(untitled)

In regard to AI's use in illustration(though you can extrapolate it to other mediums). Professional artists work with writers to convey intent. Some art styles are better than others at supporting nuance in writing, which has largely driven their development within otaku media. These nuanced art styles, encourage more sophisticated writing. Writing and art, have a mutually edifying relationship. An algorithm has no conception of intent applied within art, e.g. gesture, composition and characterization. All three, can be affected by every individual line. An algorithm which statistically composites images together, cannot produce anything with intent behind it, let alone on a individual-line basis. What do lesser artists have over an algorithm? Intention behind art can exist even at lower skill levels. It can come through via subconscious decisions even. The prompter may have an intent, but it can never be correctly expressed by the composite of images with generalized labels. Labels which cannot convey anything close to the full intent of their subject. A subject such as "drinking water", has certain intrinsic traits, but these do not include the gesture, composition and characterization, which allow art to describe narrative intent. How about the use of an algorithm to generate concepts? This is often used as the most "diplomatic" argument in favor of image generation's addition to the creative workflow. The reality is, a professional artist, can invent compelling concepts far quicker than a prompter can coax anything interesting out of a model. These models therefore add nothing in terms of expediency or quality to the creative workflow. Their utility is in allowing unskilled workers to cut corners in a project. Those with something to gain from the use of unskilled labor over skilled labor being normalized, will ceaselessly peddle the notion of their output being at least equivalent, and incentivize it within creative industries.

OP I present you a challenge. Try making a post about AI, except you say something that hasn't already been said 10000 times before. Hard mode: use less than 20 words. I'll start: what AI really needs is more room for an artist's input than a prompt. Your turn.

>>13184 I will not play by your bs rules. The truth can't be stated too many times, and everything must start from it. Your premise, that ai is useful in art, but just "needs" something more, is wrong.

What elements of your chosen image do you think represent non-replicable narrative intent OP? Do you think that non-AI art created through stochastic means are less valid for using randomness in their process? Do you think that ocean waves or snowflakes are not of aesthetic merit despite being simply a result of rules based randomness? >>13184 The corpo stuff mostly is like kicking dead whales down the beach but local AI tools have been getting more tunable, allowing for pose rigs, composition shapes, character/lighting/expression references and more iterative and segmented workflows. Still a long way from being able to fine tune them as precisely as drawing but it's getting there.

>>13236 >What elements of your chosen image do you think represent non-replicable narrative intent OP? Art is more than a collection of elements stuck together, although the element of nuanced linework is beyond the capabilites of image generation because it's not a single element, it's hundreds or thousands. Characterization and narrative intent comes from a deliberate synthesis of every element. >stochastic means Yes, that's just a novelty. >Do you think that ocean waves or snowflakes are not of aesthetic merit Their aesthetic value is in being a conceptual inspiration to artists, which only needed to occur once in history. They're not capable of having "merit".

Any original idea that gets a pass through AI is irreversibly corrupted and cheapened, even if entirely done by hand in its final form; the influence brought by the generated concept is a regression towards the mean.

>>13184 AI could enable creatives, if, for instance, it functioned as an animation studio for an inspired director otherwise obscured. >>13251 Generative AI is butchered culture, nothing more and nothing less.

>>13252 China failed to make a slice of life anime, with AI usage attempted as a last resort. https://note.com/eichan_sh/n/n1a24b97857a2

>>13252 Despite all the claims of AI cultists that their funny soykaf-generating box can animate, the actual result very often is stiff and lifeless even is technically correct. Like a month ago I saw a trailer for some small mesugaki-themed anime that used AI and it just felt wrong - characters looked very robotic and backgrounds were moving in nonsensical way during any action scene . It was just trailer so obviously it was supposed to show the best looking parts. I can't find it sadly rn because putting "Mesugaki AI anime" into google just throws at me tons of useless AI-generated images. Still, my point stands - AI will never be able to generate anything with satisfying accuracy and the best that prompt monkey can do is just take the "close enough" result and cope that it's exactly what they wanted. I guess it's good for quick corporate works but that already was heavily standardized and devoid of anything resembling emotion so it's just replacing one soulless crap with another.

i do think ai animations are pretty gross in their current form but do believe that there are a few areas of animation where generative ai can be utilized effectively in without greatly compromising the final product, like 1. drawing first passes of in-betweens (usually outsourced to cheap labor because of how tedious it is and how little artistic creativity goes into it) 2. mouth movements (like converting audio to a best guess for what mouth position should show on a frame, and letting the animators fix inaccuracies or make artistic tweaks if necessary) 3. converting sketches to backgrounds for unimportant scenes 4. maybe mockups there's probably more but as a guy who spent hours and hours drawing out frame-by-frame animations in flash when i was teen, that's the stuff that seems obvious, easy, and doesn't compromise too much on artistic integrity. god did i fuarrrking hate syncing mouths to audio unfortunately, the examples of ai animation are usually people generating the actual animation which always looks like soykaf.

>>13281 what are your thoughts on the Will Stancil Show? I only saw the first couple but seemed like a decent job as far as short garbage cartoons go. AFAIK it was sketched out by hand and then segments were generated by AI and edited/stitched together. Obviously not fantastic quality but for one person working fast seems powerful.

>>13282 It looks like soykaf and uses too much generative AI. Art style and movement isn't cohesive at all. Line work and perspective is particularly odd and bad. >Obviously not fantastic quality but for one person working fast seems powerful. There are already cheaper tools for letting one person push out poorly animated garbage quickly. For AI to be useful in animation it needs to let skilled people created good animation more quickly (which it should be capable of)

cluld we all post images of lain licking soykaf off of kylix's spincter?