Krea 2 [w4a8]

Converted from https://huggingface.co/Comfy-Org/Krea-2/tree/main/diffusion_models

All credit belongs to the original model author. License is the same as the original model.

int8convt qwen3vl text encoder: link .

About mixed precision and txtfusion layers:

This quantized ckpt uses mixed precision. Which keeps important layers in high precision. Thus it's a little bit larger than other fully quantized ckpt.

All txtfusion layers are in high precision. You don't needs to worry the precision when applying "Refusal-Reduction" LoRA (or whatever new LoRAs that try to nuke the txtfusion layers and the safety filter).