ComfyUI Extension
ModelMerge Krea 2 + Quant (INT8/INT4)
This node lets you merge two full Krea 2 bf16 models and up to three LoRAs and quantize to int8/int4
tritant/ComfyUI_Krea2_ModelMerger_Converter_int8_int4
Nodes—
On cloudLocal install
Stars6
Updated22 days ago
Readme
ComfyUI_Krea2_ModelMerger_Converter_int8_int4
ModelMerge Krea 2 + Quant (INT8/INT4)
This node lets you merge two full Krea 2 bf16 models and up to three LoRAs. It relies solely on ComfyUI's internal kitchen. Merging and quantization — int8, int4, or none, in which case it stays in bf16 — happen on the fly: you can plug it straight into a KSampler to check the result right away (quality, inference speed), and optionally save the quantized model to disk in the chosen format.
<img width="440" height="650" alt="Capture d'écran 2026-07-28 171553" src="https://github.com/user-attachments/assets/f735f5ca-6ba9-412b-af9e-afec5aeda105" />