So I suppose the main difference with using LoRAs normally is that less of the image is changed? Because it seems most of this could be done with inpainting and increasing LoRA strength, but I admit it would be difficult to keep facial features the same the way they seem to have done. What I notice are missing from these examples are actions/poses, so I wonder if it's good for that or we still need openpose/controlnet.
> So I suppose the main difference with using LoRAs normally is that less of the image is changed?
The distinct thing about concept slider LoRA isn't how much of the image is changed (which will vary between LoRA within the type widely), but that the weight at which the LoRA is applied, rather than just setting how strongly the image tends toward representing a fixed concept, chooses which concept on a continuum the image tends towards.
> What I notice are missing from these examples are actions/poses, so I wonder if it's good for that or we still need openpose/controlnet.
You can do actions/poses via LoRA, but the control you get is qualitatively different than what you get with any of the controlnets, so its good to have both tools available. I haven't seen concepr slider LoRA specifically being used for poses, though conceptually doing something like seated<->standing or standing<->running as a concept slider would make some sense.
These are LoRAs being used normally, and the level of modification is controlled by varying LoRA strength.
The main difference is in the training procedure, where they try to only target specific attributes while leaving others unchanged.
You could probably use this to create LoRAs for a specific pose, but if you want to try out many different poses and freely adjust them, the more flexible controlnet approach is likely to be more comfortable.
You can only apply a LoRA (concept slider or otherwise) to the model (well. model “family”) it is based on, not to an image directly, its a model modifier than adjusts model behavior, not an image filter.
You can use SD with image as an input in place of or in addition to a prompt, and you could apply one or more LoRA (concept slider or otherwise) to the model when doing so.
> For those in the similar boat, it apparently means Low Rank Adaptation (for Large Language Models)
Well, the abbreviation expands to Low Rank Adaptation, but the article is about diffusion models, not LLMs, and LoRA is an model-modifier approach that applies to many classes of models, not just Large Languag Models.
Frankly, these acronyms are becoming absurd. I'm really hoping for somebody to build an insanely successful programming language called LOra, just for the sake of giving everyone nightmares.
"Artists spend significant time crafting prompts and finding seeds to generate a desired image with text-to-image models."
I wish there was a different description of those who generate art via AI than "artists". When ChatGPT writes me a story based on my prompts I'm still not an "author". Sorry, I know it's a tired argument already but it'll never stop bugging me.
First of all being labeled an 'artist' has little relation to the tools used to create 'art'. 'Art' by 'artists' does inlude the Sistene Chapel amf the Matthew Passion, but also trowing a bucket of paint at a canvas, wrapping a bridge, having ice melt and dragging a urinal into a museum.
That does not make you an artist whenever you spill ketchup on your shirt, wrap a Chrismas gift or pour yourself a scotch on the rocks.
Second, while you can indeed just type a prompt into Midjourney and some images will be generated, there are 'artists' using diffusion models to meticulously craft 'art' using hundreds of itrrations combining dozens of models and loras with inpainting. outpainting, recomposing and fusing, dtawing and more to come to a unique piece of 'art'.
Third, didn't we have the same thing before? Are DJ's musicians? Some most definetly are. Creating new music by adapting, restructuring. remixing and extending existing tracks, while others use turntables as a real instrument. Others just put on some records at a wedding.
It's about intention and context, and yes,
creativity and skill, not about the tools used.
I would also add that art is also "created" when you consume it. When we consume it, we generate some interpretation, feelings or imagery. This is the last step. That's internal, but this processing of art is also art.
That explain why some people find something as art and others as BS. As you say it's about intention and context, from the artist point of view and also from the consumer.
"Artist" in the context of image creation means you're the main supplier of the talent. In other words, you painted the picture yourself and spent time developing your talent. I can make a video recording of you making the picture from scratch with your own hand.
AI "artist" isn't an artist. It's someone who uses an external product to automate the talent for them by creating an average image based on samples created by artists, of which were curated by individuals with particular tastes. It's why AI art mostly looks the same.
It's also the reason a DJ a is called a disc jockey and not a musician. They are labeled differently to show the difference in the generation of the supplied content.
You might as well say that someone who Googles "picture of a dog" is an artist as well since they learned the ins and outs of the search engine. A better term for AI Artist would be something that mentions the collage aspect of it.
Artist is still going to be the right word with these kinds of tools because you're still adjusting the result to get the desired look. Even if it were just collage it would still be art.
You do realise many very popular artists of the past including Rubens, Raphael and others had large studios where their "apprentices" actually made the paintings. Especially when these studios hot big, how much of each actual painting was physically made by "the artist" and how much was dobę by the apprentices? Perhaps just a sketch, perhaps not even that, but the head artist just made suggestions not unlike the promotes of today.
They are all artists though regardless. They are actually doing the work and doing the actual painting and require painting skills. What they are painting it itself or where they got the idea from is irrelevant. They painted it, as in the physical work and talent to achieve the result.
In the case of AI Art, there is no point in the process where you are participating in the creation of the actual initial image unless the actual source/model is based of your own artwork that you created. What you are really doing with AI art is generating a concept based on a request you make (the prompt), and then modifying the result with other tools until you get what you want (inpainting masks, animate it, etc.).
The equivalent of this would be something of like a patron/commissioner and something like a sound engineer. You aren't creating the source material, but you can ask an AI art generator to create something based on your request, and then modify and tune it afterwards to your liking. It is more of like a producer/sound engineer/post-production role.
If you have sufficient input on the work in question, then it's a collaboration between the two of you even if you never personally hold a chisel. So, yes.
For a counterexample: suppose you're really good at sketching, and you go to the Louvre and copy out the Mona Lisa. Were you the sole artist of your sketch? Leonardo Da Vinci certainly wasn't drawing on your notebook.
Depends on the intention of what you're making - if it's something that exists for its own sake with commercial value as a secondary concern then you're an artist, if it's a product to spec and you're following the design/requirements from a client or a potential customer then you're a product manager.
Informally we usually call the person involved in the art-making process an artist. In your example, there is another person in the loop who is making the art.
I don’t think anyone is arguing to AI personhood yet, so it must be the user who is the artist.
If we want to add extra conditions, that seems fine, but someone else will have to define them. If it were up to me… I’d probably end up being called a gatekeeper.
It's semantics, but if you consider Jeff Koons to be an artist, then yes. AFAIK he has never (or at least when he was starting) used his own hands to fully create something, from the very beginning he hired people to do it for him.
The "Desired Look" can be considered the "artistic" part of art, while the production can be considered the craft.
Koons is the most extreme example I can think of, but there are plenty of others who got their start creating stuff themselves and then hired people to do the total of the work.
Is a director an artist, when he doesn't write the script, touch the camera, edit the film, or act in the movie?
I wish there was a different description of those who generate art via Word Processor than "artists". If they aren't impressing upon a cuneiform tablet I am not interested.
AI art and its modern tooling ecosystem is at a point now that it unironically takes more effort to generate an intentionally innovative AI image than it is to draw it from scratch.
You genuinely can’t believe that, right? An “innovative AI image” is created all the time whereas it’s much harder to paint an “innovative painting” due to the skill required and the well-tread medium. That’s not even getting into the fact that you can set up and really learn ComfyUI in a week whereas painting is a life-long pursuit.
How do you know the background/experience of the person you're responding to? And even if the person you're claiming has authority here were the worlds leading expert on generative AI, that wouldn't make them authorative on the difficulty of drawing an intentionally innovative image from scratch.
Regardless, the original comment was clearly not serious.
People honestly overcomplicate it, the variety you can get just out of base SDXL without even using loras or other models and comfy nodes is crazy once you get a feel of it but a lot of people make the mistake of not spending the time on it to figure out how to push it in the direction they want and instead think piling on a bunch of loras and an extra model is the key to getting something different.
Honestly, that happened to me. Was making some UI elements for a game, and tried to generate some. After a while, I was so tired of getting results that weren't quite what I wanted that I just drew them.
It certainly has its place, but the "its taking people's jobs" argument kinda fell apart for me after that moment
This discussion might be heavy on semantics, but I don't think you are wrong for bringing this up.
AI can be used as a tool to empower authors and artists to create more and/or better works, but it can also be used by a lazy student to finish their 2 page writing assignment in seconds.
The only thing AI will clearly do over the next few years is raise the bar. Beginner art or copywriting is already outclassed and assignments will assume access to AI tools, similarly how many assume internet access nowadays.
Nevertheless, I truly believe that there will always be space for human art... just look at chess, with engines far better than humans, what are the tournaments about? the players.
While I won't ever call myself an artist, there are people who do not just click and get an image. My workflow involves getting the right prompt out, then manual touch up of the images (sometimes drastically so) using Krita and a Wacom tablet, or composing scenes with 3D mannequins from CLIP STUDIO PAINT and then feeding them to ControlNet (up to several CNs at once), generating and touching up again.
I would argue there's a definite creative process here.
I completely agree with you. I think AI art is a good tool, but referring to the users as "artists" is confusing to actual practice. You aren't creating the content, but rather are dictating it like a patron or client. You are just telling an engine what you hope to see, in the same way someone might tell you what to paint while watching over your shoulder.
It's also not a tired argument. You are just posting in a place that is very pro tech and not art-oriented. If you posted this in an art forum you'd get the opposite reaction.
