
oozeclues
1.2K posts

oozeclues
@oozeclue
Just another paint-chugging dungeon roomba that likes to weeb out and break games. Watch the Droplet: https://t.co/WPuSrS2NsG https://t.co/x3c9M489Z8





International Non-Binary People’s Day




PS5 Emulator for Windows is almost here... There are now 4 PS5 emulators in development, and SharpEmu has already booted Demon's Souls Remake. It only reaches the boot screen for now, but this is a crazy breakthrough. Just seeing a PS5 exclusive boot on PC is something many people thought was still years away. People don't realize how big this is. Rockstar is going to start feeling the pressure. GTA 6 is the game everyone wants on PC, and PS5 emulation moving this fast is the last thing publishers want to see.



Today I made a prototype of a system that turns a single AI-generated portrait into a living VTuber. No rigging, no Live2D, nobody spending 80 hours in an editor. The character was generated locally with SDXL using the same model and custom LoRA I use for the art bot in my Discord server. A video model (Grok) then animated her into a chain of idle clips, each one starting on the exact frame where the previous one ended, so she loops forever and rarely cuts. Her mouth is the interesting part: a tracker follows the drawn lines of her lips through every frame, measuring position, angle, and width, and a composited mouth rides along, rotating and foreshortening as her head moves. The mouth shapes themselves were inpainted onto her own face by SDXL, so every viseme is in her exact art style. Real phoneme detection drives which shape shows. Because the mouth is composited rather than baked in, it stops the instant the voice stops. The body animation never even knows speech exists. Animating her ate about half of my SuperGrok credits, which works out to $14.32 if you paid for the same experimentation directly. I used 5 of the 12 generated clips in this demo. Narrated this demo using the Kokoro TTS model for free. Next step would be webcam emotion detection so she can swap between animation sets when the streamer smiles or gasps, more mouth shapes


Let’s be real here. You don’t like AI because you won’t be able to charge ONE THOUSAND DOLLARS for a basic vtuber model

HA! They are missing out on ALL the cool stuff - so screw them! I love this program so much! quick and easy to use, even Monkey can understand how to use it. This opens up so many possibilities to create unique avatars for events or other fun streams. Thank for making this possible @Leaflit 💕


the cheapest kit of 16GB DDR4 RAM is 90$ and it's because of people like this btw





Defeat progressive inequality obsession with this one question



There it is. This AI drama has proven one thing artists have a monopoly on VTubing with ridiculous pricing. “Oh, but there are free assets and models.” Sure, but creators using them usually aren’t taken seriously. “Oh, just get a customizable model.” Too expensive for a new creator. 🤨 Then @Leaflit drops that project. As horrible as it looked, it got enough support that Suddenly we’re seeing 90% discounts on models and assets like it’s a Steam sale. Some art is absolutely worth $1,000+, but when the entry price for a basic model/art is so high for art thats not worth that much, why wouldn’t people see AI as an alternative? Until the Vgen Mafia.fix’s this issue ai Vtubing will just keep popping up




So hold on... you're telling me... An artist can create a thing that helps with AI VTubing... But a Vtuber cannot create a thing that helps with AI Art...








