FLUX.2-dev AI Toolkit LoRA Fails to Load in Maestro

What happened?
I trained a character LoRA in AI Toolkit using the official FLUX.2-dev BF16 model from Hugging Face. Training completed successfully and produced valid .safetensors checkpoints. When loading the LoRA in Maestro with FLUX.2-dev, the UI shows "Generation failed: Failed to fetch." The terminal reports a tensor split error (split_with_sizes) while loading the LoRA. This appears to be a compatibility issue between AI Toolkit FLUX.2-dev LoRAs and Maestro's current FLUX.2 loader rather than a training failure.

Steps to reproduce

1. Create FLUX.2 LoRA in Ostris AI-TOOLKIT using black-fores-labs/FLUX.2-dev
2. Place trained safetensors file in maestro loras>flux2 folder.
3. Select the LoRA and try to create an image using FLUX-2 in Maestro.

Your system (OS / GPU / RAM / VRAM / etc.)
Nvidia 5090 32GB
64GB DDR5
Intel 285k

Logs / full error output
Error loading FLUX.2-dev AI Toolkit LoRA:

RuntimeError: split_with_sizes expects split_sizes to sum exactly to 12288 (input tensor's size at dimension -2), but got split_sizes=[6144, 6144, 6144]

UI:
Generation failed: Failed to fetch