The author of this project is pushing and promoting it HARD, on HN and elsewhere. It does not appear to be even remotely at feature parity, but they write about it as if it were finished and working.
So when I went through all of them last night and found a surprising amount of functionality, especially in the Photoshop clone, I was just imagining it?
I tried the Photoshop one when they promoted it a few days ago here. I loaded up one of the client projects I'm working on right now and I could barely move the document or do anything it was so laggy and every single button/feature I tried to use had some kind of bug.
Maybe they've fixed everything in 2 days but I kind of doubt it.
Here's the thing, I suspect there are a lot of people who pay for Adobe tools who are in fact only using "the most obvious subset of functionality" and would love to have a replacement that suits their needs without the hefty subscription price.
So even if these tools never reach 100% parity with Adobe, if they offer the basics, and they're free and open source, it will be a win.
I suspect the reason alternatives haven't taken away marketshare isn't because of the software itself - it's because of the industry around it treating it as the standard. That's not going to change with a vibe-coded alternative
You're free to use Gimp today. Almost zero professionals actually do.
As a power user of Photoshop, I will say yes, most people use about 3-10 features that adobe offers.
But there are thousands of free tools for those people already, the point is this guy is saying he cloned the entirety of the adobe creative suite with vibe coding in a week.
That's not true. He made a bunch of simple and buggy "creative suite flavored" apps. That's a completely different thing than what he claims.
A lot of software developers are seduced by the old “80/20” rule. It seems to make a lot of sense: 80% of the people use 20% of the features. So you convince yourself that you only need to implement 20% of the features, and you can still sell 80% as many copies.
Unfortunately, it’s never the same 20%. Everybody uses a different set of features.
Adobe slept so incredibly hard on tools like Photoshop. They have been keeping that stack on life support for decades without any real innovation (Linux support?) and hostile dark patterns around subscriptions and cancellations. If we could peel the covers back and inspect the source I am sure it is as antiquated as a Pentium 3. They deserve to be supplanted by something else for languishing such a legendary tool. Even if it is vibe coded.
To actually test them properly you need an understanding of Adobe's products. I only know the very basics of Photoshop - I'm guessing most are in the same position
Photoshop: Used it for years. I have a perma-license copy that runs on Windows only. I sometimes (rarely) boot up my Windows partition when I have particularly complex edits to make. A UI that has rotted out over time.
Corel Photopaint: I worked for Corel. I actually really like PhotoPaint, which at least follows a Windows UI convention. Much easier to use than Photoshop; but I have not used it for many years.
Gimp: tried it. Rotted out UI, and an absolutely incomprehensible UI covention (if any). I cannot use it and will not take the time to learn it.
Krita: So much easier to use than Gimp, excellent for consistent and modern UI conventions, but currently missing important features.
ArtCraft: I have not actually tried it, although it sounds very much like what you would expect from vibe coding: buggy as heck, feature deficient, and definitely not ready for serious consideration. Yet.
To be honest, I do most of my graphics work in Inkscape these days (lots of vector icon design). Brilliant UI, consistent UI conventions. Very usable. But mostly useless for photos.
Just to qualify for your arbitrary impressionistic standards on who gets to say what about ArtCraft.
People are buzzing about it because it is bold experiment whose outcome may tell us extremely interesting things abut vibe coding. Most particularly, can you, or can you not build large applications with pure vibe coding? And lots of speculation over whether architectural rot will be better or worse than what humans do. Because human-generated architectures rot out too (Photoshop being an excellent example). I not aware of anyone, so far, who has explored that issue. So far, the grand experiment seems to support "can you not", but the experiment isn't over.
Fascinating stuff. I'm glad somebody else is doing it, and happy that I'm not doing it. Yet. But I will certainly be watching with interest. (Pro coder).
I asked precisely that question on their discord. An account of token spends.
Noting that this project is examplary experiment that may demonstrate whether the state of genAI can produce complex software before an explosion of token consumption as the code base grows, or even collapse.
In my experiments, it collapsed, each time I tried. Every 6 months or so I take the challenge. Unless a human intervenes of course. Basically dictating what genAi should do, which becomes more painful than it's worth automating code generation.
Gimp is a joke. Anyone who has used Photoshop for decades turns to Gimp, uses it for about 10 minutes, and then realizes this is is a disaster and deletes it forever.
Why would they suck the oxygen out of the room? This sounds like claiming a new distro of Linux made by new rufugees from Desktop Windows for people accustomed to Windows desktops is harming Linux by ensuring they don't go to some existing flavour which defaults middle mouse paste and thinks everyone must go on a spiritual journey of becoming one with cli tools in order to set up their social media and documenting editing machine. New people are making something they want and are empowered to make something they want, not something we've all been grateful for but bemoaned as a comparise.
For example, I love GIMP but holy shit it was a downgrade from Adobe in most ways.GIMP should stay GIMP, though, I wouldn't want my tools being completely overhauled in terms of UI and workflow anyways. I'm sure the old heads who put TLC into it would be strongly against someone using AI to significantly rewrite it at base, but also changing the interface and how it works significantly enough to matter to users. It's a sad way how it's been gone about, but in a sense this new software is building on GIMP (among many, many others) shoulders by developing openly and allowing the lessons on how to do things be adopted and not re-learned.
I don't know. As others mentioned, Gimp and others had plenty of decades of oxygen to breathe. Meanwhile, the software ecosystem keeps getting worse - that's a trajectory it was on before LLMs, so AI is not to blame here.
I find such vibe-coded efforts to resonate with me, because they reflect the same impatience I have. Impatience with enshittification of the commercial offerings, impatience with OSS following suit without realizing it (most modern UI/UX philosophy is driven by needs of enshittification), impatience with OSS being dominated by fakers and itself becoming a business model. Impatience with broken software.
Vibe-coding can be a way to vent the frustration, and in this case, it even turns into a spectator sport. Most of the vibe-coded projects I do, and that I see people I know doing, share the same, single, deep motivation - "I want a software that does this particular thing right now, and without all the bullshit". The vibe is that of awe, but it starts rooted in anger.
I wonder. My older boss was of the type that even if something wasn't 100%, his position was that 80% was better than nothing ( which offended most of our team, who had to deal with the inevitable support and fallout from his decision ).
I learned photoshop long before programming and the idea someone will vibe up not just photoshop but all the apps is absolute ballocks.
It isnt that there is no market for a cheaper version but people forget the amount of craft it takes to get something from 80% to 99%.
If all you can add is baby sitting agents, then you will never reach beyond 80%. Yes, spend 10m on tokens and 2 years improving and it may become useful but isnt that how it always was? Ela figma and canva?
Startup spending a few million dollars to decompile and replicate adobe suite in a few years would spring up so many competitors that it would basically kill adobe and creative software sub. That's at least a more useful allocation of tokens than logn -182. Porbably prosocial movement.
Honestly, I'd be surprised the Adobe or current workflow even survives in a few years with people who grew up on image prompting and sketch to image etc.
But it'd be nice to someone to throw enough tokens to make some parity Adobe software... like OpenAI wasting 10m on 1m math problem poor waste of resources... spend 100m and kill and charge $10 instead of adobe $50.
49 comments
[ 0.20 ms ] story [ 80.2 ms ] threadIMO it is vaporware until shown to be otherwise.
I tried the Photoshop one when they promoted it a few days ago here. I loaded up one of the client projects I'm working on right now and I could barely move the document or do anything it was so laggy and every single button/feature I tried to use had some kind of bug.
Maybe they've fixed everything in 2 days but I kind of doubt it.
I'm not an artist, but isn't that what people are interested in sticking with the incumbent? See: google sheets vs microsoft excel.
From the other thread he said he wanted to hold off posting it here until it was more ready.
>IMO it is vaporware until shown to be otherwise.
You can download and run it today.
> A quixotic new project takes an AI-first approach to battling Adobe, and while it’s unclear where it leads,
So even if these tools never reach 100% parity with Adobe, if they offer the basics, and they're free and open source, it will be a win.
You're free to use Gimp today. Almost zero professionals actually do.
But there are thousands of free tools for those people already, the point is this guy is saying he cloned the entirety of the adobe creative suite with vibe coding in a week. That's not true. He made a bunch of simple and buggy "creative suite flavored" apps. That's a completely different thing than what he claims.
=-=-=-
A lot of software developers are seduced by the old “80/20” rule. It seems to make a lot of sense: 80% of the people use 20% of the features. So you convince yourself that you only need to implement 20% of the features, and you can still sell 80% as many copies.
Unfortunately, it’s never the same 20%. Everybody uses a different set of features.
https://www.joelonsoftware.com/2001/03/23/strategy-letter-iv...
=-=-=-
Also, there are many image editors _already_ out there of varying levels of power and ease of use. Some open source, some commercial.
And yet Photoshop still rules.
It seems it's buzzing because it make people who post about it, buzz.
We live a strange time.
Corel Photopaint: I worked for Corel. I actually really like PhotoPaint, which at least follows a Windows UI convention. Much easier to use than Photoshop; but I have not used it for many years.
Gimp: tried it. Rotted out UI, and an absolutely incomprehensible UI covention (if any). I cannot use it and will not take the time to learn it.
Krita: So much easier to use than Gimp, excellent for consistent and modern UI conventions, but currently missing important features.
ArtCraft: I have not actually tried it, although it sounds very much like what you would expect from vibe coding: buggy as heck, feature deficient, and definitely not ready for serious consideration. Yet.
To be honest, I do most of my graphics work in Inkscape these days (lots of vector icon design). Brilliant UI, consistent UI conventions. Very usable. But mostly useless for photos.
Just to qualify for your arbitrary impressionistic standards on who gets to say what about ArtCraft.
People are buzzing about it because it is bold experiment whose outcome may tell us extremely interesting things abut vibe coding. Most particularly, can you, or can you not build large applications with pure vibe coding? And lots of speculation over whether architectural rot will be better or worse than what humans do. Because human-generated architectures rot out too (Photoshop being an excellent example). I not aware of anyone, so far, who has explored that issue. So far, the grand experiment seems to support "can you not", but the experiment isn't over.
Fascinating stuff. I'm glad somebody else is doing it, and happy that I'm not doing it. Yet. But I will certainly be watching with interest. (Pro coder).
Noting that this project is examplary experiment that may demonstrate whether the state of genAI can produce complex software before an explosion of token consumption as the code base grows, or even collapse.
In my experiments, it collapsed, each time I tried. Every 6 months or so I take the challenge. Unless a human intervenes of course. Basically dictating what genAi should do, which becomes more painful than it's worth automating code generation.
No. They suck the oxygen out of the open-source ecosystem for other more credible software, such as Photopea or Gimp or FreeCAD.
For example, I love GIMP but holy shit it was a downgrade from Adobe in most ways.GIMP should stay GIMP, though, I wouldn't want my tools being completely overhauled in terms of UI and workflow anyways. I'm sure the old heads who put TLC into it would be strongly against someone using AI to significantly rewrite it at base, but also changing the interface and how it works significantly enough to matter to users. It's a sad way how it's been gone about, but in a sense this new software is building on GIMP (among many, many others) shoulders by developing openly and allowing the lessons on how to do things be adopted and not re-learned.
I find such vibe-coded efforts to resonate with me, because they reflect the same impatience I have. Impatience with enshittification of the commercial offerings, impatience with OSS following suit without realizing it (most modern UI/UX philosophy is driven by needs of enshittification), impatience with OSS being dominated by fakers and itself becoming a business model. Impatience with broken software.
Vibe-coding can be a way to vent the frustration, and in this case, it even turns into a spectator sport. Most of the vibe-coded projects I do, and that I see people I know doing, share the same, single, deep motivation - "I want a software that does this particular thing right now, and without all the bullshit". The vibe is that of awe, but it starts rooted in anger.
I find that unless I have very detailed specs with rigorous completion verification/criteria (manually atm) or tests. It’s like 60/40 at best.
And adding all the tricks only gets me to like 75-80.
Tbh I am using cheaper Chinese models (ds4.1f) and only pay for the $20 plans from the us labs
It isnt that there is no market for a cheaper version but people forget the amount of craft it takes to get something from 80% to 99%.
If all you can add is baby sitting agents, then you will never reach beyond 80%. Yes, spend 10m on tokens and 2 years improving and it may become useful but isnt that how it always was? Ela figma and canva?
But it'd be nice to someone to throw enough tokens to make some parity Adobe software... like OpenAI wasting 10m on 1m math problem poor waste of resources... spend 100m and kill and charge $10 instead of adobe $50.
While we speak, these new apps only get better.
Clever.
I mean, claude already does it for you, constantly even