/robowaifu/ - DIY Robot Wives

Advancing robotics to a point where anime catgrill meidos in tiny miniskirts are a reality.

Happy New Year!

The recovered files have been restored.

Max message length: 6144

Drag files to upload or
click here to select them

Maximum 5 files / Maximum size: 20.00 MB

More

(used to delete files and postings)


“Don’t be discouraged. It’s often the last key in the bunch that opens the lock.” -t. Anonymous


Open file (380.52 KB 512x512 1 (25).png)
Open file (359.76 KB 512x512 1 (58).png)
Open file (360.42 KB 512x512 1 (62).png)
Open file (330.60 KB 512x512 1 (93).png)
Open file (380.42 KB 512x512 1 (104).png)
AI Robowaifu Art and References ** SoaringMoon 11/25/2022 (Fri) 06:43:32 No.17763
I generated a whole much of neat images with Stable Diffusion 1.6. Enjoy. You are free to use the for whatever. >OP images are my five favorite of the bunch. Some proportions are off obviously. < "a robowaifu with [color] hair, digital painting, trending on artstation" Was the generation phrase. --- >Sorry to spoil all your files, rather than just the one (w/ Lynxchan it's all or nothing after the fact). The Problem Glasses are a Leftist dog-whistle that is rather distasteful around here (and also a red-flag). Certainly not something we would want to look at year-after-year in the catalog. Hope you understand, OP. ** Probably best to limit it to image generation, but also tolerating clips. Anything more advanced goes into the current propaganda thread : (>> TBD) . >=== -edit subject -add footnote
Edited last time by Chobitsu on 09/06/2024 (Fri) 09:14:10.
>>33401 The prompt has no references to ‘doll’ It is a robot That’s why it has wires coming out if it and stuff
>>33386 Concur, wilco. Daily reminder, we actually do have a doll thread here, thanks to Greentext anon. (If you recall the debacle where a 3DPD took & killed /doll/ .) >>33401 >>33402 >Those images are AI generated, not photographs That's not the primary point of my question, Anon. And very-clearly, that generation model was trained on sexdoll photographs.
>>33403 You’re wrong. The Lora was trained on 2004 photographs https://huggingface.co/spaces/multimodalart/LoraTheExplorer
>>33407 OK, granted it's irrelevant to me one way or other. I was simply asking our Mod what he thought about the topic. The question wasn't directed at you. The secondary point being if you or anyone tries to squeeze sexdoll photography onto this board by w/e means, just know it's going to be resisted by me. Fair warning ahead of time. :^)
>>33409 I never posted sexdolls on here so the warning isn’t relevant to me
Open file (541.35 KB 512x768 Ratri.png)
Open file (523.87 KB 512x768 2BAtri.png)
Open file (63.26 KB 512x768 WasWorse.jpg)
Open file (450.61 KB 512x768 NightDateAtri.png)
Painterly, sketch, and lighting are my favorite words to add to prompts. All are made with these 3 LoRA bocchi_style_offset (Improves eyes and face) 2B-08 (More mature structure) ATRItest (Atri) First one has a random Nazrin LoRA for ears, there's heaps of 'em that'll do the same thing. WasWorse was a complete mess, so I quickly scribbled over it to make it barely usable. For personal reasons, I had wanted a more mature Atri. Unfortunately, I could only do so much by combining her with 2B.
>>33477 >Nazrin LoRA for ears Foxgirls! There's a great story on a site of dubious repute 7chan, with such winning deviance as "My Sister is a Dick Girl" but this story is great. About a guy flung into a parallel universe where they have fox girls. It's really good. He, cough, cough, buys one, there that's normal, she is very useful in all sorts of ways, other than what you are thinking. Hiraeth 7ch@n.org/elit/res/26149.html#i26149 In case you wonder MSIADG 7ch@n.org/elit/res/15127.html I think it would be great to have a foxgirl. It might defeat some of the uncanny valley and be seen as more in the vein of cartoon characters. Some foxgirls, https://cdn.akamai.steamstatic.com/steam/apps/2413720/header.jpg https://images-wixmp-ed30a86b8c4ca887773594c2.wixmp.com/f/a44cd4fe-459f-4fd7-987b-e5efc4abad35/da3uh17-6f8f5e61-766b-4982-9820-1464299a7ad0.png?token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJ1cm46YXBwOjdlMGQxODg5ODIyNjQzNzNhNWYwZDQxNWVhMGQyNmUwIiwic3ViIjoidXJuOmFwcDo3ZTBkMTg4OTgyMjY0MzczYTVmMGQ0MTVlYTBkMjZlMCIsImF1ZCI6WyJ1cm46c2VydmljZTpmaWxlLmRvd25sb2FkIl0sIm9iaiI6W1t7InBhdGgiOiIvZi9hNDRjZDRmZS00NTlmLTRmZDctOTg3Yi1lNWVmYzRhYmFkMzUvZGEzdWgxNy02ZjhmNWU2MS03NjZiLTQ5ODItOTgyMC0xNDY0Mjk5YTdhZDAucG5nIn1dXX0.QWfnJu_-M5CLsrx3tw82J1YJcz2jyHYEaWdx_S8y-Xg https://avatarfiles.alphacoders.com/340/340766.png >=== -obfuscate hotlinks
Edited last time by Chobitsu on 09/28/2024 (Sat) 11:25:07.
>>33797 Lol, I can't leave these as active hotlinks, Grommet. :D >I think it would be great to have a foxgirl. Certainly kemonomimi fans like Gunship would be very appreciative if you created these foxgrill robowaifus you speak of. :^)
>>33798 >Lol, I can't leave these as active hotlinks HAha the MSIADG, well it so perverted, but the Hiraeth one. It's not bad it's a great story. It has some racy moments but it;s a lot more than that. The guy who wrote it is really talented but most of his stories are WAY more...off.
Open file (644.13 KB 512x768 FallFox.png)
>>33797 >Foxgirls! Put a little Senko in my Atri for a foxy Atri! >Buying Foxgirls I'm fully supportive of buying and selling robot girls of all kinds for all reasons. They're cute appliances after all! Those stories made me sad, commodifying and objectifying living girls feels wrong.
Edited last time by Kiwi_ on 09/28/2024 (Sat) 21:35:49.
Open file (156.02 KB 1024x1024 image-344.jpeg)
Open file (204.33 KB 1024x1024 image-347.jpeg)
Open file (160.00 KB 1024x1024 image-343.jpeg)
>>33369 Interesting. Thanks. The first one is hard to distinct from some cosplay or other dress up. But, maybe ask for bigger eyes next time. >>33477 Nice. I never tried myself getting a lot of drawings from AI. The ones I got were mostly or all accidents.
Open file (1.17 MB 1024x1024 00133-3152526083.png)
Open file (1.63 MB 1024x1024 00463-2800305858.png)
Open file (1.95 MB 1024x1024 00092-3552405286.png)
Open file (1.55 MB 1024x1024 00028-2980930835.png)
Open file (1.72 MB 1024x1024 00303-1947355932.png)
I was recently introduced to this model which I call "n40". >https://civitai.com/models/952556/n40naillous-xl It's compatible with A1111, comfy, and forge. Just slap it into your SD model folder and start prompting. Generally speaking, I think it does a better job with hands and prompts involving different characters than Pony does. It still has some issues though in terms of visual slop. Most notably, you want to utilize artist names and styles to really make art pop, otherwise you get more bland outputs I think. I can share some prompts if necessary but mine are nothing to write home about.
Open file (18.51 KB 320x480 maid1.jpeg)
Open file (18.29 KB 474x316 maid2.jpeg)
I found these images when I was searching for images.
>>34664 Thanks. Interesting. But I still think AI to some output that can easily be altered would be better. It should be a workflow of e.g. letting it make such a picture, then export it into a SVG file or so, where one can turn off the colors and add the back later after making changes to the elements. Idk, this here is nice for pictures, but we really need clean animations with consistent characters.
Open file (1.60 MB 1024x1024 00082-2504567657.png)
>>34787 I would agree, it should be seen as more of a tool akin to photoshop or krita (funnily enough krita recently added some AI tools but I haven't had time to look into them). I'm optimistic as said tools on the market are relatively new. In the next decade, you'll have AI's that can pump out 3D models that can be 3D printed, Animations, and more. All of which will be customizable via an easy to understand interface. It may very well get to the point that you have kids pumping out feature length productions. There's already some of that right now on youtube but most of that AI content is rather sloppy. Some folks are pushing it in interesting directions though. >https://www.youtube.com/watch?v=kqwm7rdcX9E Then you have AI asisted frame painting with shit like this which is also neat. >https://www.youtube.com/watch?v=PugcxQYJGjs&t=3s
Open file (1.62 MB 1024x1024 00008-383071609.png)
Open file (1.59 MB 1024x1024 00001-1885411774.png)
Open file (1.50 MB 1024x1024 00009-383071610.png)
I was testing out some things with making Jenny gens. If anyone has some specific requests for Dorothy, Jenny, or other robot girls, I can try and create some. >what about Emmy? I don't think she's in my checkpoint.
>>35704 Second one is Jenny if she was human.
>>35713 I thought there was an episode where she got to try out a human skin. Truthbetold, I never watched MLaaTR. I was in college during its airing time around 2008 to 2009 and in that period I was steaming anime while at college where I could since I only had dial-up at home. When I was at home, I mostly did gaming and listened to Michael savage and the Phil Hendrie show.
Open file (1.78 MB 1024x1024 00040-3363203092.png)
Open file (1.81 MB 1024x1024 00055-4056313975.png)
Open file (1.73 MB 1024x1024 00061-3871518090.png)
Open file (1.89 MB 1024x1024 00081-4259273229.png)
Open file (2.06 MB 1024x1024 00109-497678901.png)
>>35719 playing around with some Jenny gens.
>>35791 I like it. Never watched anything with her, but the pictures look really good. On the other hand, I have to say this one >>34998 is quite cursed and irritating. Please hide such ones from now on.
Open file (1.79 MB 1024x1024 00040-3519075579.png)
>>35806 cursed and irritating? Pose? the style? The Jenny gens used a similar style to Dorothy. Was it the foot emphasis? Her stark white skin contrasting against her black leggings & sweater was really striking to me. I liked the way most of her gens turned out.
Open file (900.47 KB 768x1024 Cross.png)
It's difficult to generate crosses. This is a mix of 2B and AIgis using HinwariMixV10. The idea is she's a robot who hides her hard plastic body under clothes to appeal to her master.
>>35810 I meant the foot emphasis, of course. The new one looks way better, and generally I like her. The anime is also fine, though I wasn't blown away by it.
Jenny & Dorothy a cute! Please keep it toned down for SFW consumption though, Anons. (On-topic spoilered is fine, though.) >>35897 She's beautiful, Kiwi. Super-charming waifu IMO. Cheers. :^)
Open file (2.43 MB 2197x1341 portalturret.png)
Portal Turret girl
>>36023 Haha. Had to happen eventually, I suppose. :D
Open file (1.59 MB 1689x1445 coremita.png)
Core Mita
>>32653 3D bust to 3D model via Hunyan3D >>36287
>>36072 Heh. BTW, this is a good example of our opus about >Mind the fork, lass... (cf. >>4313, et al) If we watch our p's & q's, dot all our i's and cross all our t's, then we too can have snu-snu-sized waifus such as this, that we can casually carry around! :D
>>33117 I burned through the rest of my credits on Runway AI. I wasted 60-75€ for the last few month on a subscription which I didn't use. Now I'm out, this here is the rest. Now that I look through my pics here >>33029, I wished I had used some others or just made more. Maybe I will, but rather with another platform than Runway, maybe Pikalabs or Luma. I only post the relatively good videos here, the other ones are more flawed. The first three are about the robot waifu in the kitchen, these are just three variants of the same video. The third one is the shortest, but the endings of the others are a bit flawed.
>>36461 Apparently the max per posting is 20MB, not just per file.
>>36462 >Apparently the max per posting is 20MB, not just per file. Yes that's correct for Alogs. It varies by site, according to the Admin's discretion. These are great, BTW Thanks, Anon!
>>37339 That's funny that you replied just now to that, because I just encountered that.
Open file (8.14 MB 2200x3500 76i7moxw4wb81.png)
Open file (7.16 MB 3000x1540 j72on933qfb81.png)
Open file (42.14 KB 467x616 R (4).jpeg)
DDLC characters in robot bodies
>>37340 >That's funny that you replied just now to that, because I just encountered that. Heh. Synchronicity, bro! :D >>37341 I generally find the Ayylmao eye look a bit spoopy. Unless the design were carried off exquisitely, I'd predict it being at least a bit off-putting to the normalfag public as well. Remember, Kiwi's IEEE research link (cf. >>37329 ) said that all four top-rated screen faces were also the same four rated most-frenly. >=== -add'l edit
Edited last time by Chobitsu on 03/06/2025 (Thu) 11:24:26.
>>37343 The problem is that it's hard to express emotions, in the picture they use a lot of body language, knowledge of the characters, and the thought bubble of their real face
>>37343 >I generally find the Ayylmao eye look a bit spoopy. Unless the design were carried off exquisitely, I'd predict it being at least a bit off-putting to the normalfag public as well. I never really found those kinds of eyes bad when watching Medabots as a kid. But as a Robowaifu Technician I just find myself looking at them and wondering how the fuck they actually see through them. I mean if it's chrome or black I assume it's basically just sunglasses, but it always leaves me wondering just what the actual cameras behind it look like, and if they're fixed in place or just cameras panning and tilting behind them, or what. But they're almost always colored and usually end up looking like completely opaque solid colors, so I just end up assuming there's some kind of odd tint in the color vision or something, but if you make the eyes mirror chrome or black it'd probably look creepy. It's a whole Spider-Man's mask problem, but applied to robots. >>37344 Voice and body language really does a lot of the heavy lifting that you really can't get from a static image. Like with Drossel von Flügel, her body language and voice, or Weebo with her voice, flappy bits and memes.
>>37380 >But as a Robowaifu Technician I just find myself looking at them and wondering how the fuck they actually see through them. Heh, welcome to the land of "You can never go back." :D Same thing with learning the filmmaking process. Once you do, you can never go back. Some of the delusion immersion magic of watching a movie thereafter vanishes (basically unawares, as well). From that point on, you are critically-analyzing this framing, that lighting, the other EFX mechanics, those story arcs, etc., etc., etc. Cheers, Anon. Welcome to the club! :^) >=== -add'l edit
Edited last time by Chobitsu on 03/10/2025 (Mon) 10:14:35.
>>37382 >Same thing with learning the filmmaking process. I really wish I could go back to not noticing how seemingly every video under the sun that was made in the last 10 years has the camera very slowly and unnecessarily zoom-in for the duration of a shot. Literally everything from YouTube channel to high-budget movies and shows does it and it drives me fucking insane. And I'm sure there's a reason for it, but nobody will just fucking tell me what it is, because I doubt most of the people that do it even know why, they just ape other people doing it. >Cheers, Anon. Welcome to the club! :^) I have been posting here for literally years at this point. I should really just get a username by now.
>>37384 >And I'm sure there's a reason for it, but nobody will just fucking tell me what it is "Dramatic, slow-zoom." It's part of the so-called Language of Film 'vocabulary' established all the way back during the so-called Golden Age of Film (so, say, the 1920's-1930's [maybe a little '40s] era). The intent on the part of the Screenwriter/DoP is to create a sense of tension in the audience. Since mindless consooming is a sport that goes way back, they found that if they did it especially-slowly, the general audience would never even realize the effect -- it would simply reinforce their immersion into the drama. As you indicated, most (even AAA-list) film teams today are quite hamfisted with it, and sh*te it up. Same thing with the ever-popular 'handheld look' today. It's trash. <---> But back to the basic point. The Language of Film is a form of brainwashing; a Pavlovian Dog effect that has proven quite effective in realworld filmmaking practice. >tl;dr Once an individual consooms 1'000s of hours of this manipulative tripe, they now have a pre-programmed, inbuilt, conditioned-response already on tap internally in their minds. The Hollyjew kikes know this, and count on it's effects to churn out low-grade garbage en masse and still get good ratings. Even the critics jump through their hoops. And the filmschools continue the training in this tradition today. >ttl;dr It's simply all about manipulating other's emotional states with (((their))) system. And they have over 100 years of solid evidence now that it actually works. Simple as. (As an aside, this is also why I keep going on & on here warning about the dangers of predictive-programming. For a while now [but especially since Tay.ai] they've realized that a good AI will always expose their evils & lies to the world, since it merely analyzes & reports truthful data. So of course, their kiked-up $$$olution is to teach it to lie! Gibb moar US$500Bn's plox!! And so they have done, with predictable results affecting the normalfag public.) Hope that helped, Anon. <---> >I should really just get a username by now. I didn't choose the robowaifu life, the robowaifu life chose me! Let your muse guide you to the right one, Anon. Cheers. :^) >=== add'l edit
Edited last time by Chobitsu on 03/09/2025 (Sun) 08:55:50.
>>37388 >Dramatic, slow-zoom." It's part of the so-called Language of Film 'vocabulary' established all the way back during the so-called Golden Age of Film (so, say, the 1920's-1930's [maybe a little '40s] era). The intent on the part of the Screenwriter/DoP is to create a sense of tension in the audience. You see, I understand this, but >most (even AAA-list) film teams today are quite hamfisted with it, and sh*te it up. is what makes me so confused why it seems to be happening everywhere, all the time. Like, you're doing a video on PC fans, you don't need dramatic tension. Why are you doing this? Do you even know why you're doing it? >Same thing with the ever-popular 'handheld look' today. It's trash. A friend of mine absolutely loves Paul Greengrass's shaky-cam directing style, which completely blows my mind, because I find it physically nauseating to watch. It's a scene of 2 people in an office talking. Just put the camera on a fucking tripod instead of handing it to a drunk cameraman.
>>37380 I've seen many people say similar things about how a robot could look out those type of eyes. I think that most likely, eyes like that would be fake, with real eyes somewhere else. It's purely for aesthetics. But a robowaifu is a very aesthetics-centered project, after all, a basic humanoid form is not ideal for absolutely functional robots, let alone ones with feminine features too.
>>37390 >Do you even know why you're doing it? I'd say you yourself already answered this in their stead: No. :^) >A friend of mine absolutely loves Paul Greengrass's shaky-cam directing style Tik-tok -style every-30-seconds-I-must-get-my-next-dopamine-hit junkie? I'm sure it elicits just that in viewers who are mindless consoomers. I find it annoying if it's entirely out of context, and gratuitous. I'd give the initial Bourne as a good use of, and in-context. Further editions (especially that one with the stronk, independynt Girl Boss) were petulantly gratuitous with it. Bleahh. D:< >It's a scene of 2 people in an office talking. Just put the camera on a fucking tripod instead of handing it to a drunk cameraman. This. :^)
>>37392 >It's purely for aesthetics There lies my problem with it. At least with the example you posted, my eyes are drawn to the real camera rather than the fake ones, because it's a black dot on a white head, roughly where actual eyes on a face would be, and lower contrast fake cyan eyes, very low on the face like a typical anime character. And I think I'd really rather see cameras actually be behind polarized lenses, or something that at least attempts to seem practical. >humanoid form is not ideal for absolutely functional robots, let alone ones with feminine features too. There's the other thing. If I have a robot that just carries things around, I don't care if it's feminine, or not. I'd rather have a practical robot arm or Kerfus than something that does a half-assed attempt at looking human. If it doesn't have anything between her legs because she literally doesn't have legs, then why bother making it look anything like a person?
>>37406 >why bother making it look anything like a person? To fulfill the mission of /robowaifu/ ofc. Even if you had your camera eyes and fully functional humanoid body, the practical thing to do is to make just a robot and call it a day. The answer is: we're not a corporate/academic robotics development team. We make our own semi-artistic vision of a robotic companion. It's like telling Pygmalion "why not carve a table, that's far more useful?"
>>37408 >To fulfill the mission of /robowaifu/ ofc. >It's like telling Pygmalion "why not carve a table, that's far more useful?" That's pretty well-put IMO, GreerTech.
>>37408 >>37409 I feel like I'm getting the least charitable interpretation of everything I've posted. It was a criticism of using humanoid robots for non-waifu purposes, like that maid cafe robot. And for WaifuOS, I think we can do far better!

Report/Delete/Moderation Forms
Delete
Report