Text Encode (Krea2)
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.
ComfyUI node pack
- Registry ID
comfyui-krea2-text-encoder- Version
- 1.0.6
- Requirements
- Python >=3.10
- Models
- kreaturbo.safetensors
- Archive size
- 690.3 KB
Browse ComfyUI tools · Browse ComfyUI workflows
Resource information
- App framework
- ComfyUI
- Deployment
- Local
- Upstream last modified
- Jun 27, 2026
- License
- MIT
- Last record update
- Nov 6, 2026