View allAll Photos Tagged generativeAI
Check out my albums list for some of my best work: www.flickr.com/photos/200044612@N04/albums/
See my 'Tutorials & Commentary on AI' album for some information about how I make my images: www.flickr.com/photos/200044612@N04/albums/72177720325900...
See my main account for my photography, videos, fractal images and more here: www.flickr.com/photos/josh-rokman/
Made with Bing Image Creator, which is powered by DALL·E 3.
- Josh
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Participants in the „4IR Deep Dive The Future of IoT“ session at the Annual Meeting of the New Champions 2023 in Tianjin, People's Republic of China, 27 June 2023. Tianjin Meijiang Convention Center "Innovators Hub" Room - Copyright: World Economic Forum/Jakob Polacsek
Created using Google Gemini 2.5 Flash, aka, "Nano Banana."
Inspiration from the wind traps featured in the old, "DUNE 2000" PC game that started the Real-Time Strategy (RTS) genre of video games.
See more here: www.youtube.com/@journeymanplayer7459
See my albums list for some of my best work: www.flickr.com/photos/200044612@N04/albums/
See my main account for my photography, videos, fractal images and more here: www.flickr.com/photos/josh-rokman/
Made with Image Creator from Microsoft Designer, formerly known as the Bing Image Creator. Powered by DALL·E 3.
I think that AI image generation is similar in many ways to photography. The camera itself handles all the fine details, but the photographer is in charge of curating the types of images that will be created.
Ultimately, it is all about maximizing the probability that something good will be created.
This is very similar to AI image generation, in terms of the skills involved and what the human does vs. what the machine does.
You can't compare AI image generation to the process of actually making these images from scratch with 3D software or paint/pencils, where the human controls every detail.
However, I think the process really is very similar to that of photography, as I made the case for above. I think that DALL-E 3 is by far the most powerful AI image generation tool currently available.
- Josh
Stephen Engle, Chief North Asia Correspondent, Bloomberg Television, Bloomberg News, Hong Kong SAR, China, Kungsheng Fan, Managing Director; Head, China, Lazard Asset Management Hong Kong, Hong Kong SAR, China, Angela Liu, Chief Executive Officer, China, Barclays, United Kingdom, Jan Metzger, Managing Director; Head, Banking, Capital Markets and Advisory, Asia-Pacific, Citi, Hong Kong SAR, China, Zhang Weiying, Sinar Mas Chair Professor of Economics, National School of Development, Peking University, People's Republic of China, Thijs Aaten, Chief Executive Officer, Asia, APG Asset Management, Netherlands speaking in the Feeling the Heat: Financial Stability under Pressure session at the at the Annual Meeting of the New Champions 2023 in Tianjin, People's Republic of China, 27 June 2023. Tianjin Meijiang Convention Center - Studio. Copyright: World Economic Forum/Faruk Pinjo
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
I'm using a prompt vocabulary mashup using a birdhouse foundation to design whimsical treehouses. Here was one of the better examples.
See more here: www.youtube.com/@journeymanplayer7459
Check out my albums list for some of my best work: www.flickr.com/photos/200044612@N04/albums/
See my 'Tutorials & Commentary on AI' album for some information about how I make my images: www.flickr.com/photos/200044612@N04/albums/72177720325900...
See my main account for my photography, videos, fractal images and more here: www.flickr.com/photos/josh-rokman/
Made with Bing Image Creator, which is powered by DALL·E 3.
- Josh
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini, aka, "Nano Banana."
Inspiration from the old classic space opera PC games: Wing Commander: Privateer and Freelancer.
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini, aka, "Nano Banana."
What is a MacGuffin? grokipedia.com/page/MacGuffin
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
Post production in Adobe Firefly.
See more here: www.youtube.com/@journeymanplayer7459
Participants in the „Farewell Reception“ session at the Annual Meeting of the New Champions 2023 in Tianjin, People's Republic of China, 29 June 2023. Tianjin Meijiang Convention Center "The Village" Copyright: World Economic Forum/Jakob Polacsek
Atmospheric Moods: The Raw Power and Beauty of Earth's Climate
This collection represents a visual journey through the dynamic and ever-changing moods of our planet's atmosphere. It explores the fascinating duality of nature: the serene beauty of high-altitude cirrus clouds and vibrant rainbows contrasting with the raw, chaotic energy of electrical storms and hurricane-force winds.
From the ethereal glow of the aurora borealis dancing over mountain silhouettes to the microscopic detail of frozen hail, these scenes capture the climatic phenomena that shape our world. The series aims to evoke the feeling of witnessing the sublime power of the elements, ranging from the golden warmth of a sunrise to the ominous darkness of approaching thunderheads.
Images generated by Artificial Intelligence
See my main account for my photography, videos, fractal images and more here: www.flickr.com/photos/josh-rokman/
Made with Image Creator from Microsoft Designer, formerly known as the Bing Image Creator. Powered by DALL·E 3.
I think that AI image generation is similar in many ways to photography. The camera itself handles all the fine details, but the photographer is in charge of curating the types of images that will be created.
Ultimately, it is all about maximizing the probability that something good will be created.
This is very similar to AI image generation, in terms of the skills involved and what the human does vs. what the machine does.
You can't compare AI image generation to the process of actually making these images from scratch with 3D software or paint/pencils, where the human controls every detail.
However, I think the process really is very similar to that of photography, as I made the case for above. I think that DALL-E 3 is by far the most powerful AI image generation tool currently available.
- Josh
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini 2.5 Flash, aka, Nano Banana.
See more here: www.youtube.com/@journeymanplayer7459
Created in Google Gemini 2.5 Flash, aka, "Nano Banana."
See more here: www.youtube.com/@journeymanplayer7459
Title: Eternal Spain: An AI Reimagining of Architectural Heritage
This collection offers a sophisticated visual journey through Spain’s most iconic landmarks, blending centuries of history with the cutting-edge capabilities of generative artificial intelligence. From the ethereal evening glow over the Alhambra in Granada to the intricate, rain-slicked stone of Santiago de Compostela, each image is a meticulously crafted study in light, atmosphere, and architectural grandeur.
The series captures the "Bohemian Bourgeois" essence of these sites: a deep respect for cultural heritage, the rejection of the mundane, and an appreciation for the quiet, contemplative beauty found in nature and classical design. You will find the golden hour hitting the Sagrada Familia’s spires, the dramatic chiaroscuro within the Mosque-Cathedral of Córdoba, and the titanium curves of the Guggenheim Bilbao reflecting the sunset over the Nervión river. These aren't just mere replicas, but emotional interpretations of Spain’s soul, emphasizing texture, cinematic lighting, and a profound sense of place.
Disclaimer: These images have been generated by Artificial Intelligence.
Models P J Walker and Kes Wild
New edit: I was never happy with what my female model was originally wearing at the time of the shoot. She looked gorgeous in it but with the greatest of respect to her, her outfit was very "Anne Summers" and not fitting (in my opinion) to the mood of THIS gothic shoot. Elsewhere, it may have been great but not here....
However, on zero budget shoots, you just gotta go with what clothing the model has brought with her, even though every time I saw the shots from this shoot, I wished she'd worn something more appropriate and many, otherwise decent shots, were binned from that shoot that would not otherwise have been.
Anyway, I have now used Photoshop Generative AI (in Beta) to give her a different outfit and jewellery. It was NOT a simple one click process by any means, with a lot of tries, and I had to do small sections in stages and then hand digitally paint on them to make them all blend together, but this is the final result. Pretty realistic, I think, and I certainly prefer it to the other shot now.
So which shot do you prefer? Did I make the right choice?
In an ideal world, you'd shoot right first time, but for broke photographers like me, that is not always possible as we can't afford the costumes or props. I, for one, am grateful that AI could fix this shot. Here's the orig: www.flickr.com/photos/sophiethesax/33793007383/in/photoli...