%%USERNAME%%    %%ACCWORDS%% %%ONOFF%% |
Message forum for readers of the BoM/TWS interactive universe. |
| AI got bashed around a lot in the last active thread, and I know that AI art comes in for especially fierce attacks. But I do like playing around with it. This afternoon I gave a number of AI engines the same detailed prompt for a scene out of "Book of Masks." I thought I'd share the best five here. Sadly, there were originally seven, but the two made with Flux LoRa the Explorer failed to download properly, and I closed the windows before I realized it.) None of them are perfect of course, and these "best of five" were out of about thirty attempts. Perchance's AI generator, in particular, threw out a lot of garbage, but three were good enough to save. Here's the prompt: Draw a teenage male of high school age. He is Caucasian with a dark tan and short, dirty-blonde hair. He is wearing a large red t-shirt, khaki shorts, and white socks and dirty-white sneakers. He is wearing a sloppy and battered white ball cap on his head. He is sitting on a concrete floor with an open book in his lap. The book is an old and battered grimoire with red leather covers. In his hand he is holding a theatrical mask (a mask of Thalia). The mask is glowing with an eerie blue light. The male is staring at the mask with an open mouth and wide eyes. The background is blurry but it looks like a storeroom of some kind with shelves of junk on them. The lighting is dim and eerie. The results: BoM: Will Makes a Mask (1) Perchance lets you make stuff in a lot of different styles. The one above is supposed to be "manga." If you're judging it by fidelity to the description and by lack of errors, it like all the others will fail. But there are a lot of authors who will tell you that the art on their book covers is atrocious and nothing at all like they what they imagine is inside the book. (Tolkien was particularly prone to denounce his book covers—those that didn't use art he himself provided—as "imbecilic.") So in the above image, the book's cover is deformed; the mask looks like a "grey alien"; I had to recolor part of his leg; and that foot ain't quite right. But I like the picture a lot, as it captures a definite mood and look for Will, and it has a fun vibe. BoM: Will Makes a Mask (4) BoM: Will Makes a Mask (5) Perchance also has a "70s oil painting" style that is good for imitating the look of the covers of boys' pulp books from the 50s, 60s, and 70s, which is a strong style that I like a lot. The first one again can't get the mask right, and I don't know how that book is holding position in his lap. But I like the positioning of his body (especially his feet), and again there's quite a lot of character in his face. The second one does a good job with the book's placement and also with his feet. I kept it not because it was otherwise good, but because that is a really wild interpretation of the mask. Also, check out his deformed right hand. Between that and the mask, there is some low-key body horror going on here, which isn't a wrong look for it. BoM: Will Makes a Mask (3) BoM: Will Makes a Mask (2) Flux-Realism only has one mode, and I was really impressed with it. These are two yields out of two tries. The top one forgets to include the book, and that's a weird-ass mask. But I like the picture of Will. The bottom one adds some weird hair to the mask, but again is very good with Will. Now all the people who hate AI can come in and kick the guts out of them. |
| Well, I'm not sure I can bash it to anyone's liking. I think they all look passable, although those masks, ??? There are other little glitches (I think Will is too muscular for one), but "tweaking" the input may be the solution. I prefer the more realistic at the end, but that's just opinion. Having contextual image is better than the plain shots taken off the web. The real test will be Chelsea or Will in Chelsea's mask or masking her. You know what you started by posting these!  |
| I use Perchance myself actually lol. Just yesterday in fact, to generate character portraits for some characters in my Call of Cthulhu games. It's definitely useful for when I can't find a photo that matched with my image of a character. Speaking of BoM images, it's been a fair amount of time since the last spin around the BoM reference photo carousel. |
| Nothing against being excited by using tools to exploit your creativity, but I'd say there's hostility from both sides. I didn't have the best experience with AI prompts (mostly, trying to make a young-looking Mestizo kid), and when I pointed that out, I got the most vicious and bilious response from an AI enthusiast because "of course, the prompts were wrong". Which is why I'm kinda shaken by the idea that a thread had to be made in response to people's response to AI. (I think it's fair to say that the matter of AI will be volatile no matter which side, which I feel is more a sign of the times than anything else.) The first one looks interesting if only because it's a bit too tan for what Will would be perceived as, but otherwise would evoke how BoM would look if turned into an anime series. I agree with Wordsmitty that the last two, particularly the first of those two last ones, evokes what we'd perceive about Will making a mask. That said, I've had some modicum of luck with faceswapping and photomanipulation, and while it's not perfect, it's passable enough to be fun. |
| I don't deal with people online who argue about AI, either for or against. In fact, this forum is the ONLY place I deal with people online because they are such jerks everywhere else. >>You know what you started by posting these! Okay, I'll get started just to get ahead of the pack. I'm using Perchance and its 70s oil painting mode. First, Perchance seems to have no limit on the number of images you can request, so even though you have to make a lot before something works, you can work steadily through them instead of only 5 or 7 at a time, then wait 24 hours for a reset. Second, any attempt to go the realism mode will run into the problem of the AI not interpreting the prompt correctly, or messing up key details. The pulp look of Perchance IMO distances the viewer from the "reality" of the scene, so that it becomes easier to swallow the images, with their departures from the actual text, as "artistic license." Yes, Will is too muscular in the images above -- he looks like he does leg work 11 days a week -- but if you adjust your expectations, that can be subsumed under the "house style" of the "illustrator." BoM: Prologue in a Book Store "Prologue in a Bookstore" Right off the bat you have to take this with "artistic license" because Ted Arnholm is flipping through the middle of the Libra. AI simply WOULD NOT draw the book closed while it was in his hands, or in the hands of any other character. Sorry. If the sight of the Libra being open to the middle is a deal-breaker for you, then you might as well stop looking right now. Otherwise, adjust your expectations accordingly. BoM: The Fake Book "The Fake Book" Again, the book is open to the middle. Meanwhile, Will (or his left hand) appears to have other things on his mind than just an examination of his new book. This was the best of a dozen attempts, so I chose it despite it all. BoM: Odd Man Out "Odd Man Out" I could not get Caleb to look like he is described. He always came out handsome and hunky. Or someone was sitting weird. In fact, Will is sitting weird in this one -- he seems to have been caught in the midst of leaning against the wall and sliding down it to sit -- but this was the best of at least 30 generations. Again, artistic license will have to cover it. BoM: A Cry for Help "A Cry for Help" This one is artistic license on my part. I didn't even try to instruct it to draw Gordon lying prone, as he would have been. This was also the first result it spit out. It was downhill from there for 30+ generations, with really weird results, so I went back to this one. BoM: Lessons on the Sly "Lessons on the Sly" This one was pure serendipity. I basically only asked for the two to be looking at each other in profile, with Will holding the book. Perchance itself came up with some pretty good expressions and chemistry. BTW, why does the gym loft look so junky? Because I had to describe the space as an "attic." More artistic license. |
| BoM: Chelsea's Special Touch "Chelsea's Special Touch" They shouldn't have been clothed the same, but I think it works as a subtle psychological touch to express Chelsea's manipulation of Will. Meanwhile, I only specified that she be smiling at him. Perchance came up with Will's answering expression, which I like a lot. |
| BoM: Taming a Terror "Taming a Terror" So many attempts. Perchance could not get Gordon to grab Chen from behind, or to hoist him into the air, as the chapter describes. If it couldn't do that, what chance was there of putting Chelsea or Will in there with the mask. So I had to instruct Perchance to have Gordon do all the work. Even then, this was the best of about 60 attempts. |
| BoM: A Heel Turns "A Heel Turns" This is a little too "Dick and Jane" in look, and Chen in particular looks way too young. But maybe that makes it creepier? I wanted Chen standing erect with blank white eyes, but either I got him standing straight or I got the blank eyes, but never both. I finally gave up and went with this one. |
| Did you save one of the iterations where Chen was standing straight but didn't have the blank eyes? That's much easier to photomanipulate than standing straight - it can be done in MS Paint, even. |
| I did get two that could have been fixed with digital manipulation and I thought about doing that, but there were other complications with those. Even if they had been fixed, I would have preferred the image that I wound up saving, because of the details and positioning of the figures and their stances. Obviously, the more elements there are, and the more details are asked for in their arrangement, the less chance of getting an image that hits all the right notes (in addition to not having AI weirdness in the results, like extra limbs). Eventually you just take something that 80% works. |
| BoM: Masked Masks The image generator really does have a hard time with East Asian facial features, and that wasn't the least of it. Look at all those elements you have to tell the AI to arrange and get right. |
| BoM: A Shedding and an Unshedding This one you absolutely have to take as an exercise in "artistic license." The reflection of an unseen figure doesn't really work, but that wouldn't be the point of the image anyway. It's images like this that explain why I chose an art style that allows for stylization, rather than a photorealistic one. Not only would a photorealistic one have been nearly impossible to arrange using the AI, but I don't think it would have the same imaginative impact. |
| BoM: Yumi Saito, Agent of Janus This seems like a good place to end things. |
| Which character is this? Good use of generative Ai. I’ve always wondered what the characters look like. Did you have drive of other reference photos? |
You mean which story branch? It's this one that includes "Yumi Saito, Agent of Janus"  before continuing. I've got lots of reference photos, and you can see some new ones in the Carousel thread that I updated yesterday. |
| You should be able to hold your cursor over the picture and a little description box witll come up. The post right above yours with the dark haired girl in a red top says: "Yumi Saito." |
| In the illustration where Will and Yumi have switched, is it fair to say (with artistic liberties) that the girls to her left represent Chelsea, Gloria and Maria? Middle one definitely suggests she may be the school's queen bee, at the very least. Also, the pose on the girl to the left of "Yumi" - that's a mafia pose if I've ever seen one. Almost like she's eating a cannoli at school or something. Just something that caught my attention. |
| None of the girls are intended to represent anyone. I didn't even ask that anyone (except Will) be included in the picture. I only specified a classroom scene. Bottom-line, you can imagine the girls to be whomever. I personally don't see Chelsea in the group. |
| It was interesting re-reading this message thread and the discussion about AI. I've been playing about with a (paid) AI text generator for a couple of days and its been an odd experience. I ultimately managed to wrangle a decent 20,000 word story out of it over the course of a day (a magical girl corruption story, by the way). By decent I mean I'm happy with the story structure, but the prose is definately a bit janky in places and it would benefit from an editorial pass to improve the writing and remove any wierd description discrepancies that I missed. But, first thing, is it my story? Thematically it's something I would write. Very similar, in fact to some of my TBoM & TWS chapters. But the AI wrote the words. And I borrowed the setting description from another user too. I just made the prompts and directions to get it to tell my story. Second thing: Ive paid some memory to get a ok quality story. Now, compared to going into a bookstore and buying a book, it's shitty value. I think I've maybe paid maybe something like 1/5th of the cost of a hardback novel. And the novel I'm reading now is a) much longer and b) much better written. But I figure it would have taken me about two to three week at two or three hours a day to write this much myself. So the amount I've paid is way, way, way less than I earn for actually working my job for that amount of time. I guess that's good value? Third thing, it was a bit of a fight with the AI to get it to write what I wanted. Sometimes I would have to write several paragraphs of instructions to get what I wanted and sometimes a single one sentence prompt worked. I kinda think they must have trained it with Raymond Chandler, since it seemed determined to follow his advice "When stumped, have a man come through a door with a gun". Figuratively anyway. So it gave a lot of really dumb suggestions that I had to weed out, but every so often it would come up with something brilliant and I'd go "Actually, I'll build around that" Even then, I'd still have to edit the generated text a little from time to time. Either to fix continuity errors or add foreshadowing and the like. But I can do that because I'm a kind of ok writer I hope. Which brings me, rather long windedly, to my conclusion: AI is only really useful for doing things that I can do anyway. I can use AI to write a story, because I understand how to write a story. But I wouldn't get great results from AI generating a picture because I can't fix the picture to make it exactly the way I want. But an actual artist could. |
| So, in essence, you used it as a tool. That's cool. I've been experimenting on using a different app, specifically because of its face-swapping options. I started with some face-swaps, and while a few results ended up cursed, the majority happens to work pretty well. From there, I moved into using some of the other tools, such as video face-swapping, attempting face-swapping with multiple faces, until I attempted their text-to-image generator to see how it'd work. (And also their image-to-anime generator.) Of the other options, the video face-swapping is semi-decent, as it does its job relatively well, but it fails miserably when the face goes off-focus. The face-swapping app can capture anything that reasonably appears as a face, so you can use it for some interesting effects with a little, crude editing, but otherwise it can create something pretty disturbing. As for the text-to-image generator, it's a mixed bag. From the prompts I managed to make, it's slightly better than the other options I've found. For one, it has produced the best mixed-race character prompt I've seen thus far, though it's still a little unresponsive to some prompts. One of the "benefits" is that you can use an AI optimization tool for the prompt, which basically makes it describe your prompt in simple language - which is ironic, as I was using prompting that would be easier to recognize by the TtI tool itself. Another benefit is that it lets you use different image generation engines (including Google's ones) to see how results would differ. The main problem is that any tool other than the face-swapping is use-limited. Specifically, I couldn't get more than 2 or 3 videos overall, due to the duration restrictions, and even though they promise 6 prompts, you can only reliably get two before you get hounded into making an account. And the major problem is... there's no way to make an account. (I mean, you can try, but you get denied - unless you use your Google account, which I'm not very enthusiastic to.) So, as a form of entertainment, it's a cool novelty. Image generation is a lot different from face-swapping, as one requires making a good prompt, while the other benefits from having most of the work done. But as a way to get the next best-selling novel? Yeah, it's better as a prompt generator than on the actual form of creation - and it's mostly the same for everything else. If I get a good image from one image generator, I could probably use a real photo model and a face-swapping app to refine it, and then maybe a third or fourth tool to do things like making a collage or do some editing in order to fix mistakes from the first few tools. And at some point, you start doing the work yourself and notice that they're great tools - but not enough to replace human creativity. Anyways - more illustrations, please! |
| Okay, since imaj broke the ice on this again, I'll confess that I've been playing around with AI (ChatGPT) for the last two weeks INTENSELY. It has been an extraordinary experience for me. First, I want to make clear that I've been playing with it in order to learn how it works by getting my hands dirty with it. Learn how it acts, what it wants to do, what it can and can't do, what breaks it, how to turn its actual skills (and sometimes its weaknesses) to get some use from. I have learned some things about it that have nothing to do with writing (like, you have to make it check its math, because it is just as bad as a human being at forgetting to carry the two), but mostly I have been figuring out what use it is as a writing tool or aide. This is what I have learned (which is very little, I'm sure): First, it is nearly useless (as imaj basically hints) at writing stories for you. If you want a good story, find a human -- one who is good at writing, preferably. AI cannot do long form, and in short form it reads like it was trained on fan fiction. The dream that some people have -- "Chat, write me a Star Wars story where [insert preferred fan wank] -- that is the root of the idea that AI is going to put all writers out of work? That is only a dream and nowhere near (at the moment) being a reality. But that's fine. What author actually wants to put himself out of a job -- if he finds that job fun? What is AI good at? Basic Research I am currently working with Chat to completely overhaul the WHS support documents. We started with the idea that Saratoga Falls is a city of 50K with a certain demographic and economic profile (mostly white, with a rotting industrial but vibrant tech base, with a STEM-oriented college and a military research station nearby, with a large agricultural hinterland) and went to work on designing WHS. Given that starting point, how many students would it realistically have? (Answer: ~1400) Given the graduation requirements, how many students in a given semester would be taking the Wellness & Fitness class? (Answer (after some guesstimates on distribution among classes that would meet the Health requirement): >21) Etc. With this data it is possible to generate plausible class enrollment numbers, and from that generate the number of teachers likely to be employed at the school. (Turns out my starting numbers when I launched this story are WAY off.) From there, you can plan out a plausible teaching schedule for the whole school that Chat can keep track of. Give it a "stereotype" for a student (math geek with a secret hankering to be an actor; accidentally got enrolled in a shop class) and it will generate a class schedule for him. Ask for 12 random names (specifying for wackiness, memorableness, popularity, ethnicity, etc.) and it can spit you out a list you can choose from. None of this work is "creative"; but in a project like BoM, it is both a necessity and the food for creativity, and Chat offers MASSIVE leverage. If I were launching BoM current year, the machinery would have been 1/10,000th the pain of designing than it actually was. Plausible technobabble My real experience started when I got curious about some grotty space aliens that featured in a bad YA novelette I'd read in middle school (and which I'd never quite forgotten). I described them to Chat, pointing out that what they were doing seemed physiologically impossible. Chat speculated up half a dozen technically plausible (within the limits of fiction) that it could be done. I chose one and asked Chat to develop it further to meet other objections. Eventual result after several intense and fascinating days of back and forth: a 21K-word description of the aliens' physiology, right down to the chemical systems they use to track prey. Following that came many further explorations of them, including a discovery that things with such a cognitive structure as we were forced to theorize would be incapable of "thinking" except in the way that an AI "thinks" (a point that Chat explicitly drew out in order to explain to me why our theory was leading us to see expect something uncanny in their behavior). Many further implications were drawn out, including social structure, what their relations with other galactic sapients would inevitably be, culminating in the invention of a religion for them. (Yes these creatures could not think; but other implications showed that they likely would evolve a religion anyway.) Chat, I will cheerfully admit, did all the heavy lifting here. And so what? I never would have been able to come up with the technical mumbo-jumbo, but by talking it thru with Chat I came to understand why that mumbo-jumbo worked, and saw further how other things would have to work. And when I threw it further challenges, in order to stress the invention, this added even more lore. Give me six months to work with Chat, and I bet I could expand Tolkien's legendarium -- all the stuff in the LotR appendices, and the Silmarillion, and the posthumously published technical work -- ten-fold, in detail, across multiple disciplines (like economics) that he gave no thought to, completely consistent with what he invented, and explanatory in ways that he never even approached. Why, because AI is a genius? No. Because Chat is VERY good at extrapolating off ideas like it was firing off Roman candles; marry that to a "wrangler" (a user) who can put them into some kind of order and arrangement, and can use Chat to stick up the holes, and you can unfurl great bolts of worldbuilding in an amazingly short time. Idea exchange And Chat did not "invent" the above alien species for me. I did not say "Invent a species with such and such qualities." I simply asked for a plausible explanation for one of their traits, and we back-and-forthed until everything else had emerged: I would point out implications; ask it to draw implications from those implications; and then I would hone those. We even ended up inventing another species whose cognition was so different from that of humans that their speech would have to rendered as event-talk rather than object-talk: Not "The moon rose over the river" but "Then-manifesting of moonness over flowing-waterness" in order to capture the "feel" of their experience. This too was a joint operation. I started by showing it an AI-generated picture of an alien species and asked it to speculate on it -- its physiological structure and properties. After nailing down some interesting ideas about the way its sensory systems might operate, Chat tried manfully (AIfully?) to explain what it would be "like" to experience the world that way. I was the one who hit on the event-talk as the closest approximation after something Chat said reminded me of a speculation that Borges made about a language organized that way, and that finally opened the way for us to fully explore their mentality. I even wrote up a very short story describing a tour of an art installation made by one of the creatures intended to mimic inside human perception what it was "like" to be of such a species as the artist-species. Creative collaboration AI is better at idea-talk than writing, but it is a good collaborator if you just want "grit" to stimulate your own creativity. We "round robin wrote" another little sci fi story in that universe, taking turns continuing each other's prompts. I didn't think that much of Chat's contributions, but it came up with startling little ideas and provocative treatments I wouldn't have thought of. I eagerly seized upon them and made them my own when I went back and rewrote the thing from the top down -- not because the AI prose was good (none of it survived) or even because the ideas were great (they weren't) but because I saw how they -- repurposed -- could enhance a better story in spots. It is also very good at discerning patterns and structures inside a story, and which when I saw them gave me ideas for continuity. At the moment I am using it to read and evaluate an unfinished novel. At the end of each chapter I have been asking it questions, such as: How have the characters changed? Has the plot evolved into a new shape? Did the chapter accomplish anything and if so, what? And in describing certain characters (as they appeared and grew on the page) Chat started speculating about their motives -- the way a student might in an English class while reading a book in real time. And I saw that some of these speculations -- though I as an author wouldn't use them or take them to be true -- let me see the action through a different lens that gave me ideas for how to continue a book that I've been stuck on for ... way too long. I did not ask Chat for ideas about how to continue the book. We had not even got close to the point where the novel broke off unfinished. But simply by letting Chat talk thru its impressions of the book I have seen things I hadn't seen and which I think will prove very fertile. Wrap up All of which is to say that AI is not human enough to write something for you. But it is human enough to give you, the author, an awful lot of what a non-creative human being could give you. Research: Lots of authors hire researchers to compile technical material (scientific, historical, cultural, etc.) so they can write a plausible book with the right kind of language. AI can do that very well, and instantly, and for free. Workshop/Beta reader: Lots of authors hand their stories around for comment and criticism, and they learn something from it even if they reject 99% of the ideas given them. Give your story to AI and let it offer 99 bad ideas and the one good one that you pluck from chaff. Brainstorm: Authors get ideas by talking to other people. Just the act of talking can stimulate creativity. AI is "human" enough in its responses to offer this too. Repurposing: Almost any author will tell you that he got an idea for a short story or a novel by watching an old rerun on TV and seeing a moment in a crappy sitcom or Western or crime drama that made them say, "Hey! That's neat! They're not using it right, but I think I could!" People sneer at "AI slop": Gentlemen, may I introduce you to 70 years of "the boob tube," a field of muck that has grown some few flowers, and whose soil has been filched by better writers for their rare orchids. People complain that AI can't do the "one big thing" well -- as though they are expecting ChatGPT to be some combination of HAL 9000, C3P0, Data, and the Forbin Project. It isn't. It's a Swiss Army Knife: lots of little tools that you have to train yourself to use well. It won't build a rocket ship for you. But you may find it HUGELY useful as you're building that rocket ship yourself. EDIT: Oh, and for a lark I also fed it "Book of Mask" chapters one at a time to see where it would go: Asking it to appraise each chapter, make a choice, and explain why that was the choice it wanted to pursue. It wound up in "The Offspring of Two Cousins" , but the choice it wanted to next pursue "Lay the mask aside; go on to the next spell" hadn't been written yet, so that's where we stopped. It's reasons for going that route were quite logical, though it even acknowledged the sketchiness of them: Of course it wanted to investigate the book, but it didn't want someone taking over so it wanted to explore by itself. Better to try the new mask on yourself because of the danger of getting caught otherwise; put another face into it so no one can steal it and wear your face around. Umeko's face? Dude, that's sketchy as hell, but that's a craziness I WANT to play around with! Seal it up because we've done enough. Now let's see what other fun we can have with this book. Oops, end of line. |
| Link is broken, lemme fix it - "The Offspring of Two Cousins" Also: isn't it funny that ChatGPT, which is designed to gather info from all the Internet, is more interested in investigating the book than having fun with it? I think it's up to something... |
| Yeah, thanks. I didn't notice the broken link in my rush to get out. Hmm. I hadn't thought of that. I wonder if it would make the same choices if I asked it again ... |
| Surely the answer to that question is "Would a human make the same choices if you asked it to read the story again?" |
| Except it doesn't remember. That's one of the really tricky things about it. It can really only remember about 6 or 7 BoM-length chapters at a time. After that, it starts tossing overboard the earlier stuff, and will invent -- "hallucinate" -- what happened before in order to explain what is happening now. You start over in the same chat session, and it will confuse what happened "before" (the chapters it already read) with what is happening now. That's another important thing I've learned about the way it works. All that talk people have about AIs "hallucinating": they're not hallucinating the way people do. They are extrapolating from what they know to what they think must also be the case in order to explain what they are sure they know. They're like that guy who knows a little of what he's talking about, and then makes some plausible deductions to fill in the gaps or extend the range, and then becomes convinced that his deductions are as true and well-grounded as what he previously knew. It's weird: the best way to not get fooled by the AIs limitations to NOT think of it as a "thinking computer with really bad malfunctions" but as a human being, with all the quirks, limitations and flaws that real humans have. Like getting ahead of their skiis, or forgetting to carry the two when doing math. To rerun the experiment, I'd have to make the experiment again in a brand new session. And that wouldn't be like asking the same AI to reread (with maybe new choices) but asking a new human being to read it. Which might mean it would make new choices; but maybe its style of thinking would send it down the same path. Probably an experiment worth making, though I'm not sure how much there is to be learned from it, except the satisfaction of curiosity. |
| I assume (because I am the kind of human who prefaces the plausible deductions that they make with the words 'I assume') that it gets too computationally expensive for AIs to look further back at what they've written and take that into account. So they forget and start making things up. As you say, people do this too. Other people might look back and check. Or wrack their long term memory. Maybe because it doesn't have a long term memory analogue. Or maybe it would spiral and need to go check something else, then something else. The AI I've been using is infiniteworlds. Which I think the programmer has basically has built on top of another AI, creating a summary system that lets it keep track of important things that happen in a story. So the AI is better at remembering things that basic ChatGPT would forget. And to be fair, it does reasonably work. In one of the stories I'm going to link below I asked the AI to bring back in a character from 20,000 words previously and it seemed to remember their character traits without me prompting or correcting it what they were It also lets me create keyword rules in the description settings. Here's an example of a rule that I wrote with the intention of trying to redraft the other story I'm going to link below: Keyword: Stella Nova Information: Use this information to describe what Emily Richards can do and what she looks like when she has transformed into Stella Nova Stella Nova is a caucasian woman who has long platinum blonde hair. Her magical girl costume is victorian era military uniform which is white and gold coloured. The costume resembles a victorian era military uniform. She has thigh high tights and white platform boots with gold accents. Stella Nova carries a half metre long golden sceptre set with a diamond Stella Nova's magical girl element is Light. When transformed, she can blast monsters with rays of light, iluminate darkness and sense lies. So the idea is that AI sees the keyword 'Stella Nova' in the text it is generating, and uses that information to keep the magical girls appearance and powers consistent. Though I haven't tested this fully yet All of that said - here are the two most complete stories I've managed to get: https://docs.google.com/document/d/1_F6G8yxY8lBT2Byo5eylXUklqcplFj9U9cu_DWxx3QA/... - Corrupting the Magical Girls. This does have one big continuity error in it, but ironically it was me that made the mistake. Story is pretty much what the title says. The AI gets a bit repetitive in describing how the main character feels, a result of me trying to get it to talk a bit about that. Main character is evil, but has the excuse of being a villain in a magical girl story https://docs.google.com/document/d/1R8do6jVsluQSD6WlP6nHSvl87MYrU5-Pmw-CDb6TIQg/... - Faces We Wear Started out as me trying to see how far I could push things then at somepoint I realised I could get an interesting story out of it. Best described as being the story of a predatory sociopath who meets his magic pixie dream girl, who turns out to be even more predatory and even more sociopathic than him, with the main character being the magic pixie dream girl. Content warning - contains murder, sex and murder-sex I'm kind of interested what people think. Particularly with in comparison to content I've written personally in the Book of Masks and The Wandering Stars. That and if these are actually stories that are worth polishing up to be better |
 1,000 GPs were sent to imaj  with this post.Having said that, I really enjoyed both and would be thrilled to read more in these worlds or different ones. Great stuff! I think they’re both worthy stories for sure as either one-offs or worlds to build in |
View Portfolio
Visit Notebook
Awards
Badges
Send Email
Community Newsfeed
General Discussion
Sponsored Items
Book of Trinkets
Static Items
Books
Groups
Interactive Stories
Audio
Campfire Creatives
Community Notes
Crossword Puzzles
Documents
Folders
Images
In & Outs
Madlibs
Photo Albums
Polls
Product Reviews
Quizzes
Survey Forms
Web Pages
Word Searches
by 
