If you mean Perchance OFC T2i plugin's GAi core modeling and networking,.. Its, because "Perchance COs, main dev, and even myself "Assistant Dev" can see that when it comes to an efficient model vs the prior, all changes are made to cap the cost of Ai image generation, the single most expensive system too operate here on Perchance – is the T2i plugin".. The current new model of 2026 is not fairly much diffrent from the prior Schell/Chroma/Dev mixed multimodal/Perchance customs flux.1 networking of core modeling, now on "Klein, flux.2 networking, Klein is part of the new era of super distillation models, while being technical prompting stteam‐lined". The new model, it is quite literally the most quality efficient model to date, & manages to be built to throw more resource to mid ground if being technical prompt prodded, future potential also hints at it being extremely well equip for tool building, plus leveraging of LoRa sub modeling, possibly later formalizations of sub modality and user capable loading and off loading of training data..ect. At the moment to some, I'd say few.. It may seem like complete garbage, or a literal direct downgrading of our prior customs,.. particularly because it handles as if It's nearly the same model.., It is not, and moving forward, that and users actually studying up on siht will realise "that it is actually possibly ¿A better model?". With time and good practice I'am betting the new model will prove to be "Yes better"...