FloricSpacer

Newbie
Game Developer
Apr 27, 2020
29
127
can someone tell me the code OpenAI
You need to make your own code individually to pay for the image generation. I don’t think anyone is likely to share a code with you.

smells like copyright infringement to me :censored:. one image is one punch man wtf haha :LOL:

i bet your not the artist of some of the pictures shown here or have any permission. not cool. if im wrong im sorry but i doubt so
Yeah, for the ones in the game and the previews, I used the images from the original cyoa, which is based on borrowing images from across the internet, as is common practice for image cyoas. Though I do understand you objecting to that, which is totally fine, and is a valid criticism of the game. I have made an effort to make all of the new images I’m adding to expand the content myself, but I didn’t want to replace all of the original images, and I don’t have explicit permission of their artists for those images. I do not claim ownership of those images at all.

I was speaking specifically about the wiki, which you mentioned in your last post. I can say that I DO have either ownership or permission of all of the images uploaded online in the wiki. All of the character images there are either made by me or used with explicit permission of their owner.

Sorry for any confusion, I’m trying to be transparent with all this as much as I can while correcting any misconceptions. And I do understand the problem you have with the art in the game, so I can’t really blame you for a valid criticism. Though I do feel it’s a bit ironic considering the nature of the site here haha.

I have a NovelAI API Key, but it doesn't seem it work. Is only OpenAI possible to be used?
Unfortunately I’ve found that only DALL-E 3 has a good enough understanding of complex prompts to work for something like this, where you need to get all of the character’s details right. So you need to use an OpenAI key, and NovelAI does not work.
 
Last edited:
  • Haha
Reactions: looseylucy

Serameth

Newbie
Jun 18, 2017
62
10
Unfortunately I’ve found that only DALL-E 3 has a good enough understanding of complex prompts to work for something like this, where you need to get all of the character’s details right. So you need to use an OpenAI key, and NovelAI does not work.
Thanks for the response, but I prefer not to pay for each image generation.
 

FloricSpacer

Newbie
Game Developer
Apr 27, 2020
29
127
Thanks for the response, but I prefer not to pay for each image generation.
That’s understandable, in that case I recommend disabling that option in the settings menu and the game will remain perfectly playable like how it was before this update haha.
 
  • Like
Reactions: Serameth

Eyion

New Member
Jan 24, 2019
2
0
Wouldnt it be more sensible to grab the images from a local StableDiffusion installation? You can get it from github and generate the images on your device with training packages you can grab from other sites for free aswell, tho I dont know how much work integrating that is
 

Xakorik

Member
Sep 27, 2018
192
74
Wouldnt it be more sensible to grab the images from a local StableDiffusion installation? You can get it from github and generate the images on your device with training packages you can grab from other sites for free aswell, tho I dont know how much work integrating that is
Doesn't sound feasible for us mobile players
 

bitsybobs3

Ultimate Torrent Dude
Donor
Jun 13, 2021
3,539
1,997
AbyssDiverInteractive-1.1
You don't have permission to view the spoiler content. Log in or register now.
rpdl torrents are unaffiliated with F95Zone and the game developer.
Please note that we do not provide support for games.
For torrent-related issues use here, or join us on !
, . Downloading issues? Look here.
Want to join the team? Read more here!
 

FloricSpacer

Newbie
Game Developer
Apr 27, 2020
29
127
Do you need to subscribe paid plan in openai to generate code? wont the free one do?
don't think so. from what I see you need to put at least $5 into it
Do not subscribe to ChatGPT Plus subscription for Abyss Diver! The subscription is not necessary for the avatar generation and is a completely separate cost!

What you need to do is buy $5 worth if credit on the API platform, and then you can use the feature in the game. Theoretically you should be able to use the free credit, but from what I’ve heard that disabled free access to DALL-E 3 for some reason, even though their website says it should be available. ‍♀

Also, in a new update that should be coming very soon, I’ll be giving the player the text of the prompt I’m using for the generations, so you can use that in ChatGPT or whatever other software you prefer.

Wouldnt it be more sensible to grab the images from a local StableDiffusion installation? You can get it from github and generate the images on your device with training packages you can grab from other sites for free aswell, tho I dont know how much work integrating that is
So, I’m a big fan of Stable Diffusion, and I actually used it to generate many of the images in the game, but unfortunately it doesn’t work well for this. Stable Diffusion often relies on optimization of the prompt, and even then it often misses details and doesn’t really understand what the intention of the image is. Whereas DALL-E has a few features that are great. The first is that the API has an integrated language model that optimizes the prompts automatically, given some basic things it needs to include, which removes the need to have a person optimize the prompt. And also the understanding of the prompt is so much better, so it’s much more likely to get details, which is very important when I’m giving the model a bunch of physical characteristics to include and I want all of them to be in the final portrait.

And of course there is the other issue brought up, which is that doing it locally is actually a lot of problems. I would need to distribute the diffusion model weights, which would be 5-10 GB on their own! And then players would need to get the model running on their computers, which would be a major pain. And it would be impossible on mobile lol.

I would love to eventually move to an open model, with no censorship (for obvious reasons for this game lol), and that players can run for free themselves! But
unfortunately I don’t think that’s viable yet for a variety of reasons. I appreciate the suggestion though!
 
  • Like
Reactions: Xakorik

Mercedes

Active Member
Nov 19, 2017
703
847
Very interesting in itself, but I personally find that the balancing takes a lot of getting used to in the beginning when it comes to food, money and corruption. It took three restarts before I could get it sorted out. Ultimately, I fail on level 9 because I can't refill my water bottles (I end up on a blank screen) and die miserably of thirst.
 

BubblesTheAllMighty

Active Member
Sep 22, 2020
695
717
That’s understandable, in that case I recommend disabling that option in the settings menu and the game will remain perfectly playable like how it was before this update haha.
I am curious if sexy.ai would be possible as there are something like 27 generators to choose from on that.
Babes and Yiffymix are fairly decent depending on what you are trying to make.

One is animation generator in beta, but woof, it needs more time to learn.
 
Nov 21, 2020
19
7
Literally IDK how to play it. You just go down, get low on food and die because you can't even go up with what's left, you can explore only upper layers even by using layer's resources instead of yours.
 
3.90 star(s) 16 Votes