Playing with a kindly AI
Now stable diffusion with Vladomatic can cut out objects from backgrounds.
http://www.dangerbabecentral.com 100% Mr. X
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Its going to be more an issue of how accurate you can describe what you exactly want, that's going to be the skill going forward.
Like authors, someone can just right a sex scene that is flat and sterile but a good author adds those elements, pacing etc that the reader likes but can't put their finger on.
Remember, all of us have notepad or word but few people can write a coherent story.
http://www.dangerbabecentral.com 100% Mr. X
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Not video right now. That takes a lot of work. That pizza add for Pizza Hugs was all AI but it took a bit of work. A lot has to do with handing the AI images of what you kind of want to see so it can use those as templates. But I have no doubt in a year or two you'll see simply video on command.
All AI created, written, spoken.
http://www.dangerbabecentral.com 100% Mr. X
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Midjourney is getting really good with photo contents. It generates pretty convincing stills of faux 60s TV shows with almost no tweaks. It's a shame that it's the most prude and censored model ever, but for SFW images it's really easy to use.
See my art at https://www.deviantart.com/bladebur
I would tune in to watch this show
The costume from the top one and the mask and belt from the lower one.
Well, it creates some pretty convincing Batman and Catwoman, but it has no idea about Robin or most of the rogues.
See my art at https://www.deviantart.com/bladebur
the Batman and Catwoman looks great. I wouldn't mind seeing what she cooks of for Batgirl..
- lionbadger
- Legendary Member
- Posts: 791
- Joined: 13 years ago
a couple of recent efforts
You should host a forum tutorial.
That would be the shortest tutorial ever. All you have to do is go to the Midjourney discord and ask the bot "1966 TV show still, Batgirl wearing spandex". That's all. In fact, you don't need to go that far. One of the best images I got out from Midjourney was just asking for "Batgirl 1966". I didn't even write one celebrity name in any prompt, and still some images seem to resemble one or another. You can just ask for "1966 TV show still of Joker" (or Batman, or Catwoman) and you get great results.
(to be 100% honest, I had to ask for a 16:9 aspect ratio because it produces square images, but still).
It doesn't always work. It has no idea of who Robin or Enigma are, for example. Midjourney produces incredibly good results for some things, and complete disasters for others. It also lacks almost any kind of tool, so sometimes you get something that is *close* to what you want, but not quite, and there is no way in heaven you can make it right.
Stable Diffusion is a completely different beast which requires a tutorial even to make it run (there are plenty of those available though). But at least you can correct mistakes and guide the AI to put the characters in specific poses and a ton of other things. You can even make a 3D model of your image in Blender or similar and use it to guide it, although I am still learning that. Those are still early days and the UIs and tools are too immature and finicky.
Here is one Supergirl image that took quite a number of attempts and edits (and it's still not quite finished):
See my art at https://www.deviantart.com/bladebur
- lionbadger
- Legendary Member
- Posts: 791
- Joined: 13 years ago
I did 2 in stable diffusion (Deliberate and Protogen models) of "Batgirl 1966" and one of "Batgirl 1969" (which gave me one with 4 arms, which I actually kinda like)
- batgirl1969
- Millenium Member
- Posts: 2460
- Joined: 14 years ago
LOVE THESE!!! I WISH I had 4 arms!!
The four arms would make maintaining a secret identity a lot hard, but speed up shelving book a lot faster.
Some of the hands are pretty creepy. 4 to 6 digits. And Joker’s hands look like he stole them from Penguin
Some of the hands are pretty creepy. 4 to 6 digits. And Joker’s hands look like he stole them from Penguin
A-Zovya Photoreal model (with a LoRa and a lot of inpainting using ReV animated too).
Last edited by Bladebur 1 year ago, edited 1 time in total.
See my art at https://www.deviantart.com/bladebur
- lionbadger
- Legendary Member
- Posts: 791
- Joined: 13 years ago
My AI says thanks
-
- Henchman
- Posts: 70
- Joined: 3 years ago
- Attachments
-
- Sir_Frogdick_Supergirl_the_movie_1984_trucker_fight_dark_d8a1de68-6fd0-4ddb-8bac-861af872cdb5.png (1.24 MiB) Viewed 18895 times
-
- Sir_Frogdick_actress_Helen_Slater_in_1984_dressed_as_Supergirl__b6af5835-9ac4-4e17-83b1-94b7e6602277.png (1.48 MiB) Viewed 18895 times
-
- Sargeant 1st Class
- Posts: 215
- Joined: 1 year ago
At least for the 4-armed batgirl, it makes kind of sense that she has six fingers on a hand.
Thanks! We're getting there, but this still takes a lot of work and is full of the typical AI bullshit (things which look cool at a distance, but are pure nonsense up close, like leather straps which go nowhere or just random chaos in the details).
This next one came up a bit better IMHO:
This is from that "ReV Animated" model. Obviously not photorealistic, but tends to give pretty artistic results.
See my art at https://www.deviantart.com/bladebur
Eventually, the AI will be more poseable. right know it knows how things look from studying thousands of pictures. As I understand it, It is making an image from what it has learned, not what it knows. It has seen how a hand is supposed to look, but doesn't have a good understanding of the anatomy of the hand. If you at the heroines in bondage towards the top of the page, their hands are just twisted pretzels, same with the Joker. The program doesn't know what to do. The Batgirl in light green has her hands on her hips, it is much easier because every picture of hands on hips will look similar.
Well, that's already there, it is already fully poseable, thanks to the ControlNet stuff. The way it works is you pose a stick skeleton using a specific tool (you can even draw the stick figure in an image if you want) and then an 'upper level' AI (which identifies human body parts) directs the normal AI to pose the characters in the way they fit that skeleton. It works surprisingly well, I used it for my last two images.sneakly wrote: ↑1 year agoEventually, the AI will be more poseable. right know it knows how things look from studying thousands of pictures. As I understand it, It is making an image from what it has learned, not what it knows. It has seen how a hand is supposed to look, but doesn't have a good understanding of the anatomy of the hand. If you at the heroines in bondage towards the top of the page, their hands are just twisted pretzels, same with the Joker. The program doesn't know what to do. The Batgirl in light green has her hands on her hips, it is much easier because every picture of hands on hips will look similar.
See my art at https://www.deviantart.com/bladebur
Plus you can use depth maps to precisely control the pose. Its just you have to keep redrawing with sub pieces to get the correct face, mask etc.Bladebur wrote: ↑1 year agoWell, that's already there, it is already fully poseable, thanks to the ControlNet stuff. The way it works is you pose a stick skeleton using a specific tool (you can even draw the stick figure in an image if you want) and then an 'upper level' AI (which identifies human body parts) directs the normal AI to pose the characters in the way they fit that skeleton. It works surprisingly well, I used it for my last two images.sneakly wrote: ↑1 year agoEventually, the AI will be more poseable. right know it knows how things look from studying thousands of pictures. As I understand it, It is making an image from what it has learned, not what it knows. It has seen how a hand is supposed to look, but doesn't have a good understanding of the anatomy of the hand. If you at the heroines in bondage towards the top of the page, their hands are just twisted pretzels, same with the Joker. The program doesn't know what to do. The Batgirl in light green has her hands on her hips, it is much easier because every picture of hands on hips will look similar.
http://www.dangerbabecentral.com 100% Mr. X
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
-
- Henchman
- Posts: 70
- Joined: 3 years ago
Take no notice of the labelling of these photos.
Last edited by Supergirllegend 1 year ago, edited 1 time in total.
Scaling AIs have also improved quite a bit. Here is a higher resolution version of the previous image with a few edits.
See my art at https://www.deviantart.com/bladebur
This is an experiment trying to do a few of the things the AI is terrible at. Due to the AI going nuts with upside down people and people inside things, the result has bad lighting and broken perspective.
See my art at https://www.deviantart.com/bladebur
-
- Henchman
- Posts: 70
- Joined: 3 years ago
Apparently, it no longer takes much an enormous voice sampling to get AI to recreate a voice. Imagine having Yvonne Craig’s Batgirl doing an audio book version of Perils of Batgirl II. Or a face swap of Bondagecafe’s Perils of Batgirl with Yvonne’s face and voice and Julie Newmar. Or fully animated porn with no models at all.
I suspect things will get pretty freaky at some point.
I suspect things will get pretty freaky at some point.
I can give you the exact prompts, but it's complicated. The first step is getting a base picture, made with the following prompt:
Code: Select all
(masterpiece, best quality), 1girl, (Supergirl, spandex costume:1), solo, large breasts, bound, sex toy, bdsm bondage, vibrator, object insertion, vaginal, pussy juice, rope, shibari, spread leg , <lora:BondageAndDildos:0.6>
Negative prompt: multiple girls, wolf, animals, (low quality, worst quality:1.4),(bad_prompt_version2:0.8), (monochrome:1.1)
Steps: 25, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2113726557, Size: 512x768, Model hash: 7d3bdbad51, Model: aZovyaPhotoreal_v1, VAE: vae-ft-mse-840000-ema-pruned, Clip skip: 1
Code: Select all
Supergirl moody photo, Supergirl tied in a creepy torture chamber, big green fluorescent ropes, kneeling, hands up, (vibrator on crotch:1.1), cape, (big green fluorescent rock on neck:1.1), suffering
Negative prompt: multiple girls, wolf, animals, (low quality, worst quality:1.4),(bad_prompt_version2:0.8), (monochrome:1.1)
Steps: 25, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2156558378, Size: 512x768, Model hash: 4199bcdd14, Model: revAnimated_v122, VAE: vae-ft-mse-840000-ema-pruned, Clip skip: 1, ControlNet: "preprocessor: depth_midas, model: control_v11f1p_sd15_depth [cfd03158], weight: 1, starting/ending: (0, 1), resize mode: Crop and Resize, pixel perfect: False, control mode: My prompt is more important, preprocessor params: (512, 0, 0)"
See my art at https://www.deviantart.com/bladebur
Yes that's the thing. The inpainting and constant rerunning to get the results means this is not push button. DanO at SHC has to render out depth map pics to get poses then run inpaint iterations over and over to get kind of close to what he wants. He literally has to model the character in poser, render for img2img then a depth map then run passes with inpaint.
Its fun but this tech is not there yet other than to make random pin ups that are just variations of the LORA you use.
Its fun but this tech is not there yet other than to make random pin ups that are just variations of the LORA you use.
http://www.dangerbabecentral.com 100% Mr. X
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Yet another image with similar themes.
See my art at https://www.deviantart.com/bladebur
LORAs look promising, but I always get terrible results with them. It's like the AI learns the subject the LORA is about, but also a hundred other things you may not want. Like, you get the bondage, but also hotel rooms and plain lighting and manga fox girls with it.Mr. X wrote: ↑1 year agoYes that's the thing. The inpainting and constant rerunning to get the results means this is not push button. DanO at SHC has to render out depth map pics to get poses then run inpaint iterations over and over to get kind of close to what he wants. He literally has to model the character in poser, render for img2img then a depth map then run passes with inpaint.
Its fun but this tech is not there yet other than to make random pin ups that are just variations of the LORA you use.
Perhaps the answer is training a custom LORA with superheroine stuff. I don't think I have enough GPU for that, I think.
That workflow about rendering depth maps directly seems interesting.
See my art at https://www.deviantart.com/bladebur
- lionbadger
- Legendary Member
- Posts: 791
- Joined: 13 years ago
you're probably right about this, I also find that you have to be careful with the negative prompts as soon as you start adding Loras
that said, this "bimbo effect" one worked pretty well (no adjustment, hot from the oven)
I'm not enjoying the photo models that much, compared to the artistic ones. They look impressive, but extra custom details tend to look painted or photoshopped.
See my art at https://www.deviantart.com/bladebur
This is addictive. Also, I figured out how to upload images to the forum (duh).
- Attachments
-
- Batgirl Frozen.png (853.12 KiB) Viewed 18471 times
See my art at https://www.deviantart.com/bladebur
- sugarcoater
- Millenium Member
- Posts: 1189
- Joined: 16 years ago
Just want to thank all of you posting your AI works here. It really is some impressive stuff! (I would like to learn how to use AI for images to enhance my written stories, but it seems like a steep learning curve.)
Ignore any virtue-signaling; it's clearly just you.
Ignore any activism; it clearly doesn't exist.
Be very careful!
Don't be indoctrinated!
Ignore your common sense!
Everything is entirely normal and ignore the radical changes to culture.
Ignore any activism; it clearly doesn't exist.
Be very careful!
Don't be indoctrinated!
Ignore your common sense!
Everything is entirely normal and ignore the radical changes to culture.
I've upload edited versions of my AI images so far to my Deviantart page, if anyone is interested.
(and here is a new one, btw)
(and here is a new one, btw)
- Attachments
-
- OGirl.png (840.14 KiB) Viewed 18320 times
See my art at https://www.deviantart.com/bladebur
-
- Henchman
- Posts: 70
- Joined: 3 years ago
- Attachments
-
- Sir_Frogdick_Supergirl_in_comic_book_form_photorealistic_Superg_5cab6723-9a45-4988-87f8-f34cdadfe6de.png (5.02 MiB) Viewed 18268 times
A couple of AI images I did with a ton of inpainting.
- Attachments
-
- playing_with_fire_by_bladebur_dfx8scg.png (1.86 MiB) Viewed 18178 times
-
- struggling_for_air_by_bladebur_dfx9odv.png (1.2 MiB) Viewed 18178 times
See my art at https://www.deviantart.com/bladebur
- batgirl1969
- Millenium Member
- Posts: 2460
- Joined: 14 years ago
-
- Sargeant
- Posts: 109
- Joined: 11 years ago
What words are you using to get these images?
Yes the inpainting. I can hand you a pencil paper and you now have all the tools to draw a comic book but most people can't draw a comic book. Same with this. To get the pics that are more than just a pin up you still have to have the skills to start with a good base and inpaint and use depth maps to get poses, masks, gags etc.
http://www.dangerbabecentral.com 100% Mr. X
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
Twitter https://twitter.com/mrxdbc
Deviant Art http://mrxdbc.deviantart.com/
- batgirl1969
- Millenium Member
- Posts: 2460
- Joined: 14 years ago
I can imagine Batgirl's wrists are cuffed and hooked to a stainless steel ass hook also, making her struggle futile but also thrilling and filling!!!!Mr. X wrote: ↑1 year agoYes the inpainting. I can hand you a pencil paper and you now have all the tools to draw a comic book but most people can't draw a comic book. Same with this. To get the pics that are more than just a pin up you still have to have the skills to start with a good base and inpaint and use depth maps to get poses, masks, gags etc.
The initial prompt for the Batgirl image is "masterpiece, high quality photo, best quality, 1girl, solo, basement, lying, hogtie, bound, bondage, bound arms, bound legs, arms behind back, looking at viewer, close-up, angry, glaring, open mouth, POV, bdsm, short hair, black hair, bodysuit, medium breasts, <lora:hogtie_v1:1>". The model was amIReal_V2 (but I used others for inpainting and relighting later). It's nothing special. I'm having better luck looking at standard prompts from CivitAI (mixing the words the specific models are well trained at), and then painting and inpainting other details on top.
Just to illustrate what I'm talking about, I've attached here the original image for the Batgirl one, and a number of the intermediate steps I got in the process (the prompts used for inpainting are in the names). It takes many, many attempts and iterations. I've generated at least 1000 images just for that Batgirl.
This, 100%.Mr. X wrote: ↑1 year agoYes the inpainting. I can hand you a pencil paper and you now have all the tools to draw a comic book but most people can't draw a comic book. Same with this. To get the pics that are more than just a pin up you still have to have the skills to start with a good base and inpaint and use depth maps to get poses, masks, gags etc.
Depending of what you want, you can get a decent image out of the AI... But that's only if you want the most mundane images the AI can do, which is mostly about character pin ups. Almost anything else requires babysitting the AI and takes a ton of work.
- Attachments
-
- 05294-2057177213-masterpiece, high quality photo, best quality, 1girl, solo, basement, lying, hogtie, bound, bondage, bound arms, bound legs, arm.png (354.59 KiB) Viewed 18140 times
-
- 04050-7753344-masterpiece, high quality realistic painting, best quality, Batgirl, 1girl, solo, basement, lying, hogtie, bound, bondage, bound.png (295.31 KiB) Viewed 18140 times
-
- 04101-2586811007-neck rope, (Extremely Detailed Oil Painting_1.2), glow effects, godrays, Hand drawn, render, 8k, octane render, cinema 4d, blend.png (309.79 KiB) Viewed 18140 times
-
- 04270-1684705257-girl inside a sealed metal tank.png (285.04 KiB) Viewed 18140 times
-
- 04328-303136537-blurry background, dramatic lighting, wall with a heavy vault , floor, close-up, girl inside a sealed room, focus, clean metal w.png (416.19 KiB) Viewed 18140 times
See my art at https://www.deviantart.com/bladebur