Look at SD vs midjourney. The stuff that keeps shipping for SD from optimization to fine tunes…the community is simply faster
@waitin4agi_
-
Sparse Coding and Selective Attention Mechanisms
By
–
check out sparse coding…even selective attention could do this if I'm not wrong?
-
Using GPT API with Unreal Engine for Dynamic Content and Animation Control
By
–
We’re using the API directly to spit out JSON that we consume in Unreal Engine — drives content, head turns, animations, which GPT speaks next. https://t.co/N0cHNuMo6k pic.twitter.com/5sh8zQ9H7R
— Varun Mayya (@waitin4agi_) 15 mai 2023We’re using the API directly to spit out JSON that we consume in Unreal Engine — drives content, head turns, animations, which GPT speaks next.
-
Cold Boot Problem with Custom Model – Support Request
By
–
Hey @replicatehq we're having a cold boot problem with one of our custom models. Can someone from customer support PLEASE help?
-
Best Methods for Training AI Personality and Virtual Companions
By
–
The best way to mimic personality is probably not fine tuning GPT-4 (which we did in our last Unreal Engine demo) . For those wondering what the best way to train friend's personality, virtual girlfriends, I would recommend using:
-
Open Sourcing Replicated Functionality from Scratch
By
–
We have probably replicated their entire functionality from scratch, and will open source it 🙂
-
OSS Tortoise-TTS and Metahuman SDK for voices and lipsync
By
–
Forgot to add that we used the OSS Tortoise-TTS (
https://
github.com/neonbjb/tortoi
se-tts
…) for voices and Metahuman SDK (
https://
unrealengine.com/marketplace/en
-US/item/66b869fa0d3748e78d422e59716597b6?sessionInvalidated=true
…) for lipsync in-game -
Games with Real-Time News Integration: A Proof of Concept
By
–
Imagine games where you walk in and characters are talking about what happened in the news today! This Proof of concept should show you that is certainly possible.
