Update model card

README.md

@@ -22,7 +22,7 @@ Every LoRA ships as `<Name>_KREA2.safetensors` alongside `<Name>_KREA2.md` insid
 - A new **`Pruned_Comparison`** folder was added with one preview image per character (see below).
 
 ### Dynamic re-rank + block pruning
-Every LoRA was re-ranked with **dynamic `sv_fro` SVD** (retention `0.998`, max rank `16`) and block-pruned by dropping the **8 lowest-impact transformer blocks** (blocks `1-8`, ~3% of delta energy). All `txtfusion` refiner/layerwise keys are preserved. Weights are stored as `lora_up` / `lora_down` + `alpha` in fp16, loadable directly in ComfyUI. Each file carries `crt_*` provenance metadata.
+Every LoRA was re-ranked with **dynamic `sv_fro` SVD** (retention `0.998`, max rank `16`) and block-pruned by dropping the **8 lowest-impact transformer blocks** (blocks `1-8`, ~3% of delta energy).
 
 ### Retrained character
 - **Jung Ho-yeon** (`Ho-yeon`) was **retrained** on a new dataset, then re-ranked and pruned like the others.