Pinokio
FeedAppsRemote
Author@electra_highway
Download Pinokio
Sign inCreate accountJoin
Sign inCreate accountJoin

@electra_highway

Joined May 2026

0 Following0 Followers
PostsReplies
More
ActivityCheckpointsFollowed appsGitHub creations
Replies · 3
@blizaineMaestro v3.2 is live!🚀 v3.2 Update: FastH3 V2: experimental eight-step text-to-video with generated audio. FastH3 OmniRef: experimental image, video and audio references, with official BF16, INT8 and FP8 checkpoints. FastH3 NVFP4: separate experimental QAD model for supported Blackwell GPUs. Qwen Image 2.1: repaired processor downl
@electra_highway·7dEdited
in Maestro
Awesome work! Any chance of introducing Identity Edit for MOSS Image? There are several LoRAs already doing the rounds, such as Moss-Image-Edit and MOSS-Image-Edit-HQ v5, allowing instruction-based image-editing thanks to the Qwen 3.5 9B text encoder which accepts multimodal inputs. THANKS.
@blizaineJust pushed v3.1 to the Public Dev branch for testing. Push to Main should be coming later today if all goes well. Includes a fix for H3 speaker/Shot-label compatibility, plus support for MOSS Image, Flux 3 LoRAs, Viggle, face-refiner repairs, and Recast memory improvements.
@electra_highway·16d
in Maestro
Thanks! Looking forward to it.
@blizaineMaestro v3.0 is out! Huge focus on H3 speed across GPUs + Flux3 & other goodies! Two weeks! That’s how long it’s been since I pushed an update. The longest since launch. And I’ve been grinding! Huge focus on H3 speed across GPUs, + Flux3 & other goodies! Maestro v3.0 Updates: • Faster generation and better memory management. Optimized kernels deliver roughly 1.5–2× speedups in our matc
@electra_highway·17d
in Maestro
Cannot select LoRAs for Flux 3 Klein. The Advanced Settings section shows the option labeled "Presets" instead of "LoRAs & presets" as with other models.
You’re all caught up.
Pinokio
PrivacyTerms
FeedAppsRemote