Pinokio
FeedApps
Author@kaosbreed
Download Pinokio
Sign inCreate accountJoin
Sign inCreate accountJoin

@kaosbreed

Joined February 2026

3 Following0 Followers
PostsReplies
More
ActivityCheckpointsFollowed appsGitHub creations
Posts · 4
Pinned
@kaosbreed·16d

Quick animation intro

Hey hey, just something I made with Maestro, not finished, this is just the opening, but I'm pretty happy with the results, thought I'd share it with the community :)

MaestroBlizaine/Maestro
@kaosbreed·7dEdited

Music Video in Maestro

So, as much as the Director Mode is great for... concepts, it still falls a little flat I feel, unless I'm just bad at prompting the Director to follow my vision, but... studio mode works, here's some of a music video I've been working on, some of the shots were inspired by the Director Modes ideas, but yeah, I ended up just using Studio to chain those concepts into a bigger piece :) - (Also... this was originally supposed to be a cool music video of a hot goth vampire... and ended up being way darker as a metaphor for addiction/emotional vampirism/trauma) - 1080p Minimax H3 Fused 4 step (appr

MaestroBlizaine/Maestro
@kaosbreed·1mo ago

Running LLM on gpu

So, I've been doing a little poking around myself, as having 32gb vram means I could run the LLM on the CUDA option, if it were set up properly, so --- "Change (CUDA\d+) to ((?:CUDA|ROCm)\d+) in llama_linux_runtime.py and bundle the Lemonade SDK ROCm llama-server binary" - dunno if that's helpful at all, but it has worked for me at least, running a 27b LLM on CPU was taking.... around 2-3 hours to do a big prompt, after changing these settings, same prompt, about 5 minutes, possible you may want to add that yourself at some point, or something along the same lines for running the LLM on GPU, s

Maestro AMDyoyokits/Maestro-AMD
#discussion
0
@kaosbreed·1mo ago

architecture

What happened? whatever blizaine added with the Yue2 update, loks like he added new H3 checkpoints, and the wgp.py code is bringing up errors related to tagging of architecture Steps to reproduce update Maestro AMD, start. Your system (OS / GPU / RAM / VRAM / etc.) Ubuntu / Radeon AI Pro 9700 / 32gb vram / 64gb ram / Ryzen 9 5900x Logs / full error output Paste the full log output here ████ ██ Starting Shell 678f1554-39d4-418e-81bf-62cd15e8f41c <<PINOKIO_SHELL>>eval "$(conda shell.bash hook)" ; conda deactivate ; conda deactivate ; conda deactivate ; conda activate base ; source /home/mj84/pin

Maestro AMDyoyokits/Maestro-AMD
#bug
2
You’re all caught up.
Pinokio
PrivacyTerms
FeedApps