People that say that AI could be used as a tool to help artists clearly as never pickup a pencil to draw. The thing that makes an artists voice, that makes that art theirs are the decisions they make while making their art.
When you are drawing something, you are constantly making small micro-decisions with every stroke of your pencil, and those decision and how you make them is what makes art so beautiful, as no two artists make those decision the same way and each artist as a certain consistency in those decisions that evolves with them as a person. As such, art is so much more than a pretty picture, it is a reflection of the person who made it. Those decisions are also the fun part of making art.
AI art doesn’t let you make any decisions: you type the prompt and out comes an image. An image made of an weighted average of human made images with a similar description. You have no say in the micro-decision the machine makes, you have no say on where exactly the pencil strokes go. Therefore this machine is useless for artists. You might say “Just edit the image!”, but that doesn’t help either, as editing the image still doesn’t give you that micro-level of decision making. Also, editing a flat image with just one layer is just as useful as any other image form any search engine image search result. Unlike text, which can be easily edited to be exactly what you want.
I know their might be some wait to integrate machine learning into art, but right now the tools available don’t do that.
People who say that AI can’t be used as a tool to help artists clearly have never tried using AI as a tool. Everything you’ve written here is untrue.
Artists can manually curate unique datasets to create LoRAs. They can draw from their own photographs, drawings, paintings, etc., and then coordinate prompts and parameters to blend their custom LoRAs with other creators’ LoRAs/models/checkpoints to craft something unique. The process can be even more involved with tools like ControlNet, where artists can sketch an outline of the scene by hand. I.e., you can have precise control over where the pencil strokes go.
The tools available right now do that
I’ve used it and continue to research it.
You’re wrong. You can’t have the same level of control as the person above describes. Even if you train the model on your own work, it will still be the one generating every “stroke” of the pencil. If trained for it, it will do it based on how you must often do so, but you can’t clearly control it. You can’t control granular details of the process of creating the image. It’s all broad strokes. I don’t know what your level of experience with art is, but so much of what makes art is tied up in the process of having to think through every little addition you make to an image. And by little addition I don’t mean “let’s add a person here” but “let’s do these 200 individual strokes that make up that person”. The involvement in the process is the point, and when an image is generated for you, you remove so much of the involvement and granular decision making, that the actual point is lost.
It’s like cooking with premade, pre-prepared ingredients. You can pick the dish and put it together with the stuff you buy, but you can’t control the whole process, because you’ve given up that for the sake of speed and convenience, and the dish will be different for it.
With ControlNet, you can control that very finely though. It partially combines computer graphics into the mix which is definitely not easy to get into.
But it’s different from drawing, that is for sure. Different decisions with different outcomes and different possibilities. But you see similar differences with every form of art. You don’t make 200 strokes for a photograph, or for a cut out collage, or algorithmic art, or sculpting. But you do make different decisions that are similar in nature. They shape the end product, and in a way no other person would do exactly the same. You still have to be involved in every step of the process, even if some steps are no longer done by yourself, they are replaced by other decisions.
Again, this is assuming they aren’t just clicking generate and calling it good to go, but if someone is using ControlNet they should be well above that, since the quality of blank generations is often not the best and demands refinement to anyone with an creative outlook.
This is why we shouldn’t confuse AI art, AI assisted art, and other forms of visual art, even if they all end up making an image as the end result. Something can be impressive when drawn, but mediocre if made with AI. Just like painting a scene isn’t the same as taking a photograph of that same scene, even if they end up being visually similar. Everything exists in context.
And yes, you are giving up some creative control for sake of convenience. But the question is how much. A painter that hand crafts their brushes will make a different painting had they used a pre-made brush. But we can agree I think that the creative control they lost by doing so is negligible. Artists generally lean on what they have produced before as references too. 3D sculptors can start with a cube too, but if they’re going to be making a person they will start with a mesh of a human figure, male or female depending on what they want. There is no shame in taking shortcuts in steps where it’s possible, even if it’s commendable if you don’t.
Art takes long and is expensive to produce, it would be unsustainable in this modern day to do everything from scratch every time. And as long as you focus on the parts where your decisions make the artistic intent happen, you can still make something unique and valuable in it’s own right.
I never said that art will necessarily come from AI in its current form but it’s true that it’s what I had in mind. You basically expressed something very similar to what I meant in your last paragraph.
And yes I do love pencil drawing :)
But I’m more thinking about conceptual artists with decades of work behind them that I can imagine will create art using these AI tools that will transcend what the average Joe/Jane is producing with these tools right now. To produce something that will shock, move us, make us think.
There are so many different facets to art.
Hi, person here who’s drawn extensively with pencil as a kid but then slowed down. AI has reignited my passion for art, because unlike pencil or even digital drawing, you can iterate much more quickly, which allows me to do so while working a demanding job and having a life besides it. You are severely underestimating the amount of micro-decisions that go into AI art, and more importantly AI assisted art. If you’ll allow me, let me explain.
Lets break it down into levels of effort and creative input, I like to refer back to photography since it has some comparison:
- Empty canvas prompting.
spoiler
To me that is essentially the equivalent of taking a selfie or a random shot. On the scale of effort this is none to very little. But a prompt can be unique if you put an extreme amount of effort into specifying the exact details, just like a random shot can in fact be a very informed random shot.
You can put a rather massive amount of tokens into your prompt that all further specify this. At this point you can reasonably say you imagined at least the general look of the image before it was created. But you can’t say you had any part in actually drawing it or significantly determined how it was drawn. It’s basically impossible to get any kind of copyright protection over this unless you can back up your prompt very well, and only then would you get protection over your prompt, not what the AI drew.
- Image to image
spoiler
You can feed an image into the AI, you add noise to the image, and let the AI try to remove that noise (After all, this is the exact same as it does on an empty canvas, but that is completely random noise). This means that a large part of your original image specifies how the AI will further try to denoise the image. As such, you are guiding a large part of how the AI moves forward. No other artist would likely use the same input image as you, so human decision making plays a bigger part here.
To me this is the equivalent of choosing a location you want to take a picture, and then scouting several locations to see which one works best. That’s the micro-decisions sneaking in. You are giving the AI an existing image, either created by yourself, or from previous iterations.
At this point, you are essentially evolving an image. You are selecting attributes and design choices in the image you want to enhance and amplify. These are decisions the artists makes based on their view of how the final image will look like. Every iteration adds more decisions that no other artist would take the same way.
- Collaboration.
spoiler
The point where AI starts becoming a tool. You don’t start with point 1, or at least only use point 1 for brainstorming. You imagine the image beforehand, just like you would do with pencil. You can develop the image as much as you would like before going to the AI. You are making the exact micro decisions you are with drawing by hand, since it’s essentially the same up to this point. A photographer at this point would work out every fine detail before snapping the picture.
Except for the fact that you know you are going to be using an AI, so certain aspects need more or less refinement to properly be enhanced by the use of AI. Just like you don’t start the same if you’re going to make a painting, or a silhouette, or any other kind of technique. At some point, you return the image to the AI and mostly perform step #2, perhaps returning to brainstorming with step #1 if you want to add or remove from your existing design.
- AI truly as a tool.
spoiler
Now to make something actually with #3, you start doing this process in iterations. Constantly going back and forth between photoshop and the AI, sometimes you spend days in photoshop, other times you spend days refining a part of the image with AI. There are also additional techniques like ControlNet, LoRAs, different models, different services, that can drastically enhance how well you get to what you want. A photographer at this point would take as many shots as they would need using their creatively controlled setup, and find the best on among them. Different lenses, different vocal lengths, different lighting (if applicable), different actions in the shot.
Sadly, most people that talk confidently about how much they hate AI just know point #1 and maybe point #2. But I see point #3 and #4. And when I talk to artists that haven’t yet picked up on AI, but if they are aware (or made aware) of #3 and #4, suddenly their perspective also changes in regards to AI. But the hostility and the blind anger makes it quite hard to get through to people that not all art with AI is made equally. We should encourage people that want to use AI to reach the point of #3 and #4 so that their creative input is significant to the point it’s actually something produced by their human creativity. And this is also where an existing artist switching to using AI will most likely start off from.
Also, in terms of time. #1 might take seconds, #2 might take minutes to hours, but #3 and #4 can take days or weeks. Still not as long as drawing those same pieces by hand, but sometimes I wish it was as easy as people would make it out to be.
I’m glad you’ve found value in it. I’ve played around with a similar workflow you describe in step 3 and 4, but I just find that it always produces the blandest version. Sometimes you get a surprising iteration, but I think being used to seeing visual patterns makes it much more obvious just how predictable the image details get. It just ends up looking like a compilation of techniques.
I’m sure it won’t bring the same results for everyone, and that’s fine. I’m glad it’s that way and not just so easy it would consume all other ways of making things, as it would cease to be a tool at that point and just become the entire process. I really just try to make what I am already imagining since before I even put anything to paper, and so I know what I want the AI to help me with ahead of time. I get surprisingly close to the idea in my mind because of that. Much closer than I reasonably could get in other ways with the finite time I have.
