I think a big improvement would be different colors for the textboxes of different characters. Helps to show at a glance who is speaking. Especially in the prologue. Good luck with the game going forward.
If animations, it's not consistent, but it's getting better and better by the time, might need a few years, haha. For live2d, I believe it can be done from the base image.
I've said for a long time that the whole "make a computer squint at random noise until it sees a waifu" approach is misguided. Look for future AI paradigms that include 3D shape, spatial awareness, and some form of cause-and-effect baked into the underlying system, not stapled on after the fact. For animation to truly work, it can't just "look good," it also has to "make sense."
← Return to game
Comments
Log in with itch.io to leave a comment.
I think a big improvement would be different colors for the textboxes of different characters. Helps to show at a glance who is speaking. Especially in the prologue. Good luck with the game going forward.
Hi, that's actually a great idea! I will put it on the project task list, thank you.
I represent Sunflower Games. I'm putting together a Christmas bundle on this website with a couple of devs. Comment below if you want to join.
Any updates planned for Gabrielle? I need to ruin her day some more.
That or having Louisa ABSOLUTELY ruin me.
😂 She's planned to have new scene next update, along with Cara
Hi, just want to let you know the update with Gabrielle content is live.
Is it just me or is the number typing broken? I can't delete all the numbers. I have to use the arrow keys for now.
Hi, will check on it. Is it only happened when you delete all the numbers only?
Yeah, when I backspace the numbers it sometimes leaves one number there. It won't let me highlight and delete either. Thanks for the game.
Wait, how did you manage to make AI art that can be clothed and unclothed?
Hi, I use inpainting and retouch the results
Is it consistent enough for animation? Or just like Live2D, and if she turns her head, some of the details are suddenly different?
If animations, it's not consistent, but it's getting better and better by the time, might need a few years, haha. For live2d, I believe it can be done from the base image.
I've said for a long time that the whole "make a computer squint at random noise until it sees a waifu" approach is misguided. Look for future AI paradigms that include 3D shape, spatial awareness, and some form of cause-and-effect baked into the underlying system, not stapled on after the fact. For animation to truly work, it can't just "look good," it also has to "make sense."