#how to generate studio ghibli images

[glasierinc]

Studio Ghibli Art: Transforming Animation or Replacing Traditional Artists?

For more visit Our Blog,

Custom On-demand software solutions

Hire Android developer

Hire IOS developer

[technology-trends-by-mellisa]

Studio Ghibli Art: Transforming Animation or Replacing Traditional Artists?

For more visit Our Blog,

Custom On-demand software solutions

Hire Android developer

Hire IOS developer

[probablyasocialecologist]

Earlier this week, OpenAI launched its new image generation feature, which is integrated directly into ChatGPT and allows users to input more complex instructions for editing and organizing the presentation of the output. The first big viral trend to come out of the new service was users turning photos of family vacations, historical events, and pop cultural images into animated stills in the style of Studio Ghibli films. (The whole thing was a bit of a throwback to the heady days of 2023 when you would see AI influencers sharing photos of famous figures in the style of Wes Anderson films or whatever.) ChatGPT let users “Ghibilify” the images, so we got Ghiblified Hawk Tuah girl, Ghiblified Elon Musk (obviously), and so on. The issue here should be obvious. I won’t pretend to know exactly how Miyazaki thinks about modern generative AI systems—the tool he was commenting on was a cruder prototype—though one might venture to argue that he’d feel even more strongly about tools that further automate human art with greater ease, and often drive it further into the uncanny valley. Regardless, the man on record with likely the strongest and bluntest disavowal of using AI tools for art, is now the same man whose notoriously painstakingly handcrafted art is being giddily automated by ChatGPT users for what amounts to a promotional campaign for a tech company that’s on the verge of being valued at $300 billion. Sam Altman, OpenAI’s CEO, not only participated, changing his X avatar to a ‘Ghiblified’ self portrait, but insisted that this was the plan all along. Which in turn raises the specter of copyright infringement. Speaking to TechCrunch, a copyright lawyer very diplomatically said that while it’s unlikely infringement to produce images in the style of a studio, it’s “entirely plausible” that OpenAI’s models were trained on millions of frames of Ghibli films. He noted that it’s still an open question whether or not that in fact violates current IP law, or constitutes fair use, as the tech companies argue. On that front, judges recently dealt tech companies a blow, ruling in favor of Thomson Reuters that a pre-ChatGPT AI system was creating images that competed with the original material, and thus was not in fact fair use. OpenAI and Google, meanwhile, are desperately trying to win this battle, appealing to the Trump administration directly, and going so far as to argue that if they’re not allowed to ingest copyrighted works into their training data, China will beat the US in AI. Now, if—and of course this is a whopping if—OpenAI had consulted Studio Ghibli and its artists on all this, if those artists had consented and say reached a licensing deal before the art and frames from their films were ingested into the training data (as is pretty apparently the case), then look, this would indeed be a bout of generally wholesome fun for everyone involved. Instead, it’s an insult.

[...]

OpenAI and the other AI giants are indeed eating away at the livelihoods and dignity of working artists, and this devouring, appropriating, and automation of the production of art, of culture, at a scale truly never seen before, should not be underestimated as a menace—and it is being experienced as such by working artists, right now.

27 March 2025

[catzeart]

Ghibli artstyle Giyushino

Here's a Giyu and Shinobu fanart I did, inspired by Howl's Moving Castle, but I also need to talk about something.

I am strongly against AI filters and AI generated "art." Idc if people make and use them for fun, they're harmful for artists.

There has been a debate on the "Ghibli style AI images" because the co-founder of studio ghibli, Hayao Miyazaki, said "I would never wish to incorporate this kind of technology into my work at all" and "It is an insult to life itself ", so making those "Ghibli AI images" is literally going against his wishes.

Not to mention how harmful it's been the sudden increase of the AI usage for the environment.

Think about it and be better 👍

Here you can watch the speedpaint:

Please support human artists 😔

[windvexer]

But considering then that maybe one should learn a form of banishing, just in case, but doesn't relate to the golden down practices, what could be a practice of banishing that is more connected to witchcraft ?

We are in reference to this ask about whether or not the LBRP is required learning for all sorcerers & practitioners (it is not).

Someone asked me for my opinions and I'm giving them! Please understand this to be a post full of my personal opinions and methods.

I think a fine way to regard any practical sorcery is to consider it to be a mundane action extended into the spirit world.

Therefore the best way for a witch to deal with banishment is to ask what you if you were in a nice Studio Ghibli anime where magic is tangible. If a rambunctious pig spirit were tearing through your house, knocking over furniture, what would you do?

Banish for your needs based on what you have. Any banishment spell is better than no banishment spell. Here are a few for the intrepid witch:

Ask It To Leave

This is a good starting operation, especially if you have ethical concerns. Especially helpful for troublesome household spirits and energies.

Go to where It is. If that is not possible, create a sympathetic image (drawing, sigil, poppet, etc.; then correctly consecrated*).

Speak to the image and tell it firmly and sternly to leave. Do not ask, do not show your belly. "You have got to stop coming to morning meetings, Greg. You have better things to do and you are not helping. I am sick and tired of hearing you before lunch, Greg. Stop doing it."

Open the Door and Smack It With a Broom

Another good starting operation, but you must have access to the location; best reserved for spirits or intruders.

Open all the doors and windows you can. Speak a prayer over the broom, vacuum, or mop; invite it to cast off its lampshade and glow with the vigor of four hundred generations of exasperated grandmothers.

Sweep out the house, all the while staying intent on the idea that the intruder is going to be chased out.

Close doors and windows after, as desired.

(Modifications on the above: blessed water in a spray bottle, rolled up newspaper swatting the air, and so forth; the studious witch will observe that if a place is consecrated to be other than what it is, things on other strands of fate can be swept away.)

Cast Dispel Magic (wizard 3 abjuration)

A fine early step, but it draws a line in the sand. It's more like a temporary ward, but it'll do in a pinch. It's also energy intensive, but requires no materials.

Using energy work, root yourself down into the earth. Call up a great deal of power from the earth into your body.

Coalesce a ball of power in your abdomen (or wherever suits you best; you must already know how to work energy in this matter to use this method).

In your preferred method, program the energy to be immensely banishing; envisioning ultraviolet flame can work well.

Expand the ball of energy outwards from your center so that it grows and eclipses the space around you, sending the unwanted thing out and away.

If possible, then work the far boundary of the energy sphere to become like a wall that can't be crossed over again.

Call the Magistrate

Not so harsh, but certainly drawing a line in the sand. This can be performed not only on spirits or intruders, but also on situations (to banish unfair treatment, etc), on people, and so forth.

Take one or three dried Bay Laurel leaves, or the equivalent crumbled. Say, think, or sign, "Bay Laurel, I call you here today to assist with removing an unwanted force."

Read over them the Orphic Hymn to the Sun, all the while envisioning that the leaves begin to glow with an immensely bright light, as if you're staring at the sun.

At the completion of the hymn, politely address the leaves and explain to them exactly what you would like chased away. Ensure you clarify if this thing may come back later, or never at all, and how far away from you it should go.

When you've said you part, seal the spell (classically, "as my will, so mote it be").

Use charcoal disks or your preferred method to burn the leaves. This should be done as close as possible to the thing intended to be banished. If burning is not an option, put them in some tap water and boil it on the stove until the scent diffuses.

(To further energize: read the hymn between three and nine times, each time following up with fervent prayers)

Call the Mob

Harsh. For use when you do not want to be polite. Can be directed at anything, but be sure there is no concern of behavior escalating; this is an aggravating spell.

Take one or three dried red peppers, or a teaspoon of red pepper flakes. Say, think, or sign, "Red Peppers, I call you here today to assist with removing an unwanted force."

Read over them the Orphic Hymn to Mars, all the while envisioning that the peppers ignite into a black and scarlet flame that's like hellfire.

At the completion of the hymn, rambunctiously address the peppers and explain to them exactly what you'd like chased away. Encourage the peppers to chase after the thing like the baying hounds of hell, to chase it to the ends of the earth, and past the earth, and so far away that the thing cannot be returned.

When you've said you part, seal the spell (classically, "as my will, so mote it be").

You should not burn the peppers at all unless you can do so outside, because breathing in pepper smoke is Bad. But fire greatly improves this operation. If possible, arrange the peppers around a candle and burn the candle to activate the spell. Otherwise, use the simmer pot method.

---

*Consecrated: In this context, to assign a new magical identity, purpose, and fate. This may be done organically during its creation, or all at once with a ritual. A poppet shouldn't be used in sympathetic magic until it has been magically given the true identity of the thing you want it to represent.

[kozachenko]

[Click image for better quality]

I FIGURED OUT A WAY TO FUCKING MAKE THE IMAGE SMALLER FOR POSTING ON TUMBLR WITHOUT SACRIFICING THE ACTUAL QUALITY OF THE IMAGE OH MY GOD

Ok so, what I did is go into the clip studio paint file, make a new file, copy and paste the group in the original file, merge everything, get rid of the extra stuff outside of the canvas, and then make the flattened image smaller and crop the canvas. Once you have that, export it and you're done. This helps maintain the actual quality of the image and also helps shrink the file size down to something actually postable (if anyone has a better way of doing this please tell me)

[Edit]: Ok I guess posting something to Tumblr just naturally compresses the image a bit more somehow because I'm looking at it now and zooming in too much makes it a bit blurry so I'm still gonna have to futz around with image quality for future pieces oof

Artist's Note:

I'm so glad I figured out a way to do this because I like working on a big canvas so I can get as much detail in as I possibly can. Only problems are how laggy it gets while drawing lol.

I had an idea for a drawing with Reimu and Zanmu because I really like thinking about their potential dynamic a lot. I also wanted an excuse to draw Zanmu again but in my normal rendering style because last time I drew her she was in my more sketchy style with generally flat colours so I wanted to draw her again. Speaking of, looking at the sketch for this is a jumpscare that I never enjoy seeing, like, man am I glad I didn't use those for my final piece.

Also about her spear. I was originally gonna make it like the ones she had in game, but it kinda threw off the whole piece. It was too big, too blue, and too flat, so I just went "fuck it" and gave her a different one instead. My headcanon justifying this is that the ones she uses in game are for danmaku battles whereas in any other fight she just uses a proper yari, or she still uses the yari and just makes it all glowy to power it up, maybe both lol. I pulled as much inspiration as I could from Sengoku era spears, and even put in some blue into the decorative part of the spear and also added a little skull to pay tribute to the original spear. Also, in my research I saw some art of izanami and izanagi making japan and saw that the yari izanagi has had a little decorative tassley thingy on it so I took some inspo from that and just made it one of Zanmu's tassles (Idk when that art was from or if the spear was still accurate to Sengoku period Japan but hey, probably the same reasons Eirin puts little bow ties on her arrows, it's just for personalization purposes).

I love rendering hair and clothes so much omg, while I like the super curly hair Zanmu, the longer, wavier hair suits her better for this drawing (I imagine it only does that like how Ghibli characters hair moves when they feel angry lol). I love making Zanmu's hair all messy and crazy, as well as giving her grey hairs, this woman has aged like a fine wine. Also, if the hem on the ends of her sleeves, top of her shirt, and her pants look like gold to you, that's because it is! It's fairly light so she's not collapsing under the weight, but it's gold! (I don't care how impractical it is, it's just cool). Not the undershirt though, it's made of a gold fabric. I had a cute idea with Reimu's hair to make it have a red shine to it. I also changed up Reimu's outfit so it isn't just a blob of red. I like it a lot when Reimu's skirt and outfit is segmented into different layers, so I wanted to incorporate that.

I tried to draw their hands differently as well, but IDK how noticeable that is. Also, I am super happy with how the side profiles for the two of them turned out, I used to struggle a lot with how to make the side profile of a character actually look like the character, so I'm really happy that they actually look like themselves.

Also added in the tree and rocks in the background as an homage to Zanmu's character art in Touhou 19, just because I was getting kinda stumped on what to do with the background lol.

In terms of a story idea with Reimu and Zanmu, idk why but the potential plotline of Zanmu wanting to ascend to godhood is so fascinating to me. Like, it is very possible that if she just convinced everyone she was a god (which would be very easy for her to do), she would become one in a heartbeat. Also, if she were to become a god, with her ability to return stuff to nothing, could she hypothetically get similar abilities to (Jojo Part 5 spoiler btw) GER? Like, idk about the death timeloop stuff, but the concept has been haunting me every night as I have been trying to find loopholes in GER's ability for a while now ( for no reason in particular). Back to the main topic, I imagine that she would probably tell Reimu that if she were to become a god she would take over the Hakurei shrine since the god there might as well be dead, and Reimu just says to her, "Over my dead body bitch." Like, I have no idea how to summarize their dynamic but like, it's the type of hero-villain dynamic where the phrase "We're not so different, you and I" would definitely be a phrase said during a fight. I think that if another IN style game were to release, Reimu and Zanmu would be in a team together. They could also have an interesting mentor and pupil kind of dynamic. Can you tell that Zanmu has been charging my mind rent these part few months? Like, instead of living in my head rent free, she kinda just uno reversed the whole situation and now she's the one charging me rent. What happens if I get evicted from my own brain? Actually, scratch that, I don't think I wanna know.

[canmom]

oh no she's talking about AI some more

to comment more on the latest round of AI big news (guess I do have more to say after all):

chatgpt ghiblification

trying to figure out how far it's actually an advance over the state of the art of finetunes and LoRAs and stuff in image generation? I don't keep up with image generation stuff really, just look at it occasionally and go damn that's all happening then, but there are a lot of finetunes focusing on "Ghibli's style" which get it more or less well. previously on here I commented on an AI video model generation that patterned itself on Ghibli films, and video is a lot harder than static images.

of course 'studio Ghibli style' isn't exactly one thing: there are stylistic commonalities to many of their works and recurring designs, for sure, but there are also details that depend on the specific character designer and film in question in large and small ways (nobody is shooting for My Neighbours the Yamadas with this, but also e.g. Castle in the Sky does not look like Pom Poko does not look like How Do You Live in a number of ways, even if it all recognisably belongs to the same lineage).

the interesting thing about the ghibli ChatGPT generations for me is how well they're able to handle simplification of forms in image-to-image generation, often quite drastically changing the proportions of the people depicted but recognisably maintaining correspondence of details. that sort of stylisation is quite difficult to do well even for humans, and it must reflect quite a high level of abstraction inside the model's latent space. there is also relatively little of the 'oversharpening'/'ringing artefact' look that has been a hallmark of many popular generators - it can do flat colour well.

the big touted feature is its ability to place text in images very accurately. this is undeniably impressive, although OpenAI themeselves admit it breaks down beyond a certain point, creating strange images which start out with plausible, clean text and then it gradually turns into AI nonsense. it's really weird! I thought text would go from 'unsolved' to 'completely solved' or 'randomly works or doesn't work' - instead, here it feels sort of like the model has a certain limited 'pipeline' for handling text in images, but when the amount of text overloads that bandwidth, the rest of the image has to make do with vague text-like shapes! maybe the techniques from that anthropic thought-probing paper might shed some light on how information flows through the model.

similarly the model also has a limit of scene complexity. it can only handle a certain number of objects (10-20, they say) before it starts getting confused and losing track of details.

as before when they first wired up Dall-E to ChatGPT, it also simply makes prompting a lot simpler. you don't have to fuck around with LoRAs and obtuse strings of words, you just talk to the most popular LLM and ask it to perform a modification in natural language: the whole process is once again black-boxed but you can tell it in natural language to make changes. it's a poor level of control compared to what artists are used to, but it's still huge for ordinary people, and of course there's nothing stopping you popping the output into an editor to do your own editing.

not sure the architecture they're using in this version, if ChatGPT is able to reason about image data in the same space as language data or if it's still calling a separate image model... need to look that up.

openAI's own claim is:

We trained our models on the joint distribution of online images and text, learning not just how images relate to language, but how they relate to each other. Combined with aggressive post-training, the resulting model has surprising visual fluency, capable of generating images that are useful, consistent, and context-aware.

that's kind of vague. not sure what architecture that implies. people are talking about 'multimodal generation' so maybe it is doing it all in one model? though I'm not exactly sure how the inputs and outputs would be wired in that case.

anyway, as far as complex scene understanding: per the link they've cracked the 'horse riding an astronaut' gotcha, they can do 'full glass of wine' at least some of the time but not so much in combination with other stuff, and they can't do accurate clock faces still.

normal sentences that we write in 2025.

it sounds like we've moved well beyond using tools like CLIP to classify images, and I suspect that glaze/nightshade are already obsolete, if they ever worked to begin with. (would need to test to find out).

all that said, I believe ChatGPT's image generator had been behind the times for quite a long time, so it probably feels like a bigger jump for regular ChatGPT users than the people most hooked into the AI image generator scene.

of course, in all the hubbub, we've also already seen the white house jump on the trend in a suitably appalling way, continuing the current era of smirking fascist political spectacle by making a ghiblified image of a crying woman being deported over drugs charges. (not gonna link that shit, you can find it if you really want to.) it's par for the course; the cruel provocation is exactly the point, which makes it hard to find the right tone to respond. I think that sort of use, though inevitable, is far more of a direct insult to the artists at Ghibli than merely creating a machine that imitates their work. (though they may feel differently! as yet no response from Studio Ghibli's official media. I'd hate to be the person who has to explain what's going on to Miyazaki.)

google make number go up

besides all that, apparently google deepmind's latest gemini model is really powerful at reasoning, and also notably cheaper to run, surpassing DeepSeek R1 on the performance/cost ratio front. when DeepSeek did this, it crashed the stock market. when Google did... crickets, only the real AI nerds who stare at benchmarks a lot seem to have noticed. I remember when Google releases (AlphaGo etc.) were huge news, but somehow the vibes aren't there anymore! it's weird.

I actually saw an ad for google phones with Gemini in the cinema when i went to see Gundam last week. they showed a variety of people asking it various questions with a voice model, notably including a question on astrology lmao. Naturally, in the video, the phone model responded with some claims about people with whatever sign it was. Which is a pretty apt demonstration of the chameleon-like nature of LLMs: if you ask it a question about astrology phrased in a way that implies that you believe in astrology, it will tell you what seems to be a natural response, namely what an astrologer would say. If you ask if there is any scientific basis for belief in astrology, it would probably tell you that there isn't.

In fact, let's try it on DeepSeek R1... I ask an astrological question, got an astrological answer with a really softballed disclaimer:

Individual personalities vary based on numerous factors beyond sun signs, such as upbringing and personal experiences. Astrology serves as a tool for self-reflection, not a deterministic framework.

Ask if there's any scientific basis for astrology, and indeed it gives you a good list of reasons why astrology is bullshit, bringing up the usual suspects (Barnum statements etc.). And of course, if I then explain the experiment and prompt it to talk about whether LLMs should correct users with scientific information when they ask about pseudoscientific questions, it generates a reasonable-sounding discussion about how you could use reinforcement learning to encourage models to focus on scientific answers instead, and how that could be gently presented to the user.

I wondered if I'd asked it instead to talk about different epistemic regimes and come up with reasons why LLMs should take astrology into account in their guidance. However, this attempt didn't work so well - it started spontaneously bringing up the science side. It was able to observe how the framing of my question with words like 'benefit', 'useful' and 'LLM' made that response more likely. So LLMs infer a lot of context from framing and shape their simulacra accordingly. Don't think that's quite the message that Google had in mind in their ad though.

I asked Gemini 2.0 Flash Thinking (the small free Gemini variant with a reasoning mode) the same questions and its answers fell along similar lines, although rather more dry.

So yeah, returning to the ad - I feel like, even as the models get startlingly more powerful month by month, the companies still struggle to know how to get across to people what the big deal is, or why you might want to prefer one model over another, or how the new LLM-powered chatbots are different from oldschool assistants like Siri (which could probably answer most of the questions in the Google ad, but not hold a longform conversation about it).

some general comments

The hype around ChatGPT's new update is mostly in its use as a toy - the funny stylistic clash it can create between the soft cartoony "Ghibli style" and serious historical photos. Is that really something a lot of people would spend an expensive subscription to access? Probably not. On the other hand, their programming abilities are increasingly catching on.

But I also feel like a lot of people are still stuck on old models of 'what AI is and how it works' - stochastic parrots, collage machines etc. - that are increasingly falling short of the more complex behaviours the models can perform, now prediction combines with reinforcement learning and self-play and other methods like that. Models are still very 'spiky' - superhumanly good at some things and laughably terrible at others - but every so often the researchers fill in some gaps between the spikes. And then we poke around and find some new ones, until they fill those too.

I always tried to resist 'AI will never be able to...' type statements, because that's just setting yourself up to look ridiculous. But I will readily admit, this is all happening way faster than I thought it would. I still do think this generation of AI will reach some limit, but genuinely I don't know when, or how good it will be at saturation. A lot of predicted 'walls' are falling.

My anticipation is that there's still a long way to go before this tops out. And I base that less on the general sense that scale will solve everything magically, and more on the intense feedback loop of human activity that has accumulated around this whole thing. As soon as someone proves that something is possible, that it works, we can't resist poking at it. Since we have a century or more of science fiction priming us on dreams/nightmares of AI, as soon as something comes along that feels like it might deliver on the promise, we have to find out. It's irresistable.

AI researchers are frequently said to place weirdly high probabilities on 'P(doom)', that AI research will wipe out the human species. You see letters calling for an AI pause, or papers saying 'agentic models should not be developed'. But I don't know how many have actually quit the field based on this belief that their research is dangerous. No, they just get a nice job doing 'safety' research. It's really fucking hard to figure out where this is actually going, when behind the eyes of everyone who predicts it, you can see a decade of LessWrong discussions framing their thoughts and you can see that their major concern is control over the light cone or something.

[deepdreamnights]

Vidu and the Quest to Make More Toons

So, a ways back I talked about Minmax, but I've been trying out basically all the video generators looking for the tools I need, and low and behold this week I find out I've been accepted into the Vidu Artists program now, wherein I get credits and access to access their cooler features in in exchange for... talking about the tech and how I use it.

Well twist my arm. I shall endeavor to be objective and informative despite free stuff (a challenge my spirit needs practice withstanding if anyone else wishes to test me)

So let's talk Vidu.

(outside of being converted to gif, no animations in this post have been cut or edited)

Also, everyone say hi to Maureen the Lizard Queen, every hero needs an evil queen that really wants in his pteruges, and she's that for TyrannoMax.

Vidu's got a bit more oomph under the hood than MinMax (no shade to MinMax, they're brand new and very promising) and it's way too early to be picking winners when it comes to video.

Anyhow, basic features that are nice include the options to upload start and end frames, options for a 4 or 8 second duration (more about that later), and a cleanup/upscale. Credits line up more or less with seconds. 4 credits for a 4 second clip, 8 for an 8 second, and again at upscale. It's straightforward in a way a lot of services aren't.

Apetomic Pyle, done on the fast settings. (not to shabby still, and it gave him monkey legs which a lot of systems balk at)

If you're on the $30/mo tier, you can choose to do a double-cost "quality" over "speed" option. Thankfully, the artist program gets me access. Since there's not yet a seed option it's hard to do a direct comparison, but the quality is going to be a must if you're doing anything that looks like cel. Much cleaner, much smoother.

(4 and 8 second quality gens)

One of the nicest features is the character reference feature. Basically it's like Midjourney's --cref, but with a very strict adherence to character details.

The above images used reference shots of Maureen and Dr. Underfang, and it got the stripes on Underfang's tie right in basically every gen. That's a ridiculous level of character model adherence and, for my purposes, all but essential.

It did misinterpret Maureen's undertail coloration for a sort of fin or drape, but the shot I used was oddly cropped, and sometimes stuff like that happens with gen AI. Given my measuring stick for errors is the era of animation I'm emulating, whatever does slip through is only going to make it more authentic.

There is a limitation in that character-reference and text-only prompts default to 16:9 presently with no options to adjust, but some room to pan is always handy and most people are going to be outputting for phone and not outdated CRT televisions, so, it's understandable it'd be a lower priority feature for the devs.

Walk cycles! By Saint Eniac it's a miracle!

On the left we have one prompted with TyrannoMax's control art, and on the right we have one using that art as the starting frame (4 and 8 seconds, respectively).

Way More details under the fold.

Vidu likes a hefty prompt.

A lot of detail and evocative language helps, and older prompting tricks like mojo-jojoing important concepts are back. For the Max walk cycles above I used:

1986 vintage cel-shaded cartoon character walk cycle. The orange dinosaur-anthro wearing blue gladiator armor walks toward screen right, the camera tracks him, holding him in center-frame. He completes a full, brisk walk cycles from the side view. He walks boldly, back straight, head high, heroic. His tail sways behind him as he moves. The whole clip has the look and feel of vintage 1986 action adventure cel-animated cartoons. The animation quality is high, with flawless motion and anatomy. animated by Tokyo Movie Shinsha, studio Ghibli, don bluth. BluRay remaster. flat chroma-key green screen background

The potential for use with my Filmation-inspired technique is readily apparent. Both versions are on-model as much as any two shots in a 1980s action-figure shilling cartoon would be, some minor blurring to clean up in post but nothing serious. It should be pretty easy to extract the needed frames for looping and compositing.

Some Extra Points

There are the usual issues with hands, though more often than not it corrects my four-fingered anthros to having a human five-fingered hand. Buzby Spurlock animation was known for those kinds of inconsistencies, though. So an opening credits video is much less far off than it was at the last post.

It's also generally impressive how well it does with my dinosaur characters. Non-humanoid dinosaurs are difficult for most image generators, much less anthrosaurs in a vintage aesthetic. Vidu has yet to override the character art to give Underfang or Max the Jurassic Park style t-rex jaw, which is something both MJ and Dall-E 3 have trouble with.

Human characters like Kitty Concolor here, much more stable.

As always, clips are curated. I didn't choose my absolute best ones (gotta have something for the videos), and I'm working on a fun series of jank reels across all the generators.

[kinmokusei-stars]

🐕💎 Inuyasha and Kouko in the style of studio Ghibli! (100% Human drawn)

I've seen some other artists do pieces in the studio Ghibli style to protest the recent trend of AI generated images (I'm not even going to call it AI art), and I thought it was a wonderful idea! So here's my little quick piece of InuKou in the Ghibli style!

This was all drawn with my own two hands, from sketch to final piece! I colored it, shaded it, and added all of the effects and overlays to give it the old school texture and coloration myself. It took me about an hour and 25 minutes from start to finish, but it was incredibly worth it!

There's something so rewarding about making something yourself, creation is really such a beautiful process. It's never perfect, but that's what makes it so special. My lingering style and slipups make it real and special. ( ´ ꒳ ` )

I've always been a massive Studio Ghibli fan, so drawing these two in that style was really fun! (ﾉ´ヮ`)ﾉ*: ･ﾟ

I referenced Ashitaka from Princess Mononoke for Inuyasha, and Spiller from The Secret World of Arrietty for Kouko! (I had actually thought Spiller was a masculine girl when I saw Arrietty for the first time, so he was definitely my first thought for a reference for Kouko. I've always liked him a lot lol)

It's not perfect, to be sure, but I actually really love how it came out for a first attempt! I like how different from normal they look in this style, and I had actually sketched out two front profiles for them too before settling on this sketch instead!

I know I could've made Kouko look more like Sophie or Princess Mononoke, but Spiller was really my favorite reference point I could've picked for her. LMAO Her face being a lot softer and more blocky looking while Inuyasha's is a lot more angular and has more points is just a really cute contrast to me-

If I had to pick another character to reference for Kouko, though, it'd 100% be Nausicaä. ( ´ ꒳ ` )

[whitewallskyhigh]

10th Eid Later.

An AI-generated image inspired by the art of Studio Ghibli— a soft tribute that captures how I like to remember our last Eid together.

This marks the tenth Eid without you, Abah. A whole decade. Somehow, that number feels surreal—a milestone I never imagined having to count.

There’s something about Eid that always brings you back to me in the quietest, yet most powerful way. The sound of the takbir, the chaos of everyone getting ready to head out—and especially that warm buzz when the house slowly fills up with your grandchildren coming home. That was your favourite part. You were always the most excited one whenever we gathered for Raya, the one standing by the door, grinning as each family member arrived. That image of you—joyful, proud, content—never leaves me.

I know I don’t talk about you a lot these days. But that doesn’t mean you ever slips from my mind. In fact, it’s in the quiet wins, the moments of growth, the milestones reached, that I feel and miss you the most. Every time I achieve something, there’s a part of me that still whispers, “I wish you were here. I wish I could share this with you.”

There are so many things I’d tell you now—not for validation, but just to see the pride in your eyes, to hear you say you’re proud, to feel that rare kind of unconditional love that I’ve yet to feel again from anyone else. Ten years—And still, there are days when I’d give anything just to sit with you just for a few minutes.

To anyone who read this, if you still have your parents around—cherish them. Truly celebrate them while you can. Let them know you see their efforts, their love, their presence. Don’t wait for a milestone, or a perfect moment. Sometimes, the only thing that matters is knowing you made them feel appreciated while they were here.

Selamat Hari Raya Aidilfitri to all my Muslim friends. I hope your Raya is warm, filled with meaning, and spent with the people who matter most.

[the-s1lly-corner]

I'M SORRY I KNOW I SHOULD'VE LIKE PUT THIS IN THE SAME REQUEST BUT AFTER I READ YOUR TIMXDECEASED!READER I GOT AN IDEA..

BUT IDK HOW THIS WORKS LIKE WHAT IF SHE GOT REVIVED OR SMTH (OR LIKE IDK SHE DIDN'T EXACTLY D*E JUST WENT MISSING OR SOMETHING BUT GOT DECLARED DEAD?)

AND BTW

I love the way you write and thank you thank you so much for Doug my request:3

Remember to rest and stay hydrated mwa I love you!!<333

-🙀 anon

Tim x reader who went missing but returns!

UEUEUEUEUE thank you!! i was so nervous that the post was going to be kind EUGH!! since im rusty with MH and my brains foggy on the lore + still experimenting with how i write the og/mh versions of tim !! admin grew up with creepypasta first marble hornets later (though its been a blast getting into mh!! yahoo!!) that said i hope you enjoy this as well!! previous post/post in question!

just like a lightning bolt i was struck with the image of tim and reader hugging, studio ghibli style. you know. like getting INTO it

though.... would it be in character? in not sure, actually..! because on one hand i can see him being happy to see you still kicking, after being supposedly "dead" for lord k nows how long, but i can also see him cautious... like are you a threat? are you going to pull some stuff? i think it depends on how far into the whole mess of MH that this would take place in

thinks

god know because you know how in the other post i mentioned that he would make a little memorial... thing for you. like its just a space somewhere with your picture and some stuff you like/had. thats going to be fun to explain to you. probably takes it down when youre confirmed to still be alive

do not tease him about it. i do think that would actually cause some issues. like i thought about this as a joke but can you imagine how messed up that would be, to try to joke with him about that?

therapy. you guys both go to therapy. i mean he needed it even before you showed back up, but i doubt you just suddenly coming home is going to erase all the grieving he went through

"youre just as beautiful as the day i lost you"/ref or however the quote goes

oooooooouuuugh imagine its been so long and you guys have the rekindle your relationship if you guys want to make things work

i dont know, the admin just enjoys tropes like that. same energy as the "we knew each other in a past life and have once again found our way to each other" but in a different font... kinda...

if this is post-MH you guys both grieve together over all that was lost/who had died, as well as generally trying to recover

i do think that after the initial shock he would ask a few questions... though im not actually sure if he would interrogate you... i can see both, actually. on one hand he wants to know exactly what happened to you and where youve been, but on the other hand hes just so exhausted that he doesnt think he can handle the truth for the foreseeable future

baby steps, you know

[unknownarmageddon]

Now playing: Hold Me Like a Grudge; Fall Out Boy

| 2:17 ————————— • ————— 3:36 | << ⏸︎ >>

wanna see furry art and original characters?? head over to @armageddonunknown!!!!

More information below!

primary info (the important stuff to read if you plan on following me):

- My main interest is UTMV but I’m also really big on fall out boy, green day, hozier, nine inch nails, st. vincent, the wrecks, set it off, various other bands, the QSMP, adventure time, fullmetal alchemist brotherhood, studio ghibli films, horror, pokemon, twin peaks, and several video games (namely warframe, though many other as well)!! and just a variety of other stuff. you will get all of my bullshit

- As of now I do NOT take art requests or commissions, so please don’t ask. (i may be open to the idea of art trades or collabs with friends/mutuals) - Also absolutely do not claim my art as yours on any site!!! you can use my work only for personal stuff like pfps, banners, etc. as long as there is explicit credit. however, my ocs and sonas, and art i’ve made of them, are not for others’ personal use unless i know you well (fanart is fine). asking beforehand is also very very encouraged if you want to use my art for something. thumbs up emoji

- as a general warning I will occasionally reblog and/or post, create, etc things that contain blood and gore, disturbing imagery, violence, and similar themes, and several of my aus will more often than not include these as well

- i don’t have a set dni i’m very big on blocking and moving on. thumbs up emoji - There will be absolutely NO dreammare, frans, or fontcest, or any similar ships on my blogs, because they personally make me very uncomfortable, but lots of sanscest stuff, so. obviously don’t follow if that’s not your thing. but dont, in any capacity, talk to me about ship discourse i legitimately could not care less how someone engages with fiction as long as no one’s hurting anyone. i am aware of who i’m following and i cater my own experience. thumbs up emoji

main things i’ve written (all kross-based):

- ⭐️ Sirius (Ongoing; 14 chapters)

- Bathroom Sink (Drabble)

- Christ Alive (One-Shot)

- Hope You’re Not Too Mad (One-Shot)

links and tags:

- UT AU Masterpost ; has information, references, etc, for the majority of my original aus and aus i co-own with friends (i recommend you check this if you’re looking for something specific, i promise it’s made to be helpful)

- AO3 account

- #armageddon art ; art that’s mine tag (mostly fanart)

- #wip ; unfinished snippets of whatever drawing i’m working on at the time

- #rambles ; text posts tag

- [this used to be #armageddon rambles woah, so that’s where most of the other things i’ve said are]

- #answering asks ; self explanatory

- [asks are sorted via “[url] asks” and “anon asks”]

- #headphones emoji ; my friends send me a lot of songs to listen to, so i started reacting to them under this tag!

- #sona ; main sona tag

- #sheepsona ; main fursona (finn) tag

- #fursona ; second main fursona (lazarus) tag

- #jimmy ; jimmy tag

- #armageddon’s fanfics ; tag for shit i’ve written

- #sirius ; tag for my main ongoing fic

- sheep’s head ; tag for one of my own original projects that i am gradually expanding

- #creepy stuff ; tag for horror/surreal-adjacent art i’ve reblogged and enjoy

- [there will be blood, gore, and just generally dark subjects under this tag, and i typically don’t tag specifics for each thing i reblog, so feel free to filter this one as needed]

- #cool ass forests ; forest photos (and some art) i think are very very neat :]

- #banger art ; tag for more general art i find rad

- [all other interest-related tags are just the thing, ie #fob or #birds or #studio ghibli or whatever. typically i try to stick to using abbreviations.]

Last image (left) from psycho-chair!! pete + patrick gifs from glassofpumpkinjuice, princess mononoke from filmtvtoday, twin peaks gif from inthedarktrees; fob blinkies from here; pony town gif at the very top from chair; trans beam cross image from jakei

[hoursofreading]

The flood of Ghibli-style images, delightful at first, leads to a “semantic satiation”, Erik says. A feeling of emptiness. Ed Newton-Rex, who champions creators’ rights, called it “the biggest art heist in history.” Here’s how I see it: in some cases, this kind of approach can actually increase awareness of an artist—their style, their work, their world. A Ghibli-style portrait of me doesn’t replace the experience of watching a Studio Ghibli film or engaging with other human-made art. If anything, it invites curiosity. We saw a similar pattern in the early internet era, when fan-fiction exploded online. Rights owners initially sought to exterminate it, pursuing cease-and-desist with gusto, rather than recognising it as signs of a deepening loyalty and the emergence of a remix culture that could extend a franchise’s life. It’s hard to imagine someone seeing a Simpsonized version of a person and thinking, “That’s enough—I don’t need to watch The Simpsons anymore.” More likely, it sparks nostalgia or interest, prompting them to seek out the real thing. But that connection isn’t automatic. When a visual style becomes widely replicated without context—like with Ghibli-fication divorced from the actual narratives and themes of Ghibli films—it risks becoming hollow. This highlights where the real value of art lies. If style alone becomes a cheap, easily generated commodity through AI, then human creativity will have to differentiate itself in more meaningful ways—it will need to move “up the stack.” That shift points toward a renewed emphasis on what AI struggles to replicate: conceptual richness, original storytelling, personal perspective shaped by lived experience and transparent creative processes that reveal intent and authorship. In a world awash with convincing fakes, authenticity—real, verifiable and human—becomes more valuable than ever. And that could reshape how we create and consume art, with greater appreciation for forms where the artist’s process is not just present but essential to the work itself. The irony, of course, is that Studio Ghibli is exactly that: a deeply human process, painstaking in its labor and swimming against the tide. Says Hayao Miyazaki, the creator, “We have chosen the opposite position to the trend.”

🔮 The Sunday edition #517: Ghibli, AI & semantic apocalypse; AI colleagues; China’s order; nuclear, hacker enzymes, intergalactic travel++

[joeeatsdvds]

Only Yesterday

it's the next edition in my ghibli collection collection and today it's only yesterday! now originally i intended to watch this film and write this post last night but neither of those things ended up happening since i got a little distracted while cleaning up some work i had been doing... but anyways it's not like this the first time i've made a post about a film i haven't seen for a dvd showcase friday! general impression of the film from both sides of the cover it looks quite wholesome with the misty pastel colours used all around the cover. from my limited knowledge of the film it features the main character, as an adult, travelling from the city back to her home town taking a trip down memory lane as she remembers the days of her youth. makes sense why the misty pastel colours are used since it's evoking that feeling of nostalgia the main character is feeling. speaking of the main character she's such a little cutie patootie on these covers!!

this is one of the more recent editions to my little collection being purchased at the same time as porco rosso, another ghibli film i haven't gotten around to watching yet that you'll see on a future dvd showcase friday.

inside of the case we've got a little insert advertising a giveaway optimum were running at the time to win some dvds. i'll talk more about it below but get used to seeing this little postcard in the ghibli collection because it features in quite a few of them in both postcard and other forms!

the disc features a screencap from the film which happens to be the same one used on the back of the cover. for whatever reason however they've made it so she's on the left and i do understand that they did this so she wasn't getting impaled by the disc hole but it ends up creating a lot of dead space on the right side of the disc. also because the colours of the disc are the light pastels it makes it so that the dvd and studio logos aren't really that visible. i do like the image but i think they could've probably chosen a better screencap from the film or just another design in general for the disc.

back to that little insert postcard! if you're in before april 20th 2008 you'll love this giveaway!! you've got the chance to win ten dvds from optimum releasing's film catalogue and all you've gotta do is post back the postcard to the po box listed or you can even email oprimum releasing for the chance to get a prize, how very modern!

[canmom]

it was a matter of time but pure-generative-AI animation has progressed to the point of looking 'not utterly shit'.

it's obvs a blatant ghibli pastiche, there's sometimes e.g. some inconsistent spacing (the leg on the walking cat for example) that I would criticise in a human animator, but the level of spatial and temporal coherence is much, much higher than it was before and it basically 'feels like' human animation, or at least a lot closer to it, than previous efforts that I've seen.

the process used involves a lot of 'human in the feedback loop' iteration - the artist used one generative model to produce still shots, and a second generative model to produce animations out of them, and additional generative models to get foley and music - but this was done in a weekend, compared to the weeks of work (months if you include preproduction) by experienced experts that it would take to produce comparable animation by the traditional techniques. the video generation is controlled by a text description of what you want to happen in the shot, but it doesn't seem like there is much fine-grained control over the details here.

traditional animation is a thoroughly collaborative process (unless you're Don Hertzfeldt), it takes large teams, and generally speaking only functions at all in the modern world by outsourcing large parts of the labour to countries where the cost of living is lower. the most celebrated (and higher-paid) roles in the process tend to be roles like storyboarding and key animation, where artistic choice is highest. animation lore is full of frustration from artists at this end of the pipeline, about the intent of a cut being lost through rushed or thoughtless inbetweening and compositing.

although image generation competes with this 'planning' stage, its unpredictability and lack of a connection to a 'personality' means I think that direction and key animation will still be a thing in animation to come. I'm less sure about inbetweening. current techniques for AI gen aren't there yet, but it doesn't seem to be far off the point where we can give an AI some keyframes and have it generate a reasonably convincing path between them, taking over the roles of cleanup, inbetweening, and compositing.

I doubt it will stop here either. the question will be how amenable it is to artistic control. for making an impressive-looking non-narrative twitter video you can just take a few generations that look good and staple them together, but these tools will only be useful for filmmaking if they can maintain consistency of character designs and respond reasonably to tweaking, without having cumbersome text input.

at the demoscene event this weekend, I was struck by how, as much as there is plenty of excitement about exploring new techniques, there was perhaps even more work being produced in the 'old school'/'mid school' categories targeting machines like the Commodore 64, Amiga, BBC Micro, or even modern low-level fantasy consoles like the TIC-80. new techniques are still being discovered for C64 demos, despite the hardware being decades old and no longer produced, and oldschool demos are still being made and appreciated by an audience who didn't necessarily grow up with the tech. not to mention the fact that we still draw and paint as furiously as ever.

art and medium are intimately connected; knowing how someone made something is a huge part of the context I bring to interpret it. so I don't fear that nobody will ever want to produce animation anymore.

but a demo is something that can be produced by a solo coder and generally not done for money. animation is produced in a variety of ways - there is a strong subculture of solo or small-team independent animators - but animated films are rarely made except by a whole studio working full time. I'm not sure how AI is going to affect that whole economic structure, and affect the future of this medium I love, but it's getting much closer to the day that we find out.

[soapver4]

Ghibli Geometry Homework

Merch Bubble: A petition for Studio Ghibli to best OpenAI by channeling the 2025 trend of cheery citrus-juiced images into an endeavor with more lasting impact — revamping the image of math and captivating young learners through geometry problem sets jazzed up with visuals and story contexts from its films.

Picture the following in their relevant aesthetic backdrops:

Estimate the height Spirited Away's Chihiro successfully descends despite her fear as she speeds down a rickety stairway section with 20 horizontal steps. Each gap between the steps is 5 units in slope and 4 units in width.

Spirited Away's No-Face tries out a circular mask 3 units in radius. Its holes for his eyes are 0.3 units in radius. How many times larger in area is his fake face compared to his fake eyes?

He next tries out a fancy circular mask which outline circumscribes tightly-packed, non-overlapping circles each 0.3 units in radius. The circles are made up of k rings of six circles surrounding one circle. Two of those hexagonally packed circles form holes for his eyes. How many times larger in area is his fake face compared to his fake eyes?

Witch Kiki in Kiki's Delivery Service is on a 10-unit long broomstick tilted at 45 degrees as she takes freshly baked cinnamon rolls to a customer. As she passes by a tall structure, she notices its tip is labeled 10, 000 units. The rolls are in a 2-unit long satchel hanging halfway on the broom. Since the temperature of the air affects how fast pastries go stale, she wonders: How far are the rolls from the ground?

A bunch of kids are squeezing onto the ginormous, fluffy tummy of the furry creature Totoro from My Neighbor Totoro. Predict how many kids can stay on the tummy given the relevant simplifications, assumptions and information. (You already got the drift.)

Make no mistake. There's much virtue in the uncluttered designs of typical math worksheets: faster concept rendering, faster information perception, lower workloads, lower technical requirements and lower production costs. One might sum them up as higher time, resource and cost efficiencies. Add to those pros a potential cultivation of academic asceticism on the learners' part. That would be efficiency as well, in the sense that we meet two student developmental goals (math and discipline) in one shot.

In eyeing these efficiencies, however, teachers and allied industry players may be neglecting their numerator terms, most of which concern learner progress. That is ironically where pure quantitative logic breaks down. We are all emotional creatures. That is all the more so, all things equal, in young people whose brains are still underdeveloped. Looking around, we can see many school leavers who have not matured in time to take full advantage of educational resources temporally and financially accessible only in early life stages. Nor have they met adult figures sufficiently skilled in the elusive art of mathematical motivation. By the time such school leavers gain an appetite for delayed gratification, austere thinking as well as for the inherent beauty in quantitative subjects, adulthood commitments and sociocultural barriers like ageist biases often deter or delay their reentry into the educational system, threatening their scholastic journey and any STEM career trajectory. There is therefore a case to be made for deep yet down-to-earth arts-based engagement of apathetic young learners, many of whom struggle to perceive the relevance of abstract fields like geometry and find math problems in general mundane, through instructor-independent means. The emotional resonance and relatability of Studio Ghibli's works — evinced through their box office successes and the controversial generative art trend applying a warm, effusive and rustic Ghibli style to personal images — would make them powerful helpmates in battles against math hate viruses, which feel as far-reaching as influenza bugs.

Even engagement of kids who will become non-STEM high-fliers can make a huge difference. Ever heard of the phrase "The medium is the message"? Our communication approaches communicate values and signals beyond what our content says. In denying all exuberant expressions of emotion and wonder a place in mathematical materials, even in the face of learners impaired by hopelessness despite their best efforts, adults are reinforcing perceptions of mathematics experts as inflexible, unfeeling and boring nerds. The persistence of those stereotypes in spite of genial, approachable educators painstakingly passing down the magical field's legacy of ingenious problem-solving tactics to students is unfair. And the few pops of color in worksheets that do try to inject fun are not enough to make a strong counter-statement. In the end, non-STEM high-fliers inherit the math as well as the stereotypes, perpetuating the latter in everyday life interactions and media portrayals. Reversal of such perpetuated negativity may spur more kids, especially counterparts who struggle in non-STEM careers and could have flourished in STEM careers, to persevere in the subject and widen their career options.

Ghibli geometry should not distract attention from school-based or educational ecosystem solutions like sharing of best pedagogical practices since they involve different chief solution architects. Content drafting may be accomplished by Studio Ghibli through the blending of its imagery and story contexts with licensed, existing geometry problem sets, leaving only an ideally quick task of expert review to math educators. Moreover, pedagogy discussions and Ghibli-related visuals occupy different influential niches. One speaks to educators, from whom successful translation of advice into action is not guaranteed. The other speaks directly to students.

The existence of entertaining math video clips and games does not obliterate the potential value of Studio Ghibli's math creations either. Unlike graphics that can be transferred onto printouts, video engagement prolongs device usage, already a hot issue of concern in today's youth climate. Moreover, no math clip or game to date has matched the cultural reach and memeability of Ghibli works. The maker of a long string of fantasy films has big shoes no mortal teacher, Tiktoker, YouTuber or software developer can readily fill.

A formidable rival to pop culture, on the other hand, is pop culture itself. This proposal can be generalized to cover a wide array of quantitative subjects and popular screen brands, except that it can be problematic to bring investigations of real-world physics into universes governed by supernatural forces.

By and by, we may even wean captivated students off fancy elements after the relevant aesthetics and narrative structures coax them to develop a fondness for the subjects' intermingling of order and surprises. The capacity for such standalone devotion can stand them in good stead in professional lives dotted all over with mundane but vital to-dos. But first, we need that captivation.