- Thread starter LocusTenebrarum_Rue
- Start date
There’s about an hour of content right now. The demo includes 3 lewd scenes, and the patron build includes one additional lewd scene that’s pretty long and involved.
I’m very actively developing the game, so new content is happening all the time. You can take a look at my Patreon posts to get a sense of how often I update the game.
The top image is from the part where you walk around in 3D environments and talk to people. Basically a 3D adventure game.
Then during lewd scenes it switches over to something more like a visual novel.
- Aug 28, 2017
- 356
- 737
Games with animations attract more people, that's a given. But yeah, not that kind of animation lol
Having your 2D art also in 3D/animations would be the dream though.
Best of luck either way.
I say go the other route, drop the 2D, work on improving animations and graphics.
The 2d girls are beautiful, I can't wait for a future where we can get good art framed in complex scenes. It's a very interesting topic and I'm curious now to learn how far are we with this AI tech. It could change the AVN scene for good.
the 2d art is insanely good, wasnt expecting the 3d part from the gallery imagine put in the thread
It won't as long as people want animations in their porn games. Like it or not, 3d models are currently the only way to produce such videos in anything that resembles a timely manner.
Yeah, I’m using Stable Diffusion for the environments and characters. I’ve got a process for turning the environments into 3D models which required building some custom tooling.
As for the portraits, AI is part of it, but there’s a bunch of work that goes into each image. It’s a lot of fixing things in Photoshop, painting over things, running them through img2img, some creative abuse of AI upsampling and downsampling, and often bashing together elements from multiple images to create a kind of collage. I’d say I spend 40 minutes on most images, but the more complicated ones are more like 90-120 minutes.
I don’t think traditional artists are going away any time soon. I have to put quite a lot of work into each image to get the final result. That includes some manual paint-over work in Photoshop, along with lots of blending, level adjustment, recoloring, etc.
I don’t think AI will kill artists any more than power drills killed carpenters. These are power tools for artists who know how to use them.
- Sep 22, 2018
- 404
- 650
There’s a dream fragment with an extended scene with her that you find in one of the 3D environments. Be sure to find it and go to the Dream Emporium to talk to Talulah.
You get a tiny glimpse of that scene the first time you go to the Dream Emporium, but the fragment version has about a dozen images (including the version of the Patreon header image that I’m not allowed to post on Patreon).
- Jun 28, 2017
- 1,954
- 3,015
Arts fine, improvement over fucking daz models.
I wish f95 banned unity games that didn't feature basic chat functionality.
I wish f95 banned unity games that didn't feature basic chat functionality.
Christa's dialogue in that last sneak peek on the front page reminded me of this exchange:
Ron Burgundy: I don’t know how to put this but I’m kind of a big deal.
Veronica Corningstone: Really.
Ron Burgundy: People know me.
Veronica Corningstone: Well, I’m very happy for you.
Ron Burgundy: I’m very important. I have many leather-bound books and my apartment smells of rich mahogany.
Ron Burgundy: I don’t know how to put this but I’m kind of a big deal.
Veronica Corningstone: Really.
Ron Burgundy: People know me.
Veronica Corningstone: Well, I’m very happy for you.
Ron Burgundy: I’m very important. I have many leather-bound books and my apartment smells of rich mahogany.
nothingyet - you may want to request ownership of this thread.
Also... HOW do you go about using StableDiffusion with NSFW content? I get a message about it and then it returns a black image.
I am using this one:
You must be registered to see the links
using pytorch>>> prompt = "a naked woman with big breasts"
>>> with autocast("cuda"):
... image = pipe(prompt, guidance_scale=7.5).images[0]
... image.save("v:\\nwbb.jpg")
...
100%|████████████████████████████████████████████████████████████████████████████████████████████| 51/51 [02:36<00:00, 3.07s/it]
Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.
Last edited:
What I am wondering is, how do you keep characters consistent in an AI environment where you just ask for something? Do you teach it how your character has to look exactly or can you be very specific (ie "who looks like Kenzie Reeves") or what? Otherwise, you'd just get a load of random women.
It takes a lot of time and work. I spend a lot of time in Photoshop editing things, running them back through the AI, doing paint-overs, inpainting the face, hands, clothes, etc.
Things like Dreambooth can help, but it can be tricky. I have a backlog of stuff I need to do right now, but I'm planning to spend more time with Dreambooth once I've got time.
Would be probably easier/faster to just run filters and touch-ups on real world pictures to produce similar "panting" effect, but with much better control over poses and appearances.