Someone told me, “When I want a Recipe for a certain look, I just ask AI to make it for me.” I’ve heard a similar sentiment a few times. In fact, there are a couple of website and apps that will do it for you. Just upload a picture, and AI will create a Recipe that supposedly matches the picture. ChatGPT and other AI programs can do it, too. But is it any good?
It’s an easy test, actually. Use a photo that was made using a Recipe, and see if it comes up with the same or similar settings. If not, then it doesn’t do a good job. Test it again using a photo made using that same Recipe, and see if it gives you the same or similar settings as the first time. If it doesn’t, then it’s inconsistent and can’t be trusted. In order for AI to be a useful tool for this, it needs to be both accurate and consistent; if neither are true, it’s not a good tool.
If you upload a photo to AI and ask it to create a Fujifilm Recipe, you hope that it’s going to produce reasonably similar results to the photo you uploaded. If not, then what’s the point? You might as well just use random settings, or let darts or dice determine what to program into your camera. Someone once told me that AI is better than a complete novice, but not as good as an expert. I think there’s a lot of truth to that, but when it comes to creating Recipes, AI might actually be worse than the novice.
For example, I uploaded the image at the top, Bike Bags, which was made using my Provia Positive Recipe, and asked ChatGPT to make a Recipe from that photo. You can see my chat with AI below:
I noticed two things immediately. First, it has a lot of similarities to Reggie’s Portra. Certainly not 100% (and for sure it’s not as good), but there some obvious parallels. Second, it says to use base ISO 160 and also DR200; since the Dynamic Range settings are ISO dependent, you can’t use DR200 at ISO 160. A minor grievance, but it illustrates that AI isn’t fully versed in Fujifilm settings. This is how Provia Positive compares to AI’s “Nordic Harbor” (a.k.a. Reggie’s Portra tweak):
The results are pretty divergent. You might like the AI version (it’s basically Reggie’s Portra with a slight green cast), but you can’t say that it’s a good facsimile of the Recipe it’s suppose to look like. Using the same account, I started a new chat and asked ChatGPT again to make a Recipe using the same photo, but I worded the question slightly different. It basically gave the same Recipe but with four changes: Reala Ace instead of Classic Chrome, Color 0 instead of +1, Shadow -2 instead of -1, and WB Shift +1 Red & -3 Blue instead of -2 Red & -4 Blue. Let’s take a look:
After this, I used a separate ChatGPT account and repeated step one precisely, and got even different results (this time it suggested Velvia). I then tried using different photos made with the same Provia Positive Recipe, and each time it gave me a different Recipe, and none were very close to my Recipe. Between the two accounts, I asked ChatGPT to make a Recipe based on a Provia Positive photo a total of 10 times. Even if it had given an accurate result once (which it didn’t), how could you trust it with divergent suggestions each time? How could you ever know which one would be most correct?
I then tried other AI programs and apps, and repeated the test. Interestingly enough, on my first attempt with Claude, it gave a Reggie’s Portra like Recipe (just like ChatGPT), but with an even stronger green cast than ChatGPT’s iteration. Gemini also chose Classic Chrome on the first attempt, but played it safe and didn’t venture very far from factory-defaults. After 10 tries with these other AI apps and programs, plus the 10 I did with ChatGPT, I had a total of 20 results. Three things shocked me. First, Classic Chrome was chosen nine times, far more than any other film simulations. I assume this is because Classic Chrome is by far the most popular film sim for those who use Recipes, and that’s influencing AI’s answers. Second, Provia wasn’t picked even once. Not one time did AI choose the correct film simulation—not Provia, the “standard” option. Even on the programs specifically intended for making Fujifilm Recipes from photos, it got it wrong. If I had picked at complete random, most likely I would have chosen Provia at least one time (there are 20 film sims, and I made 20 attempts, but nine of them are monochromatic and not color). Third, one time Acros was given for the film simulation. One of the AI’s thought that Acros—a B&W film simulation—was the most correct! Wow.
This article is already way too long, so let me wrap this up. Yes, AI can make a Recipe that is based on a photo that you upload to it. Anytime you ask AI to do something, it will give you an answer. But is that answer any good? When it comes to Fujifilm Recipes, probably not. First, as you can see above, AI couldn’t figure it out. It also gave a different answer each time, and sometimes very nonsensical ones. Both the inaccuracies and inconsistencies are major red flags, and demonstrate that it’s not a trustworthy source for this particular task. It’ll probably get there someday, but it’s not there today. This is a very easy test, one that you can do yourself. If you ever wonder if any AI program or app can make a Recipe that matches the aesthetic of a picture that you upload to it, simply use an image that you already know the parameters of; if it can’t match it—or at least be in the general ballpark of it—then it’s not a good resource. You might actually be better off throwing darts, rolling dice, or picking the settings out of a hat at random.
Absolutely great information here. Thank you very much.
You are welcome!
Greets.
New tech is initially good for two things.
1. Porn.
2. De-skilling or reducing the work force.
Go figure.
Malcolm.
I feel kind of icky just using it to test this out. I “get” that it’s the future and all, but it’s definitely not all sunshine and lollipops.
That was super interesting, thanks. It’s quite a comfort that AI this time produced bad results :), but as you say, someday it will get there. And that’s a sad thought for everyone who is involved in creative processes.
I hate using it to test this out, I feel it’s kind of a waste of time and (natural) resources, but a lot of people seem to think that it’s a miracle program and much better than it actually is. I guess it’s good to know where it’s at, kind of a mileage marker.
I have found if you are really descriptive in what you want, almost overly descriptive, many of the AI’s out there can get you in the ballpark. One thing they mostly lack is strong image processing, it’s more a math problem for them, so matching photos is rather problematic. Also if you work with them long enough many will begin to understand your esthetic, pick up on what you use often, like, understand the reasons you like them, how you correct recipes, etc. So its possible to get some recipes that are very close to not simply what you want, but your style.
So why does this work? They match wording with the solutions they have been trained on with similar wording. After a while it recognizes what you really want and if you are highly descriptive it will match up your words (and settings) with the words and settings others have used…. then calibrate based on available information a solution. It reminds me a bit of first client interactions with architects, the design the client describes isn’t always the design the client really wants, it takes refinement to achieve the vision.
Are they good at recipes? Overall, no. More like a college freshman with the principles and no experience. Still, they went to school, and with the right teachers some develop reasonable outcomes even if you would tweak the design in the critique.
I think saying AI is equivalent to a college freshman is a bit generous. For example, my High School student had a math problem that he couldn’t figure out. He asked for my help, and I couldn’t figure it out, either (I’m no mathematician). I suggested he try AI, so that he could at least learn how to solve it. So he did. It gave him an answer, but apparently it was wrong. AI is supposed to be good at math, but even HS math is apparently a struggle. When it comes to art or artful things, AI is even worse.
My opinion is that people want AI to be truly great, so they believe it is. But it’s not. It can be ok, but it’s far from trustworthy. Ask it the same question (about anything) twice using two separate accounts, and you are very likely to get two answers. Which one is correct? Maybe one is, maybe neither is.
There is going to be an AI bubble that pops, much like the dot com bubble 25 years ago. After awhile, though, the technology will mature and we’ll figure out what it’s actually good for (and, just as importantly, what it’s not). At that time it will be more useful. Right now too many are acting like it’s some kind of miracle when it’s actually more of a card trick.