogenized finite element models of single vertebrae were generated from micro CT images for both healthy and metastati…

Freie Bahn für Copy Paste von KI-generierten Bildern?? 🤨
Zum Artikel: https://heise.de/-9689843?wt_mc=sm.red.ho.mastodon.mastodon.md_beitraege.md_beitraege&utm_source=mastodon

wie verbringt ihr so eure Mittagspause? Ich versuche mit Dall-E besser klar zu kommen :)
#dallE3

Öffentlich-rechtlicher Rundfunk und die AfD: Wie viel Raum sollte man ihnen geben? Wir - @… und ich - diskutieren bei #9vor9 über den Umgang mit Rechtsradikalen und demokratiefeindlichen Gruppierungen in den Medien. Welche Rolle spielen Talkshows und wie können sie inh…

Öffentlich-Rechtlicher Rundfunk: Wie mit AfD-Vertretern umgehen?
Öffentlich-rechtlicher Rundfunk und die AfD: Wie viel Raum sollte man ihnen geben? Wir diskutieren über den Umgang mit Rechtsradikalen und demokratiefeindlichen Gruppierungen in den Medien. Welche …

Acquisto pesante :discogs:

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Yutaro Yamada, Khyathi Chandu, Yuchen Lin, Jack Hessel, Ilker Yildirim, Yejin Choi
https://arxiv.org/abs/2402.09052

L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects
Diffusion-based image generation models such as DALL-E 3 and Stable Diffusion-XL demonstrate remarkable capabilities in generating images with realistic and unique compositions. Yet, these models are not robust in precisely reasoning about physical and spatial configurations of objects, especially when instructed with unconventional, thereby out-of-distribution descriptions, such as "a chair with five legs". In this paper, we propose a language agent with chain-of-3D-thoughts (L3GO), an inferen…

A new semi-coherent targeted search for continuous gravitational waves from pulsars in binary systems
Lorenzo Mirasola, Paola Leaci, Pia Astone, Luca D'Onofrio, Simone Dall'Osso, Alessandro De Falco, Michela Lai, Simone Mastrogiovanni, Cristiano Palomba, Alessandro Riggio, Andrea Sanna
https://arxiv.org/abs/2404.03721

A new semi-coherent targeted search for continuous gravitational waves from pulsars in binary systems
We present a novel semi-coherent targeted search method for continuous gravitational waves (CW) emitted by pulsars in binary systems. The method is based on a custom optimization of the coherence time according to the orbital parameters and their uncertainties, as provided by electromagnetic observations. While rotating pulsars are expected to produce quasi-monochromatic CWs in their reference frame, their orbital motion introduces an additional modulation in the observer frame, alongside the o…

🔊 #NowPlaying on BBCRadio3's #ThroughTheNight
Franz Liszt, Silvio Celeghin, Chorus of the Accademia Nazionale di Santa Cecilia & Andrea Secchi:
🎵 Dall'Alma Roma, S.36
#FranzLiszt #SilvioCeleghin #ChorusoftheAccademiaNazionalediSantaCecilia #AndreaSecchi

Graphika: the viral pornographic deepfakes of Taylor Swift originated from a 4chan challenge to bypass anti-porn filters on Microsoft Designer and DALL-E (Margi Murphy/Bloomberg)
https://www.bloomberg.com/news/articles/20

Taylor Swift Deepfakes Originated From AI Challenge, Report Says
The pornographic deepfakes of Taylor Swift that proliferated on social media late last month originated from an online challenge to break safety mechanisms designed to block people from generating lewd images with artificial intelligence, according to social network analysis company Graphika.

This https://arxiv.org/abs/2312.07130 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass Safety Filters of Text-to-Image Models
Text-to-image (TTI) models offer many innovative services but also raise ethical concerns due to their potential to generate unethical images. Most public TTI services employ safety filters to prevent unintended images. In this work, we introduce the Divide-and-Conquer Attack to circumvent the safety filters of state-of the-art TTI models, including DALL-E 3 and Midjourney. Our attack leverages LLMs as text transformation agents to create adversarial prompts. We design attack helper prompts tha…

🔊 #NowPlaying on BBCRadio3's #ThroughTheNight
Franz Liszt, Silvio Celeghin, Chorus of the Accademia Nazionale di Santa Cecilia & Andrea Secchi:
🎵 Dall'Alma Roma, S.36
#FranzLiszt #SilvioCeleghin #ChorusoftheAccademiaNazionalediSantaCecilia #AndreaSecchi

Self-similarity of the magnetic field at different scales: the case of G31.41 0.31
M. T. Beltr\'an (INAF-Osservatorio Astrofisico di Arcetri), M. Padovani (INAF-Osservatorio Astrofisico di Arcetri), D. Galli (INAF-Osservatorio Astrofisico di Arcetri), N. \'A\~nez-L\'opez (Universit\'e Paris-Saclay), J. M. Girart (Institut de Ci\`encies de l'Espai), R. Cesaroni (INAF-Osservatorio Astrofisico di Arcetri), D. Dall'Olio (Chalmers University of Technology), G. Anglad…

Self-similarity of the magnetic field at different scales: the case of G31.41+0.31
Context. Dust polarization observations of the massive protocluster G31.41+0.31 carried out at ~1'' (~3750 au) resolution with the SMA at 870 microm have revealed one of the clearest examples to date of an hourglass-shaped magnetic field morphology in the high-massregime. Additionally, ~0.24'' (~900 au) resolution observations with ALMA at 1.3 mm have confirmed these results. The next step is to investigate whether the magnetic field maintains its hourglass-shaped morphology down to circumstell…

🔊 #NowPlaying on BBCRadio3's #ThroughTheNight
Evaristo Felice Dall'Abaco & Il Tempio Armonico:
🎵 Concerto a piu istrumenti in F major Op 6`3
#EvaristoFeliceDallAbaco #IlTempioArmonico
https://open.spotify.com/track/7DaVEcRX5APxxjBfLXyGTZ