How to turn 'sfo-jfk' into a suitable photo

Posted by bblcla 4 hours ago

Counter20Comment16OpenOriginal

Comments

Comment by mips_avatar 14 minutes ago

The annoying thing with Unsplash is that it sounds like a really permissive license, but the moment you try and do it at scale you're no longer in compliance with their terms. Also their definition of not building a competing service is really broad. Maybe i'm being overly cautious but I get eeked out by all that.

Comment by busymom0 1 hour ago

Couldn'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:

https://en.wikipedia.org/wiki/Deadvlei

Comment by kazinator 2 hours ago

[flagged]

Comment by dang 2 hours ago

"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

https://news.ycombinator.com/newsguidelines.html

Comment by linkjuice4all 1 hour ago

I realize dang has already tagged this (and I get it) but I don’t know who is actually benefiting from this. This is deceptive as it doesn’t represent a traveler’s actual/expected experience and just adds more slop to the pile. This is a case where you should pay actual photographers to take verified pictures of the places you are recommending people visit. Why would someone cheapen their brand like this?

Comment by properbrew 1 hour ago

If you read the article you'll see it's not about generating AI slop images:

> Take a freeform query (like ‘sfo->jfk’) and turn it into a ‘place’

> Build a database of ‘places’ -> pictures

> Build a software system that can take a ‘place’, look it up in a database and spit out the right picture – even if that ‘place’ isn’t in the database

Comment by dang 55 minutes ago

[stub for offtopicness]

[sorry I messed up with that title! perils of not reading the articles closely]

Comment by npinsker 1 hour ago

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.

Comment by dang 58 minutes ago

Ok! that was my attempt to avoid linkbait and make the title less provocative (submitted title was "How to design an AI app with a sense of taste"). But I missed the mark this time, so have reverted the title to the article's own headline, except I'm not going to keep the word 'beautiful' up there since that would be certain to provoke shallow objections.

Comment by MrZander 1 hour ago

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.

Comment by echelon 1 hour ago

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.

Comment by tehjoker 1 hour ago

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.

Comment by hayksaakian 1 hour ago

the article doesn't talk about AI generating photos. it talks about using AI to interpret user queries into photo selections from photographers

Comment by nluken 1 hour ago

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"

Comment by dang 56 minutes ago

Ok, sorry! but re 'beautiful' see https://news.ycombinator.com/item?id=46802571

Comment by tehjoker 54 minutes ago

sorry i skimmed the post and confused myself then