How to turn 'sfo-jfk' into a suitable photo
approachwithalacrity.com
How to turn 'sfo-jfk' into a suitable photo
1–10 of 24 posts
Re: How to turn 'sfo-jfk' into a suitable photo
#2[flagged]
Re: How to turn 'sfo-jfk' into a suitable photo
#3[flagged]
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."
Re: How to turn 'sfo-jfk' into a suitable photo
#4[stub for offtopicness] [sorry I messed up with that title! perils of not reading the articles closely]
I’m not sure it’s good idea to use AI for this purpose. When you’re talking about travel, you’re talking about a real place.
If you show something photorealistic and AI generated, what is shown is simply an illusion.
If you use a cartoon style maybe they can work because the user will immediately understand what is shown is not a photograph.
Re: How to turn 'sfo-jfk' into a suitable photo
#5[stub for offtopicness] [sorry I messed up with that title! perils of not reading the articles closely]
I’m not sure it’s good idea to use AI for this purpose. When you’re talking about travel, you’re talking about a real place. If you show something photorealistic and AI generated, what is shown is simply an illusion. If you use a cartoon style maybe they can work because the user will immediately understand what is shown is not a photograph.
the article doesn't talk about AI generating photos. it talks about using AI to interpret user queries into photo selections from photographers
Re: How to turn 'sfo-jfk' into a suitable photo
#6[stub for offtopicness] [sorry I messed up with that title! perils of not reading the articles closely]
The title on HN is incorrect/misleading, they are not generating AI images. They are hand curating a database of images by location and using an LLM to pick the pictures.
Re: How to turn 'sfo-jfk' into a suitable photo
#7[stub for offtopicness] [sorry I messed up with that title! perils of not reading the articles closely]
The headline (currently: “Trying to craft AI images that are worth displaying to end users”) is misleading and changed from the original. Author isn’t crafting any AI images; they’re using AI in tandem with manual work to help choose from a set of human-authored images.
Re: How to turn 'sfo-jfk' into a suitable photo
#8Couldn't you grab the image from the Wikipedia page of that location? For example searching for "Deadvlei" from the blog post gives this which has a photo:
Re: How to turn 'sfo-jfk' into a suitable photo
#9Earlier quoted context omitted.
I’m not sure it’s good idea to use AI for this purpose. When you’re talking about travel, you’re talking about a real place. If you show something photorealistic and AI generated, what is shown is simply an illusion. If you use a cartoon style maybe they can work because the user will immediately understand what is shown is not a photograph.
the article doesn't talk about AI generating photos. it talks about using AI to interpret user queries into photo selections from photographers
The post title here is extremely misleading. Per HN standards, the post should use the original title, "How to turn 'sfo-jfk' into a beautiful photo"
Re: How to turn 'sfo-jfk' into a suitable photo
#10[stub for offtopicness] [sorry I messed up with that title! perils of not reading the articles closely]
Speaking of "crafting", I think this is the perfect word to describe something more than "prompting".
It's extremely hard to block out a scene with just words, eg. "rotate hand 45 degrees, stand perpendicular to the column, shadows from light source 60 degrees above horizon, large box in front of chest, approximately 2 feet wide", etc.
Image-to-image, ControlNets, previz-to-final, etc. are the way to go, and I'm convinced this is the core interface for image and video creation. Text prompts will get you a coarse grained first approximation, which you then visually adjust to your exact needs with UI/UX-first models.
I built an intentional "crafting" engine so people could mold images like clay, with full intention:
https://github.com/storytold/artcraft
This is really early days though. I expect more tools and models to enable you to fully manipulate everything first-class, in 2d/3d. As if everything in an image were mutable.
As a film director, this is really exciting stuff.