By the way, PhotoSuite is just a stolen copy of my project www.photopea.com , which I have been working on for 8 hours a day for the past ... 14 years? :D
It was discussed here on HN yesterday and then, the anonymous person behind it removed the "Issues" section completely from their Github
Never got to try out PhotoSuite, looks like it really was just ripping-off your code, the repo owner already deleted it, and now it forks PhotoCraft.
I have a huge respect for your work on Photopea, been using it constantly since the time I completely moved to Linux a year ago. It has the best Photoshop parity yet to find! Would you ever consider to:
1. Open sourcing your work (partially or completely) under some kind of a permissive/copyleft license.
2. Rewriting some parts of the website that require performance as WASM targets.
3. Using any modern JS frameworks, e.g. Svelte.
I remember using your tool a lot for years but in the past year or so the ads have made it unusable. It feels more like browsing ign.com with no adblock or something. Just brutally slow and intrusive visually speaking.
The thing is: there are color spaces, correct filtering etc, etc.
Sure you can do a Photoshop clone as in "Ps in 1990" if you just ask an LLM because then (and for years after) Ps itself got all this stuff wrong and people used it, professionally nevertheless.
But getting these things right requires, as-always, in-depth understanding of the theory behind it or the LLMs will gladly omit those parts.
Not least because the majority of OSS code dealing with those things gets it subtly wrong. And they've been trained on that.
A good start is btw. to ask your agent of choice to copy all theory/basics from OpenImageIO.
How do I know? I'm maintaining a closed-source, heavily LLM-assisted Rust crate that is the backbone of all image processing we do at my employer (kringers fossed it will be OSS eventually).
The amount of subtly-wrong- bites-you-eventually bugs I fixed (or had an agent fix, rather), despite tight specs and good tests, over the last 10 months, is ... noteworthy.
That said, for a lot of users it probably doesn't matter if interpolating between red and green means getting a muddy brown or that you get subtely wrong colors when you downsample and some (or quite a bit ) of aliasing when you do so more than 2× etc.
But while a lot of people want to prompt a clone of app X and an unexpected many also seem to have the patience for it: few have the background to get sth. out of that endeavour that will be genuinely useful in the end.
The CAD/parametric 3D modeling segment is another category I'm watching closely where a lot of people have the same issue w/o (yet) realizing.
And ofc, there are always exceptions where seemingly someone is behind the project who actually do know what they're doing. :)
I think people aren't thinking enough about the second-order effects of this.
The immediate reaction is to ask whether any of these would be good enough to replace Photoshop (or Pixelmator or whatever). That's a first-order question and it's an open one --- you probably couldn't replace a real workflow with vibe Photoshop today, but I wouldn't bet against that being the case a year from now.
But the second-order questions include consideration of the people who can't use Photoshop, either because of cost or (to me, more importantly) because of lack of platform support.
In a world where 90% of the functionality of things like Photoshop and Word are replaceable with personal apps, how much does platform support matter anymore? How much do platforms matter anymore? I'm a committed macOS user and have been since the TiBook. Will I be 5 years from now? I'm deeply uncertain, but one thing I'm pretty sure of is that if I'm not a macOS user, I also won't be a Windows or Linux user.
Plus, most people don't use 90% of Photoshop. How does the saying go? "The average user only uses 10% of a software's features, but every user uses a different 10%."
Now, you can just prompt the 10% you need and not even have to use up your computer's resources with the rest of Photoshop. I didn't like a single one of the many Android TV video player apps. Most of them were way too big, had all kinds of features I didn't need, took a while to launch, had stupid "libraries" that you had to populate your videos into, and relied on third party lookup services to get things like movie posters and other metadata. Pre-2020 I would have just picked the least bad one and lived with it. Now, I just vibe-slopped a player app with only the features I want and nothing else.
I predicted something a few years ago that I still believe will come true: in time, you won't search YouTube for an existing, pre-recorded video that solves your itch, instead you'll describe a problem and a video will be generated in real-time, on the spot that meets your needs. This video will (legally, with consent) use the faces and voices of "YouTubers" (humans who have signed up their personality) to communicate with you. If you don't have subscriptions or the system wants to show you new "creators", then it'll still do what it does today plus generate new personalities that fit your profile - gay/heterosexual, male/female, 20-25 years old, etc.
The same applies to software: you'll describe a problem and a network of agents will write a solution faster than you can Google it, download it, install it, and start using it. It'll work with your accessibility requirements out of the box; it's UI will be in your language; the data will be stored where ever you like; and so on.
I have thought about something kind of similar to your last paragraph.
Instead of having a web application with a typical frontend and backend, I have fantasized about thin UI/UX interfaces with an almost pure LLM backend. Just having one or more bots receive parsed http requests, CRUD-ing the data based on training and tool access, and responding back if necessary.
(I have a strong dislike for web development, so perhaps my fantasies are a form of escapism.)
I agree, this is the right direction to be thinking in. I’ve made a bunch of tools for myself with AI, been interested to see if I could release it, and found 10 open source projects that do some flavor of what I made, but with zero traction. I feel like the unlimited personalization of these types of apps is what’s going to prevent there from being “the free photoshop”, I think that everyone will just have their own personalized vibecoded photoshop that does exactly what they need.
Will all these platforms just disappear? I think that the real winners will adapt to this new AI world, evolving their platforms around agent-based workflows.
Those who won’t will be just left behind (sadly)
Because of IP laws, I believe. Even China can't rip Apple's trackpad tech and copy it because they _really_ like having iPhones made and sold in China... can't rock that boat. But if the latter wasn't true, you'd have 500 brands with an Apple-like or better trackpad.
I don't know if I believe that. Nobody seems to be reaching for absolute top shelf quality anymore. You have Apple, then you have every other computer maker battling it out to try to win the "low cost plastic junk" market. A few of them have a "premium" tier which itself is still comparatively low-cost and sub-par.
My brother recently bought a used piece of industrial machinery. The $1500 control software did not come with it. In less than an hour, with no prior coding or vibe coding experience, he prompted claude.ai (yes the web version) to create a functional control app, nicely packaged as a .deb file for installing on linux. (It didn't cost him anything as he used my claude sub and it didn't noticeably impact my quota).
I feel like a major problem here is that people are more interested in vibeslopping their own Photoshop clone than contributing to an existing one. This results in a situation where theres a million clones that split the market and don't gain any traction.
You can view it as a problem, or a point on a trend line where building software becomes ever easier and cheaper. If you follow that trend far enough, when you need for something Photoshop-shaped, you ask for it, and you get exactly the functionality you need. If you need it to do something PS doesn't, that capability just appears.
I've said it in other venues, but we're reaching a point where using someone else's software is like chewing someone else's gum.
One thing I don’t get about “personal software” is - why would you want something photoshop shaped, when you can describe what your image should look like? Most common issue - passport photos with specific background requirements and aspect ratios. Just take a photo on your phone, ask Gemini to meet the specs - you are done.
For now, while we are still riding this wonderful subsidized AI gravytrain, but how much will it cost in tokens/$$$ next year when investors finally want a return on their investment? Or if the AI bubble pops? I doubt running 7B models locally will suffice, even at the rate of improvement we are seeing.
For me, I dont like photoshop and only have it to get lightroom so I can do basic editing on photos. I am in photoshop maybe 6 hours a year and only to do some minor edits or things I should probably do in another app like InDesign or whatever it is for layouts (I truly have no idea, but I'm not giving adobe more money).
For me, I just want to easily organize some folders, cull stuff, throw the culls into a marked directory, and process them to JPEG with some lighting adjustments since I shoot raw. Lightroom honestly is painful to use. I don't think gimp fills my needs since its more like photoshop. I'm happy to look at something else though!
Yes. None of these developers are seemingly as interested in the project as they are in the fiefdom. It’s a widespread problem in AI-driven development.
Nobody really needs a perfect Photoshop clone, they need an image editor for their particular workflow. Photoshop excels, in a way, because it handle almost every potential workflow -- one product for many users.
But if I'm vibe-coding an app for myself, I only want it to what I want it to do. One product for one user.
That's been the question running in my mind reading this thread. I'm wondering how many of these slimmed down custo versions are just some frontend written for ImageMagick.
For people interested in a Photoshop clone, https://www.photopea.com/ was amazing long before LLMs existed. It runs in the browser and was built by a single person!
$260 / 12 = $21.67/month. Any person using Photoshop professionally will have no problems justifying that expense. Even if paying for the full suite, the cost will just be claimed as an expense and used as a deduction. One paying job will cover the fee while ensuring they are able to deliver a compatible file. The PSD file is a dumpster fire of a format with who knows how many footguns hidden within making compatibility a nightmare.
As a professional, there's no way I'd risk not using the real code. As a hobbyist, I can/have use something like Photopea.
So far it’s GPU accelerated (GPUI), cross platform, supports 95% of excel functions, supports charts, is about 40x faster than Numbers, and can render 240fps.
I thought I’d leave this process with a new appreciation for manual dev/details. I haven’t found that yet. I’m getting more into architecture details, writing more benchmarks, testing more. I know there are limits, but I’m still trying to find them.
It would be absolute garbage if I wasn’t already and engineer. It probably is absolute garbage in ways I don’t know because I haven’t read the code. But the app is… quite good.
I like to make fun of Excel as much as the next guy and I realize my use of tabular data is very limited compared to the full abilities within the app, but what in the world in Excel needs to be rendered at 240fps?
Honestly, if this topples Adobe from its unearned throne then fantastic. Adobe’s monopoly is a disgrace to design software and their apps should’ve gotten a lot more attention throughout the years than they have enjoyed historically—especially in the age of AI, where everything they do seems to be focused entirely on their useless Firefly being shoved into every corner of every app, bloating the hell out of already bloated as fuck software.
I’m forced to use Adobe’s apps because they are the golden standard at the moment but I wish with all my heart this to not be the case anymore.
Adobe fucking sucks.
Side-note to whomever attempts to build a new Photoshop: workshop better names. The ones on the article are woefully bad to the point of hilarity.
Adobe's unearned throne? Monopoly?
There's much to criticize with Adobe but what makes you say these specific things? They made the best software for their specific field and have been reaping the rewards for a long time. I feel like that throne is(was?) pretty earned.
And how are they in a monopoly position? Is this about proprietary formats or something else? Genuinely interested to know about this if it wasn't just hyperbole.
"An open-source, clean-room reimplementation of Adobe Photoshop in pure Rust".
They also have:
VectorCraft Vector illustration;
FilmCraft Video editing, color and sound;
LightCraft Photo library and raw development;
PrintCraft Reading, organizing and protecting PDF;
EffectCraft Motion graphics and visual effects;
DesignCraft Page layout and publishing
It was discussed here on HN yesterday and then, the anonymous person behind it removed the "Issues" section completely from their Github
https://news.ycombinator.com/item?id=49972730
https://replayweb.page/?source=https://archive.org/cors/gith...
I have a huge respect for your work on Photopea, been using it constantly since the time I completely moved to Linux a year ago. It has the best Photoshop parity yet to find! Would you ever consider to: 1. Open sourcing your work (partially or completely) under some kind of a permissive/copyleft license. 2. Rewriting some parts of the website that require performance as WASM targets. 3. Using any modern JS frameworks, e.g. Svelte.
If I may ask, if you were to do this all over again in 2024 - 2026, would you choose SSR?
edit: if so, Sveltekit, Nuxt, something else? (I would love to hear opinions on this)
Sure you can do a Photoshop clone as in "Ps in 1990" if you just ask an LLM because then (and for years after) Ps itself got all this stuff wrong and people used it, professionally nevertheless.
But getting these things right requires, as-always, in-depth understanding of the theory behind it or the LLMs will gladly omit those parts.
Not least because the majority of OSS code dealing with those things gets it subtly wrong. And they've been trained on that.
A good start is btw. to ask your agent of choice to copy all theory/basics from OpenImageIO.
How do I know? I'm maintaining a closed-source, heavily LLM-assisted Rust crate that is the backbone of all image processing we do at my employer (kringers fossed it will be OSS eventually).
The amount of subtly-wrong- bites-you-eventually bugs I fixed (or had an agent fix, rather), despite tight specs and good tests, over the last 10 months, is ... noteworthy.
That said, for a lot of users it probably doesn't matter if interpolating between red and green means getting a muddy brown or that you get subtely wrong colors when you downsample and some (or quite a bit ) of aliasing when you do so more than 2× etc.
But while a lot of people want to prompt a clone of app X and an unexpected many also seem to have the patience for it: few have the background to get sth. out of that endeavour that will be genuinely useful in the end.
The CAD/parametric 3D modeling segment is another category I'm watching closely where a lot of people have the same issue w/o (yet) realizing.
And ofc, there are always exceptions where seemingly someone is behind the project who actually do know what they're doing. :)
The immediate reaction is to ask whether any of these would be good enough to replace Photoshop (or Pixelmator or whatever). That's a first-order question and it's an open one --- you probably couldn't replace a real workflow with vibe Photoshop today, but I wouldn't bet against that being the case a year from now.
But the second-order questions include consideration of the people who can't use Photoshop, either because of cost or (to me, more importantly) because of lack of platform support.
In a world where 90% of the functionality of things like Photoshop and Word are replaceable with personal apps, how much does platform support matter anymore? How much do platforms matter anymore? I'm a committed macOS user and have been since the TiBook. Will I be 5 years from now? I'm deeply uncertain, but one thing I'm pretty sure of is that if I'm not a macOS user, I also won't be a Windows or Linux user.
Now, you can just prompt the 10% you need and not even have to use up your computer's resources with the rest of Photoshop. I didn't like a single one of the many Android TV video player apps. Most of them were way too big, had all kinds of features I didn't need, took a while to launch, had stupid "libraries" that you had to populate your videos into, and relied on third party lookup services to get things like movie posters and other metadata. Pre-2020 I would have just picked the least bad one and lived with it. Now, I just vibe-slopped a player app with only the features I want and nothing else.
Out of curiosity, how much did that cost?
The same applies to software: you'll describe a problem and a network of agents will write a solution faster than you can Google it, download it, install it, and start using it. It'll work with your accessibility requirements out of the box; it's UI will be in your language; the data will be stored where ever you like; and so on.
Instead of having a web application with a typical frontend and backend, I have fantasized about thin UI/UX interfaces with an almost pure LLM backend. Just having one or more bots receive parsed http requests, CRUD-ing the data based on training and tool access, and responding back if necessary.
(I have a strong dislike for web development, so perhaps my fantasies are a form of escapism.)
Which is apparently impossible.
Who does Jony Ive work for now?
I'll stick to gimp I guess.
I've said it in other venues, but we're reaching a point where using someone else's software is like chewing someone else's gum.
If I have magic box that can give me anything, I'm not going to ask for tools and materials to build a house, I'm gonna ask for a house.
For now, while we are still riding this wonderful subsidized AI gravytrain, but how much will it cost in tokens/$$$ next year when investors finally want a return on their investment? Or if the AI bubble pops? I doubt running 7B models locally will suffice, even at the rate of improvement we are seeing.
For me, I just want to easily organize some folders, cull stuff, throw the culls into a marked directory, and process them to JPEG with some lighting adjustments since I shoot raw. Lightroom honestly is painful to use. I don't think gimp fills my needs since its more like photoshop. I'm happy to look at something else though!
But if I'm vibe-coding an app for myself, I only want it to what I want it to do. One product for one user.
I don't imagine that many of their big customers are fans of taking unnecessary risks to save what isn't much money for most of them.
As a professional, there's no way I'd risk not using the real code. As a hobbyist, I can/have use something like Photopea.
https://github.com/scosman/freecell
So far it’s GPU accelerated (GPUI), cross platform, supports 95% of excel functions, supports charts, is about 40x faster than Numbers, and can render 240fps.
I thought I’d leave this process with a new appreciation for manual dev/details. I haven’t found that yet. I’m getting more into architecture details, writing more benchmarks, testing more. I know there are limits, but I’m still trying to find them.
It would be absolute garbage if I wasn’t already and engineer. It probably is absolute garbage in ways I don’t know because I haven’t read the code. But the app is… quite good.
Then
>can this be done” at all? (...) The mere existence of these tools is proof that it can be done.
Then
>DISCLAIMER: I obviously can’t know whether any of these projects were definitely “vibe-coded”, but it also doesn’t matter
..????
Opus et all are able to do everything needed client side
I’m forced to use Adobe’s apps because they are the golden standard at the moment but I wish with all my heart this to not be the case anymore.
Adobe fucking sucks.
Side-note to whomever attempts to build a new Photoshop: workshop better names. The ones on the article are woefully bad to the point of hilarity.
And how are they in a monopoly position? Is this about proprietary formats or something else? Genuinely interested to know about this if it wasn't just hyperbole.
Why is their throne unearned? They created and continue to maintain their software, which is, as you said, still considered the gold standard.
"An open-source, clean-room reimplementation of Adobe Photoshop in pure Rust".
They also have: VectorCraft Vector illustration; FilmCraft Video editing, color and sound; LightCraft Photo library and raw development; PrintCraft Reading, organizing and protecting PDF; EffectCraft Motion graphics and visual effects; DesignCraft Page layout and publishing