Vision-aware text conditioning for the Krea2 / K2 model. Feeds reference images through the Qwen3-VL-4B vision path with the Krea2 descriptor template; optional per-image mask crops to the masked region. No VAE (Krea2 has no reference-latent pathway). Auto-growing image+mask slots.
https://github.com/ethanfel/ComfyUI-Krea2TextEncoder
git clone https://github.com/ethanfel/ComfyUI-Krea2TextEncoder
comfy node install comfyui-krea2-text-encoder