# Released a photorealism LoRA for Krea 2 Turbo by merging mixed LoRA and LoKR adapters

> Source: <https://discuss.huggingface.co/t/released-a-photorealism-lora-for-krea-2-turbo-by-merging-mixed-lora-and-lokr-adapters/180333#post_1>
> Published: 2026-09-12 19:32:16+00:00

Most mergers (kohya, mergekit) only combine adapters that share the same low-rank format. Public Krea-2 realism packs are a mix of classic LoRA and LoKR, so those tools stop there.

**Badaramoni Fusion** works in weight-delta space instead:

`ΔW = B·A``ΔW = kron(w1, w2)``ΔW = Σ wᵢ · ΔWᵢ`
You get a single portable `.safetensors` — not a naive alpha-average, and not a multi-adapter stack at inference.

No trigger word. Write a normal descriptive sentence.

**Settings for the samples**

`krea/Krea-2-Turbo`
This is a many-to-one, lossy-by-design compression. The contribution is the fusion algorithm that makes mixed-format realism adapters usable as one file.

License follows the Krea 2 Community License. You need access to `krea/Krea-2-Turbo` to run it.
