Hi Blizaine!
First of all, thank you for your incredible work on Maestro!
I'd love to see native support for the new FLUX.3 Image Klein in a future update.
Its capabilities look very promising, especially text-to-image generation, image editing with up to 10 reference images, improved character consistency, and multi-step editing.
It would be fantastic to have support for GGUF quantizations (including Unsloth dynamic GGUFs), along with Maestro's excellent VRAM management and CPU offloading, making the model accessible to users with GPUs like the RTX 3060 12GB.
Native integration with Maestro's interface, reference image workflows, and prompt enhancement system would be amazing.
Of course, we understand that implementing a new architecture takes time and effort. Just wanted to suggest it as a potential addition to your roadmap.
Thanks again for your dedication to making local AI more accessible and powerful!
@blizaineMaestro v2.6.0 is out! Live Preview & Reference Mode long videos Maestro v2.6.0 is out! MiniMax H3 Reference Mode now supports long videos (like this stock footage) & Maestro auto-splits across seamless windows. Combine w/ Character Swap LoRA; keep the background true, or add effects. Maestro v2.6.0 Updates: • Live generation previews: Watch motion develop while rendering, w
