Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines
(1 edit) (+1)

I liked your progress and approach in more than words so thought I'd take a look at this too. It seems like a good start. The mini-game is pretty brutal. You're having a normal conversation and then are forced to suddenly blurt out some incredibly awkward attempt at flirting. It's hilarious, but you just have to hope that the AI interprets it well.

I was impressed by the AI loading speed in this one, it was faster than in More then Words! I was a little disappointed in that as far as I could tell, the videos were just random and not associated with either her mood or the conversation. I apologize if they were responsive. I also hope that you can get the speech synthesis up and running for this game too.

I've seen someone else working on a similar kind of continuous AI video concept. Check out David Browne on Youtube. He also has some interesting stuff with making an anime style android alongside his AI video experiments.

Hi XenoCow, it's good to hear from you again, thanks so much for playing!

I'm glad you like the minigame and understand its purpose; other players have been confused about why it. The idea is to simulate a state of nervousness and the player to say something silly and wait to see how she reacts.

It loads faster because LLM no longer conflicts with Unreal Engine for resources, haha. The videos are random, although when she gets really upset, you start seeing videos of her being upset. Associating videos with states isn't a technical challenge; the problem is that the game's file size gets too large. About speech synthesis; since it's pre-rendered, there's no way to adapt the lip movements, so I decided to remove it.

I've seen the video; it's exactly the same concept, nice work! Just a side note, he's loading MP4 videos. If you wanted to combine it with a local LLM, you'd run into problems... In my case, video decoding is done offline, and JPEGs are packaged into a binary file (let's say a custom video format like .bin). Then the process only involves loading the video into memory, not decoding it. The downside is that .bin videos are larger than MP4s :(.

What's the problem with the MP4s? The decoding can't take that much of your GPU's resources. And if it's a latency thing, you could start loading  the next video before the previous finishes... Maybe grabbing a few of the first frames if there is some kind of difficulty in switching between the two.

In SFML image loading and editing operations are performed on the CPU (RAM), and drawing operations on the GPU (VRAM). Everything is done on the CPU if the computer doesn't have a graphics card.

FFMPEG's native operation is CPU-based, while MP4 decoding is done in software via h264 (CPU). The advantage of this approach is that it's cross-platform. Is possible change the decoder to use CUDA, but we lose the aforementioned advantage.

We can conclude that standard decoding would be done on the CPU. This decoding, performed while LLM is generating, is what I'm to avoiding. Although I would have to implement the version from mp4s to truly see the impact.

After the release of My Summer Love, I'll certainly test it. If it could be run directly from mp4, the size of the video game would be substantially reduced and more animations could be included.

Thank you very much for the observation.

(+1)

It's a bit over my head. I appreciate the detailed explanation nonetheless.

I wish you the best in development and hope that the game gains some popularity on Steam when you launch it there.

I really appreciate your good wishes! I'll do my best!